@inproceedings{Chauhan2026,

title = {Colored Shared Spaces (CSS): How Visual Design Transforms Pedestrian Experiences},

author = {Vishal Chauhan and Anubhav Anubhav and Chia Ming Chang and Ehsan Javanmardi and Takeo Igarashi and Alex Orsholits and Kantaro Fujiwara and Manabu Tsukada},

year  = {2026},

date = {2026-07-16},

booktitle = {28th International Conference on Human-Computer Interaction (HCII2026)},

address = {Montreal, Canada},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{nokey,

title = {Trajectory Planning for UAV-Based Smart Farming Using Imitation-Based Triple Deep Q-Learning },

author = {Wencan Mao and Quanxi Zhou and Tomás Couso Coddou and Manabu Tsukada and Liu Yunling and Yusheng Ji},

year  = {2026},

date = {2026-06-01},

urldate = {2026-06-01},

booktitle = {IEEE International Conference on Robotics & Automation (ICRA 2026)},

address = {Vienna, Austria},

abstract = {Unmanned aerial vehicles (UAVs) have emerged as a promising auxiliary platform for smart agriculture, capable of simultaneously performing weed detection, recognition, and data collection from wireless sensors. However, trajectory planning for UAV-based smart agriculture is challenging due to the high uncertainty of the environment, partial observations, and limited battery capacity of UAVs. To address these issues, we formulate the trajectory planning

problem as a Markov decision process (MDP) and leverage multi-agent reinforcement learning (MARL) to solve it. Furthermore, we propose a novel imitation-based triple deep Q-network (ITDQN) algorithm, which employs an elite imitation mechanism to reduce exploration costs and utilizes a mediator Q-network over a double deep Q-network (DDQN) to accelerate and stabilize training and improve performance. Experimental results in both simulated and real-world environments demonstrate the effectiveness of our solution. Moreover, our proposed ITDQN outperforms DDQN by 4.43% in weed recognition rate and 6.94% in data collection rate. },

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Wu2026,

title = {A Synthetic Benchmark for Collaborative 3D Semantic Occupancy Prediction in V2X-Enabled Autonomous Driving },

author = {Hanlin Wu and Pengfei Lin and Ehsan Javanmardi and Naren Bao and Bo Qian and Hao Si and Manabu Tsukada},

url = {https://arxiv.org/abs/2506.17004

https://github.com/tlab-wide/Co3SOP},

year  = {2026},

date = {2026-06-01},

urldate = {2026-06-01},

booktitle = {IEEE International Conference on Robotics & Automation (ICRA 2026)},

address = {Vienna, Austria},

abstract = {3D semantic occupancy prediction is an emerging perception paradigm in autonomous driving, providing a voxel-level representation of both geometric details and semantic categories. However, its effectiveness is inherently constrained in single-vehicle setups by occlusions, restricted sensor range, and narrow viewpoints. To address these limitations, collaborative perception enables the exchange of complementary information, thereby enhancing

the completeness and accuracy of predictions. Despite its potential, research on collaborative 3D semantic occupancy prediction is hindered by the lack of dedicated datasets. To bridge this gap, we design a high-resolution semantic voxel sensor in CARLA to produce dense and comprehensive annotations. We further develop a baseline model that performs inter-agent feature fusion via spatial alignment and attention aggregation. In addition, we establish

benchmarks with varying prediction ranges designed to systematically assess the impact of spatial extent on collaborative prediction.  Experimental results demonstrate the superior performance of our baseline, with increasing gains observed as range expands. },

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Cong2026,

title = {Adaptive Entropy-Regularized Reinforcement Learning for Routing and Slot Allocation in MTNs},

author = {Lin Cong and Ying Wang and Peng Yu and Xuesong Qiu and Shaoyong Guo and Manabu Tsukada and Long Qu and Jice Liu

},

year  = {2026},

date = {2026-05-18},

booktitle = {IEEE/IFIP Network Operations and Management Symposium (NOMS) 2026},

address = {Rome, Italy},

abstract = {As emerging services such as AI datacenter interconnection, immersive AR/VR, and autonomous driving demand greater transport flexibility and resource efficiency, Metro Transport Networks (MTNs) have become the critical infrastructure for next-generation metro backbones providing flexible and efficient resource orchestration. Nevertheless, the Routing and Slot Allocation (RSA) problem in MTNs remains challenging due to combinatorial complexity, high-dimensional coupling in the action space, and resource fragmentation. We propose EFP-RSA, a novel entropy-regularized reinforcement learning framework that addresses the RSA problem through factorized policy. It factorizes the joint optimization into coordinated path selection and slot assignment, alongside entropy regularization annealing to balance exploration with convergence. Compared with baselines, EFP-RSA reduces blocking probability by 35.3%–60.7% and increases slot utilization by 19.4%–58.6%, while maintaining low load variance and high solution efficiency, demonstrating strong generalization and scalability in complex MTN scenarios.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Gui2026,

title = {Peeking Ahead of the Field Study: Exploring VLM Personas as Support Tools for Embodied Studies in HCI},

author = {Xinyue Gui and Ding Xia and Mark Colley and Yuan Li and Vishal Chauhan and Anubhav Anubhav and Zhongyi Zhou and Ehsan Javanmardi and Stela Hanbyeol Seo Social and Chia-Ming Chang and Manabu Tsukada and Takeo Igarashi},

year  = {2026},

date = {2026-04-13},

urldate = {2026-04-13},

booktitle = {ACM CHI conference on Human Factors in Computing Systems 2026},

address = {Barcelona, Spain},

abstract = {Field studies are irreplaceable but costly, time-consuming, and error-prone, which need careful preparation. Inspired by rapid-prototyping in manufacturing, we propose a fast, low-cost evaluation method using Vision-Language Model (VLM) personas to simulate outcomes comparable to field results. While LLMs show human-like reasoning and language capabilities, autonomous vehicle (AV)-pedestrian interaction requires spatial awareness, emotional empathy, and behavioral generation. This raises our research question: To what extent can VLM personas mimic human responses in field studies? We conducted parallel studies: 1) one real-world study with 20 participants, and 2) one video-study using 20 VLM personas, both on a street-crossing task. We compared their responses and interviewed five HCI researchers on potential applications. Results show that VLM personas mimic human response patterns (e.g., average crossing times of 5.25 s vs. 5.07 s) lack the behavioral variability and depth. They show promise for formative studies, field study preparation, and human data augmentation.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{nokey,

title = {Don't Worry, Just Follow Me: Prototyping and In-the-Wild Evaluation of Smart Pole Interaction Unit with Mobility},

author = {Vishal Chauhan and Anubhav Anubhav and Mark Colley and Chia-Ming Chang and Xinyue Gui and Ding Xia and Ehsan Javanmardi and Takeo Igarashi and Kantaro Fujiwara and Manabu Tsukada},

year  = {2026},

date = {2026-04-13},

booktitle = {ACM CHI conference on Human Factors in Computing Systems 2026},

address = {Barcelona, Spain},

abstract = {Pedestrian–automated vehicle(AV) encounters in shared spaces often involve hesitation and ambiguity. Vehicle-mounted external human–machine interfaces(eHMIs) can help, but obscured or poorly timed communications create significant challenges. To address this, we present a mobile smart pole interaction unit(SPIU) with integrated cameras and LED displays, designed as a pedestrian-side system to deliver explicit cues(``WALK,'' ``STOP''). An in-the-wild evaluation of the SPIU(N=21) using a four-factor analysis (CarBehavior, Mobility, eHMI, SPIU) showed that the SPIU improved understandability, trust, and perceived safety, and reduced workload compared with the baseline, with a combination(eHMI+SPIU) yielding the strongest results. Beyond these quantitative benefits, participants appreciated the mobility of the SPIU for its ``clear'' and ``easy to decide'' mediation. This work contributes to(1) a design and deployment framework for a mobile SPIU and(2) an in-the-wild evaluation protocol for pedestrian–AV interactions in nonsignalized spaces. Our work sparks discussions on real world evaluations involving detailed vehicle kinematics and accessible multimodality(e.g., audio), focusing on the role of personal robots as user-side eHMIs.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Ghosh2026,

title = {SwitchAuthn: Trusted Hardware-Based Layer-2 Authentication to Prevent MAC Spoofing in Ethernet Networks},

author = {Anisha Ghosh and Manabu Tsukada},

year  = {2026},

date = {2026-04-08},

booktitle = {The 40-th International Conference on Advanced Information Networking and Applications (AINA2026)},

address = {Victoria University of Wellington, New Zealand},

abstract = {Modern switches rely on Access Control Lists (ACLs) for Media Access Control (MAC)-based access control, leaving networks vulnerable to MAC address spoofing attacks that succeed in 78% of enterprise networks. This paper presents SwitchAuthn, a device-centric TPM 2.0-secured challenge-response mechanism that closes the critical authentication gap before MACsec channel establishment. Unlike IEEE 802.1AE (MACsec) and 802.1X approaches that assume pre-established device trust, SwitchAuthn enforces cryptographic device identity verification at Layer-2 using HMAC-SHA256 with hardware-protected keys. Prototype evaluation using GNS3 with authentic Cisco IOS images (v15.1) and TPM 2.0 simulator demonstrates: (1) mean authentication latency of 2.827 ms (median 2.695 ms, <10 ms target); (2) 100% MAC spoofing prevention across 1,000 test attempts (vs. 0% for baseline port security); (3) <3% CPU overhead under sustained load (7-1000 devices); (4) comprehensive defense against replay attacks (nonce-based), MITM attacks (challenge uniqueness), and DoS attacks (rate-limiting with attestation-bound queues). The protocol achieves RFC 4868, FIPS 180-4/198-1, and ISO/IEC 11889-3 compliance while maintaining seamless IEEE 802.1X/RADIUS integration. Experimental validation demonstrates linear scalability, zero false positives observed over 48-hour continuous operation (1,400+ authentication cycles, 95% confidence interval: 0-0.26% false positive rate), and production-ready deployment architecture addressing rate-limit abuse through three-layer hybrid countermeasures.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Djelloul2026,

title = {Spatial ID Authoring in Mixed Reality: A Unified Platform Integrating Anchoring and Visualization},

author = {Sami Brahim Djelloul and Yanru Chen and Alex Orsholits and Manabu Tsukada},

year  = {2026},

date = {2026-01-26},

booktitle = {IEEE International Conference on Artificial Intelligence and Virtual Reality (AIxVR), Work in Progress (WiP)},

address = {Osaka, Japan},

abstract = {We present a Mixed Reality (MR) authoring platform that leverages Spatial IDs as a standardized reference to align digital content with the physical environment. The platform enables users to tag and annotate space through Spatial IDs, with annotations managed through a decoupled architecture where a queryable Spatial ID index links spatial entities to external databases containing attributes and application-specific content. To support this, we integrate two enabling components. First, anchoring: Spatial IDs provide a hierarchical four-dimensional indexing system that ensures consistent alignment across datasets and localization methods. Second, visualization: anchored Spatial IDs allow both real-world data streams and authored datasets to be rendered in MR. As a proof of concept, we integrate cloud-based object detection from an external depth camera, streaming recognized objects into MR and visualizing them at their true physical locations. Together, these components demonstrate how Spatial IDs enable accurate visualization and persistent authoring, offering a unified pipeline for next-generation spatial computing.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Chen2026,

title = {Spatial ID-Driven Edge-Cloud Architecture for Real-Time Urban Digital Twins},

author = {Yanru Chen and Sami Brahim Djelloul and Alex Orsholits and Manabu Tsukada and Hiroshi Esaki},

doi = {10.1109/CCNC65079.2026.11366402},

year  = {2026},

date = {2026-01-08},

urldate = {2026-01-08},

booktitle = {IEEE Consumer Communications & Networking Conference (CCNC2026)},

address = {Las Vegas, USA},

abstract = {Only the chairs can edit The integration of static geospatial datasets and real-time IoT streams is essential for responsive and scalable urban Digital Twins (DTs). However, current infrastructures remain fragmented across domains, formats, and reference systems, limiting interoperability and city-scale deployment. This paper presents the first city-scale implementation of a Spatial ID-driven edge-cloud architecture that unifies heterogeneous static and dynamic urban data under a hierarchical four-dimensional identifier. Unlike prior DT systems that rely on ad hoc tiling or local schemas, our design operationalizes Spatial ID as a universal indexing layer across batch and streaming pipelines, enabling multi-resolution queries, real-time synchronization, and cross-domain interoperability. A prototype deployment in Tokyo's Chiyoda and Bunkyo wards demonstrates the approach, integrating 3D city models with live IoT streams. Static data are encoded into Spatial IDs and distributed via a geospatial database and vector tiles, while dynamic streams are processed at the edge and synchronized with a cloud backend using a publish/subscribe model. The system supports real-time encoding, querying, distribution, and web/Mixed Reality (MR)-based visualization. Evaluation shows millisecond-to-second query performance over 148 million records, sub-100 ms vector tile delivery, and real-time IoT stream processing at 30 fps. These results establish Spatial ID not only as a conceptual framework but as a practical, deployable foundation for interoperable, low-latency, and scalable Digital Twin infrastructures aligned with the vision of Society 5.0.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Meng2025b,

title = {Patch Exploration-Based Route Planning for Autonomous Vehicles},

author = {Huan Meng and Jinhui Zhang and Xiaobing Huang and Ehsan Javanmardi and Manabu Tsukada},

year  = {2025},

date = {2025-11-18},

urldate = {2025-11-18},

booktitle = {28th IEEE International Conference on Intelligent Transportation Systems (ITSC2025)},

address = {Gold Coast, Australia},

abstract = {Route planning is a crucial component of autonomous

driving, making it essential to develop efficient planning

methods tailored to different scenarios. To address the

limitations of the existing RRT* methods, we propose a

Patch Exploration RRT* (PE-RRT*). First, separating

hyperplanes and half-spaces are utilized to construct patch

for each node in the tree structure, allowing adaptation to

the environmental density. Additionally, during the

sampling process, the patches guide the expansion of the

random tree, enabling rapid searches and efficient use of

sampled points. Moreover, the patches are applied for route

pruning, simplifying the route representation. Simulation

results demonstrate that the proposed method achieves high

search efficiency across various scenarios. },

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Chauhan2025b,

title = {A Silent Negotiator? Cross-cultural VR Evaluation of Smart Pole Interaction Units in Dynamic Shared Spaces},

author = {Vishal Chauhan and Anubhav Anubhav and Robin Sidhu and Yu Asabe and Kanta Tanaka and Chia-Ming Chang and Xiang Su and Dr. Ehsan Javanmardi and Takeo Igarashi and Alex Orsholits and Kantaro Fujiwara and Manabu Tsukada},

url = {https://github.com/tlab-wide/Smartpole-VR-AWSIM.git},

doi = {10.1145/3756884.3765991},

year  = {2025},

date = {2025-11-12},

urldate = {2025-11-12},

booktitle = {The ACM Symposium on Virtual Reality Software and Technology (VRST2025) },

address = {Montreal, Canada},

abstract = {As autonomous vehicles (AVs) enter pedestrian-centric environments, existing vehicle-mounted external human–machine interfaces (eHMIs) often fall short in shared spaces due to line-of-sight limitations, inconsistent signaling, and increased cognitive burden on pedestrians. To address these challenges, we introduce the Smart Pole Interaction Unit (SPIU), an infrastructure-based eHMI that decouples intent signaling from vehicles and provides context-aware, elevated visual cues. We evaluate SPIU using immersive VR-AWSIM simulations in four high-risk urban scenarios: four-way intersections, autonomous mixed traffic, blindspots, and nighttime crosswalks. The experiment was developed in Japan and replicated in Norway, where forty participants engaged in 32 trials each under both SPIU-present and SPIU-absent conditions. Behavioral (response time) and subjective (acceptance scale) data were collected. Results show that SPIU significantly improves pedestrian decision-making, with reductions ranging from 40% to over 80% depending on scenario and cultural context, particularly in complex or low-visibility scenarios. Cross-cultural analyses highlight SPIU's adaptability across differing urban and social contexts. We release our open-source Smartpole-VR-AWSIM framework to support reproducibility and global advancement of infrastructure-based eHMI research through reproducible and immersive behavioral studies.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Li2025d,

title = {Multi-PrefDrive: Optimizing Large Language Models for Autonomous Driving Through Multi-Preference Tuning},

author = {Yun Li and Ehsan Javanmardi and Simon Thompson and Kai Katsumata and Alex Orsholits and Manabu Tsukada},

url = {https://liyun0607.github.io/},

doi = {10.1109/IROS60139.2025.11247608},

year  = {2025},

date = {2025-10-19},

urldate = {2025-10-19},

booktitle = {2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},

address = {Hangzhou, China},

abstract = {This paper introduces Multi-PrefDrive, a framework that significantly enhances LLM-based autonomous driving through multidimensional preference tuning. Aligning LLMs with human driving preferences is crucial yet challenging, as driving scenarios involve complex decisions where multiple incorrect actions can correspond to a single correct choice. Traditional binary preference tuning fails to capture this complexity. Our approach pairs each chosen action with multiple rejected alternatives, better reflecting real-world driving decisions. By implementing the Plackett-Luce preference model, we enable nuanced ranking of actions across the spectrum of possible errors. Experiments in the CARLA simulator demonstrate that our algorithm achieves an 11.0% improvement in overall score and an 83.6% reduction in

infrastructure collisions, while showing perfect compliance with traffic signals in certain environments. Comparative analysis against DPO and its variants reveals that Multi-PrefDrive’s superior discrimination between chosen and rejected actions, which achieving a margin value of 25, and such ability has been directly translates to enhanced driving performance. We implement memory-efficient techniques including LoRA and 4-bit quantization to enable deployment on consumer-grade hardware and will open-source our training code and multi-rejected dataset to advance research in LLM-based autonomous driving systems. Project Page (https://liyun0607.github.io/)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Si2025,

title = {You Share Beliefs, I Adapt: Progressive Heterogeneous Collaborative Perception},

author = {Hao Si and Ehsan Javanmardi and Manabu Tsukada},

url = {https://sihaoo1.github.io/PHCP_Page/

https://arxiv.org/abs/2509.09310

https://github.com/sihaoo1/PHCP},

year  = {2025},

date = {2025-10-19},

urldate = {2025-10-19},

booktitle = {International Conference on Computer Vision (ICCV2025)},

address = {Honolulu, Hawai'i},

abstract = {Collaborative perception enables vehicles to overcome individual perception limitations by sharing information, allowing them to see further and through occlusions. In real-world scenarios, models on different vehicles are often heterogeneous due to manufacturer variations. Existing methods for heterogeneous collaborative perception address this challenge by fine-tuning adapters or the entire network to bridge the domain gap. However, these methods are impractical in real-world applications, as each new collaborator must undergo joint training with the ego vehicle on a dataset before inference, or the ego vehicle stores models for all potential collaborators in advance. Therefore, we pose a new question: Can we tackle this challenge directly during inference, eliminating the need for joint training? To answer this, we introduce Progressive Heterogeneous Collaborative Perception (PHCP), a novel framework that formulates the problem as few-shot unsupervised domain adaptation. Unlike previous work, PHCP dynamically aligns features by self-training an adapter during inference, eliminating the need for labeled data and joint training. Extensive experiments on the OPV2V dataset demonstrate that PHCP achieves strong performance across diverse heterogeneous scenarios. Notably, PHCP achieves performance comparable to SOTA methods trained on the entire dataset while using only a small amount of unlabeled data.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Meng2025,

title = {Robust composite control strategy for constrained continuous-time nonlinear systems},

author = {Huan Meng and Jinhui Zhang and Manabu Tsukada},

year  = {2025},

date = {2025-10-05},

booktitle = {IEEE International Conference on Systems, Man, and Cybernetics (SMC2025)},

address = {Vienna, Austria},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Li2025b,

title = {State-Guided Spatial Cross-Attention for Enhanced End-to-End Autonomous Driving},

author = {Dongyang Li and Ehsan Javanmardi and Manabu Tsukada},

year  = {2025},

date = {2025-09-30},

urldate = {2025-09-30},

booktitle = {IEEE International Automated Vehicle Validation Conference (IAVVC 2025)},

address = {Baden-Baden, Germany},

abstract = {Handling near-accident scenarios is a significant challenge for end-to-end autonomous driving (E2E-AD), as these situations often involve sudden environmental changes, complex interactions with other road users, and high-risk decision-making under uncertainty. Unlike routine driving tasks, near-accident scenarios require rapid and precise responses based on external perception and internal vehicle dynamics. Successfully navigating such situations demands not only a comprehensive understanding of the surrounding environment but also an accurate assessment of the ego vehicle's state, including speed, acceleration, and steering angle, to ensure safe and reliable control. However, conventional E2E-AD models struggle to handle these safety-critical situations effectively. Standard approaches primarily rely on raw sensor inputs to learn driving policies, often overlooking the crucial role of vehicle state information in decision-making. Since many near-accident scenarios involve conditions where the same environmental observation could require vastly different responses depending on the ego vehicle's motion state-such as whether the vehicle is braking, accelerating, or experiencing traction loss-ignoring these internal dynamics can lead to unsafe or suboptimal actions. Furthermore, E2E-AD models typically learn a direct mapping from sensory inputs to control outputs, making it difficult to generalize to highly dynamic and unpredictable interactions, such as emergency evasive maneuvers or sudden braking events. To address these challenges, we propose a state-guided cross-attention mechanism that explicitly models the interaction between the ego vehicle's states and its perception of the environment. By incorporating vehicle state information into the decision-making process, our approach ensures that the model can dynamically adjust its attention to critical sensory inputs based on real-time driving conditions. This allows the autonomous system to make more context-aware decisions, improving its ability to respond effectively to complex and safety-critical scenarios.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Zhang2025,

title = {AWSIM-VR: A Tightly-Coupled Virtual Reality Extension for Human-in-the-Loop Pedestrian-Autonomous Vehicle Interaction},

author = {Shangkai Zhang and Alex Orsholits and Ehsan Javanmardi and Manabu Tsukada},

url = {https://github.com/zhangshangkai/AWSIM-VR},

doi = {10.1109/MetaCom65502.2025.00063},

year  = {2025},

date = {2025-08-27},

urldate = {2025-08-27},

booktitle = {3rd Annual IEEE International Conference on Metaverse Computing, Networking, and Applications (IEEE MetaCom 2025)},

address = {Seoul, Republic of Korea},

abstract = {Effective communication between autonomous vehicles (AVs) and pedestrians is crucial for ensuring future urban traffic safety. While external Human-Machine Interfaces (eHMIs) have emerged as promising solutions, current evaluation methodologies — particularly Virtual Reality (VR)-based studies — typically rely on scripted or pre-defined autonomous vehicle behaviors, limiting realism and neglecting pedestrians' active role in interactions. To address this, we introduce AWSIM-VR, a tightly-coupled VR extension of the AWSIM autonomous driving simulator, enabling real-time, human-in-the-loop pedestrian-AV interactions by directly integrating unmodified, real autonomous driving software (Autoware) into the simulation loop. Unlike previous systems, AWSIM-VR provides authentic, bidirectional interaction: pedestrians' actions dynamically influence vehicle decision-making and eHMI responses in real-time, closely emulating real-world AV scenarios. In user studies directly comparing AWSIM-VR to existing methodologies, participants reported significantly higher perceived realism and immersion, underscoring the importance of authentic autonomous behaviors in VR-based pedestrian interaction research. By directly utilizing production-level autonomous driving stacks, AWSIM-VR represents a significant methodological advancement, enabling more realistic, effective, and safer development and evaluation of eHMIs and AV technologies.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Bao2025,

title = {4D Path Planning via Spatiotemporal Voxels in Urban Airspaces},

author = {Naren Bao and Alex Orsholits and Manabu Tsukada},

doi = {10.1109/MetaCom65502.2025.00022},

year  = {2025},

date = {2025-08-27},

urldate = {2025-08-27},

booktitle = {3rd Annual IEEE International Conference on Metaverse Computing, Networking, and Applications (IEEE MetaCom 2025)},

address = {Seoul, Republic of Korea},

abstract = {This paper presents an approach to four-dimensional (4D) path planning for unmanned aerial vehicles (UAVs) in complex urban environments. We introduce a spatiotemporal voxel-based representation that effectively models both spatial and temporal dimensions of urban airspaces. By integrating the 4D spatio-temporal ID framework with reinforcement learning techniques, our system generates efficient and safe flight paths while considering dynamic obstacles and environmental constraints. The proposed method combines off-line pretraining and online fine-tuning of reinforcement learning models to achieve computational efficiency without compromising path quality. Experiments conducted using PLATEAU datasets in various urban scenarios demonstrate that our approach outperforms traditional path planning algorithms by 24% in safety metrics and 18% in efficiency metrics. Our framework advances the state-of-the-art in urban air mobility by providing a scalable solution for airspace management in increasingly congested urban environments.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Li2025c,

title = {PrefDrive: Enhancing Autonomous Driving through Preference-Guided Large Language Models},

author = {Yun Li and Ehsan Javanmardi and Simon Thompson and Kai Katsumata and Alex Orsholits and Manabu Tsukada},

url = {https://github.com/LiYun0607/PrefDrive/

https://huggingface.co/liyun0607/PrefDrive

https://huggingface.co/datasets/liyun0607/PrefDrive},

doi = {10.1109/IV64158.2025.11097672},

year  = {2025},

date = {2025-06-22},

urldate = {2025-06-22},

booktitle = {36th IEEE Intelligent Vehicles Symposium (IV2025)},

address = {Cluj-Napoca, Romania},

abstract = {This paper presents PrefDrive, a novel framework that integrates driving preferences into autonomous driving models through large language models (LLMs). While recent advances in LLMs have shown promise in autonomous driving, existing approaches often struggle to align with specific driving behaviors (e.g., maintaining safe distances, smooth acceleration patterns) and operational requirements (e.g., traffic rule compliance, route adherence). We address this challenge by developing a preference learning framework that combines multimodal perception with natural language understanding. Our approach leverages Direct Preference Optimization (DPO) to fine-tune LLMs efficiently on consumer-grade hardware, making advanced autonomous driving research more accessible to the broader research community. We introduce a comprehensive dataset of 74,040 sequences, carefully annotated with driving preferences and driving decisions, which, along with our trained model checkpoints, will be made publicly available to facilitate future research. Through extensive experiments in the CARLA simulator, we demonstrate that our preference-guided approach significantly improves driving performance across multiple metrics, including distance maintenance and trajectory smoothness. Results show up to 28.1% reduction in traffic rule violations and 8.5% improvement in navigation task completion while maintaining appropriate distances from obstacles. The framework demonstrates robust performance across different urban environments, showcasing the effectiveness of preference learning in autonomous driving applications.  },

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Jiang2025,

title = {Towards Efficient Roadside LiDAR Deployment: A Fast Surrogate Metric Based on Entropy-Guided Visibility},

author = {Yuze Jiang and Ehsan Javanmardi and Manabu Tsukada and Hiroshi Esaki},

url = {https://arxiv.org/abs/2504.06772},

doi = {10.1109/IV64158.2025.11097554},

year  = {2025},

date = {2025-06-22},

urldate = {2025-06-22},

booktitle = {36th IEEE Intelligent Vehicles Symposium (IV2025)},

address = {Cluj-Napoca, Romania},

abstract = {The deployment of roadside LiDAR sensors plays a crucial

role in the development of Cooperative Intelligent

Transport Systems (C-ITS). However, the high cost of LiDAR

sensors necessitates efficient placement strategies to

maximize detection performance. Traditional roadside LiDAR

deployment methods rely on expert insight, making them

time-consuming.  Automating this process, however, demands

extensive computation, as it requires not only visibility

evaluation but also assessing detection performance across

different LiDAR placements. To address this challenge, we

propose a fast surrogate metric, the Entropy-Guided

Visibility Score (EGVS), based on information gain to

evaluate object detection performance in roadside LiDAR

configurations. EGVS leverages Traffic Probabilistic

Occupancy Grids (TPOG) to prioritize critical areas and

employs entropy-based calculations to quantify the

information captured by LiDAR beams. This eliminates the

need for direct detection performance evaluation, which

typically requires extensive labeling and computational

resources. By integrating EGVS into the optimization

process, we significantly accelerate the search for optimal

LiDAR configurations. Experimental results using the AWSIM

simulator demonstrate that EGVS strongly correlates with

Average Precision (AP) scores and effectively predicts

object detection performance. This approach offers a

computationally efficient solution for roadside LiDAR

deployment, facilitating scalable smart infrastructure

development. },

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Rao2025,

title = {A LEO satellite routing method based on incremental evolutionary graph reinforcement learning},

author = {Zheheng Rao and Zhenyu Zhu and Wei Yang Bryan Lim and Ye Yao and Yanyan Xu and Manabu Tsukada and Yanyu Cheng},

year  = {2025},

date = {2025-06-08},

booktitle = {IEEE International Conference on Communications (ICC 2025)},

address = {Montreal, Canada},

abstract = {Only the chairs can edit With the advent of sixth-generation (6G) technologies and growing communication demands, Low Earth Orbit (LEO) satellite networks have become essential in modern communications. However, due to the dynamic topology and complex network state of LEO environments, existing routing methods often fail to make effective decisions, limiting transmission performance. This paper proposes a novel routing method, DGA-IES. To address network state perception challenges, we introduce a topological learning model using deep graph attention (DGA), which captures complex inter-satellite connectivity and resource states. Additionally, by integrating incremental evolution strategies (IES) into deep reinforcement learning (DRL), we replace sequential interactive proximal policy optimization (PPO) with global parallel ES, achieving efficient routing convergence in the highly dynamic LEO environment. Experimental results demonstrate that our DGA-IES approach enhances LEO network load balancing by reducing end-to-end (E2E) network latency, decreasing packet loss and improving throughput compared with the benchmark approaches.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Orsholits2025,

title = {Context-Rich Interactions in Mixed Reality through Edge AI Co-Processing},

author = {Alex Orsholits and Manabu Tsukada},

url = {https://link.springer.com/chapter/10.1007/978-3-031-87772-8_3},

doi = {10.1007/978-3-031-87772-8_3},

isbn = {978-3-031-87771-1},

year  = {2025},

date = {2025-04-09},

urldate = {2025-04-09},

booktitle = {The 39-th International Conference on Advanced Information Networking and Applications (AINA 2025)},

address = {Barcelona, Spain},

abstract = {Spatial computing is evolving towards leveraging data streaming for computationally demanding applications, facilitating a shift to lightweight, untethered, and standalone devices. These devices are therefore ideal candidates for co-processing, where real-time context understanding and low-latency data streaming are fundamental for seamless, general-purpose Mixed Reality (MR) experiences. This paper demonstrates and evaluates a scalable approach to augmented contextual understanding in MR by implementing multi-modal edge AI co-processing through a Hailo-8 AI accelerator, a low-power ARM-based single board computer (SBC), and the Magic Leap 2 AR headset. The proposed system utilises the native WebRTC streaming capabilities of the Magic Leap 2 to continuously stream camera data to the edge co-processor, where a collection of vision AI models-object detection, pose estimation, face recognition, and depth estimation-are executed. The resulting inferences are then streamed back to the headset for spatial re-projection and transmitted to cloud-based systems for further integration with large-scale AI models, such as LLMs and VLMs. This seamless integration enhances real-time contextual understanding in MR while facilitating advanced multi-modal, multi-device collaboration, supporting richer, scalable spatial cognition across distributed systems.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Zhu2025,

title = {A Distributed Content Subscription Mechanism with Revision Discovery to Decouple Content Sharing Platform and Creator ID},

author = {Zhihai Zhu and Ye Tao and Manabu Tsukada and Hiroshi Esaki},

year  = {2025},

date = {2025-02-18},

urldate = {2025-02-18},

booktitle = {International Conference on Artificial Intelligence in Information and Communication (ICAIIC 2025) },

address = {Fukuoka, Japan},

abstract = {Only the chairs can edit This paper proposes a distributed content subscription mechanism that enables content creators to share updates with their audience while maintaining platform independence and anonymity. The mechanism extends the Kademlia distributed hash table (DHT) protocol by incorporating revision numbers and republication timestamps into the DHT key computation, allowing subscribers to discover content updates through heuristic revision queries. It leverages public key cryptography for creator identification and content authenticity, while integrating with established peer-to-peer protocols like BitTorrent for efficient content distribution. Preliminary testing with 200 simulated nodes demonstrates the mechanism's ability to maintain content availability and update discovery even when content creators are offline. This approach particularly benefits creators operating under strict content controls or surveillance, offering them greater creative freedom and distribution autonomy compared to existing centralized and decentralized solutions.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Yamane2025,

title = {Low Latency Redundant Network Architecture for Enhanced 5G Mobile Communication Quality},

author = {Nayuta Yamane and Jin Nakazato and Koki Ito and Manabu Mikami and Takahiro Tsuchiya and Manabu Tsukada and Hiroshi Esaki},

year  = {2025},

date = {2025-01-14},

booktitle = {39th International Conference on Information Networking (ICOIN) 2025},

address = {Chiang Mai, Thailand},

abstract = {With growing demand for high-capacity, low-latency communication driven by the increasing use of video streaming and real-time data applications, efficient data transfer methods have become essential. While 5G technology provides enhanced data transfer capabilities, its directional nature can lead to stability issues, including connection interruptions, frequent handoffs, data loss, and increased latency. To address these challenges, we propose a system architecture with a redundant configuration that separates LTE and 5G-SA within a single MNO, alongside a method to reduce overhead. Initial verification in a stationary environment demonstrated the reduction of latency by 38.1 ms compared to the conventional method, underscoring the potential of our approach for stable and efficient data transmission.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Lin2024c,

title = {A Rule-Compliance Path Planner for Lane-Merge Scenarios Based on Responsibility-Sensitive Safety},

author = {Pengfei Lin and Ehsan Javanmardi and Yuze Jiang and Manabu Tsukada},

doi = {10.1109/ICARCV63323.2024.10821557},

year  = {2024},

date = {2024-12-12},

urldate = {2024-12-12},

booktitle = {2024 18th International Conference on Control, Automation, Robotics and Vision (ICARCV)},

address = {Dubai, UAE},

abstract = {Lane merging is one of the critical tasks for selfdriving cars, and how to perform lane-merge maneuvers effectively and safely has become one of the important standards

in measuring the capability of autonomous driving systems.

However, due to the ambiguity in driving intentions and

right-of-way issues, the lane merging process in autonomous

driving remains deficient in terms of maintaining or ceding

the right-of-way and attributing liability, which could result

in protracted durations for merging and problems such as

trajectory oscillation. Hence, we present a rule-compliance

path planner (RCPP) for lane-merge scenarios, which initially

employs the extended responsibility-sensitive safety (RSS) to

elucidate the right-of-way, followed by the potential field-based

sigmoid planner for path generation. In the simulation, we have

validated the efficacy of the proposed algorithm. The algorithm

demonstrated superior performance over previous approaches

in aspects such as merging time (Saved 72.3%), path length

(reduced 53.4%), and eliminating the trajectory oscillation.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Sugizaki2024,

title = {Digital Twin Based Open Platform for IoT Offloading Control: Enabling System Transparency and User Participation},

author = {Yusuke Sugizaki and Jin Nakazato and Manabu Tsukada},

doi = {10.1145/3732437.3732770},

year  = {2024},

date = {2024-11-28},

urldate = {2024-11-28},

booktitle = {International Conference on Intelligent Computing and its Emerging Applications (ICEA2024)},

pages = {63 - 68},

address = {Tokyo, Japan},

abstract = {In the integrated infrastructure of Society 5.0, efficiently managing complex IoT (Internet of Things) systems is crucial. IoT devices frequently encounter limitations like limited network bandwidth, storage, and processing power, which lead to data congestion and reliance on cloud computing. Recent advancements in edge computing have emphasized hybrid offloading methods. Despite these technological strides, managing IoT systems still presents significant challenges. Typically, these systems are complex and closed, making it difficult for non-specialists to engage with and manage them effectively. This complexity is contrary to the principles of open platforms, which aim to democratize access and control, allowing a broader range of stakeholders to participate in system management. In this paper, we propose a novel system that integrates IoT offloading with a digital twin (DT) on an open web platform, enhancing both the transparency and the inclusivity of IoT system management. The system utilizes a machine learning model to dynamically select the most efficient data processing routes—either edge or cloud—based on real-time network conditions and data volume. Our case study, focused on person detection, employed linear regression and decision tree regression to optimize offloading decisions, achieving accuracies of 73.9 % and 95.7 % respectively. This setup not only demonstrated the effectiveness of the proposed system in real-world scenarios but also highlighted its capability to provide seamless integration and control through a DT interface, thus making complex IoT systems more accessible and manageable.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Chauhan2024b,

title = {Connected Shared Spaces: Expert Insights into the Impact of eHMI and SPIU for Next-Generation Pedestrian-AV Communication},

author = {Vishal Chauhan and Anubhav Anubhav and Chia-Ming Chang and Jin Nakazato and Ehsan Javanmardi and Alex Orsholits and Takeo Igarashi and Kantaro Fujiwara and Manabu Tsukada},

doi = {10.1145/3732437.3732752},

year  = {2024},

date = {2024-11-28},

urldate = {2024-11-28},

booktitle = {International Conference on Intelligent Computing and its Emerging Applications (ICEA2024)},

pages = {16 - 20},

address = {Tokyo, Japan},

abstract = {Increasing prevalence of Autonomous Vehicles (AVs) necessitates efficient communication with susceptible road users, especially pedestrians, in communal urban areas. To improve pedestrians’ trust and safety, Smart Pole Interaction Units (SPIU) and external Human-Machine Interfaces (eHMI) have become crucial interfaces. In this study, we ask 12 automotive UI design experts to evaluate eHMI, SPIU, and eHMI+SPIU through an online survey. They evaluated the interfaces’ effects on five key parameters: Safety, Seamless, Adaptability, Accessibility, and Trust. Our findings show that eHMI stands out for its smooth integration (Seamless), whereas SPIU is favoured for fostering Safety, Adaptability, Accessibility, and Trust. Furthermore, an integrated eHMI+SPIU solution is rated higher than individual eHMI and SPIU. In particular, when several AVs interact, the best way to promote pedestrian trust is to employ eHMI in conjunction with SPIU. This study highlights the benefits of SPIU as a centralised information hub for reliable pedestrian communication and presents innovative design considerations for eHMI on AVs in shared spaces. The results provide a framework for more practical testing of these systems to create safe, inclusive, and human-centric pedestrian-AV interactions in various urban environments beyond shared spaces.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Nakazato2024,

title = {Toward 6G Mobility Networks: A Proposal for Cell-Free Cooperative Distributed Beamforming},

author = {Jin Nakazato and Sojin Ozawa and Yuki Sasaki and Kengo Suzuki and Kazuki Maruta andTetsuya Iye and Yuki Susukida and Eisaku Sato and Manabu Tsukada},

doi = {10.1145/3732437.3732750},

year  = {2024},

date = {2024-11-28},

urldate = {2024-11-28},

booktitle = {International Conference on Intelligent Computing and its Emerging Applications (ICEA2024)},

address = {Tokyo, Japan},

abstract = {This paper proposes a hybrid beamforming architecture utilizing multiple distributed Roadside Units (RSUs) to improve the overall channel capacity of millimeter-wave (mmWave) vehicular networks. The proposed system leverages a cell-free mobility network architecture with distributed RSUs, enhancing communication performance in Vehicle-to-Everything (V2X) scenarios. Through computer simulations, we demonstrate that increasing the number of distributed RSUs leads to improved channel capacity, even though the per-RSU Signal-to-Noise Ratio (SNR) decreases due to reduced transmit power and fewer antenna elements. Furthermore, our results show that the proposed architecture can effectively mitigate interference and support reliable communications, making it a viable approach for future 6G autonomous driving systems. Future work will include extending the proposed method to environments with multiple Connected Autonomous Vehicles (CAVs) and varying mobility patterns to verify its robustness and scalability.

},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Kambara2024,

title = {Geographic-Aware Network Analysis and Visualization System for CAVs},

author = {Koichi Kambara and Ehsan Javanmardi and Jin Nakazato and Shunya Yamada and Hiroaki Takada and Yousuke Watanabe and Kenya Sato and Manabu Tsukada},

doi = {10.1145/3732437.3732743},

year  = {2024},

date = {2024-11-28},

urldate = {2024-11-28},

booktitle = {International Conference on Intelligent Computing and its Emerging Applications (ICEA2024)},

address = {Tokyo, Japan},

abstract = {Recently, connected autonomous vehicles (CAVs) have attracted increasing attention owing to their potential to improve traffic safety and increase traffic flow by utilizing vehicle-to-everything (V2X) communication capabilities. One of the key requirements for CAVs is ensuring that each vehicle sends/receives the message at the proper time and place; therefore, it is essential to meet the specific communication conditions for sending/receiving V2X messages. The analysis/visualization of measured data in CAVs is also indispensable. However, existing network analyzers for CAV applications do not consider geographic characteristics. This paper proposes a geographic-aware CAV-specific network analysis and visualization system that reports key real-time network performance indicators like packet loss, bandwidth, and jitter. We developed and evaluated a prototype of the system through two outdoor experiments conducted in dedicated and residential areas in Japan. We confirmed that the implemented systems were tied to geographic characteristics and successfully worked in the two areas. Furthermore, we analyzed multiple methods to interpolate data gaps in the data acquisition during the data acquisition period of CAVs caused by their velocity and demonstrated the effectiveness of propagation-based methods.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Dolatabadi2024,

title = {Neural Error Covariance Estimation for Precise LIDAR Localization},

author = {Minoo Dolatabadi and Fardin Ayar and Ehsan Javanmardi and Manabu Tsukada and Mahdi Javanmardi},

url = {https://arxiv.org/abs/2501.02558},

doi = {10.1145/3732437.3732738},

year  = {2024},

date = {2024-11-28},

urldate = {2024-11-28},

booktitle = {International Conference on Intelligent Computing and its Emerging Applications (ICEA2024)},

pages = {21 - 26},

address = {Tokyo, Japan},

abstract = {Autonomous vehicles have gained significant attention due to technological advancements and their potential to transform transportation. A critical challenge in this domain is precise localization, particularly in LiDAR-based map matching, which is prone to errors due to degeneracy in the data. Most sensor fusion techniques, such as the Kalman filter rely on accurate error covariance estimates for each sensor to improve localization accuracy. However, obtaining reliable covariance values for map matching remains a complex task. To address this challenge, we propose a neural network-based framework for predicting localization error covariance in LiDAR map matching. To achieve this, we introduce a novel dataset generation method specifically designed for error covariance estimation. In our evaluation using a Kalman filter, we achieved a 2 cm improvement in localization accuracy, a significant enhancement in this domain.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Zakerian2024,

title = {Enhancing Unsupervised Person Re-Identification with GAN-Driven Multi-Pose Augmentation},

author = {Romina Zakerian and Ehsan Javanmardi and Manabu Tsukada and Mahdi Javanmardi and Mohammad Rahmati},

doi = {10.1145/3732437.3732742},

year  = {2024},

date = {2024-11-28},

urldate = {2024-11-28},

booktitle = {International Conference on Intelligent Computing and its Emerging Applications (ICEA2024)},

pages = {27 - 32},

address = {Tokyo, Japan},

abstract = {Person re-identification is a crucial computer vision task, particularly for surveillance systems. This process aims to retrieve the identity of individuals across non-overlapping camera views. Despite significant advancements, the manual annotation process makes real-world deployments less scalable. To address this challenge, data augmentation techniques such as Generative Adversarial Networks (GANs) have proven effective in various studies. However, there is limited research combining unsupervised learning with GAN-based data augmentation for person re-identification. This study proposes leveraging unsupervised learning and GANs to enhance person re-identification. We generate images of the same person in a new pose using GANs and utilize these images across different independent methods to train the person re-identification model. The goal is to improve model robustness and generalization by exposing it to a wider range of poses and appearance variations. We explore four distinct methods to enhance model learning through data augmentation and evaluate their performance. The results demonstrate that our approach consistently outperforms the baseline methods, leading to an improvement of 4.1 percent in Rank-1 and 13.1 percent in mAP.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Ayar2024,

title = {LiDAR-Camera Fusion for Video Panoptic Segmentation without Video Training},

author = {Fardin Ayar and Ehsan Javanmardi and Manabu Tsukada and Mahdi Javanmardi and Mohammad Rahmati},

url = {https://arxiv.org/abs/2412.20881},

doi = {10.1145/3732437.3732763},

year  = {2024},

date = {2024-11-28},

urldate = {2024-11-28},

booktitle = {International Conference on Intelligent Computing and its Emerging Applications (ICEA2024)},

pages = {1-7},

address = {Tokyo, Japan},

abstract = {Panoptic segmentation, which combines instance and semantic segmentation, has gained a lot of attention in autonomous vehicles, due to its comprehensive representation of the scene. This task can be applied to cameras and LiDAR sensors, but there has been a limited focus on combining both sensors to enhance image panoptic segmentation (PS). Although previous research has acknowledged the benefit of 3D data on camera-based scene perception, no specific study has explored the influence of 3D data on image and video panoptic segmentation (VPS). This work seeks to introduce a feature fusion module that enhances PS and VPS by fusing LiDAR and image data for autonomous vehicles. We also illustrate that, in addition to this fusion, our proposed model, which utilizes two simple modifications, can further deliver even more high-quality VPS without being trained on video data. The results demonstrate a substantial improvement in both the image and video panoptic segmentation evaluation metrics by up to 5 points.},

note = {Best Paper Award (Bronze)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{nokey,

title = {Where Do You Go? Pedestrian Trajectory Prediction using Scene Features},

author = {Mohammad Ali Rezaei and Fardin Ayar and Ehsan Javanmardi and Manabu Tsukada and Mahdi Javanmardi},

url = {https://arxiv.org/abs/2501.13848},

doi = {10.1145/3732437.3732751},

year  = {2024},

date = {2024-11-28},

urldate = {2024-11-28},

booktitle = {International Conference on Intelligent Computing and its Emerging Applications (ICEA2024)},

pages = {123 - 128},

address = {Tokyo, Japan},

abstract = {Accurate prediction of pedestrian trajectories is crucial for enhancing the safety of autonomous vehicles and reducing traffic fatalities involving pedestrians. While numerous studies have focused on modeling interactions among pedestrians to forecast their movements, the influence of environmental factors and scene-object placements has been comparatively underexplored. In this paper, we present a novel trajectory prediction model that integrates both pedestrian interactions and environmental context to improve prediction accuracy. Our approach captures spatial and temporal interactions among pedestrians within a sparse graph framework. To account for pedestrian-scene interactions, we employ advanced image enhancement and semantic segmentation techniques to extract detailed scene features. These scene and interaction features are then fused through a cross-attention mechanism, enabling the model to prioritize relevant environmental factors that influence pedestrian movements. Finally, a temporal convolutional network processes the fused features to predict future pedestrian trajectories. Experimental results demonstrate that our method significantly outperforms existing state-of-the-art approaches, achieving ADE and FDE values of 0.252 and 0.372 meters, respectively, underscoring the importance of incorporating both social interactions and environmental context in pedestrian trajectory prediction.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Li2024,

title = {Cross-Attention Enhanced Imitation Learning for End-to-end Autonomous Driving in Unprotected Turns},

author = {Dongyang Li and Ehsan Javanmardi and Naren Bao and Manabu Tsukada},

doi = {10.1145/3732437.3732764},

year  = {2024},

date = {2024-11-28},

urldate = {2024-11-28},

booktitle = {International Conference on Intelligent Computing and its Emerging Applications (ICEA2024)},

pages = {81 - 86},

address = {Tokyo, Japan},

abstract = {Performing an unprotected turn in the intersection is a complex scenario for autonomous vehicles. It not only requires a comprehensive understanding of the surrounding environment but also highly relies on the ego vehicle’s current state to make safe decisions. A conventional way to learn end-to-end autonomous driving is imitation learning, which is learning from expert demonstrations. While most imitation learning methods focus on imitating the expert action, they often fail to imitate a complex policy efficiently when the ego vehicle’s states are crucial to the scenario because there might be arbitrary optimal actions under different states. To address this issue and investigate how vehicle states affect autonomous driving, we present a novel cross-attention enhanced imitation learning approach for end-to-end autonomous driving in unprotected turns, focusing on capturing the relationships between the ego vehicle’s states and its perception of the environment. We evaluate our model in AWSIM, an open-source autonomous driving

simulator, and the results demonstrate that our model outperformed conventional imitation learning-based baselines in performing unprotected turn scenarios, showcasing its ability to imitate a complex policy efficiently.},

note = {Best Paper Award (Silver)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Orsholits2024b,

title = {PLATONE: Assessing Simulation Accuracy of Environment-Dependent Audio Spatialization},

author = {Alex Orsholits and Eric Nardini and Tsukada Manabu},

doi = {10.1145/3732437.3732746},

year  = {2024},

date = {2024-11-28},

urldate = {2024-11-28},

booktitle = {International Conference on Intelligent Computing and its Emerging Applications (ICEA2024)},

pages = {57 - 62},

address = {Tokyo, Japan},

abstract = {As the convergence of physical and virtual spaces gains importance in the Internet of Realities (IoR), accurate spatial audio is critical for enhancing immersive urban experiences. In previous work, PLATONE [2] introduced a platform for city-scale, environment-dependent audio spatialization using 3D georeferenced data. Expanding on this foundation, this paper presents a preliminary assessment of PLATONE’s audio simulation accuracy in Montreux, Switzerland, utilizing 3D building and topographic data from the Swiss Federal Office of Topography (swisstopo). By comparing real-world audio propagation—captured in-situ using high-resolution microphones—with simulated audio rendered via PLATONE, this study aims to evaluate the platform’s precision in a new urban context. The findings highlight the impact of environmental factors such as topography and building geometry on the spatialization model, providing insights for improving large-scale immersive audio systems.

},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Grosset2024,

title = {Generation of V2X messages from Carla Simulator for cooperative perception: Application to pedestrian safety},

author = {Juliette Grosset and Jean-Marie Bonnin and Alain-Jérôme Fougères and Manabu Tsukada and Moise Djoko-Kouam},

doi = {10.1109/VTC2024-Fall63153.2024.10757467},

year  = {2024},

date = {2024-10-07},

urldate = {2024-10-07},

booktitle = {The IEEE 100th Vehicular Technology Conference (VTC2024-Fall)},

address = {Washington DC, USA},

abstract = {Despite advancements in connected and autonomous vehicles (CAVs), vulnerable road users (VRUs) face a challenge as they lack Communication-Intelligent Transport System (C-ITS) equipment. This deficiency impedes their interaction with CAVs. We underscore the significance of Vehicle-to-Everything (V2X) communication in enhancing road safety with VRUs by facilitating information exchange between CAVs and the infrastructure. This communication is pivotal for reintegrating VRUs into the environmental awareness of CAVs. The Carla Simulator, used for autonomous vehicle training, currently lacks comprehensive V2X communication capabilities. In response, we propose an architecture for Carla, integrating OpenCDA and ROS2 to establish a simulated V2X network communication system for CAVs and roadside units (RSUs) within the Carla environment. This setup allows for the generation of V2X datasets and the refinement of algorithms for Advanced Driver Assistance Systems (ADAS). To illustrate and assess our proposed architecture, we present a scenario involving a pedestrian concealed in a blind spot for a connected vehicle.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Yun2024,

title = {Large Language Models for Human-like Autonomous Driving Decision Making: A Survey},

author = {Yun Li and Kai Katsumata and Ehsan Javanmardi and Manabu Tsukada},

doi = {10.1109/ITSC58415.2024.10919629},

year  = {2024},

date = {2024-09-24},

urldate = {2024-09-24},

booktitle = {27th IEEE International Conference on Intelligent Transportation Systems (ITSC 2024)},

address = {Edmonton, Canada},

abstract = {Large Language Models (LLMs), AI models trained on massive text corpora with remarkable language understanding and generation capabilities, are transforming the field of Autonomous Driving (AD). As AD systems evolve from rule-based and optimization-based methods to learning-based techniques like deep reinforcement learning, they are now poised to embrace a third and more advanced category: knowledge-based AD empowered by LLMs. This shift promises to bring AD closer to human-like AD. However, integrating LLMs into AD systems poses challenges in real-time inference, safety assurance, and deployment costs. This survey provides a comprehensive and critical review of recent progress in leveraging LLMs for AD, focusing on their applications in modular AD pipelines and end- to-end AD systems. We highlight key advancements, identify pressing challenges, and propose promising research directions to bridge the gap between LLMs and AD, thereby facilitating the development of more human-like AD systems. The survey first introduces LLMs’ key features and common training schemes, then delves into their applications in modular AD pipelines and end-to-end AD, respectively, followed by discussions on open challenges and future directions. Through this in-depth analysis, we aim to provide insights and inspiration for researchers and practitioners working at the intersection of AI and autonomous vehicles, ultimately contributing to safer, smarter, and more human-centric AD technologies.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Jiang2024b,

title = {Accurate Cooperative Localization Utilizing LiDAR-equipped Roadside Infrastructure for Autonomous Driving},

author = {Yuze Jiang and Ehsan Javanmardi and Manabu Tsukada and Hiroshi Esaki},

url = {https://arxiv.org/abs/2407.08384 },

doi = {10.1109/ITSC58415.2024.10920101},

year  = {2024},

date = {2024-09-24},

urldate = {2024-09-24},

booktitle = {27th IEEE International Conference on Intelligent Transportation Systems (ITSC 2024)},

address = {Edmonton, Canada},

abstract = {Recent advancements in LiDAR technology have significantly lowered costs and improved both its precision and resolution, thereby solidifying its role as a critical component in autonomous vehicle localization. Using sophisticated 3D reg- istration algorithms, LiDAR now facilitates vehicle localization with centimeter-level accuracy. However, these high-precision techniques often face reliability challenges in environments devoid of identifiable map features. To address this limitation, we propose a novel approach that utilizes road side units (RSU) with vehicle-to-infrastructure (V2I) communications to assist vehicle self-localization. By using RSUs as stationary reference points and processing real-time LiDAR data, our method enhances localization accuracy through a cooperative localization framework. By placing RSUs in critical areas, our proposed method can improve the reliability and precision of vehicle localization when the traditional vehicle self-localization technique falls short. Evaluation results in an end-to-end autonomous driving simulator AWSIM show that the proposed method can improve localization accuracy by up to 80% under vulnerable environments compared to traditional localization methods. Additionally, our method also demonstrates robust resistance to network delays and packet loss in heterogeneous network environments.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Gui2024,

title = {Shrinkable Arm-based eHMI on Autonomous Delivery Vehicle for Effective Communication with Other Road Users},

author = {Xinyue Gui and Mikiya Kusunoki and Bofei Huang and Stela Hanbyeol Seo and Chia-Ming Chang and Haoran Xie and Manabu Tsukada and Takeo Igarashi},

doi = {10.1145/3640792.3675716},

year  = {2024},

date = {2024-09-22},

urldate = {2024-09-22},

booktitle = {16th International ACM Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutoUI 2024)},

address = {California, USA},

abstract = {When employing autonomous driving technology in logistics, small autonomous delivery vehicles (aka delivery robots) encounter challenges different from passenger vehicles when interacting with other road users. We conducted an online video survey as a pre-study and found that autonomous delivery vehicles need external human-machine interfaces (eHMIs) to ask for help due to their small size and functional limitations. Inspired by everyday human communication, we chose arms as eHMI to show their request through limb motion and gesture. We held an in-house workshop to identify the arm’s requirements for designing a specific arm with shrink-ability (conspicuous when delivering messages but not affect traffic at other times). We prototyped a small delivery robot with a shrinkable arm and filmed the experiment videos. We conducted two studies (a video-based and a 360-degree-photo VR-based) with 18 participants. We demonstrated that arm-on-delivery robots can increase interaction efficiency by drawing more attention and communicating specific information.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Chauhan2024,

title = {Transforming Pedestrian and Autonomous Vehicles Interactions in Shared Spaces: A Think-Tank Study on Exploring Human-Centric Designs},

author = {Vishal Chauhan and Anubhav Anubhav and Chia-Ming Chang and Jin Nakazato and Ehsan Javanmardi and Alex Orsholits and Takeo Igarashi and Kantaro Fujiwara and Manabu Tsukada



},

doi = {10.1145/3641308.3685037},

year  = {2024},

date = {2024-09-22},

urldate = {2024-09-22},

booktitle = {16th International ACM Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutoUI 2024), Work in Progress (WiP)},

pages = {1-8},

address = {California, USA},

abstract = {Our research focuses on the smart pole interaction unit (SPIU) as an infrastructure external human-machine interface (HMI) to enhance pedestrian interaction with autonomous vehicles (AVs) in shared spaces. We extensively study SPIU with external human-machine interfaces (eHMI) on AVs as an integrated solution. To discuss interaction barriers and enhance pedestrian safety, we engaged 25 participants aged 18-40 to brainstorm design solutions for pedestrian-AV interactions, emphasising effectiveness, simplicity, visibility, and clarity. Findings indicate a preference for real-time SPIU interaction over eHMI on AVs in multiple AV scenarios. However, the combined use of SPIU and eHMI on AVs is crucial for building trust in decision-making. Consequently, we propose innovative design solutions for both SPIU and eHMI on AVs, discussing their pros and cons. This study lays the groundwork for future autonomous mobility solutions by developing human-centric eHMI and SPIU prototypes as ieHMI.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Trumpp2024,

title = {RaceMOP: Mapless Online Path Planning for Multi-Agent Autonomous Racing using Residual Policy Learning},

author = {Raphael Trumpp and Ehsan Javanmardi and Jin Nakazato and Manabu Tsukada and Marco Caccamo},

url = {http://github.com/raphajaner/racemop},

doi = {10.1109/IROS58592.2024.10801657},

year  = {2024},

date = {2024-09-14},

urldate = {2024-09-14},

booktitle = {The 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024)},

address = {Abu Dhabi ,UAE},

abstract = {The interactive decision-making in multi-agent autonomous racing offers insights valuable beyond the domain of self-driving cars. Mapless online path planning is particularly of practical appeal but poses a challenge for safely overtaking opponents due to the limited planning horizon. Accordingly, this paper introduces RaceMOP, a novel method for mapless online path planning designed for multi-agent racing of F1TENTH cars. Unlike classical planners that depend on predefined racing lines, RaceMOP operates without a map, relying solely on local observations to overtake other race cars at high speed. Our approach combines an artificial potential field method as a base policy with residual policy learning to introduce long-horizon planning capabilities. We advance the field by introducing a novel approach for policy fusion with the residual policy directly in probability space. Our experiments for twelve simulated racetracks validate that RaceMOP is capable of long-horizon decision-making with robust collision avoidance during over- taking maneuvers. RaceMOP demonstrates superior handling over existing mapless planners while generalizing to unknown racetracks, paving the way for further use of our method in robotics. We make the open-source code for RaceMOP available at http://github.com/raphajaner/racemop.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Orsholits2024,

title = {PLATONE: An Immersive Geospatial Audio Spatialization Platform},

author = {Alex Orsholits and Yiyuan Qian and Eric Nardini and Yusuke Obuchi and Manabu Tsukada},

doi = {10.1109/MetaCom62920.2024.00020},

year  = {2024},

date = {2024-08-12},

urldate = {2024-08-12},

booktitle = {The 2nd Annual IEEE International Conference on Metaverse Computing, Networking, and Applications (MetaCom 2024)},

address = {Hong Kong, China},

abstract = {In the rapidly evolving landscape of mixed reality (MR) and spatial computing, the convergence of physical and virtual spaces is becoming increasingly crucial for enabling immersive, large-scale user experiences and shaping inter-reality dynamics. This is particularly significant for immersive audio at city-scale, where the 3D geometry of the environment must be considered, as it drastically influences how sound is perceived by the listener. This paper introduces PLATONE, a novel proof-of-concept MR platform designed to augment urban contexts with environment-dependent spatialized audio. It leverages custom hardware for localization and orientation, alongside a cloud-based pipeline for generating real-time binaural audio. By utilizing open-source 3D building datasets, sound propagation effects such as occlusion, reverberation, and diffraction are accurately simulated. We believe that this work may serve as a compelling foundation for further research and development.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Takada2024,

title = {Design of Digital Twin Architecture for 3D Audio Visualization in AR},

author = {Tokio Takada and Jin Nakazato and Alex Orsholits and Manabu Tsukada and Hideya Ochiai and Hiroshi Esaki},

doi = {10.1109/MetaCom62920.2024.00044},

year  = {2024},

date = {2024-08-12},

urldate = {2024-08-12},

booktitle = {The 2nd Annual IEEE International Conference on Metaverse Computing, Networking, and Applications (MetaCom 2024)},

address = {Hong Kong, China},

abstract = {Digital twins have recently attracted attention from academia and industry as a technology connecting physical space and cyberspace. Digital twins are compatible with Augmented Reality (AR) and Virtual Reality (VR), enabling us to understand information in cyberspace. In this study, we focus on music and design an architecture for a 3D representation of music using a digital twin. Specifically, we organize the requirements for a digital twin for music and design the architecture. We establish a method to perform 3D representation in cyberspace and map the recorded audio data in physical space. In this paper, we implemented the physical space representation using a smartphone as an AR device and employed a visual positioning system (VPS) for self-positioning. For evaluation, in addition to system errors in the 3D representation of audio data, we conducted a questionnaire evaluation with several users as a user study. From these results, we evaluated the effectiveness of the implemented system. At the same time, we also found issues we need to improve in the implemented system in future works.},

key = {CREST},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Iwaki2024b,

title = {Enhancing V2X Communication: Machine Learning Assisted Dynamic mmWave Beam Search},

author = {Ryo Iwaki and Jin Nakazato and Kazuki Maruta and Manabu Tsukada and Hideya Ochiai and Hiroshi Esaki},

doi = {10.1109/ICUFN61752.2024.10625435},

year  = {2024},

date = {2024-07-02},

urldate = {2024-07-02},

booktitle = {The 15th International Conference on Ubiquitous and Future Networks (ICUFN2024)},

address = {Budapest, Hungary},

abstract = {Only the chairs can edit This paper addresses the challenges of dynamic beam search in millimeter wave (mmWave) communications for vehicle-to-everything (V2X) applications. With the rapid mobility of connected autonomous vehicles (CAVs) and dense urban environments, maintaining high-quality mmWave connections is critical for the reliability and efficiency of V2X communications. We propose a novel machine learning-assisted framework for dynamic mmWave beam search, which significantly enhances the adaptability and performance of V2X communication systems. Our approach leverages real-time environmental data and CAV dynamics to predict optimal beam directions, improving connection stability. Simulation results demonstrate the effectiveness of the proposed method in a real-world road scenario, offering a partial improvement over conventional beam search techniques.},

note = {Best Paper Award},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Yoshimura2024,

title = {Towards Robust Communication in ITS: A Comprehensive Study of Blockchain for V2I},

author = {Atsuki Yoshimura and Jin Nakazato and Manabu Tsukada and Hiroshi Esaki},

doi = {10.1109/ICUFN61752.2024.10624948},

year  = {2024},

date = {2024-07-02},

urldate = {2024-07-02},

booktitle = {The 15th International Conference on Ubiquitous and Future Networks (ICUFN2024)},

address = {Budapest, Hungary},

abstract = {V2X in connected autonomous vehicles (CAV) plays an important role in information sharing through communication. The integration of V2X and blockchain has the potential to create functionalities such as seamless V2X information sharing, similar to Bitcoin, and post-accident investigation utilities that leverage data immutability. However, the integration of blockchain into V2X communication requires addressing CAV mobility. In this study, we propose a framework that takes into account the high mobility of CAVs. Furthermore, we propose a method that not only addresses this challenge but also achieves load balancing by facilitating cooperation among nodes responsible for member management. In this paper, we integrate the ITS simulator, the communication simulator, and the blockchain simulator to build an infrastructure that can be evaluated end-to-end. Using the integrated simulator, we perform an evaluation based on metrics such as latency and member change rate in a mobile environment with a single roadside unit (RSU). In the future, we plan to implement the proposed methodology and perform evaluations in environments with multiple RSUs.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Chi2024,

title = {V2I Blockage Modeling and Performance Evaluation for Connected Autonomous Vehicle},

author = {Weiqi Chi and Jin Nakazato and Tomoki Murakami and Manabu Tsukada},

doi = {10.1109/VTC2024-Spring62846.2024.10683381},

year  = {2024},

date = {2024-06-24},

urldate = {2024-06-24},

booktitle = {The IEEE 99th Vehicular Technology Conference (VTC2024-Spring)},

address = {Singapore},

abstract = {The burgeoning Intelligent Transportation System (ITS) spurs global technological advancements, notably in innovative community development through vehicle-to-everything (V2X) communication. This study focuses on the high data rates and low latency offered by a millimeter-wave (mmWave) enabled vehicular network while addressing the significant challenge of link quality degradation due to blockages, exacerbated by the mmWave band’s small wavelength in high mobility and traffic conditions. We propose an RSU-assisted ITS system tailored for multi-lane, straight-road scenarios, effectively identifying blockage status for vehicles. Combining Simulation of Urban Mobility (SUMO) and MATLAB, this blockage-aware scheme lays the groundwork for future ITS enhancements. The research also delves into the effects of various frequency bands, vehicle types, and communication ranges, offering a holistic system performance analysis.},

note = {IEEE VTS Tokyo/Japan Chapter Young Researcher's Encouragement Award},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Ito2024,

title = {Enhancing Real-Time Streaming Quality through a Multipath Redundant Communication Framework},

author = {Koki Ito and Jin Nakazato and Romain Fontugne and Manabu Tsukada and Hiroshi Esaki},

doi = {10.23919/IFIPNetworking62109.2024.10619885},

year  = {2024},

date = {2024-06-03},

urldate = {2024-06-03},

booktitle = {IFIP/IEEE Networking 2024},

address = {Thessaloniki, Greece},

abstract = {Recently, as networks operate as the infrastructure of modern society, the demands placed on the network by applications have become more complex. In particular, an increasing annual demand for high-capacity and low-latency services, including real-time streaming. 5G services have been launched to meet this demand, but their stability varies de- pending on location and time and can only sometimes be considered sufficient. One method to improve communication stability is multipath redundant communication, and much research has been conducted in this area. However, most of this research has focused on TCP-based communication and cannot be applied to real-time UDP streaming. Hence, we propose a multipath redundant communication framework to improve the quality of real-time media streaming communication. Tunneling at the IP layer in our proposed framework was performed to overcome the limitations of transport layer protocols, which was a challenge for traditional multipath redundant communication systems. Furthermore, to address the packet order inconsistency caused by multipath redundant communication, a buffering mechanism was implemented on the receiving side of our system. Our proposed system was verified using multipath redundant communication and multiple mobile networks from a vehicle moving in an urban area. The experiments used a real-time streaming application based on WebRTC, and the framework significantly reduced packet loss and improved bitrate compared to existing multipath redundant communication systems without interfering with the application’s congestion control.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Tao2024b,

title = {Zero-Knowledge Proof of Distinct Identity: a Standard-compatible Sybil-resistant Pseudonym Extension for C-ITS},

author = {Ye Tao and Hongyi Wu and Ehsan Javanmardi and Manabu Tsukada and Hiroshi Esaki},

url = {https://arxiv.org/abs/2403.14020},

doi = {10.1109/IV55156.2024.10588511},

year  = {2024},

date = {2024-06-02},

urldate = {2024-06-02},

booktitle = {35th IEEE Intelligent Vehicles Symposium (IV2024)},

address = {Jeju Island, Korea},

abstract = {Pseudonyms are widely used in Cooperative Intelligent Transport Systems (C-ITS) to protect the location privacy of vehicles. However, the unlinkability nature of pseudonyms also enables Sybil attacks, where a malicious vehicle can pretend to be multiple vehicles at the same time. In this paper, we propose a novel protocol called zero-knowledge Proof of Distinct Identity (zk-PoDI,) which allows a vehicle to prove that it is not the owner of another pseudonym in the local area, without revealing its actual identity. Zk-PoDI is based on the Diophantine equation and zk-SNARK, and does not rely on any specific pseudonym design or infrastructure assistance. We show that zk-PoDI satisfies all the requirements for a practical Sybil-resistance pseudonym system, and it has low latency, adjustable difficulty, moderate computation overhead, and negligible communication cost. We also discuss the future work of implementing and evaluating zk-PoDI in a realistic city-scale simulation environment.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}