Publication
2024
鈴木健吾, 中里仁, 丸田一輝, エッサン ジャワーンマーディ, 塚田学, 江崎浩, "協調型自動運転における複数路側機からの安定したビーム送信の検討", 無線通信システム研究会(RCS), 東北大学 青葉記念会館, 2024.Conference | BibTeX
@conference{鈴木健吾2024,
title = {協調型自動運転における複数路側機からの安定したビーム送信の検討},
author = {鈴木健吾 and 中里仁 and 丸田一輝 and エッサン ジャワーンマーディ and 塚田学 and 江崎浩},
year = {2024},
date = {2024-01-18},
urldate = {2024-01-18},
booktitle = {無線通信システム研究会(RCS)},
address = {東北大学 青葉記念会館},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Ryo Iwaki, Jin Nakazato, Muhammad Asad, Ehsan Javanmardi, Kazuki Maruta, Manabu Tsukada, Hideya Ochiai, Hiroshi Esaki, "Optimizing mmWave Beamforming for High-Speed Connected Autonomous Vehicles: An Adaptive Approach", 2024 IEEE 21st Consumer Communications & Networking Conference (CCNC), Poster, 2024.Miscellaneous | Abstract | BibTeX | Links:
@misc{Iwaki2024,
title = {Optimizing mmWave Beamforming for High-Speed Connected Autonomous Vehicles: An Adaptive Approach},
author = {Ryo Iwaki and Jin Nakazato and Muhammad Asad and Ehsan Javanmardi and Kazuki Maruta and Manabu Tsukada and Hideya Ochiai and Hiroshi Esaki},
url = {https://tlab.hongo.wide.ad.jp/papers/2023_CCNC2023_poster_Iwaki.pdf},
year = {2024},
date = {2024-01-06},
urldate = {2024-01-06},
abstract = {The commercialization of 5G has been initiated for a while. Furthermore, millimeter wave (mmWave) has been introduced to small cells with small coverage due to its strong linearity and non-winding characteristics. On the other hand, in connected autonomous vehicles (CAVs), where various traffic systems can cooperatively perform recognition, decision-making, and execution, communication is assumed to be always connected. Therefore, to use low latency mmWave for high-speed moving CAV, beamforming in 5G cannot follow them at high speed. This paper proposes an improved beam tracking algorithm for high-speed CAVs, which can be evaluated in a more general environment using a traffic simulator. We proposed an adaptive algorithm for a general road environment by increasing the number of beam searches and search dimensions.},
howpublished = {2024 IEEE 21st Consumer Communications & Networking Conference (CCNC), Poster},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
The commercialization of 5G has been initiated for a while. Furthermore, millimeter wave (mmWave) has been introduced to small cells with small coverage due to its strong linearity and non-winding characteristics. On the other hand, in connected autonomous vehicles (CAVs), where various traffic systems can cooperatively perform recognition, decision-making, and execution, communication is assumed to be always connected. Therefore, to use low latency mmWave for high-speed moving CAV, beamforming in 5G cannot follow them at high speed. This paper proposes an improved beam tracking algorithm for high-speed CAVs, which can be evaluated in a more general environment using a traffic simulator. We proposed an adaptive algorithm for a general road environment by increasing the number of beam searches and search dimensions.
2023
Kazuto Matsumoto, Ehsan Javanmardi, Jin Nakazato, Manabu Tsukada, "Localizability Estimation for Autonomous Driving: A Deep Learning-Based Place Recognition Approach", In: IEEE Robotic Computing 2023, California, USA, 2023.Proceedings Article | Abstract | BibTeX
@inproceedings{Matsumoto2023b,
title = {Localizability Estimation for Autonomous Driving: A Deep Learning-Based Place Recognition Approach},
author = {Kazuto Matsumoto and Ehsan Javanmardi and Jin Nakazato and Manabu Tsukada},
year = {2023},
date = {2023-12-11},
booktitle = {IEEE Robotic Computing 2023},
address = {California, USA},
abstract = {In recent years, research and development aimed at the societal implementation of autonomous driving have attracted increasing attention. Localization, which involves obtaining in- formation about the surrounding environment from sensor data and estimating the vehicle’s position, is necessary for realizing autonomous driving. Localization is commonly performed with 3D LiDAR as a sensor owing to its high measurement accuracy and immunity to ambient light conditions, which allow for precise localization. However, localization accuracy may decrease when the surrounding area does not have distinctive features. In this study, we proposed a method based on deep learning to estimate localization accuracy for autonomous driving. The overall localization accuracy can be improved by estimating the accuracy of localization using other sensors, such as GNSS and IMU, or pavement markings in areas with poor accuracy. We created a dataset for estimating localization accuracy using an open-source autonomous driving simulator. In an experiment, we applied the proposed method to the created dataset. Estimations with low MSE were obtained. The results indicate that the proposed method can accurately estimate localization accuracy.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In recent years, research and development aimed at the societal implementation of autonomous driving have attracted increasing attention. Localization, which involves obtaining in- formation about the surrounding environment from sensor data and estimating the vehicle’s position, is necessary for realizing autonomous driving. Localization is commonly performed with 3D LiDAR as a sensor owing to its high measurement accuracy and immunity to ambient light conditions, which allow for precise localization. However, localization accuracy may decrease when the surrounding area does not have distinctive features. In this study, we proposed a method based on deep learning to estimate localization accuracy for autonomous driving. The overall localization accuracy can be improved by estimating the accuracy of localization using other sensors, such as GNSS and IMU, or pavement markings in areas with poor accuracy. We created a dataset for estimating localization accuracy using an open-source autonomous driving simulator. In an experiment, we applied the proposed method to the created dataset. Estimations with low MSE were obtained. The results indicate that the proposed method can accurately estimate localization accuracy.
岩城燎, 中里仁, 小澤爽仁, 丸田一輝, ムハマド アサード, エッサン ジャワーンマーディ, 塚田学, 落合秀也, 江崎浩, "一般道路環境における高速ビーム追従の適応的アルゴリズムの提案", 無線通信システム研究会(RCS), 熊本県, 2023.Conference | Abstract | BibTeX | Links:
@conference{Iwaki2023,
title = {一般道路環境における高速ビーム追従の適応的アルゴリズムの提案},
author = {岩城燎 and 中里仁 and 小澤爽仁 and 丸田一輝 and ムハマド アサード and エッサン ジャワーンマーディ and 塚田学 and 落合秀也 and 江崎浩},
url = {https://tlab.hongo.wide.ad.jp/papers/2023_RCS_Iwaki.pdf},
year = {2023},
date = {2023-11-15},
urldate = {2023-11-15},
booktitle = {無線通信システム研究会(RCS)},
address = {熊本県},
abstract = {2019年より世界中でサービスが開始された5Gでは,ミリ波が移動体通信として初めて導入された.ミリ波は直進性が強く,回り込みしない特徴からカバレッジが小さいスモールセルへの導入がされている.一方で,様々な交通システムが協調的に認知,判断,実行を担える協調型自動運転では,通信に常時繋がることが前提とされている.高速移動する車両に対して低遅延であるミリ波を用いるためには5Gにおけるビームフォーミングでは高速で追従できない課題がある.そこで本稿では,その課題の1つの解決策となる,高速で移動する車両に対し高速にビーム追従を行うビーム追従アルゴリズムについて,交通シミュレータと連携させることでより一般的な環境で評価することを行うことを可能とする.さらに,ビーム探索数の増加と探索次元の増加方式を提案し,一般的な道路環境にて評価し,適応的なアルゴリズムであることを示した.
},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
2019年より世界中でサービスが開始された5Gでは,ミリ波が移動体通信として初めて導入された.ミリ波は直進性が強く,回り込みしない特徴からカバレッジが小さいスモールセルへの導入がされている.一方で,様々な交通システムが協調的に認知,判断,実行を担える協調型自動運転では,通信に常時繋がることが前提とされている.高速移動する車両に対して低遅延であるミリ波を用いるためには5Gにおけるビームフォーミングでは高速で追従できない課題がある.そこで本稿では,その課題の1つの解決策となる,高速で移動する車両に対し高速にビーム追従を行うビーム追従アルゴリズムについて,交通シミュレータと連携させることでより一般的な環境で評価することを行うことを可能とする.さらに,ビーム探索数の増加と探索次元の増加方式を提案し,一般的な道路環境にて評価し,適応的なアルゴリズムであることを示した.
Naren Bao, Jin Nakazato, Muhammad Asad, Ehsan Javanmardi, Manabu Tsukada, "Towards a Trusted Inter-Reality: Exploring System Architectures for Digital Identification", The 1st International Workshop on Internet of Realities (IoR-WS 2023) at International Conference on the Internet of Things, Nagoya, Japan, 2023.Workshop | Abstract | BibTeX | Links:
@workshop{Bao2023b,
title = {Towards a Trusted Inter-Reality: Exploring System Architectures for Digital Identification},
author = {Naren Bao and Jin Nakazato and Muhammad Asad and Ehsan Javanmardi and Manabu Tsukada},
doi = {10.1145/3627050.3631566},
year = {2023},
date = {2023-11-07},
urldate = {2023-11-07},
booktitle = {The 1st International Workshop on Internet of Realities (IoR-WS 2023) at International Conference on the Internet of Things},
address = {Nagoya, Japan},
abstract = {The concept of a trusted inter-reality, where physical and virtual worlds seamlessly converge, represents a paradigm shift in how digital identities are formed and managed. This paper explores the complex landscape of system architectures designed to enable secure and user-centric digital identification within interconnected realities. Our survey focuses on user-centric security, recognizing the prevalence of wearable devices and immersive technologies in inter-reality environments. We advocate for user-friendly authentication methods and privacy-preserving techniques that prioritize user control within the trust model. Furthermore, we delve into the influence of social and cultural factors, particularly age and gender, on the shaping of digital identity within interconnected realities. We argue in favor of adaptable system architectures that respect generational and gender diversity. In conclusion, we emphasize the alignment of system architectures with these principles to promote a secure, user-centric, and culturally sensitive digital identity experience. This research contributes to the ongoing discourse on digital identification in interconnected realities, providing actionable guidance for stakeholders in the evolving landscape of trusted inter-reality.
},
keywords = {},
pubstate = {published},
tppubtype = {workshop}
}
The concept of a trusted inter-reality, where physical and virtual worlds seamlessly converge, represents a paradigm shift in how digital identities are formed and managed. This paper explores the complex landscape of system architectures designed to enable secure and user-centric digital identification within interconnected realities. Our survey focuses on user-centric security, recognizing the prevalence of wearable devices and immersive technologies in inter-reality environments. We advocate for user-friendly authentication methods and privacy-preserving techniques that prioritize user control within the trust model. Furthermore, we delve into the influence of social and cultural factors, particularly age and gender, on the shaping of digital identity within interconnected realities. We argue in favor of adaptable system architectures that respect generational and gender diversity. In conclusion, we emphasize the alignment of system architectures with these principles to promote a secure, user-centric, and culturally sensitive digital identity experience. This research contributes to the ongoing discourse on digital identification in interconnected realities, providing actionable guidance for stakeholders in the evolving landscape of trusted inter-reality.
Yiwei Cheng, Jin Nakazato, Ehsan Javanmardi, Chia-Ming Chang, Manabu Tsukada, "Pedestrian-centric Augmented Reality Visualization of Real-time Autonomous Vehicle Dynamics", The Workshop on Intelligent Cloud Continuum for B5G Services in the IEEE International Conference on Cloud Networking (CloudNet) 2023, New York City, USA, 2023.Workshop | Abstract | BibTeX | Links:
@workshop{Cheng2023,
title = {Pedestrian-centric Augmented Reality Visualization of Real-time Autonomous Vehicle Dynamics},
author = {Yiwei Cheng and Jin Nakazato and Ehsan Javanmardi and Chia-Ming Chang and Manabu Tsukada},
url = {https://www.researchgate.net/profile/Jin-Nakazato/publication/374387897_Pedestrian-centric_Augmented_Reality_Visualization_of_Real-time_Autonomous_Vehicle_Dynamics/links/651bda961e2386049df3c4ee/Pedestrian-centric-Augmented-Reality-Visualization-of-Real-time-Autonomous-Vehicle-Dynamics.pdf},
year = {2023},
date = {2023-11-04},
urldate = {2023-11-04},
booktitle = {The Workshop on Intelligent Cloud Continuum for B5G Services in the IEEE International Conference on Cloud Networking (CloudNet) 2023},
address = {New York City, USA},
abstract = {Connected Autonomous Vehicles (CAVs) produce a variety of information within their systems. With the advancement of communication and V2X (Vehicle-to-Everything) communication technology, there is a growing challenge to effectively convey this information to pedestrians and enhance their sense of safety when encountering such vehicles. Efforts to communicate this information to pedestrians have been made through various means, with Augmented Reality (AR) emerging as a notable approach. However, previous studies have yet to integrate a functional AR application with a real-world autonomous driving system. In response to this gap, we proposed an architecture for an AR application that visualizes real-time data from an active CAV and subsequently developed the system. Furthermore, we conducted field experiments using this developed system and conducted user surveys during exhibitions to gather insights into the public’s perception of the system. Our results showed that the system can effectively transmit information from the CAV, and when provided with additional information, people tend to feel safer regarding the vehicle. },
keywords = {},
pubstate = {published},
tppubtype = {workshop}
}
Connected Autonomous Vehicles (CAVs) produce a variety of information within their systems. With the advancement of communication and V2X (Vehicle-to-Everything) communication technology, there is a growing challenge to effectively convey this information to pedestrians and enhance their sense of safety when encountering such vehicles. Efforts to communicate this information to pedestrians have been made through various means, with Augmented Reality (AR) emerging as a notable approach. However, previous studies have yet to integrate a functional AR application with a real-world autonomous driving system. In response to this gap, we proposed an architecture for an AR application that visualizes real-time data from an active CAV and subsequently developed the system. Furthermore, we conducted field experiments using this developed system and conducted user surveys during exhibitions to gather insights into the public’s perception of the system. Our results showed that the system can effectively transmit information from the CAV, and when provided with additional information, people tend to feel safer regarding the vehicle.
Pengfei Lin, Ehsan Javanmardi, Jin Nakazato, Manabu Tsukada, "Potential Field-based Path Planning with Interactive Speed Optimization for Autonomous Vehicles", In: 49th Annual Conference of the IEEE Industrial Electronics Society (IECON 2023), 2023.Proceedings Article | Abstract | BibTeX | Links:
@inproceedings{Lin2023c,
title = {Potential Field-based Path Planning with Interactive Speed Optimization for Autonomous Vehicles},
author = {Pengfei Lin and Ehsan Javanmardi and Jin Nakazato and Manabu Tsukada},
url = {https://arxiv.org/abs/2306.06987},
year = {2023},
date = {2023-10-16},
urldate = {2023-10-16},
booktitle = {49th Annual Conference of the IEEE Industrial Electronics Society (IECON 2023)},
abstract = {Path planning is critical for autonomous vehicles (AVs) to determine the optimal route while considering constraints and objectives. The potential field (PF) approach has become prevalent in path planning due to its simple structure and computational efficiency. However, current PF methods used in AVs focus solely on the path generation of the ego vehicle while assuming that the surrounding obstacle vehicles drive at a preset behavior without the PF-based path planner, which ignores the fact that the ego vehicle’s PF could also impact the path generation of the obstacle vehicles. To tackle this problem, we propose a PF-based path planning approach where local paths are shared among ego and obstacle vehicles via vehicle-to- vehicle (V2V) communication. Then by integrating this shared local path into an objective function, a new optimization function called interactive speed optimization (ISO) is designed to allow driving safety and comfort for both ego and obstacle vehicles. The proposed method is evaluated using MATLAB/Simulink in the urgent merging scenarios by comparing it with conventional methods. The simulation results indicate that the proposed method can mitigate the impact of other AVs’ PFs by slowing down in advance, effectively reducing the oscillations for both ego and obstacle AVs.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Path planning is critical for autonomous vehicles (AVs) to determine the optimal route while considering constraints and objectives. The potential field (PF) approach has become prevalent in path planning due to its simple structure and computational efficiency. However, current PF methods used in AVs focus solely on the path generation of the ego vehicle while assuming that the surrounding obstacle vehicles drive at a preset behavior without the PF-based path planner, which ignores the fact that the ego vehicle’s PF could also impact the path generation of the obstacle vehicles. To tackle this problem, we propose a PF-based path planning approach where local paths are shared among ego and obstacle vehicles via vehicle-to- vehicle (V2V) communication. Then by integrating this shared local path into an objective function, a new optimization function called interactive speed optimization (ISO) is designed to allow driving safety and comfort for both ego and obstacle vehicles. The proposed method is evaluated using MATLAB/Simulink in the urgent merging scenarios by comparing it with conventional methods. The simulation results indicate that the proposed method can mitigate the impact of other AVs’ PFs by slowing down in advance, effectively reducing the oscillations for both ego and obstacle AVs.
Vishal Chauhan, Chia-Ming Chang, Ehsan Javanmardi, Jin Nakazato, Koki Toda, Pengfei Lin, Takeo Igarashi, Manabu Tsukada, "Keep Calm and Cross: Smart Pole Interaction Unit for Easing Pedestrian Cognitive Load", In: The 9th IEEE World Forum on Internet of Things (IEEE WFIoT2023), Aveiro, Portugal, 2023.Proceedings Article | Abstract | BibTeX | Links:
@inproceedings{Chauhan2023,
title = {Keep Calm and Cross: Smart Pole Interaction Unit for Easing Pedestrian Cognitive Load},
author = {Vishal Chauhan and Chia-Ming Chang and Ehsan Javanmardi and Jin Nakazato and Koki Toda and Pengfei Lin and Takeo Igarashi and Manabu Tsukada},
url = {https://www.researchgate.net/profile/Jin-Nakazato/publication/374582122_Keep_Calm_and_Cross_Smart_Pole_Interaction_Unit_for_Easing_Pedestrian_Cognitive_Load/links/6525681eb32c91681fb2e1b5/Keep-Calm-and-Cross-Smart-Pole-Interaction-Unit-for-Easing-Pedestrian-Cognitive-Load.pdf},
year = {2023},
date = {2023-10-12},
urldate = {2023-10-12},
booktitle = {The 9th IEEE World Forum on Internet of Things (IEEE WFIoT2023)},
address = {Aveiro, Portugal},
abstract = {Recently, there has been a growing emphasis on autonomous vehicles (AVs), and as they coexist with pedestrians, ensuring pedestrian safety at crosswalks has become paramount. While AVs exhibit commendable performance on traditional roads with established traffic infrastructure, their interaction in different environments, such as shared spaces lacking traffic lights or sign rules (also known as naked streets), can present significant challenges, including right-of-way and accessibility concerns. To address these challenges, this study proposes a novel approach to enhance pedestrian safety in shared spaces, focusing on the proposed smart pole interaction unit (SPIU) combined with an external human-machine interface (eHMI). By evaluating the proposal of SPIU developed by a virtual reality system, we explore its usability and effectiveness in facilitating vehicle-to-pedestrian (V2P) interactions at crosswalks. Our findings from this study showed that SPIU facilitates safe, quicker decision-making to stop and pass at crosswalks in shared space and reduces cognitive load compared to scenarios where an SPIU is absent for pedestrians and reduce the need for eHMI to see on multiple AVs. The SPIU addition with the eHMI in vehicles yields a noteworthy 21 % improvement in response time, enhancing efficiency during pedestrian stops. In both scenarios, whether with a single AV (1-way) or multiple AVs (2-way), SPIU has a positive impact on interaction dynamics and statistically demonstrates a significant improvement (p = 0.001). },
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Recently, there has been a growing emphasis on autonomous vehicles (AVs), and as they coexist with pedestrians, ensuring pedestrian safety at crosswalks has become paramount. While AVs exhibit commendable performance on traditional roads with established traffic infrastructure, their interaction in different environments, such as shared spaces lacking traffic lights or sign rules (also known as naked streets), can present significant challenges, including right-of-way and accessibility concerns. To address these challenges, this study proposes a novel approach to enhance pedestrian safety in shared spaces, focusing on the proposed smart pole interaction unit (SPIU) combined with an external human-machine interface (eHMI). By evaluating the proposal of SPIU developed by a virtual reality system, we explore its usability and effectiveness in facilitating vehicle-to-pedestrian (V2P) interactions at crosswalks. Our findings from this study showed that SPIU facilitates safe, quicker decision-making to stop and pass at crosswalks in shared space and reduces cognitive load compared to scenarios where an SPIU is absent for pedestrians and reduce the need for eHMI to see on multiple AVs. The SPIU addition with the eHMI in vehicles yields a noteworthy 21 % improvement in response time, enhancing efficiency during pedestrian stops. In both scenarios, whether with a single AV (1-way) or multiple AVs (2-way), SPIU has a positive impact on interaction dynamics and statistically demonstrates a significant improvement (p = 0.001).
Vishal Chauhan, Chia-Ming Chang, Ehsan Javanmardi, Jin Nakazato, Lin Pengfei, Takeo Igarashi, Manabu Tsukada, "Fostering Fuzzy Logic in Enhancing Pedestrian Safety: Harnessing Smart Pole Interaction Unit for Autonomous Vehicle-to-Pedestrian Communication and Decision Optimization", In: Electronics, vol. 12, no. 20, 2023, ISSN: 2079-9292.Journal Article | Abstract | BibTeX | Links:
@article{Chauhan2023c,
title = {Fostering Fuzzy Logic in Enhancing Pedestrian Safety: Harnessing Smart Pole Interaction Unit for Autonomous Vehicle-to-Pedestrian Communication and Decision Optimization},
author = {Vishal Chauhan and Chia-Ming Chang and Ehsan Javanmardi and Jin Nakazato and Lin Pengfei and Takeo Igarashi and Manabu Tsukada},
url = {https://www.mdpi.com/2079-9292/12/20/4207},
doi = {10.3390/electronics12204207},
issn = {2079-9292},
year = {2023},
date = {2023-10-11},
urldate = {2023-10-11},
journal = {Electronics},
volume = {12},
number = {20},
abstract = {In autonomous vehicles (AVs), ensuring pedestrian safety within intricate and dynamic settings, particularly at crosswalks, has gained substantial attention. While AVs perform admirably in standard road conditions, their integration into unique environments like shared spaces devoid of traditional traffic infrastructure control presents complex challenges. These challenges involve issues of right-of-way negotiation and accessibility, particularly in “naked streets”. This research delves into an innovative smart pole interaction unit (SPIU) with an external human–machine interface (eHMI). Utilizing virtual reality (VR) technology to evaluate the SPIU efficacy, this study investigates its capacity to enhance interactions between vehicles and pedestrians at crosswalks. The SPIU is designed to communicate the vehicles’ real-time intentions well before arriving at the crosswalk. The study findings demonstrate that the SPIU significantly improves secure decision making for pedestrian passing and stops in shared spaces. Integrating an SPIU with an eHMI in vehicles leads to a substantial 21% reduction in response time, greatly enhancing the efficiency of pedestrian stops. Notable enhancements are observed in unidirectional (one-way) and bidirectional (two-way) scenarios, highlighting the positive impact of the SPIU on interaction dynamics. This work contributes to AV–pedestrian interaction and underscores the potential of fuzzy-logic-driven solutions in addressing complex and ambiguous pedestrian behaviors.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In autonomous vehicles (AVs), ensuring pedestrian safety within intricate and dynamic settings, particularly at crosswalks, has gained substantial attention. While AVs perform admirably in standard road conditions, their integration into unique environments like shared spaces devoid of traditional traffic infrastructure control presents complex challenges. These challenges involve issues of right-of-way negotiation and accessibility, particularly in “naked streets”. This research delves into an innovative smart pole interaction unit (SPIU) with an external human–machine interface (eHMI). Utilizing virtual reality (VR) technology to evaluate the SPIU efficacy, this study investigates its capacity to enhance interactions between vehicles and pedestrians at crosswalks. The SPIU is designed to communicate the vehicles’ real-time intentions well before arriving at the crosswalk. The study findings demonstrate that the SPIU significantly improves secure decision making for pedestrian passing and stops in shared spaces. Integrating an SPIU with an eHMI in vehicles leads to a substantial 21% reduction in response time, greatly enhancing the efficiency of pedestrian stops. Notable enhancements are observed in unidirectional (one-way) and bidirectional (two-way) scenarios, highlighting the positive impact of the SPIU on interaction dynamics. This work contributes to AV–pedestrian interaction and underscores the potential of fuzzy-logic-driven solutions in addressing complex and ambiguous pedestrian behaviors.
Hu Dou, Jin Nakazato, Ehsan Javanmardi, Muhammad Asad, Manabu Tsukada, Kazuki Maruta
, "Extended Kalman filter based beam tracking for vehicle position and velocity estimation under intersection scenario", 革新的無線通信技術に関する横断型研究会(MIKA), 沖縄県, 2023.Conference | Abstract | BibTeX
@conference{Dou2023,
title = {Extended Kalman filter based beam tracking for vehicle position and velocity estimation under intersection scenario},
author = {Hu Dou and Jin Nakazato and Ehsan Javanmardi and Muhammad Asad and Manabu Tsukada and Kazuki Maruta
},
year = {2023},
date = {2023-10-10},
urldate = {2023-10-10},
booktitle = {革新的無線通信技術に関する横断型研究会(MIKA)},
address = {沖縄県},
abstract = {As typified by the IoT, mobile traffic continues to increase with the spread of devices equipped with wireless communication functions. Deploying small cell base stations (BSs) is known to straight forward way to efficiently support such traffic. Meanwhile, the facility cost increases when large numbers of BSs are deployed in a fixed manner. It is possible to construct an efficient wireless network by installing BS functions in moving objects such as vehicles and UAVs, and allowing them to move autonomously or activate wireless functions to follow the traffic demand. This paper proposes a method for estimating propagation channels and vehicle position/velocity information at intersections based on vehicle-oriented beam control using a Kalman filter.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
As typified by the IoT, mobile traffic continues to increase with the spread of devices equipped with wireless communication functions. Deploying small cell base stations (BSs) is known to straight forward way to efficiently support such traffic. Meanwhile, the facility cost increases when large numbers of BSs are deployed in a fixed manner. It is possible to construct an efficient wireless network by installing BS functions in moving objects such as vehicles and UAVs, and allowing them to move autonomously or activate wireless functions to follow the traffic demand. This paper proposes a method for estimating propagation channels and vehicle position/velocity information at intersections based on vehicle-oriented beam control using a Kalman filter.
Muhammad Asad, Saima Shaukat, Ehsan Javanmardi, Jin Nakazato, Naren Bao, Manabu Tsukada, "Secure and Efficient Blockchain-based Federated Learning Approach For VANETs", In: IEEE Internet of Things Journal, 2023.Journal Article | Abstract | BibTeX | Links:
@article{Asad2023c,
title = {Secure and Efficient Blockchain-based Federated Learning Approach For VANETs},
author = {Muhammad Asad and Saima Shaukat and Ehsan Javanmardi and Jin Nakazato and Naren Bao and Manabu Tsukada},
doi = {10.1109/JIOT.2023.3322221},
year = {2023},
date = {2023-10-05},
urldate = {2023-10-17},
journal = {IEEE Internet of Things Journal},
abstract = {The rapid increase in the number of connected vehicles on roads has made Vehicular Ad-hoc Networks (VANETs) an attractive target for malicious actors. As a result, VANETs require secure data transmission to maintain the network’s integrity. Federated Learning (FL) has been proposed as a secure data-sharing method for VANETs, but it is limited in its ability to protect sensitive data. This paper proposes integrating Blockchain technology into FL to provide an additional layer of security for VANETs. In particular, we propose a Secure and Efficient Blockchain-based FL (SEBFL) approach to ensure communication efficiency and data privacy in VANETs. To this end, we use the FL model for VANETs, where computation tasks are decomposed from a base station to individual vehicles. This effectively reduces the congestion delay and communication overhead. Integrating blockchain with the FL model provides a reliable and secure data communication system between vehicles, roadside units, and a cloud server. Additionally, we use a Homomorphic Encryption System (HES) that effectively preserves the confidentiality and credibility of vehicles. Besides, the proposed SEBFL leverages the asynchronous FL model, minimizing the long delay while avoiding possible threats and attacks using HES. The experiment results show the proposed SEBFL achieves 0.87% accuracy while a model inversion attack and 0.86% accuracy while a membership inference attack.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The rapid increase in the number of connected vehicles on roads has made Vehicular Ad-hoc Networks (VANETs) an attractive target for malicious actors. As a result, VANETs require secure data transmission to maintain the network’s integrity. Federated Learning (FL) has been proposed as a secure data-sharing method for VANETs, but it is limited in its ability to protect sensitive data. This paper proposes integrating Blockchain technology into FL to provide an additional layer of security for VANETs. In particular, we propose a Secure and Efficient Blockchain-based FL (SEBFL) approach to ensure communication efficiency and data privacy in VANETs. To this end, we use the FL model for VANETs, where computation tasks are decomposed from a base station to individual vehicles. This effectively reduces the congestion delay and communication overhead. Integrating blockchain with the FL model provides a reliable and secure data communication system between vehicles, roadside units, and a cloud server. Additionally, we use a Homomorphic Encryption System (HES) that effectively preserves the confidentiality and credibility of vehicles. Besides, the proposed SEBFL leverages the asynchronous FL model, minimizing the long delay while avoiding possible threats and attacks using HES. The experiment results show the proposed SEBFL achieves 0.87% accuracy while a model inversion attack and 0.86% accuracy while a membership inference attack.
Yuji Yamazaki, Yasumasa Tamura, Xavier Defago, Ehsan Javanmardi, Manabu Tsukada, "ToST: Tokyo SUMO traffic scenario ", In: The 26th edition of the IEEE International Conference on Intelligent Transportation Systems (ITSC 2023), Bilbao, Bizkaia, Spain, 2023.Proceedings Article | Abstract | BibTeX
@inproceedings{Yamazaki2023,
title = {ToST: Tokyo SUMO traffic scenario },
author = {Yuji Yamazaki and Yasumasa Tamura and Xavier Defago and Ehsan Javanmardi and Manabu Tsukada},
year = {2023},
date = {2023-09-24},
urldate = {2023-09-24},
booktitle = {The 26th edition of the IEEE International Conference on Intelligent Transportation Systems (ITSC 2023)},
address = {Bilbao, Bizkaia, Spain},
abstract = {In recent years, research, development, and demonstrations aimed at the societal implementation of autonomous driving have attracted increasing attention. Localization, which involves obtaining information of the surrounding environment from sensor data and estimating the vehicle's position, is necessary for realizing autonomous driving. Localization is commonly performed with 3D LiDAR as a sensor owing to its high measurement accuracy and immunity to ambient light conditions, which allow for precise localization. However, when the surrounding area has distinctive features, localization accuracy may decrease. In this study, we proposed a method based on deep learning to predict the localization accuracy for autonomous driving. The overall localization accuracy can be improved by predicting the accuracy of localization using other sensors, such as GNSS and IMU, or pavement markings in areas with poor accuracy. We created a dataset for predicting the localization accuracy using an open-source autonomous driving simulator. In an experiment, we applied the proposed method to the created dataset. Thresholds were set for errors in the x-direction, y-direction, and distance for localization. Predictions with high accuracy and F-values were obtained. The results indicate that the proposed method can accurately predict the localization accuracy. },
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In recent years, research, development, and demonstrations aimed at the societal implementation of autonomous driving have attracted increasing attention. Localization, which involves obtaining information of the surrounding environment from sensor data and estimating the vehicle's position, is necessary for realizing autonomous driving. Localization is commonly performed with 3D LiDAR as a sensor owing to its high measurement accuracy and immunity to ambient light conditions, which allow for precise localization. However, when the surrounding area has distinctive features, localization accuracy may decrease. In this study, we proposed a method based on deep learning to predict the localization accuracy for autonomous driving. The overall localization accuracy can be improved by predicting the accuracy of localization using other sensors, such as GNSS and IMU, or pavement markings in areas with poor accuracy. We created a dataset for predicting the localization accuracy using an open-source autonomous driving simulator. In an experiment, we applied the proposed method to the created dataset. Thresholds were set for errors in the x-direction, y-direction, and distance for localization. Predictions with high accuracy and F-values were obtained. The results indicate that the proposed method can accurately predict the localization accuracy.
Ye Tao, Ehsan Javanmardi, Jin Nakazato, Manabu Tsukada, Hiroshi Esaki, "Flowsim: A Modular Simulation Platform for Microscopic Behavior Analysis of City-Scale Connected Autonomous Vehicles", In: The 26th edition of the IEEE International Conference on Intelligent Transportation Systems (ITSC 2023), Bilbao, Bizkaia, Spain, 2023.Proceedings Article | Abstract | BibTeX | Links:
@inproceedings{nokey,
title = {Flowsim: A Modular Simulation Platform for Microscopic Behavior Analysis of City-Scale Connected Autonomous Vehicles},
author = {Ye Tao and Ehsan Javanmardi and Jin Nakazato and Manabu Tsukada and Hiroshi Esaki},
url = {https://arxiv.org/abs/2306.05738},
year = {2023},
date = {2023-09-24},
booktitle = {The 26th edition of the IEEE International Conference on Intelligent Transportation Systems (ITSC 2023)},
address = {Bilbao, Bizkaia, Spain},
abstract = {As connected autonomous vehicles (CAVs) become increasingly prevalent, there is a growing need for simulation platforms that can accurately evaluate CAV behavior in large-scale environments. In this paper, we propose Flowsim, a novel simulator specifically designed to meet these requirements. Flowsim offers a modular and extensible architecture that enables the analysis of CAV behaviors in large-scale scenarios. It provides researchers with a customizable platform for studying CAV interactions, evaluating communication and networking protocols, assessing cybersecurity vulnerabilities, optimizing traffic management strategies, and developing and evaluating policies for CAV deployment. Flowsim is implemented in pure Python in approximately 1,500 lines of code, making it highly readable, understandable, and easily modifiable. We verified the functionality and performance of Flowsim via a series of experiments based on realistic traffic scenarios. The results show the effectiveness of Flowsim in providing a flexible and powerful simulation environment for evaluating CAV behavior and data flow. Flowsim is a valuable tool for researchers, policymakers, and industry professionals who are involved in the development, evaluation, and deployment of CAVs. The code of Flowsim is publicly available on GitHub under the MIT license. },
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
As connected autonomous vehicles (CAVs) become increasingly prevalent, there is a growing need for simulation platforms that can accurately evaluate CAV behavior in large-scale environments. In this paper, we propose Flowsim, a novel simulator specifically designed to meet these requirements. Flowsim offers a modular and extensible architecture that enables the analysis of CAV behaviors in large-scale scenarios. It provides researchers with a customizable platform for studying CAV interactions, evaluating communication and networking protocols, assessing cybersecurity vulnerabilities, optimizing traffic management strategies, and developing and evaluating policies for CAV deployment. Flowsim is implemented in pure Python in approximately 1,500 lines of code, making it highly readable, understandable, and easily modifiable. We verified the functionality and performance of Flowsim via a series of experiments based on realistic traffic scenarios. The results show the effectiveness of Flowsim in providing a flexible and powerful simulation environment for evaluating CAV behavior and data flow. Flowsim is a valuable tool for researchers, policymakers, and industry professionals who are involved in the development, evaluation, and deployment of CAVs. The code of Flowsim is publicly available on GitHub under the MIT license.
Pengfei Lin, Ehsan Javanmardi, Jin Nakazato, Manabu Tsukada, "Occlusion-Aware Path Planning for Collision Avoidance: Leveraging Potential Field Method with Responsibility-Sensitive Safety", In: The 26th edition of the IEEE International Conference on Intelligent Transportation Systems (ITSC 2023), 2023.Proceedings Article | Abstract | BibTeX | Links:
@inproceedings{Lin2023b,
title = {Occlusion-Aware Path Planning for Collision Avoidance: Leveraging Potential Field Method with Responsibility-Sensitive Safety},
author = {Pengfei Lin and Ehsan Javanmardi and Jin Nakazato and Manabu Tsukada},
url = {https://arxiv.org/abs/2306.06981},
year = {2023},
date = {2023-09-24},
urldate = {2023-09-24},
booktitle = {The 26th edition of the IEEE International Conference on Intelligent Transportation Systems (ITSC 2023)},
series = {Bilbao, Bizkaia, Spain},
abstract = {Collision avoidance (CA) has always been the foremost task for autonomous vehicles (AVs) under safety criteria. And path planning is directly responsible for generating a safe path to accomplish CA while satisfying other commands. Due to the real-time computation and simple structure, the potential field (PF) has emerged as one of the mainstream path-planning algorithms. However, the current PF is primarily simulated in ideal CA scenarios, assuming complete obstacle information while disregarding occlusion issues where obstacles can be partially or entirely hidden from the AV's sensors. During the occlusion period, the occluded obstacles do not possess a PF. Once the occlusion is over, these obstacles can generate an instantaneous virtual force that impacts the ego vehicle. Therefore, we propose an occlusion-aware path planning (OAPP) with the responsibility-sensitive safety (RSS)-based PF to tackle the occlusion problem for non-connected AVs. We first categorize the detected and occluded obstacles, and then we proceed to the RSS violation check. Finally, we can generate different virtual forces from the PF for occluded and non-occluded obstacles. We compare the proposed OAPP method with other PF-based path planning methods via MATLAB/Simulink. The simulation results indicate that the proposed method can eliminate instantaneous lateral oscillation or sway and produce a smoother path than conventional PF methods.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Collision avoidance (CA) has always been the foremost task for autonomous vehicles (AVs) under safety criteria. And path planning is directly responsible for generating a safe path to accomplish CA while satisfying other commands. Due to the real-time computation and simple structure, the potential field (PF) has emerged as one of the mainstream path-planning algorithms. However, the current PF is primarily simulated in ideal CA scenarios, assuming complete obstacle information while disregarding occlusion issues where obstacles can be partially or entirely hidden from the AV's sensors. During the occlusion period, the occluded obstacles do not possess a PF. Once the occlusion is over, these obstacles can generate an instantaneous virtual force that impacts the ego vehicle. Therefore, we propose an occlusion-aware path planning (OAPP) with the responsibility-sensitive safety (RSS)-based PF to tackle the occlusion problem for non-connected AVs. We first categorize the detected and occluded obstacles, and then we proceed to the RSS violation check. Finally, we can generate different virtual forces from the PF for occluded and non-occluded obstacles. We compare the proposed OAPP method with other PF-based path planning methods via MATLAB/Simulink. The simulation results indicate that the proposed method can eliminate instantaneous lateral oscillation or sway and produce a smoother path than conventional PF methods.
Nicholaus Danispadmanaba Yosodipuro, Ehsan Javanmardi, Jin Nakazato, Yasumasa Tamura, Xavier Defago, Manabu Tsukada, "Mixed-traffic Intersection Management using Traffic-load-responsive Reservation and V2X-enabled Speed Coordination", In: The 26th edition of the IEEE International Conference on Intelligent Transportation Systems (ITSC 2023), Bilbao, Bizkaia, Spain, 2023.Proceedings Article | Abstract | BibTeX | Links:
@inproceedings{Yosodipuro2023,
title = {Mixed-traffic Intersection Management using Traffic-load-responsive Reservation and V2X-enabled Speed Coordination},
author = {Nicholaus Danispadmanaba Yosodipuro and Ehsan Javanmardi and Jin Nakazato and Yasumasa Tamura and Xavier Defago and Manabu Tsukada},
url = {https://www.researchgate.net/profile/Jin-Nakazato/publication/374470825_Mixed-traffic_Intersection_Management_using_Traffic-load-responsive_Reservation_and_V2X-enabled_Speed_Coordination/links/651ee8d63ab6cb4ec6bde79a/Mixed-traffic-Intersection-Management-using-Traffic-load-responsive-Reservation-and-V2X-enabled-Speed-Coordination.pdf},
year = {2023},
date = {2023-09-24},
urldate = {2023-09-24},
booktitle = {The 26th edition of the IEEE International Conference on Intelligent Transportation Systems (ITSC 2023)},
address = {Bilbao, Bizkaia, Spain},
abstract = {Vehicle-to-everything (V2X) communication enables connected autonomous vehicles (CAVs) to share information and generate optimal decisions. The networking abilities of CAVs have led to the development of unsignalized autonomous intersection management (AIM) methods that leverage CAVs to significantly improve traffic flows. However, AIM methods assume 100% CAV market penetration, which is currently unrealistic owing to the gradual adoption of CAVs. Therefore, CAVs must share road usage with nonconnected vehicles (NCVs). Thus, we propose a mixed-traffic intersection management method that considers NCVs while ensuring high traffic flow, called traffic-load-responsive reservation for intersection management (TLRRIM). In TLRRIM, the roadside unit (RSU) first classifies vehicles and groups them into clusters before selecting a reservation cluster to cross an intersection. The reservation cluster selection considers both traffic load and crossing urgency. In addition, the RSU utilizes V2X-enabled speed coordination (VESC) for CAVs within the reservation cluster to further improve traffic flow, while utilizing traffic lights to guide NCVs. Simulation-based experiments using OpenCDA and CARLA showed that TLRRIM can increase throughput and reduce waiting time by up to 89.63% and 60.71%, respectively, compared with the fixed-time signaling method. Moreover, adding VESC can increase throughput by 12.21% and reduce waiting time by 10.80%, further enhancing traffic flow. },
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Vehicle-to-everything (V2X) communication enables connected autonomous vehicles (CAVs) to share information and generate optimal decisions. The networking abilities of CAVs have led to the development of unsignalized autonomous intersection management (AIM) methods that leverage CAVs to significantly improve traffic flows. However, AIM methods assume 100% CAV market penetration, which is currently unrealistic owing to the gradual adoption of CAVs. Therefore, CAVs must share road usage with nonconnected vehicles (NCVs). Thus, we propose a mixed-traffic intersection management method that considers NCVs while ensuring high traffic flow, called traffic-load-responsive reservation for intersection management (TLRRIM). In TLRRIM, the roadside unit (RSU) first classifies vehicles and groups them into clusters before selecting a reservation cluster to cross an intersection. The reservation cluster selection considers both traffic load and crossing urgency. In addition, the RSU utilizes V2X-enabled speed coordination (VESC) for CAVs within the reservation cluster to further improve traffic flow, while utilizing traffic lights to guide NCVs. Simulation-based experiments using OpenCDA and CARLA showed that TLRRIM can increase throughput and reduce waiting time by up to 89.63% and 60.71%, respectively, compared with the fixed-time signaling method. Moreover, adding VESC can increase throughput by 12.21% and reduce waiting time by 10.80%, further enhancing traffic flow.
Muhammad Asad, Saima Shaukat, Dou Hu, Zekun Wang, Ehsan Javanmardi, Jin Nakazato, Manabu Tsukada, "Limitations and Future Aspects of Communication Costs in Federated Learning: A Survey", In: Sensors, vol. 23, no. 17, 2023, ISSN: 1424-8220.Journal Article | Abstract | BibTeX | Links:
@article{Asad2023b,
title = {Limitations and Future Aspects of Communication Costs in Federated Learning: A Survey},
author = {Muhammad Asad and Saima Shaukat and Dou Hu and Zekun Wang and Ehsan Javanmardi and Jin Nakazato and Manabu Tsukada},
doi = {10.3390/s23177358},
issn = {1424-8220},
year = {2023},
date = {2023-08-23},
urldate = {2023-08-23},
journal = {Sensors},
volume = {23},
number = {17},
abstract = {This paper explores the potential for communication-efficient federated learning (FL) in modern distributed systems. FL is an emerging distributed machine learning technique that allows for distributed training of a single machine learning model across multiple geographically distributed clients. This paper surveys the various approaches to communication-efficient FL, including model updates, compression techniques, resource management for edge and cloud, and client selection. We also review the various optimization techniques associated with communication-efficient FL, such as compression schemes and structured updates. Finally, we highlight the current research challenges and discuss the potential future directions for communication-efficient FL.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This paper explores the potential for communication-efficient federated learning (FL) in modern distributed systems. FL is an emerging distributed machine learning technique that allows for distributed training of a single machine learning model across multiple geographically distributed clients. This paper surveys the various approaches to communication-efficient FL, including model updates, compression techniques, resource management for edge and cloud, and client selection. We also review the various optimization techniques associated with communication-efficient FL, such as compression schemes and structured updates. Finally, we highlight the current research challenges and discuss the potential future directions for communication-efficient FL.
松本 和人, Ehsan Javanmardi, 中里 仁, 塚田 学, "深層学習を用いた自動運転向け自己位置推定精度の予測", マルチメディア,分散,協調とモバイル(DICOMO2023)シンポジウム, 富山, 2023.Conference | Abstract | BibTeX | Links:
@conference{Matsumoto2023,
title = {深層学習を用いた自動運転向け自己位置推定精度の予測},
author = {松本 和人 and Ehsan Javanmardi and 中里 仁 and 塚田 学},
url = {https://tlab.hongo.wide.ad.jp/papers/2023_DICOMO_matsumoto.pdf},
year = {2023},
date = {2023-07-05},
urldate = {2023-07-05},
booktitle = {マルチメディア,分散,協調とモバイル(DICOMO2023)シンポジウム},
address = {富山},
abstract = {近年,自動運転の社会実装に向けた研究開発や実証実験が盛んに行われている.自動運転を実現するにあたって,センサ情報から周囲の環境の情報を取得し,車体の位置を推定する必要がある.これを自己位置推定という.自己位置推定のセンサには3DLiDARがよく用いられる.3DLiDARは測定精度が高く,周囲の明るさの影響を受けないため,高精度に自己位置推定を行えるが,周囲に特徴物が少ないところでは自己位置推定の精度が低下するという課題がある.本研究では,自己位置推定の精度を予測する手法を提案する.自己位置推定精度の予測を行い,精度が悪い場所に対してGNSSやIMUなど3DLiDAR以外のセンサを用いたり,舗装マーキングを用いたりすることで,全体的な自己位置推定の精度を向上させることができる.オープンソース自動運転シミュレータを用いて自己位置推定精度予測のためのデータセットを作成した.実験では作成したデータセットに対して提案手法を行った.結果として,自己位置推定精度を高精度で予測できたことを報告する.
},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
近年,自動運転の社会実装に向けた研究開発や実証実験が盛んに行われている.自動運転を実現するにあたって,センサ情報から周囲の環境の情報を取得し,車体の位置を推定する必要がある.これを自己位置推定という.自己位置推定のセンサには3DLiDARがよく用いられる.3DLiDARは測定精度が高く,周囲の明るさの影響を受けないため,高精度に自己位置推定を行えるが,周囲に特徴物が少ないところでは自己位置推定の精度が低下するという課題がある.本研究では,自己位置推定の精度を予測する手法を提案する.自己位置推定精度の予測を行い,精度が悪い場所に対してGNSSやIMUなど3DLiDAR以外のセンサを用いたり,舗装マーキングを用いたりすることで,全体的な自己位置推定の精度を向上させることができる.オープンソース自動運転シミュレータを用いて自己位置推定精度予測のためのデータセットを作成した.実験では作成したデータセットに対して提案手法を行った.結果として,自己位置推定精度を高精度で予測できたことを報告する.
Zekun Wang, Jin Nakazato, Muhammad Asad, Ehsan Javanmardi, Manabu Tsukada, "Overcoming Environmental Challenges in CAVs Through MEC-Based Federated Learning", In: 14th International Conference on Ubiquitous and Future Networks (ICUFN2023), pp. 1-6, Paris, France, 2023.Proceedings Article | Abstract | BibTeX | Links:
@inproceedings{Wang2023,
title = {Overcoming Environmental Challenges in CAVs Through MEC-Based Federated Learning},
author = {Zekun Wang and Jin Nakazato and Muhammad Asad and Ehsan Javanmardi and Manabu Tsukada},
url = {https://www.researchgate.net/profile/Jin-Nakazato/publication/371685830_Overcoming_Environmental_Challenges_in_CAVs_through_MEC-based_Federated_Learning/links/64a420ea8de7ed28ba7465c7/Overcoming-Environmental-Challenges-in-CAVs-through-MEC-based-Federated-Learning.pdf},
doi = {10.1109/ICUFN57995.2023.10200688},
year = {2023},
date = {2023-07-04},
urldate = {2023-07-04},
booktitle = {14th International Conference on Ubiquitous and Future Networks (ICUFN2023)},
pages = {1-6},
address = {Paris, France},
abstract = {Connected autonomous vehicles (CAVs), through vehicle-to-everything communication and computing resources, enable the vital exchange of information. Although deep learning is crucial in this landscape, it requires extensive and intricate datasets covering all potential scenarios. Furthermore, this situation poses a hazard, as the likelihood of accidents associated with imbalanced datasets increases, particularly in scenarios where processing analysis is compromised due to fluctuating weather conditions. We propose a Federated Learning (FL) framework undergirded by Multi-Access Edge Computing (MEC) to counter these challenges. This local device-focused framework enhances task-specific models' caching and continual updating across various conditions. In a more specific sense, edge nodes (ENs) operate as MEC, each caching multiple dedicated models and serving as the aggregator as part of the FL process. Additionally, we have engineered two innovative algorithms that categorize various states into multiple classes, thereby ensuring the efficient utilization of computing resources in ENs. Simulation results substantiate the effectiveness of our approach, showing that the proposed dedicated model consistently outperforms a general model designed for all situations.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Connected autonomous vehicles (CAVs), through vehicle-to-everything communication and computing resources, enable the vital exchange of information. Although deep learning is crucial in this landscape, it requires extensive and intricate datasets covering all potential scenarios. Furthermore, this situation poses a hazard, as the likelihood of accidents associated with imbalanced datasets increases, particularly in scenarios where processing analysis is compromised due to fluctuating weather conditions. We propose a Federated Learning (FL) framework undergirded by Multi-Access Edge Computing (MEC) to counter these challenges. This local device-focused framework enhances task-specific models' caching and continual updating across various conditions. In a more specific sense, edge nodes (ENs) operate as MEC, each caching multiple dedicated models and serving as the aggregator as part of the FL process. Additionally, we have engineered two innovative algorithms that categorize various states into multiple classes, thereby ensuring the efficient utilization of computing resources in ENs. Simulation results substantiate the effectiveness of our approach, showing that the proposed dedicated model consistently outperforms a general model designed for all situations.
Yu Asabe, Ehsan Javanmardi, Jin Nakazato, Manabu Tsukada, Hiroshi Esaki, "AutowareV2X: Reliable V2X Communication and Collective Perception for Autonomous Driving", In: The 2023 IEEE 97th Vehicular Technology Conference (VTC2023-Spring), Florence, Italy, 2023.Proceedings Article | Abstract | BibTeX | Links:
@inproceedings{Asabe2023b,
title = {AutowareV2X: Reliable V2X Communication and Collective Perception for Autonomous Driving},
author = {Yu Asabe and Ehsan Javanmardi and Jin Nakazato and Manabu Tsukada and Hiroshi Esaki},
url = {https://www.researchgate.net/profile/Jin-Nakazato/publication/371903099_AutowareV2X_Reliable_V2X_Communication_and_Collective_Perception_for_Autonomous_Driving/links/649b1457c41fb852dd36b04d/AutowareV2X-Reliable-V2X-Communication-and-Collective-Perception-for-Autonomous-Driving.pdf
https://github.com/tlab-wide/AutowareV2X
https://www.youtube.com/watch?v=57fx3-gUNxU},
doi = {10.1109/VTC2023-Spring57618.2023.10199425},
year = {2023},
date = {2023-06-20},
urldate = {2023-06-20},
booktitle = {The 2023 IEEE 97th Vehicular Technology Conference (VTC2023-Spring)},
address = {Florence, Italy},
abstract = {For cooperative intelligent transport systems (C-ITS), vehicle-to-everything (V2X) communication is utilized to allow autonomous vehicles to share critical information with each other. We propose AutowareV2X, an implementation of a V2X communication module that is integrated into the autonomous driving (AD) software, Autoware. AutowareV2X provides external connectivity to the entire AD stack, enabling the end-to-end (E2E) experimentation and evaluation of connected autonomous vehicles (CAV). The Collective Perception Service was also implemented, allowing the transmission of Collective Perception Messages (CPMs). A dual-channel mechanism that enables wireless link redundancy on the critical object information shared by CPMs is also proposed. Performance evaluation in field experiments has indicated that the E2E latency of perception information is around 30 ms, and shared object data can be used by the AD software to conduct collision avoidance maneuvers. Dual-channel delivery of CPMs enabled the CAV to dynamically select the best CPM from CPMs received from different links, depending on the freshness of their information.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
For cooperative intelligent transport systems (C-ITS), vehicle-to-everything (V2X) communication is utilized to allow autonomous vehicles to share critical information with each other. We propose AutowareV2X, an implementation of a V2X communication module that is integrated into the autonomous driving (AD) software, Autoware. AutowareV2X provides external connectivity to the entire AD stack, enabling the end-to-end (E2E) experimentation and evaluation of connected autonomous vehicles (CAV). The Collective Perception Service was also implemented, allowing the transmission of Collective Perception Messages (CPMs). A dual-channel mechanism that enables wireless link redundancy on the critical object information shared by CPMs is also proposed. Performance evaluation in field experiments has indicated that the E2E latency of perception information is around 30 ms, and shared object data can be used by the AD software to conduct collision avoidance maneuvers. Dual-channel delivery of CPMs enabled the CAV to dynamically select the best CPM from CPMs received from different links, depending on the freshness of their information.
Dou Hu, Jin Nakazato, Ehsan Javanmardi, Muhammad Asad, Manabu Tsukada
, "An Extended Kalman Filter Enabled Beam Tracking Framework in Intersection Management", European Conference on Networks and Communications (EuCNC) & 6G Summit Poster, 2023.Miscellaneous | Abstract | BibTeX | Links:
@misc{Hu2023,
title = {An Extended Kalman Filter Enabled Beam Tracking Framework in Intersection Management},
author = {Dou Hu and Jin Nakazato and Ehsan Javanmardi and Muhammad Asad and Manabu Tsukada
},
url = {https://www.researchgate.net/profile/Jin-Nakazato/publication/371358188_An_Extended_Kalman_Filter_Enabled_Beam_Tracking_Framework_in_Intersection_Management/links/64807e24b3dfd73b776baeed/An-Extended-Kalman-Filter-Enabled-Beam-Tracking-Framework-in-Intersection-Management.pdf},
year = {2023},
date = {2023-06-06},
urldate = {2023-06-06},
address = {Gothenburg, Sweden},
abstract = {Recently, vehicle-to-everything (V2X) has been at- tracting attention for its potential to improve traffic safety and increase traffic volume worldwide, improving the accuracy of data and parameters collected from moving vehicles is widely discussed in the V2X. The most common technique of GPS may not be efficient during some specific scenarios, like some intersections full of skyscrapers, or some special terrains with obstacles. In such cases, GPS technology has a longer detection period and lower tracking accuracy, so beam tracking can be a fast and efficient solution in these circumstances. Therefore we propose an anti-diverge extend Kalman filter-enabled beam tracking method in V2X to help the intersection management. The numerical results show that our method has the ability to resist the Kalman filter’s divergence and can detect data in an accurate manner.},
howpublished = {European Conference on Networks and Communications (EuCNC) & 6G Summit Poster},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Recently, vehicle-to-everything (V2X) has been at- tracting attention for its potential to improve traffic safety and increase traffic volume worldwide, improving the accuracy of data and parameters collected from moving vehicles is widely discussed in the V2X. The most common technique of GPS may not be efficient during some specific scenarios, like some intersections full of skyscrapers, or some special terrains with obstacles. In such cases, GPS technology has a longer detection period and lower tracking accuracy, so beam tracking can be a fast and efficient solution in these circumstances. Therefore we propose an anti-diverge extend Kalman filter-enabled beam tracking method in V2X to help the intersection management. The numerical results show that our method has the ability to resist the Kalman filter’s divergence and can detect data in an accurate manner.
Pengfei Lin, Ehsan Javanmardi, Ye Tao, Vishal Chauhan, Jin Nakazato, Manabu Tsukada, "Time-To-Collision-Aware Lane-Change Strategy Based on Potential Field and Cubic Polynomial for Autonomous Vehicles", In: 2023 IEEE Intelligent Vehicles Symposium (IEEE IV 2023), Anchorage, Alaska, USA, 2023.Proceedings Article | Abstract | BibTeX | Links:
@inproceedings{Lin2023,
title = {Time-To-Collision-Aware Lane-Change Strategy Based on Potential Field and Cubic Polynomial for Autonomous Vehicles},
author = {Pengfei Lin and Ehsan Javanmardi and Ye Tao and Vishal Chauhan and Jin Nakazato and Manabu Tsukada},
url = {https://arxiv.org/abs/2306.06981},
year = {2023},
date = {2023-06-04},
urldate = {2023-06-04},
booktitle = {2023 IEEE Intelligent Vehicles Symposium (IEEE IV 2023)},
address = {Anchorage, Alaska, USA},
abstract = {Making safe and successful lane changes (LCs) is one of the many vitally important functions of autonomous vehicles (AVs) that are needed to ensure safe driving on expressways. Recently, the simplicity and real-time performance of the potential field (PF) method have been leveraged to design decision and planning modules for AVs. However, the LC trajectory planned by the PF method is usually lengthy and takes the ego vehicle laterally parallel and close to the obstacle vehicle, which creates a dangerous situation if the obstacle vehicle suddenly steers. To mitigate this risk, we propose a time-to-collision-aware LC (TTCA-LC) strategy based on the PF and cubic polynomial in which the TTC constraint is imposed in the optimized curve fitting. The proposed approach is evaluated using MATLAB/Simulink under high-speed conditions in a comparative driving scenario. The simulation results indicate that the TTCA-LC method performs better than the conventional PF-based LC (CPF-LC) method in generating shorter, safer, and smoother trajectories. The length of the LC trajectory is shortened by over 27.1%, and the curvature is reduced by approximately 56.1% compared with the CPF-LC method.
},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Making safe and successful lane changes (LCs) is one of the many vitally important functions of autonomous vehicles (AVs) that are needed to ensure safe driving on expressways. Recently, the simplicity and real-time performance of the potential field (PF) method have been leveraged to design decision and planning modules for AVs. However, the LC trajectory planned by the PF method is usually lengthy and takes the ego vehicle laterally parallel and close to the obstacle vehicle, which creates a dangerous situation if the obstacle vehicle suddenly steers. To mitigate this risk, we propose a time-to-collision-aware LC (TTCA-LC) strategy based on the PF and cubic polynomial in which the TTC constraint is imposed in the optimized curve fitting. The proposed approach is evaluated using MATLAB/Simulink under high-speed conditions in a comparative driving scenario. The simulation results indicate that the TTCA-LC method performs better than the conventional PF-based LC (CPF-LC) method in generating shorter, safer, and smoother trajectories. The length of the LC trajectory is shortened by over 27.1%, and the curvature is reduced by approximately 56.1% compared with the CPF-LC method.
Muhammad Asad, Saima Shaukat, Ehsan Javanmardi, Jin Nakazato, Manabu Tsukada, "A Comprehensive Survey on Privacy-Preserving Techniques in Federated Recommendation Systems", In: Applied Sciences , 2023, ISSN: 2076-3417.Journal Article | Abstract | BibTeX | Links:
@article{Asad2023,
title = {A Comprehensive Survey on Privacy-Preserving Techniques in Federated Recommendation Systems},
author = {Muhammad Asad and Saima Shaukat and Ehsan Javanmardi and Jin Nakazato and Manabu Tsukada},
doi = {10.3390/app13106201},
issn = {2076-3417},
year = {2023},
date = {2023-05-18},
urldate = {2023-05-18},
journal = {Applied Sciences },
abstract = {Big data is a rapidly growing field, and new developments are constantly emerging to address various challenges. One such development is the use of federated learning for recommendation systems (FRSs). An FRS provides a way to protect user privacy by training recommendation models using intermediate parameters instead of real user data. This approach allows for cooperation between data platforms while still complying with privacy regulations. In this paper, we explored the current state of research on FRSs, highlighting existing research issues and possible solutions. Specifically, we looked at how FRSs can be used to protect user privacy while still allowing organizations to benefit from the data they share. Additionally, we examined potential applications of FRSs in the context of big data, exploring how these systems can be used to facilitate secure data sharing and collaboration. Finally, we discuss the challenges associated with developing and deploying FRSs in the real world and how these challenges can be addressed.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Big data is a rapidly growing field, and new developments are constantly emerging to address various challenges. One such development is the use of federated learning for recommendation systems (FRSs). An FRS provides a way to protect user privacy by training recommendation models using intermediate parameters instead of real user data. This approach allows for cooperation between data platforms while still complying with privacy regulations. In this paper, we explored the current state of research on FRSs, highlighting existing research issues and possible solutions. Specifically, we looked at how FRSs can be used to protect user privacy while still allowing organizations to benefit from the data they share. Additionally, we examined potential applications of FRSs in the context of big data, exploring how these systems can be used to facilitate secure data sharing and collaboration. Finally, we discuss the challenges associated with developing and deploying FRSs in the real world and how these challenges can be addressed.
神原滉一, Ehsan Javanmardi, 中里仁, 山田俊也, 渡辺陽介, 高田広章, 佐藤健哉, 塚田学, "協調型自動運転のための地理的特性を考慮したネットワーク補間", 電子情報通信学会 ITS研究会, 広島, 2023.Conference | Abstract | BibTeX | Links:
@conference{神原滉一2023,
title = {協調型自動運転のための地理的特性を考慮したネットワーク補間},
author = {神原滉一 and Ehsan Javanmardi and 中里仁 and 山田俊也 and 渡辺陽介 and 高田広章 and 佐藤健哉 and 塚田学},
url = {https://tlab.hongo.wide.ad.jp/papers/2023_IEICE_kambara.pdf
https://ken.ieice.org/ken/paper/20230222ZCRc/},
year = {2023},
date = {2023-02-21},
urldate = {2023-02-21},
booktitle = {電子情報通信学会 ITS研究会},
address = {広島},
abstract = {近年,協調型の自動運転が交通安全や交通流の効率化につながるとして注目されている.協調型自動運転とは,自動運転車が周囲の車両や道路に設置した路側機と通信を行い,自車の車載センサでは認識できなかった情報やタスクを共有するシステムのことである.協調型自動運転の重要な要件の一つは,すべての車両が適切なタイミングで適切なメッセージを受信することであり,そのためには,一定以上の通信性能の担保が必要である.事前に通信性能を把握しておくことによって,自動運転車は適切な認知方法の選択や,経路計画を行うことができる.そこで,本研究では,協調型自動運転のための地理的特性を考慮した通信性能分析,可視化システムを提案する.このシステムでは,車両が一度通過した場所の通信性能を分析,可視化し,クラウドに保存することによって,次に同じ場所を通過する車が,事前に通信性能を参照し,移動ルート決定ができるようになる.本提案システムを自動運転のためのオープンソースソフトウェアであるAutowareとダイナミックマッププラットフォームであるDM2.0PFを用いて実装し,東京大学柏キャンパステストコースにて,アウトドア実験,評価を行った結果を報告する.
},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
近年,協調型の自動運転が交通安全や交通流の効率化につながるとして注目されている.協調型自動運転とは,自動運転車が周囲の車両や道路に設置した路側機と通信を行い,自車の車載センサでは認識できなかった情報やタスクを共有するシステムのことである.協調型自動運転の重要な要件の一つは,すべての車両が適切なタイミングで適切なメッセージを受信することであり,そのためには,一定以上の通信性能の担保が必要である.事前に通信性能を把握しておくことによって,自動運転車は適切な認知方法の選択や,経路計画を行うことができる.そこで,本研究では,協調型自動運転のための地理的特性を考慮した通信性能分析,可視化システムを提案する.このシステムでは,車両が一度通過した場所の通信性能を分析,可視化し,クラウドに保存することによって,次に同じ場所を通過する車が,事前に通信性能を参照し,移動ルート決定ができるようになる.本提案システムを自動運転のためのオープンソースソフトウェアであるAutowareとダイナミックマッププラットフォームであるDM2.0PFを用いて実装し,東京大学柏キャンパステストコースにて,アウトドア実験,評価を行った結果を報告する.
浅部佑, エッサン ジャワーンマーディ, 中里仁, 塚田学, 江崎浩, "AutowareV2X:自動運転におけるV2X通信と協調認知の実現", 電子情報通信学会 ITS研究会, 広島, 2023.Conference | Abstract | BibTeX | Links:
@conference{浅部佑2023,
title = {AutowareV2X:自動運転におけるV2X通信と協調認知の実現},
author = {浅部佑 and エッサン ジャワーンマーディ and 中里仁 and 塚田学 and 江崎浩},
url = {https://tlab.hongo.wide.ad.jp/papers/2023_IEICE_asabe.pdf
https://ken.ieice.org/ken/paper/202302223CR2/},
year = {2023},
date = {2023-02-21},
urldate = {2023-02-21},
booktitle = {電子情報通信学会 ITS研究会},
address = {広島},
abstract = {近年,自律型自動運転の研究開発と社会実装が着々と進む中,その技術的な課題や限界点も指摘され始めている.そこで,最先端の無線通信技術やネットワーク技術を活かして様々な交通システムが協調的に認知,判断,実行を担える協調型自動運転の分野が注目されている.特に,多くのコネクテッドな交通参加者が自らのセンサーで認識した物標情報を共有することで,ネットワーク全体の環境の認識率の向上を図る「協調認知」の活用は大きく期待されている.本研究では,自動運転ソフトウェアに統合可能なV2X通信機能の要求事項を検討し,オープンソースの自動運転ソフトウェアである「Autoware」に外部接続性を提供できるV2Xモジュール「AutowareV2X」を提案した.本提案では,自律型自動運転の基本機能に加え,汎用性のある標準化されたV2Xメッセージでの通信を可能にすることにより,協調型自動運転アプリケーションを実装,実証実験できる基盤を実現した.さらに,協調認知のアプリケーションを実装し協調認知メッセージ(CPM)による物標情報の共有を可能とした.AutowareV2Xを活用することで路側機で認知した物標情報を自動運転車両に30ミリ秒以内で伝達することを実証実験により証明するができた.また,死角から歩行者や車両が飛び出てくるシナリオにおいては,道路脇に設置された路側機から物標情報をリアルタイムに共有されることにより,自動運転車両が減速・停止という危険回避動作を実現できた.本実証実験より,協調認知に限らず行動調停などの他のアプリケーションへのAutowareV2Xの活用も期待される.
},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
近年,自律型自動運転の研究開発と社会実装が着々と進む中,その技術的な課題や限界点も指摘され始めている.そこで,最先端の無線通信技術やネットワーク技術を活かして様々な交通システムが協調的に認知,判断,実行を担える協調型自動運転の分野が注目されている.特に,多くのコネクテッドな交通参加者が自らのセンサーで認識した物標情報を共有することで,ネットワーク全体の環境の認識率の向上を図る「協調認知」の活用は大きく期待されている.本研究では,自動運転ソフトウェアに統合可能なV2X通信機能の要求事項を検討し,オープンソースの自動運転ソフトウェアである「Autoware」に外部接続性を提供できるV2Xモジュール「AutowareV2X」を提案した.本提案では,自律型自動運転の基本機能に加え,汎用性のある標準化されたV2Xメッセージでの通信を可能にすることにより,協調型自動運転アプリケーションを実装,実証実験できる基盤を実現した.さらに,協調認知のアプリケーションを実装し協調認知メッセージ(CPM)による物標情報の共有を可能とした.AutowareV2Xを活用することで路側機で認知した物標情報を自動運転車両に30ミリ秒以内で伝達することを実証実験により証明するができた.また,死角から歩行者や車両が飛び出てくるシナリオにおいては,道路脇に設置された路側機から物標情報をリアルタイムに共有されることにより,自動運転車両が減速・停止という危険回避動作を実現できた.本実証実験より,協調認知に限らず行動調停などの他のアプリケーションへのAutowareV2Xの活用も期待される.
2022
Yu Asabe, Ehsan Javanmardi, Jin Nakazato, Manabu Tsukada, Hiroshi Esaki, "AutowareV2X: Enabling V2X Communication and Collective Perception for Autonomous Driving", Asian Internet Engineering Conference (AINTEC) 2022 Poster, 2022, (Best Poster Award).Miscellaneous | Abstract | BibTeX | Links:
@misc{Asabe2022,
title = {AutowareV2X: Enabling V2X Communication and Collective Perception for Autonomous Driving},
author = {Yu Asabe and Ehsan Javanmardi and Jin Nakazato and Manabu Tsukada and Hiroshi Esaki},
url = {https://tlab.hongo.wide.ad.jp/papers/2022_AINTEC2022_poster_asabe.pdf},
year = {2022},
date = {2022-12-20},
urldate = {2022-12-20},
abstract = {For cooperative intelligent transport systems (C-ITS), vehicle-to-everything (V2X) communication is utilized to allow autonomous vehicles to share critical information with each other, enabling cooperatively enhanced environmental awareness and decision-making. We propose AutowareV2X, an implementation of a V2X communication module that is integrated into the autonomous driving (AD) software, Autoware. AutowareV2X provides external connectivity to the entire AD stack, enabling the end-to-end experimentation and evaluation of connected autonomous vehicles (CAV).},
howpublished = {Asian Internet Engineering Conference (AINTEC) 2022 Poster},
note = {Best Poster Award},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
For cooperative intelligent transport systems (C-ITS), vehicle-to-everything (V2X) communication is utilized to allow autonomous vehicles to share critical information with each other, enabling cooperatively enhanced environmental awareness and decision-making. We propose AutowareV2X, an implementation of a V2X communication module that is integrated into the autonomous driving (AD) software, Autoware. AutowareV2X provides external connectivity to the entire AD stack, enabling the end-to-end experimentation and evaluation of connected autonomous vehicles (CAV).
Koichi Kambara, Ehsan Javanmardi, Jin Nakazato, Yousuke Watanabe, Kenya Sato, Hiroaki Takada, Manabu Tsukada, "Towards Cooperative Automated Driving: Geographic-Aware Network Analysis and Visualization tool", Asian Internet Engineering Conference (AINTEC) 2022 Poster, 2022.Miscellaneous | Abstract | BibTeX | Links:
@misc{Kambara2022,
title = {Towards Cooperative Automated Driving: Geographic-Aware Network Analysis and Visualization tool},
author = {Koichi Kambara and Ehsan Javanmardi and Jin Nakazato and Yousuke Watanabe and Kenya Sato and Hiroaki Takada and Manabu Tsukada},
url = {https://tlab.hongo.wide.ad.jp/papers/2022_AINTEC2022_poster_kambara.pdf},
year = {2022},
date = {2022-12-19},
urldate = {2022-12-19},
abstract = {In recent years the cooperative automated vehicle (CAV) concept has been gaining attention due to its potential to increase traffic safety and traffic flow by utilizing the vehicle-to-everything communication capability. One of the key requirements for CAV is ensuring every vehicle receives relevant messages at the right time and place; therefore, measuring and visualizing network performance is vital. However, for CAV applications, more network analyzers than those extant are needed because these do not consider geographical characteristics. In this study, we proposed a geographically-aware CAV-specific network analysis and visualization tool that can report the network performance factors such as packet loss, bandwidth, and jitter in real time. Further, we developed a proposal tool and evaluated it in an outdoor proof-of-concept study at the University of Tokyo’s Hongo Campus.},
howpublished = {Asian Internet Engineering Conference (AINTEC) 2022 Poster},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
In recent years the cooperative automated vehicle (CAV) concept has been gaining attention due to its potential to increase traffic safety and traffic flow by utilizing the vehicle-to-everything communication capability. One of the key requirements for CAV is ensuring every vehicle receives relevant messages at the right time and place; therefore, measuring and visualizing network performance is vital. However, for CAV applications, more network analyzers than those extant are needed because these do not consider geographical characteristics. In this study, we proposed a geographically-aware CAV-specific network analysis and visualization tool that can report the network performance factors such as packet loss, bandwidth, and jitter in real time. Further, we developed a proposal tool and evaluated it in an outdoor proof-of-concept study at the University of Tokyo’s Hongo Campus.