We are pleased to announce that two papers from Tsukada Laboratory have been accepted to the IEEE International Conference on Robotics and Automation 2026 (ICRA 2026). ICRA is one of the flagship international conferences in robotics and automation, and ICRA 2026 will be held in Vienna, Austria, from June 1 to 5, 2026.
The first paper, “A Synthetic Benchmark for Collaborative 3D Semantic Occupancy Prediction in V2X-Enabled Autonomous Driving,” presents a synthetic benchmark for collaborative 3D semantic occupancy prediction in autonomous driving. The work addresses the limitations of single-vehicle perception, such as occlusion, limited sensing range, and narrow viewpoints, by enabling collaborative perception through shared information among agents. The paper introduces a high-resolution semantic voxel sensor in CARLA, generates dense annotations, and develops a baseline model with inter-agent feature fusion based on spatial alignment and attention aggregation. The authors also establish benchmarks with different prediction ranges to systematically evaluate collaborative prediction. The related Co3SOP project has also been made public.
The second paper, “Trajectory Planning for UAV-Based Smart Farming Using Imitation-Based Triple Deep Q-Learning,” focuses on trajectory planning for UAV-assisted smart farming. In this setting, UAVs are expected to perform weed recognition and wireless sensor data collection under uncertainty, partial observations, and limited battery capacity. To address these challenges, the paper formulates the problem as a Markov decision process and proposes a new imitation-based triple deep Q-network (ITDQN) algorithm built on multi-agent reinforcement learning. Experimental results in both simulation and real-world environments show that the proposed method outperforms DDQN by 4.43% in weed recognition rate and 6.94% in data collection rate.
These two papers highlight the breadth of research in Tsukada Laboratory, spanning both collaborative perception for autonomous driving and intelligent robotics for smart agriculture. We are excited to present these results at ICRA 2026 and to continue advancing interdisciplinary research across mobility, robotics, AI, and real-world systems.
