Mobile Robot
Mobile robots are autonomous systems designed to navigate and interact with their environment, with research focusing on improving their perception, navigation, and manipulation capabilities. Current efforts concentrate on enhancing robustness through sensor fusion (e.g., combining radar and vision data), efficient motion planning guided by natural language instructions or reinforcement learning, and reliable localization using techniques like visual odometry and polygon-based mapping. These advancements are crucial for expanding the applications of mobile robots in diverse fields, including manufacturing, logistics, healthcare, and exploration, by enabling safer, more efficient, and adaptable operation in complex and dynamic settings.
Papers
Mobile-Seed: Joint Semantic Segmentation and Boundary Detection for Mobile Robots
Youqi Liao, Shuhao Kang, Jianping Li, Yang Liu, Yun Liu, Zhen Dong, Bisheng Yang, Xieyuanli Chen
Analyzing Behaviors of Mixed Traffic via Reinforcement Learning at Unsignalized Intersections
Supriya Sarker
EnduRL: Enhancing Safety, Stability, and Efficiency of Mixed Traffic Under Real-World Perturbations Via Reinforcement Learning
Bibek Poudel, Weizi Li, Kevin Heaslip