Relaxing the Limitations of the Optimal Reciprocal Collision Avoidance Algorithm for Mobile Robots in Crowds

被引:0
作者
Liu, Zhihao [1 ]
Na, Wenjie [1 ]
Yao, Chenpeng [1 ]
Liu, Chengju [1 ,2 ]
Chen, Qijun [1 ]
机构
[1] Tongji Univ, Dept Elect & Informat Engn, Shanghai 201804, Peoples R China
[2] Tongji Res Inst Artificial Intelligence, Suzhou 215131, Peoples R China
基金
中国国家自然科学基金;
关键词
Collision avoidance; Robots; Pedestrians; Planning; Navigation; Mobile robots; Vectors; Autonomous vehicle navigation; Motion and Path Planning; Reinforcement Learning; OBSTACLES;
D O I
10.1109/LRA.2024.3390561
中图分类号
TP24 [机器人技术];
学科分类号
080202 ; 1405 ;
摘要
The Optimal Reciprocal Collision Avoidance (ORCA) algorithm is widely used for modeling agents in collision avoidance scenarios. However, suffering from limitations such as the improper reciprocal assumption that each agent is supposed to take half the responsibility for collision avoidance, the performance of ORCA-based mobile robots in crowds is not ideal. In this letter, to relax these limitations, we firstly simplify the planning process of ORCA from the principle horizon to solve ORCA being unsolvable in some cases. Then the escape velocity and collision avoidance responsibility are explored simultaneously based on deep reinforcement learning (DRL) to solve the limitation of local optimum caused by only exploring the responsibility in other works. We compare our method with baselines in environments with different numbers of pedestrians and test in different real-world scenarios. The results show that our method is beneficial in reducing the collision probability and the average number of ORCA no solutions for the robot in crowds.
引用
收藏
页码:5520 / 5527
页数:8
相关论文
共 22 条
[1]  
Charlton John, 2020, Transactions on Computational Science XXXVII. Special Issue on Computer Graphics. Lecture Notes in Computer Science (LNCS 12230), P129, DOI 10.1007/978-3-662-61983-4_8
[2]  
Chen CG, 2019, IEEE INT CONF ROBOT, P6015, DOI [10.1109/icra.2019.8794134, 10.1109/ICRA.2019.8794134]
[3]  
Choi J, 2019, IEEE INT CONF ROBOT, P5993, DOI [10.1109/ICRA.2019.8793979, 10.1109/icra.2019.8793979]
[4]   Getting Robots Unfrozen and Unlost in Dense Pedestrian Crowds [J].
Fan, Tingxiang ;
Cheng, Xinjing ;
Pan, Jia ;
Long, Pinxin ;
Liu, Wenxi ;
Yang, Ruigang ;
Manocha, Dinesh .
IEEE ROBOTICS AND AUTOMATION LETTERS, 2019, 4 (02) :1178-1185
[5]   VR-ORCA: Variable Responsibility Optimal Reciprocal Collision Avoidance [J].
Guo, Ke ;
Wang, Dawei ;
Fan, Tingxiang ;
Pan, Jia .
IEEE ROBOTICS AND AUTOMATION LETTERS, 2021, 6 (03) :4520-4527
[6]   SOCIAL FORCE MODEL FOR PEDESTRIAN DYNAMICS [J].
HELBING, D ;
MOLNAR, P .
PHYSICAL REVIEW E, 1995, 51 (05) :4282-4286
[7]  
Koenig N., 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566), P2149
[8]  
Li Hengduo, 2019, arXiv
[9]   GAMMA: A General Agent Motion Model for Autonomous Driving [J].
Luo, Yuanfu ;
Cai, Panpan ;
Lee, Yiyuan ;
Hsu, David .
IEEE ROBOTICS AND AUTOMATION LETTERS, 2022, 7 (02) :3499-3506
[10]   PORCA: Modeling and Planning for Autonomous Driving Among Many Pedestrians [J].
Luo, Yuanfu ;
Cai, Panpan ;
Bera, Aniket ;
Hsu, David ;
Lee, Wee Sun ;
Manocha, Dinesh .
IEEE ROBOTICS AND AUTOMATION LETTERS, 2018, 3 (04) :3418-3425