TY - GEN
T1 - Collision-free Navigation of Human-centered Robots via Markov Games
AU - Ye, Guo
AU - Lin, Qinjie
AU - Juang, Tzung Han
AU - Liu, Han
N1 - Funding Information:
Acknowledgement We sincerely thank Jiayi Wang and Zhihan Zhou from the Northwestern University for providing very helpful discussions and graphics materials in this paper. Han Liu’s research is supported by the NSF BIGDATA 1840866, NSF CAREER 1841569, NSF TRIPODS 1740735, DARPA-PA-18-02-09-QED-RML-FP-003, along with an Alfred P Sloan Fellowship and a PECASE award.
PY - 2020/5
Y1 - 2020/5
N2 - We exploit Markov games as a framework for collision-free navigation of human-centered robots. Unlike the classical methods which formulate robot navigation as a single-agent Markov decision process with a static environment, our framework of Markov games adopts a multi-agent formulation with one primary agent representing the robot and the remaining auxiliary agents form a dynamic or even competing environment. Such a framework allows us to develop a path-following type adversarial training strategy to learn a robust decentralized collision avoidance policy. Through thorough experiments on both simulated and real-world mobile robots, we show that the learnt policy outperforms the state-of-the-art algorithms in both sample complexity and runtime robustness.
AB - We exploit Markov games as a framework for collision-free navigation of human-centered robots. Unlike the classical methods which formulate robot navigation as a single-agent Markov decision process with a static environment, our framework of Markov games adopts a multi-agent formulation with one primary agent representing the robot and the remaining auxiliary agents form a dynamic or even competing environment. Such a framework allows us to develop a path-following type adversarial training strategy to learn a robust decentralized collision avoidance policy. Through thorough experiments on both simulated and real-world mobile robots, we show that the learnt policy outperforms the state-of-the-art algorithms in both sample complexity and runtime robustness.
KW - Collision-free navigation
KW - adversarial training
KW - deep reinforcement learning
KW - human-centered robotics
KW - multi-agent system
UR - http://www.scopus.com/inward/record.url?scp=85092720157&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85092720157&partnerID=8YFLogxK
U2 - 10.1109/ICRA40945.2020.9196810
DO - 10.1109/ICRA40945.2020.9196810
M3 - Conference contribution
AN - SCOPUS:85092720157
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 11338
EP - 11344
BT - 2020 IEEE International Conference on Robotics and Automation, ICRA 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE International Conference on Robotics and Automation, ICRA 2020
Y2 - 31 May 2020 through 31 August 2020
ER -