Human-Aware Robot Navigation via Reinforcement Learning with Hindsight Experience Replay and Curriculum Learning

Li，Keyu1; Lu，Ye1; Meng，Max Q.H.1,2,3

10.1109/ROBIO54168.2021.9739519

2021

978-1-6654-0536-2

2021 IEEE International Conference on Robotics and Biomimetics, ROBIO 2021

346-351

27-31 Dec. 2021

Sanya, China

In recent years, the growing demand for more intelligent service robots is pushing the development of mobile robot navigation algorithms to allow safe and efficient operation in a dense crowd. Reinforcement learning (RL) approaches have shown superior ability in solving sequential decision making problems, and recent work has explored its potential to learn navigation polices in a socially compliant manner. However, the expert demonstration data used in existing methods is usually expensive and difficult to obtain. In this work, we consider the task of training an RL agent without employing the demonstration data, to achieve efficient and collision-free navigation in a crowded environment. To address the sparse reward navigation problem, we propose to incorporate the hindsight experience replay (HER) and curriculum learning (CL) techniques with RL to efficiently learn the optimal navigation policy in the dense crowd. The effectiveness of our method is validated in a simulated crowd-robot coexisting environment. The results demonstrate that our method can effectively learn human-aware navigation without requiring additional demonstration data.

collision avoidance human-aware navigation mobile robot reinforcement learning sparse reward

其他

英语

EI

20221611977608

Curricula ; Decision making ; Demonstrations ; Intelligent robots ; Navigation ; Reinforcement learning

Artificial Intelligence:723.4 ; Robotics:731.5 ; Robot Applications:731.6 ; Education:901.2 ; Management:912.2

2-s2.0-85128241229

Scopus

1.Chinese University of Hong Kong,Department of Electronic Engineering,Hong Kong
2.Department of Electronic and Electrical Engineering,Southern University of Science and Technology,Shenzhen,China
3.Shenzhen Research Institute,Chinese University of Hong Kong,Shenzhen,China

Li，Keyu,Lu，Ye,Meng，Max Q.H.. Human-Aware Robot Navigation via Reinforcement Learning with Hindsight Experience Replay and Curriculum Learning[C],2021:346-351.