Traditional person following robots usually need hand-crafted features and a well-designed controller to follow the assigned person. Normally it is difficult to be applied in outdoor situations due to variability and complexity of the environment. In this paper, we propose an approach in which an agent is trained by hybrid-supervised deep reinforcement learning (DRL) to perform a person following task in end-to-end manner. The approach enables the robot to learn features autonomously from monocular images and to enhance performance via robot-environment interaction. Experiments show that the proposed approach is adaptive to complex situations with significant illumination variation, object occlusion, target disappearance, pose change, and pedestrian interference. In order to speed up the training process to ensure easy application of DRL to real-world robotic follower controls, we apply an integration method through which the agent receives prior knowledge from a supervised learning (SL) policy network and reinforces its performance with a value-based or policy-based (including actor-critic method) DRL model. We also utilize an efficient data collection approach for supervised learning in the context of person following. Experimental results not only verify the robustness of the proposed DRL-based person following robot system, but also indicate how easily the robot can learn from mistakes and improve performance.
|Number of pages||14|
|Journal||Journal of Intelligent and Robotic Systems: Theory and Applications|
|Early online date||25 May 2019|
|Publication status||Published online - 25 May 2019|
Bibliographical noteFunding Information:
This work is supported by the Fundamental Research Funds for the Central Universities(N172608005, N182608004), Young and Middle-aged Innovative Talent Plan of Shenyang(RC170490), Natural Science Foundation of Liaoning (No.20180520040) and National Natural Science Foundation of China (No. 61471110, 61733003).
© 2019, Springer Nature B.V.
Copyright 2020 Elsevier B.V., All rights reserved.
- Deep reinforcement learning
- Efficient data collection
- Integration method
- Person following robot
- Real-world situations