Toward stable astronaut following of extravehicular activity assistant robots using deep reinforcement learning

摘要

The use of mobile robots for assisting astronauts in extravehicular activities could be an effective option for improving mission productivity and crew safety. It is thus critical that these robots follow the astronaut and maintain a stable distance to provide personalized and timely assistance. However, most extraterrestrial bodies exhibit rugged terrain that can impede a robot’s movements. As such, a novel predictive-guide following strategy is proposed to improve the stability of astronaut–robot distance in obstructive environments. This strategy combines a deep reinforcement learning navigator and a Kalman filter-based predictor to generate optimized motion sequences for safely following the astronaut and acquire predictive guidance concerning future astronaut movements. The proposed model achieved a success rate of 95.0% in simulated navigation tasks and adapted well to untrained complex environments and varied robot movement settings. Comparative tests indicated our strategy managed to stabilize the following distance to within ±1.0 m of the reference value in obstructed environments, significantly outperforming other following strategies. The feasibility and advantage of the proposed approach was validated with a physical robotic follower in a Mars-like environment. [Formula: see text]