Surface exploration and data collection by planetary rovers are challenging due to unknown complex planet terrains. This paper focuses on developing a Deep Reinforcement Learning (DRL)-based controller for rovers to enable safe operation. The necessary control input for safe and efficient vehicle maneuver is derived using the Control Barrier Function (CBF)-based safety protocols. Deep Deterministic Policy Gradient (DDPG) algorithm is used as a DRL framework to find the optimal exploration policies for the rover. Numerical simulations on different vehicle models show the efficacy of the proposed safety method for planetary rovers.
Safe Deep Reinforcement Learning-Based Controller (SDRLC) for Autonomous Navigation of Planetary Rovers
2024-07-22
1141665 byte
Conference paper
Electronic Resource
English
Autonomous Navigation of Rovers for Planetary Exploration
British Library Conference Proceedings | 1999
|Numerical simulations for planetary rovers safe navigation and LIDAR based localization
BASE | 2021
|Terrain Adaptive Navigation for planetary rovers
British Library Online Contents | 2009
|