Abstract
The global path planning of planetary surface rovers is crucial for optimizing exploration benefits and system safety. For the cases of long-range roving or obstacle constraints that are time-varied, there is an urgent need to improve the computational efficiency of path planning. This paper proposes a learning-based global path planning method that outperforms conventional searching and sampling-based methods in terms of planning speed. First, a distinguishable feature map is constructed through a traversability analysis of the extraterrestrial digital elevation model. Then, considering planning efficiency and adaptability, a hierarchical framework consisting of step iteration and block iteration is designed. For the planning of each step, an end-to-end step planner named SP-ResNet is proposed that is based on deep reinforcement learning. This step planner employs a double-branch residual network for action value estimation, and is trained over a simulated DEM map collection. Comparative analyses with baselines demonstrate the prominent advantage of our method in terms of planning speed. Finally, the method is verified to be effective on real lunar terrains using CE2TMap2015.
Highlights
The path planning of planetary rovers is crucial for improving exploration benefits and system safety in extraterrestrial exploration
It is of great significance to improve the computational efficiency of planetary roving path planning, especially for the cases of long-range maneuvers or obstacle constraints that are time-varied, such as illumination
The study is an important attempt to improve the path planning efficiency in longrange extraterrestrial roving based on a learning method
Summary
The path planning of planetary rovers is crucial for improving exploration benefits and system safety in extraterrestrial exploration. The right path can be identified by some path searching algorithms, such as the A* [8,9], the rapidly exploring random trees (RRT) [10,11], the ant colony algorithm [12], and the genetic algorithm [13], etc These methods are operable in most instances, but may suffer from the exponential explosion of computation time when it comes to wide-range or high-resolution maps. We propose a novel learning-based planning method for the global path planning of planetary roving, which can significantly improve the planning speed for long-range roving and which, can adapt to arbitrarily sized maps. (1) A novel learning-based method combining a hierarchical planning framework and an end-to-end step planner improves the computational efficiency for long-range path planning.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
