Learning-Based End-to-End Path Planning for Lunar Rovers with Safety Constraints.

Xiaoqiang Yu,Ping Wang,Zexu Zhang

doi:10.3390/s21030796

Xiaoqiang Yu, Ping Wang + Show 1 more

Open Access

https://doi.org/10.3390/s21030796

Copy DOI

Abstract

Path planning is an essential technology for lunar rover to achieve safe and efficient autonomous exploration mission, this paper proposes a learning-based end-to-end path planning algorithm for lunar rovers with safety constraints. Firstly, a training environment integrating real lunar surface terrain data was built using the Gazebo simulation environment and a lunar rover simulator was created in it to simulate the real lunar surface environment and the lunar rover system. Then an end-to-end path planning algorithm based on deep reinforcement learning method is designed, including state space, action space, network structure, reward function considering slip behavior, and training method based on proximal policy optimization. In addition, to improve the generalization ability to different lunar surface topography and different scale environments, a variety of training scenarios were set up to train the network model using the idea of curriculum learning. The simulation results show that the proposed planning algorithm can successfully achieve the end-to-end path planning of the lunar rover, and the path generated by the proposed algorithm has a higher safety guarantee compared with the classical path planning algorithm.

Highlights

As the closest celestial body to the Earth in the universe, the Moon is the main goal of human beings for deep space exploration because of its great location advantage and abundant material resources
(2) We propose a learning-based endto-end path planning algorithm with safety constraints, in which a safety reward function considering the sliding behavior of the lunar rover is designed, and the sliding rate of the lunar rover is predicted based on the slope angle of the terrain in which the lunar rover is located, and it is used as a reward feedback for the current state to improve the safety assurance of the lunar rover autonomous exploration process
Aiming at the problem of autonomous exploration path planning for lunar rover, this paper proposes a learning-based end-to-end path planning algorithm with safety constraints

Summary

Introduction

As the closest celestial body to the Earth in the universe, the Moon is the main goal of human beings for deep space exploration because of its great location advantage and abundant material resources. With the gradual understanding of the Moon, the main lunar exploration goals of the world’s major aerospace nations in the future will focus on the development and utilization of lunar resources, the establishment of lunar bases, and the way to deep space through the moon. In the lunar exploration plans of various countries, the lunar rover, as the executive body and an important part of the lunar exploration mission, is the main research object. The autonomous movement and detection capability of lunar rover will undoubtedly provide a more autonomous and robust detection mode for lunar exploration, and greatly improve the efficiency of lunar exploration

Objectives

Results

Discussion

Conclusion