Research on Robot Path Planning Based on Reinforcement Learning

TL;DR

This paper develops a Visual SLAM system based on ORB-SLAM3 for dense mapping, converts the map for 2D path planning, and compares reinforcement learning algorithms, finding DQN most effective in complex environments.

Contribution

The work integrates Visual SLAM with reinforcement learning for robot path planning and identifies DQN as the most suitable algorithm for high-dimensional environments.

Findings

DQN outperforms Q-learning and SARSA in convergence speed and performance.

The Visual SLAM system is validated with open-source and custom datasets.

The map conversion process produces lightweight grid maps suitable for path planning.

Abstract

This project has conducted research on robot path planning based on Visual SLAM. The main work of this project is as follows: (1) Construction of Visual SLAM system. Research has been conducted on the basic architecture of Visual SLAM. A Visual SLAM system is developed based on ORB-SLAM3 system, which can conduct dense point cloud mapping. (2) The map suitable for two-dimensional path planning is obtained through map conversion. This part converts the dense point cloud map obtained by Visual SLAM system into an octomap and then performs projection transformation to the grid map. The map conversion converts the dense point cloud map containing a large amount of redundant map information into an extremely lightweight grid map suitable for path planning. (3) Research on path planning algorithm based on reinforcement learning. This project has conducted experimental comparisons between the Q-learning algorithm, the DQN algorithm, and the SARSA algorithm, and found that DQN is the algorithm with the fastest convergence and best performance in high-dimensional complex environments. This project has conducted experimental verification of the Visual SLAM system in a simulation environment. The experimental results obtained based on open-source dataset and self-made dataset prove the feasibility and effectiveness of the designed Visual SLAM system. At the same time, this project has also conducted comparative experiments on the three reinforcement learning algorithms under the same experimental condition to obtain the optimal algorithm under the experimental condition.