/RL-Narrow-Space-Exploration

Code for paper "Reinforcement Learning for Self-exploration in Narrow Spaces"

Primary LanguagePython

"Reinforcement Learning for Self-exploration in Narrow Spaces"

by Zhaofeng Tian | Website

New Repo for this project, which contains ROS RL envs.

demo

RL Algorithms

This repo includes five RL algorithms that benchmarked in the paper. To work the code on your local machine, you may need appopriate APIs to OpenAI gym and ROS. In our case, we run the code with our tailored gazebo simulator for our robot ZebraT. More details may be published later.

Reference

  1. ZebraT Simulator
  2. RL with Phil

Cite Paper

@inproceedings{tian2024unguided, title={Unguided Self-exploration in Narrow Spaces with Safety Region Enhanced Reinforcement Learning for Ackermann-steering Robots}, author={Tian, Zhaofeng and Liu, Zichuan and Zhou, Xingyu and Shi, Weisong}, booktitle={2024 IEEE International Conference on Mobility, Operations, Services and Technologies (MOST)}, pages={260--268}, year={2024}, organization={IEEE} }