MIRSim-RL: A Simulated Mobile Industry Robot Platform and Benchmarks for Reinforcement Learning

Qingkai Li, Zijian Ma, Chenxing Li, Chenxing Li, Yinlong Liu, Tobias Recker, Daniel Brauchle, Jan Seyler, Mingguo Zhao, Shahram Eivazi, Shahram Eivazi

2025

Abstract

The field of mobile robotics has undergone a transformation in recent years due to advances in manipulation arms. One notable development is the integration of a 7-degree robotic arm into mobile platforms, which has greatly enhanced their ability to autonomously navigate while simultaneously executing complex manipulation tasks. As such, the key success of these systems heavily relies on continuous path planning and precise control of arm movements. In this paper, we evaluate a whole-body control framework that tackles the dynamic instabilities associated with the floating base of mobile platforms in a simulation closely modeling real-world configurations and parameters. Moreover, we employ reinforcement learning to enhance the controller’s performance. We provide results from a detailed ablation study that shows the overall performance of various RL algorithms when optimized for task-specific behaviors over time. Our experimental results demonstrate the feasibility of achieving real-time control of the mobile robotic platform through this hybrid control framework.

Paper Citation

in Harvard Style

Li Q., Ma Z., Li C., Liu Y., Recker T., Brauchle D., Seyler J., Zhao M. and Eivazi S. (2025). MIRSim-RL: A Simulated Mobile Industry Robot Platform and Benchmarks for Reinforcement Learning. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 56-67. DOI: 10.5220/0013159400003890

in Bibtex Style

@conference{icaart25,
author={Qingkai Li and Zijian Ma and Chenxing Li and Yinlong Liu and Tobias Recker and Daniel Brauchle and Jan Seyler and Mingguo Zhao and Shahram Eivazi},
title={MIRSim-RL: A Simulated Mobile Industry Robot Platform and Benchmarks for Reinforcement Learning},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART},
year={2025},
pages={56-67},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013159400003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART
TI - MIRSim-RL: A Simulated Mobile Industry Robot Platform and Benchmarks for Reinforcement Learning
SN - 978-989-758-737-5
AU - Li Q.
AU - Ma Z.
AU - Li C.
AU - Liu Y.
AU - Recker T.
AU - Brauchle D.
AU - Seyler J.
AU - Zhao M.
AU - Eivazi S.
PY - 2025
SP - 56
EP - 67
DO - 10.5220/0013159400003890
PB - SciTePress