Skip to Main content Skip to Navigation
New interface
Journal articles

An Open-Source Software Framework for Reinforcement Learning-based Control of Tracked Robots in Simulated Indoor Environments

A Mitriakov 1, 2 Panagiotis Papadakis 1, 2 Serge Garlatti 2 
1 Lab-STICC_RAMBO - Equipe Robot interaction, Ambient system, Machine learning, Behaviour, Optimization
Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance : UMR6285
Abstract : A simulation framework based on the open-source robotic software Gazebo and the Robot Operating System (ROS) is presented for articulated tracked robots, designed for reinforcement learning-based (RL) control skill acquisition. In particular, it is destined to serve as a research tool in the development and evaluation of methods in the domain of mobility learning for articulated tracked robots, in 3D indoor environments. Its architecture allows to interchange between different RL libraries and algorithm implementations, while learning can be customized to endow specific properties within a control skill. To demonstrate its utility, we focus on the most demanding case of staircase ascent and descent using depth image data, while respecting safety via reward function shaping and incremental, domain randomization-based, end-to-end learning.
Complete list of metadata

https://hal-imt-atlantique.archives-ouvertes.fr/hal-03671418
Contributor : Panagiotis Papadakis Connect in order to contact the contributor
Submitted on : Wednesday, May 18, 2022 - 12:58:19 PM
Last modification on : Thursday, August 18, 2022 - 3:33:51 PM
Long-term archiving on: : Monday, October 3, 2022 - 2:29:13 PM

File

 Restricted access
To satisfy the distribution rights of the publisher, the document is embargoed until : 2023-05-18

Please log in to resquest access to the document

Identifiers

Citation

A Mitriakov, Panagiotis Papadakis, Serge Garlatti. An Open-Source Software Framework for Reinforcement Learning-based Control of Tracked Robots in Simulated Indoor Environments. Advanced Robotics, 2022, Special Issue on Software Framework for Robot System Integration, 36 (11), ⟨10.1080/01691864.2022.2076570⟩. ⟨hal-03671418⟩

Share

Metrics

Record views

26