This paper introduces novel deep reinforcement learning (Deep-RL) techniques using parallel distributional actor-critic networks for navigating terrestrial mobile robots. Our approaches use laser range findings, relative distance, and angle to the target to guide the robot. We trained agents in the Gazebo simulator and deployed them in real scenarios. Results show that parallel distributional Deep-RL algorithms enhance decision-making and outperform non-distributional and behavior-based approaches in navigation and spatial generalization.
@article{arxiv.2408.05744,
title = {Parallel Distributional Deep Reinforcement Learning for Mapless Navigation of Terrestrial Mobile Robots},
author = {Victor Augusto Kich and Alisson Henrique Kolling and Junior Costa de Jesus and Gabriel V. Heisler and Hiago Jacobs and Jair Augusto Bottega and André L. da S. Kelbouscas and Akihisa Ohya and Ricardo Bedin Grando and Paulo Lilles Jorge Drews-Jr and Daniel Fernando Tello Gamarra},
journal= {arXiv preprint arXiv:2408.05744},
year = {2024}
}
Comments
Paper accepted at the 24th International Conference on Control, Automation and Systems (ICCAS)