Arena-Rosnav: Towards Deployment of Deep-Reinforcement-Learning-Based Obstacle Avoidance into Conventional Autonomous Navigation Systems

TL;DR

This paper presents Arena-Rosnav, a system integrating deep reinforcement learning local planners into traditional navigation stacks to improve long-range autonomous navigation in industrial mobile robots.

Contribution

It introduces a framework for training and testing deep RL-based local planners within conventional navigation systems for better long-range performance.

Findings

Outperforms traditional planners in safety, efficiency, and robustness.

Demonstrates effective integration of deep RL into industrial navigation.

Provides a comprehensive training and testing framework for deep RL navigation algorithms.

Abstract

Recently, mobile robots have become important tools in various industries, especially in logistics. Deep reinforcement learning emerged as an alternative planning method to replace overly conservative approaches and promises more efficient and flexible navigation. However, deep reinforcement learning approaches are not suitable for long-range navigation due to their proneness to local minima and lack of long term memory, which hinders its widespread integration into industrial applications of mobile robotics. In this paper, we propose a navigation system incorporating deep-reinforcement-learning-based local planners into conventional navigation stacks for long-range navigation. Therefore, a framework for training and testing the deep reinforcement learning algorithms along with classic approaches is presented. We evaluated our deep-reinforcement-learning-enhanced navigation system against various conventional planners and found that our system outperforms them in terms of safety, efficiency and robustness.