Robot Navigation with Reinforcement Learned Path Generation and Fine-Tuned Motion Control

TL;DR

This paper introduces a reinforcement learning-based path generation method combined with motion fine-tuning for mobile robot navigation, achieving higher success rates and safety without prior environment exploration.

Contribution

The paper presents a novel RL-based path generation approach using a deep Markov model and a motion fine-tuning module, improving navigation effectiveness and safety.

Findings

Higher success rate than DWA-RL and APF approaches

Effective navigation demonstrated in simulation and real-world tests

Enhanced safety through motion fine-tuning

Abstract

In this paper, we propose a novel reinforcement learning (RL) based path generation (RL-PG) approach for mobile robot navigation without a prior exploration of an unknown environment. Multiple predictive path points are dynamically generated by a deep Markov model optimized using RL approach for robot to track. To ensure the safety when tracking the predictive points, the robot's motion is fine-tuned by a motion fine-tuning module. Such an approach, using the deep Markov model with RL algorithm for planning, focuses on the relationship between adjacent path points. We analyze the benefits that our proposed approach are more effective and are with higher success rate than RL-Based approach DWA-RL and a traditional navigation approach APF. We deploy our model on both simulation and physical platforms and demonstrate our model performs robot navigation effectively and safely.