IPAPRec: A promising tool for learning high-performance mapless navigation skills with deep reinforcement learning

TL;DR

This paper introduces IPAPRec, a novel input pre-processing method for LiDAR data in deep reinforcement learning, significantly enhancing mapless navigation generalization and reducing training time in simulation and real-world tests.

Contribution

The paper presents a new adaptive LiDAR data pre-processing approach, IPAPRec/IPAPRecN, that improves DRL navigation agents' performance and training efficiency.

Findings

Enhanced generalization in navigation tasks

Reduced training time for DRL agents

Validated effectiveness in simulation and real-world experiments

Abstract

This paper studies how to improve the generalization performance and learning speed of the navigation agents trained with deep reinforcement learning (DRL). Although DRL exhibits huge potential in robot mapless navigation, DRL agents performing well in training scenarios are often found to perform poorly in unfamiliar scenarios. In this work, we propose that the representation of LiDAR readings is a key factor behind the degradation of agents' performance and present a powerful input pre-processing (IP) approach to address this issue. As this approach uses adaptively parametric reciprocal functions to pre-process LiDAR readings, we refer to this approach as IPAPRec and its normalized version as IPAPRecN. IPAPRec/IPAPRecN can highlight important short-distance values and compress the range of less-important long-distance values in laser scans, which well address the issues induced by conventional representations of laser scans. Their high performance was validated by extensive simulation and real-world experiments. The results show that our methods can substantially improve navigation agents' generalization performance and greatly reduce the training time compared to conventional methods.