Experimental investigation of pose informed reinforcement learning for skid-steered visual navigation

TL;DR

This paper introduces a structured learning approach for visual navigation of skid-steered vehicles, addressing modeling challenges and demonstrating improved performance through simulations and hardware tests.

Contribution

It proposes a novel structured formulation for learning visual navigation tailored for skid-steered vehicles, enhancing robustness and accuracy.

Findings

Significantly improved navigation performance in simulations

Successful hardware validation of the proposed method

Ablation studies confirming the effectiveness of the approach

Abstract

Vision-based lane keeping is a topic of significant interest in the robotics and autonomous ground vehicles communities in various on-road and off-road applications. The skid-steered vehicle architecture has served as a useful vehicle platform for human controlled operations. However, systematic modeling, especially of the skid-slip wheel terrain interactions (primarily in off-road settings) has created bottlenecks for automation deployment. End-to-end learning based methods such as imitation learning and deep reinforcement learning, have gained prominence as a viable deployment option to counter the lack of accurate analytical models. However, the systematic formulation and subsequent verification/validation in dynamic operation regimes (particularly for skid-steered vehicles) remains a work in progress. To this end, a novel approach for structured formulation for learning visual navigation is proposed and investigated in this work. Extensive software simulations, hardware evaluations and ablation studies now highlight the significantly improved performance of the proposed approach against contemporary literature.