Path Generation for Wheeled Robots Autonomous Navigation on Vegetated Terrain

TL;DR

This paper introduces the PE-RRT* algorithm for wheeled robot navigation in vegetated terrains, combining perception and terrain estimation to generate safe, real-time paths despite occlusions and uneven ground.

Contribution

The paper presents a novel support plane estimation method integrated with a sampling algorithm for improved navigation in vegetation environments.

Findings

High safety and robustness demonstrated in outdoor experiments

Effective terrain estimation using MV-GPR at sampling nodes

Real-time feasible path generation in complex outdoor terrains

Abstract

Wheeled robot navigation has been widely used in urban environments, but little research has been conducted on its navigation in wild vegetation. External sensors (LiDAR, camera etc.) are often used to construct point cloud map of the surrounding environment, however, the supporting rigid ground used for travelling cannot be detected due to the occlusion of vegetation. This often causes unsafe or not smooth path during planning process. To address the drawback, we propose the PE-RRT* algorithm, which effectively combines a novel support plane estimation method and sampling algorithm to generate real-time feasible and safe path in vegetation environments. In order to accurately estimate the support plane, we combine external perception and proprioception, and use Multivariate Gaussian Processe Regression (MV-GPR) to estimate the terrain at the sampling nodes. We build a physical experimental platform and conduct experiments in different outdoor environments. Experimental results show that our method has high safety, robustness and generalization.