G-VOM: A GPU Accelerated Voxel Off-Road Mapping System

TL;DR

This paper introduces G-VOM, a GPU-accelerated 3D voxel mapping system for off-road navigation that enables real-time obstacle detection, slope, and roughness estimation, demonstrated on multiple vehicles with open-source code.

Contribution

The paper presents a novel GPU-based voxel mapping framework that achieves online performance for off-road navigation, including obstacle detection and terrain analysis.

Findings

Real-time mapping at 10 Hz update rate

Successful deployment on three different vehicles

Open-source implementation available

Abstract

We present a local 3D voxel mapping framework for off-road path planning and navigation. Our method provides both hard and soft positive obstacle detection, negative obstacle detection, slope estimation, and roughness estimation. By using a 3D array lookup table data structure and by leveraging the GPU it can provide online performance. We then demonstrate the system working on three vehicles, a Clearpath Robotics Warthog, Moose, and a Polaris Ranger, and compare against a set of pre-recorded waypoints. This was done at 4.5 m/s in autonomous operation and 12 m/s in manual operation with a map update rate of 10 Hz. Finally, an open-source ROS implementation is provided. https://github.com/unmannedlab/G-VOM