Learning Ground Traversability from Simulations

TL;DR

This paper introduces a CNN-based method to predict traversable terrain patches for ground robots using simulated heightmaps, enabling effective path planning in unstructured environments.

Contribution

It presents a novel simulation-trained CNN classifier for terrain traversability that generalizes to real-world heightmaps for diverse robot types.

Findings

High accuracy in simulation-based terrain classification

Successful transfer to real-world datasets

Effective path planning demonstrated in real environments

Abstract

Mobile ground robots operating on unstructured terrain must predict which areas of the environment they are able to pass in order to plan feasible paths. We address traversability estimation as a heightmap classification problem: we build a convolutional neural network that, given an image representing the heightmap of a terrain patch, predicts whether the robot will be able to traverse such patch from left to right. The classifier is trained for a specific robot model (wheeled, tracked, legged, snake-like) using simulation data on procedurally generated training terrains; the trained classifier can be applied to unseen large heightmaps to yield oriented traversability maps, and then plan traversable paths. We extensively evaluate the approach in simulation on six real-world elevation datasets, and run a real-robot validation in one indoor and one outdoor environment.