Learning When to Jump for Off-road Navigation

TL;DR

This paper introduces a motion-aware terrain representation that models terrain traversability as a velocity-dependent Gaussian function, enabling real-time, agile off-road navigation with improved safety and efficiency.

Contribution

It proposes the Motion-aware Traversability (MAT) model that explicitly accounts for complex motion dynamics in terrain cost prediction, improving off-road path planning.

Findings

MAT reduces path detours by 75% in challenging terrains.

The system achieves real-time terrain cost prediction during navigation.

MAT enhances safety and agility in off-road environments.

Abstract

Low speed does not always guarantee safety in off-road driving. For instance, crossing a ditch may be risky at a low speed due to the risk of getting stuck, yet safe at a higher speed with a controlled, accelerated jump. Achieving such behavior requires path planning that explicitly models complex motion dynamics, whereas existing methods often neglect this aspect and plan solely based on positions or a fixed velocity. To address this gap, we introduce Motion-aware Traversability (MAT) representation to explicitly model terrain cost conditioned on actual robot motion. Instead of assigning a single scalar score for traversability, MAT models each terrain region as a Gaussian function of velocity. During online planning, we decompose the terrain cost computation into two stages: (1) predict terrain-dependent Gaussian parameters from perception in a single forward pass, (2) efficiently update terrain costs for new velocities inferred from current dynamics by evaluating these functions without repeated inference. We develop a system that integrates MAT to enable agile off-road navigation and evaluate it in both simulated and real-world environments with various obstacles. Results show that MAT achieves real-time efficiency and enhances the performance of off-road navigation, reducing path detours by 75% while maintaining safety across challenging terrains.