Learning Smooth State-Dependent Traversability from Dense Point Clouds

TL;DR

SPARTA is a novel method that estimates terrain traversability conditioned on approach angle from dense point clouds, using a smooth, reusable analytical function based on Fourier basis functions, improving off-road navigation.

Contribution

The paper introduces SPARTA, a geometric, smooth function-based approach to predict approach angle-dependent traversability from point clouds, reducing computational overhead and enhancing generalization.

Findings

Achieved 91% success rate in simulation crossing a boulder field.

Outperformed baseline with 73% success rate.

Demonstrated real-world applicability on hardware.

Abstract

A key open challenge in off-road autonomy is that the traversability of terrain often depends on the vehicle's state. In particular, some obstacles are only traversable from some orientations. However, learning this interaction by encoding the angle of approach as a model input demands a large and diverse training dataset and is computationally inefficient during planning due to repeated model inference. To address these challenges, we present SPARTA, a method for estimating approach angle conditioned traversability from point clouds. Specifically, we impose geometric structure into our network by outputting a smooth analytical function over the 1-Sphere that predicts risk distribution for any angle of approach with minimal overhead and can be reused for subsequent queries. The function is composed of Fourier basis functions, which has important advantages for generalization due to their periodic nature and smoothness. We demonstrate SPARTA both in a high-fidelity simulation platform, where our model achieves a 91\% success rate crossing a 40m boulder field (compared to 73\% for the baseline), and on hardware, illustrating the generalization ability of the model to real-world settings. Our code will be available at https://github.com/neu-autonomy/SPARTA.