Terrain Costmap Generation via Scaled Preference Conditioning

TL;DR

This paper introduces SPACER, a new method for generating terrain costmaps that combines generalization to diverse terrains with rapid adaptation to user preferences, improving off-road robot navigation.

Contribution

SPACER is a novel approach that leverages synthetic training data and preference conditioning to produce adaptable, high-quality terrain costmaps for off-road navigation.

Findings

SPACER outperforms existing methods in costmap accuracy.

SPACER achieves lowest regret in 5 of 7 environments.

SPACER effectively generalizes to new terrains.

Abstract

Successful autonomous robot navigation in off-road domains requires the ability to generate high-quality terrain costmaps that are able to both generalize well over a wide variety of terrains and rapidly adapt relative costs at test time to meet mission-specific needs. Existing approaches for costmap generation allow for either rapid test-time adaptation of relative costs (e.g., semantic segmentation methods) or generalization to new terrain types (e.g., representation learning methods), but not both. In this work, we present scaled preference conditioned all-terrain costmap generation (SPACER), a novel approach for generating terrain costmaps that leverages synthetic data during training in order to generalize well to new terrains, and allows for rapid test-time adaptation of relative costs by conditioning on a user-specified scaled preference context. Using large-scale aerial maps, we provide empirical evidence that SPACER outperforms other approaches at generating costmaps for terrain navigation, with the lowest measured regret across varied preferences in five of seven environments for global path planning.