Task-Conditioned Uncertainty Costmaps for Legged Locomotion

TL;DR

This paper introduces a method for legged robots to predict footholds with uncertainty modeling, enabling better detection of unfamiliar terrains and more reliable path planning in complex environments.

Contribution

It presents a novel approach to model epistemic uncertainty in foothold predictions conditioned on terrain data and commands, improving out-of-distribution detection and planning robustness.

Findings

Up to 37% reduction in feasibility error on OOD terrains.

Enhanced detection of out-of-distribution regions in simulation and real-world.

More reliable path planning compared to geometry-only baselines.

Abstract

Legged robots maintain dynamic feasibility through multicontact interactions with terrain. Learned foothold prediction can provide feasibility-aware costs for motion planning and path selection, but accurately predicting future contacts from perceptual inputs such as height scans remains challenging on highly unstructured terrain, even with a repetitive gait cycle. In this work, we show that modeling epistemic uncertainty in predicted footholds, conditioned on terrain observations and commanded motion, distinguishes in-distribution from out-of-distribution operating regimes in simulation and real-world settings. This allows a single learned model, trained on limited data distributions, to express uncertainty caused by missing training coverage. We use this learned uncertainty to detect OOD regions and incorporate them into a unified costmap-generation framework for uncertainty-aware path planning. Using these uncertainty-aware costmaps, we evaluate feasibility error across in-distribution and OOD terrains in simulation and real-world settings. The results show improved OOD detection, up to a 37% reduction in simulation feasibility error, and more reliable planning behavior than geometry-only baselines.