Task-Conditioned Uncertainty Costmaps for Legged Locomotion
For legged locomotion on unstructured terrain, this provides a way to detect and handle out-of-distribution scenarios, improving planning reliability.
This work introduces a method for legged robots to model epistemic uncertainty in foothold predictions, conditioned on terrain and commanded motion, enabling detection of out-of-distribution terrains. Using uncertainty-aware costmaps for path planning, they achieve up to a 37% reduction in simulation feasibility error and more reliable planning compared to geometry-only baselines.
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.