Summary
TERRA is an end-to-end system for terrain-aware musculoskeletal motion retargeting and control. It reconstructs support geometry from motion and contact evidence, then trains a muscle-actuated controller on aligned motion-terrain pairs.
TERRA is an end-to-end system for terrain-aware musculoskeletal motion retargeting and control. It reconstructs support geometry from motion and contact evidence, then trains a muscle-actuated controller on aligned motion-terrain pairs.
Locomotion researchers can model movement across varied terrain while checking anatomical, tendon, and contact constraints. Core capabilities include Terrain reconstruction from trajectories, Contact-aware support geometry, Anatomical retargeting constraints, and Tendon-continuity constraints.
Public code or model weights are linked from the project, with setup instructions for running or adapting the system. Additional characteristics include Motion-terrain pairing, Muscle-actuated control, A shared locomotion policy, and Multi-dataset training.
Get more likes & reach the top of search results by adding this button on your site!


Get top updates in AI to your inbox every weekend. It's free!