EPFL's TERRA pipeline teaches muscle-actuated agents to walk 9.4 hours of diverse terrain
amathislab · hf · 2026-10-01
EPFL researchers present TERRA, an end-to-end pipeline for terrain-aware retargeting and control of musculoskeletal locomotion.
- Problem: muscle-actuated RL agents can reproduce complex motions but remain confined to flat ground due to lack of aligned terrain geometry in motion datasets.
- Method: from kinematic trajectories alone, TERRA combines terrain priors, contact estimation, and negative free-space evidence to recover support geometry, respecting anatomical, tendon-continuity, and contact constraints during retargeting.
- Results: using motion-terrain pairs from five datasets, they train a single muscle-actuated policy on 9.4 hours of diverse locomotion, improving terrain accuracy, sharply reducing violations, and achieving the highest completion rates.
Project page: cnai.epfl.ch/terra
More from Embodied
- U-BOT robot doubles its wheels after casters got stuck in driveway test — _Stocko_ · 2026-10-01
- Robot demo shows tactile sensing across fingers and entire palm — CyberRobooo · 2026-10-01
- LATENT wins IROS 2026 award: humanoid robots rally at human level from imperfect motion data — chris_j_paxton · 2026-10-01
- EngineAI T800 hailed as China's most dynamic robot, but fell more than any other at IROS — chris_j_paxton · 2026-10-01
- Custom Retro Hardware Is a Whole New World with AI for Hardware Design — pvncher · 2026-10-01
- Researcher dismantles Figure's IP excuse for destroying F.02: "awful marketing" — MarwaEldiwiny · 2026-10-01