MotionDisco: Motion Discovery for Extreme Humanoid Loco-Manipulation
Introduces an automated framework for discovering long-horizon, contact-rich humanoid loco-manipulation skills without human motion capture, teleoperation, or retargeting.
Evidence notes
- Combines LLM-guided evolutionary search over contact plans, kinodynamic optimization, pruning, and reinforcement-learning tracking policies.
- Project page and arXiv paper report transfer of discovered trajectories to real humanoid hardware across cluttered scenes and multi-object transport tasks.
Company context
Research university with robotics groups publishing open-source dexterous hand hardware and robot-learning systems.