Whole-Body Mobile Manipulation using Offline Reinforcement Learning on Sub-optimal Controllers
Mobile Manipulation (MoMa) of articulated objects, such as opening doors, drawers, and cupboards, demands simultaneous, whole-body coordination between a robot's base and arms. Classical whole-body controllers (WBCs) can solve such problems via hierarchical optimization, but require extensive hand-tuned optimization and remain brittle.
Evidence notes
- Experiments use TIAGo as the physical evaluation platform.
- The reported results provide an independent evaluation on TIAGo hardware.
Company context
Develops service and humanoid robots for research, industrial, and public-facing environments, with a focus on modular platforms and long-term deployment in real-world settings.