Paper Overview
- Field: Machine Learning / Robotics
- Authors: Nicolas Kosanovic, Jordan Dowdy, Jean Chagas Vaz
- Published: 2026-07-24
- arXiv: 2507.18393
- Framework experiments on ROBOTIS OP3 hardware demonstrated walking speeds of up to 0.45 m/s, independent of arm motion.
- Tele-loco-manipulation was demonstrated through cube-relocation experiments with expert human operators.
- On average, the teleoperation system moved two different 40 g cubes within 10 minutes, covering a total walking distance of about 5 meters.
English Translation of Abstract (Summary)
Full-sized humanoid robot capabilities have grown exponentially in recent years, aiming towards general-purpose deployment in human environments. A popular control method used by manufacturers utilizes Virtual Reality for upper-body teleoperation and Reinforcement Learning for lower-body balance and locomotion control. As a result, a single remote operator can see, manipulate, and navigate about a real, distant physical environment. This powerful control stack is often relegated to expensive full-sized robots, many of which are inaccessible to the research community. Miniature humanoids are more prevalent, but employ less biomimicry in their design (e.g. fewer sensors, Degrees of Freedom, etc) and lack similar developments. This paper describes a compliant full-body telepresence control stack developed from scratch for miniature humanoid robots.
Key Results
Takeaway
The developed system demonstrates the potential of teleoperated loco-manipulation on miniature humanoid robots, extending VR teleoperation + RL locomotion stacks to affordable, research-accessible platforms.
> Note: The original abstract excerpt in the source post was truncated; content above reflects the full translated summary provided in the post.