Event
NeurIPS 2026 position paper proposes body-control co-design initiative for humanoid robots
1 reports · 1 sources
A NeurIPS 2026 position paper proposes a "physical recursive self-improvement" (RSI) route: humanoid robots use the experience of their current body and policy to recursively improve both morphology and behavior simultaneously, that is, treating body-control co-design as the path to achieve this. The methods discussed in the paper include co-design based on strategic exploration, Sim2Real transfer, and meta-policy learning, and it argues for its necessity from methodological, application, and community perspectives, while listing open research questions ranging from short-term innovations to long-term goals. The above are the claims and research agenda proposed by the paper; the report does not provide verified results.
Report timeline
- Toward Physical Recursive Self-Improvement: A Call for Body-Control Co-Design for Humanoid Robots
A NeurIPS 2026 Position Paper proposes body-control co-design to achieve physical Recursive Self-Improvement (RSI) in humanoid robots: using experience from the current body and policy to recursively improve both morphology and behavior at the same time. The paper discusses co-design methods grounded in strategic exploration, Sim2Real transfer, and meta-policy learning, argues for their necessity from methodological, application, and community perspectives, and lists open research questions ranging from short-term innovations to long-term goals.
arXiv cs.RO ·