AIToday
Large Language ModelsRoboticsarXiv cs.RO (Robotics)Published: Apr 28, 2026, 13:00 JST

RecoverFormer: End-to-End Recovery Policy for Humanoid Robots Learns to Switch Among Multiple Stabilization Strategies

Send on LINE

3 Key Points

  1. Researchers present RecoverFormer, a fully end-to-end humanoid recovery policy that learns when and how to switch among recovery behaviors—including compensatory stepping, hand-environment contact, and center-of-mass reshaping—while maintaining robust performance under model mismatch.

  2. The architecture combines a causal transformer over a 50-step observation history with a latent recovery mode (enabling smooth transitions among distinct recovery strategies) and a contact affordance head (predicting which environmental surfaces like walls, railings, and table edges are beneficial for stabilization).

  3. When trained only on open floor and tested on Unitree G1 humanoid in MuJoCo, RecoverFormer transfers zero shot to walled environments, achieving 100% recovery success across 100–300 N pushes and across wall distances from 0.25–1.4m. Under zero-shot dynamics mismatch, it reaches 75.5% at plus +25% mass, 89% under 30 ms latency, 91.5% at low friction, and 99% under compound friction, latency and mass perturbation.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, every morning.

arXiv cs.RO (Robotics)Read Original Article
Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleResearchers propose Decision Language Model (DLM) for multi-agent offline decision-making, formulating the task as dialogue-style sequence prediction