Mismatch-Aware Adaptive Constraint Tightening (MACT) sets state-dependent safety margins using a derived T-squared scaling coefficient from model mismatch analysis, achieving full safety with 84% less wasted margin than fixed baselines in simulations.
Realization of a real-time optimal control strategy to stabilize a falling humanoid robot with hand contact
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.RO 2years
2026 2representative citing papers
A single causal-transformer policy with latent recovery modes and contact-affordance prediction enables humanoid robots to recover from 100-300 N pushes with 100% success in simulation, generalizing zero-shot across wall distances, mass, friction, and latency changes.
citing papers explorer
-
Mismatch-Aware Adaptive Constraint Tightening for Bicycle-Model Trajectory Optimization
Mismatch-Aware Adaptive Constraint Tightening (MACT) sets state-dependent safety margins using a derived T-squared scaling coefficient from model mismatch analysis, achieving full safety with 84% less wasted margin than fixed baselines in simulations.
-
RecoverFormer: End-to-End Contact-Aware Recovery for Humanoid Robots
A single causal-transformer policy with latent recovery modes and contact-affordance prediction enables humanoid robots to recover from 100-300 N pushes with 100% success in simulation, generalizing zero-shot across wall distances, mass, friction, and latency changes.