LIMBO: Learning and Internalizing Model-Free Barrier Objectives for Agile and Safe Whole-Body Control

2026-09-18

AI Summary

研究提出LIMBO框架，通过学习状态-动作控制障碍函数并将其安全结构提炼到任务策略中，以解决高维度非线性动力学下的安全全身控制问题。

Abstract

Safe whole-body control requires coordinating collision avoidance and balance under high-dimensional, nonlinear dynamics--making safety certificates difficult to design and reuse across behaviors. We present LIMBO, a framework for synthesizing a state-action control barrier function and distilling its safety structure into a task policy. LIMBO learns the safety certificate from black-box transitions and a state-based failure specification over residual actions around a frozen base controller, making Q-CBF synthesis tractable in the full control dimension while placing the certificate in the task policy's control space. During synthesis, the learned safety value drives risk-guided sampling near the estimated boundary of recoverability; during task learning, it serves as a teacher that provides action-level safety feedback, yielding a robust task policy and alleviating the need for an online safety filter at deployment. We demonstrate LIMBO on a 29-degree-of-freedom humanoid performing dodgeball avoidance and locomotion beneath low obstacles. Beyond scaling learned Q-CBFs to whole-body control, we show that risk-guided boundary sampling provides a theoretically grounded way to explore the edge of recoverability. Under the same safety specification, ceteris paribus, varying the sampling concentration produces strategies ranging from crouching to a novel backward-leaning limbo maneuver. In both settings, the learned policies transfer to hardware without online safety filtering, showing that learned safety synthesis scales to agile whole-body control.

Problem

• safe whole-body control
• collision avoidance
• balance
• high-dimensional dynamics
• nonlinear dynamics

Innovation

• Q-CBF synthesis
• risk-guided sampling
• whole-body control
• safety certificate