Learning-Based Predictive Impedance Control Towards Safe Predefined-Time Physical Robotic Interaction

Abstract

Impedance control can be achieved within a model predictive control (MPC) framework for optimization and constraint compliance. However, user-defined or optimization-derived impedance models can be too conservative to achieve a timely convergence, or too aggressive to ensure safety. To address this, an MPC-based impedance control framework with learning-based tuning for predefined-time (PdT) convergence is proposed. On the low level, the framework dynamically selects between a task-oriented and a safety-oriented impedance model based on real-time interaction force modeling and safety assessments, ensuring optimal performance and maintaining safety while interacting with unknown and complex environments. On the high level, the framework achieves PdT convergence via reinforcement learning for meta-parameter tuning, allowing users to specify the desired convergence time upper bound. Lastly, the superiority of the proposed framework is validated on interaction safety and PdT convergence via experiments.