Deep Model Predictive Variable Impedance Control

TL;DR

This paper introduces a deep learning-based model predictive control method for variable impedance in robotic manipulation, enabling adaptive compliance without retraining, demonstrated on a Franka Panda robot.

Contribution

It presents a novel deep model predictive variable impedance control framework that learns a Cartesian impedance model and adapts impedance parameters in real-time for different tasks.

Findings

Outperforms model-free and model-based reinforcement approaches in transferability and performance.

Effective in both simulation and real-world experiments with a Franka Panda robot.

Achieves desired compliance behavior without retraining or fine-tuning.

Abstract

The capability to adapt compliance by varying muscle stiffness is crucial for dexterous manipulation skills in humans. Incorporating compliance in robot motor control is crucial to performing real-world force interaction tasks with human-level dexterity. This work presents a Deep Model Predictive Variable Impedance Controller for compliant robotic manipulation which combines Variable Impedance Control with Model Predictive Control (MPC). A generalized Cartesian impedance model of a robot manipulator is learned using an exploration strategy maximizing the information gain. This model is used within an MPC framework to adapt the impedance parameters of a low-level variable impedance controller to achieve the desired compliance behavior for different manipulation tasks without any retraining or finetuning. The deep Model Predictive Variable Impedance Control approach is evaluated using a Franka Emika Panda robotic manipulator operating on different manipulation tasks in simulations and real experiments. The proposed approach was compared with model-free and model-based reinforcement approaches in variable impedance control for transferability between tasks and performance.