# Learning Variable Impedance Control for Contact Sensitive Tasks

## TL;DR

This paper explores how learning variable impedance control policies enhances robustness in contact-sensitive robotic tasks, outperforming traditional torque and position control under contact uncertainties, and demonstrates transferability to real systems.

## Contribution

It introduces a novel approach of learning impedance and position as policy outputs, improving robustness and interpretability in contact-rich tasks.

## Key findings

- Variable impedance policies outperform torque and position control under contact uncertainties.
- Regularization improves interpretability and transferability of learned policies.
- Successful real-system deployment demonstrates practical applicability.

## Abstract

Reinforcement learning algorithms have shown great success in solving different problems ranging from playing video games to robotics. However, they struggle to solve delicate robotic problems, especially those involving contact interactions. Though in principle a policy directly outputting joint torques should be able to learn to perform these tasks, in practice we see that it has difficulty to robustly solve the problem without any given structure in the action space. In this paper, we investigate how the choice of action space can give robust performance in presence of contact uncertainties. We propose learning a policy giving as output impedance and desired position in joint space and compare the performance of that approach to torque and position control under different contact uncertainties. Furthermore, we propose an additional reward term designed to regularize these variable impedance control policies, giving them interpretability and facilitating their transfer to real systems. We present extensive experiments in simulation of both floating and fixed-base systems in tasks involving contact uncertainties, as well as results for running the learned policies on a real system.