Model Predictive Impedance Control with Gaussian Processes for Human and Environment Interaction

TL;DR

This paper introduces a model predictive control framework that plans robot trajectory and impedance online, incorporating uncertainties from contact, human goals, and disturbances, using Gaussian Processes for efficient learning and ensuring safety in human-robot interaction.

Contribution

It presents a novel MPC approach that jointly considers multiple uncertainties in real-time, integrating Gaussian Process-based learning for adaptable and safe human-robot collaboration.

Findings

Validated in co-manipulation tasks with multiple goals

Demonstrated effective uncertainty handling in collaborative tasks

Achieved real-time planning with safety constraints

Abstract

Robotic tasks which involve uncertainty--due to variation in goal, environment configuration, or confidence in task model--may require human input to instruct or adapt the robot. In tasks with physical contact, several existing methods for adapting robot trajectory or impedance according to individual uncertainties have been proposed, e.g., realizing intention detection or uncertainty-aware learning from demonstration. However, isolated methods cannot address the wide range of uncertainties jointly present in many tasks. To improve generality, this paper proposes a model predictive control (MPC) framework which plans both trajectory and impedance online, can consider discrete and continuous uncertainties, includes safety constraints, and can be efficiently applied to a new task. This framework can consider uncertainty from: contact constraint variation, uncertainty in human goals, or task disturbances. An uncertainty-aware task model is learned from a few ($\leq3$) demonstrations using Gaussian Processes. This task model is used in a nonlinear MPC problem to optimize robot trajectory and impedance according to belief in discrete human goals, human kinematics, safety constraints, contact stability, and frequency-domain disturbance rejection. This MPC formulation is introduced, analyzed with respect to convexity, and validated in co-manipulation with multiple goals, a collaborative polishing task, and a collaborative assembly task.