Reactive Planar Manipulation with Convex Hybrid MPC

TL;DR

This paper introduces a real-time convex hybrid MPC approach for planar manipulation that uses machine learning to handle contact mode complexity, enabling effective trajectory tracking.

Contribution

It proposes a novel convex hybrid MPC formulation that separates mode sequence search from control input optimization, leveraging machine learning for real-time performance.

Findings

Achieves good closed-loop performance on trajectory tracking

Handles multiple contact modes efficiently in real-time

Validates approach on a planar manipulation setup

Abstract

This paper presents a reactive controller for planar manipulation tasks that leverages machine learning to achieve real-time performance. The approach is based on a Model Predictive Control (MPC) formulation, where the goal is to find an optimal sequence of robot motions to achieve a desired object motion. Due to the multiple contact modes associated with frictional interactions, the resulting optimization program suffers from combinatorial complexity when tasked with determining the optimal sequence of modes. To overcome this difficulty, we formulate the search for the optimal mode sequences offline, separately from the search for optimal control inputs online. Using tools from machine learning, this leads to a convex hybrid MPC program that can be solved in real-time. We validate our algorithm on a planar manipulation experimental setup where results show that the convex hybrid MPC formulation with learned modes achieves good closed-loop performance on a trajectory tracking problem.