Hierarchical Control Strategy for Moving A Robot Manipulator Between Small Containers

TL;DR

This paper explores a hierarchical control approach combining model predictive control with a high-level policy to improve robotic manipulation in uncertain, occluded environments, addressing MPC's limitations.

Contribution

The paper introduces a hierarchical control strategy that enhances MPC with a high-level policy for better object manipulation in complex environments.

Findings

MPC is robust to environmental uncertainties.

MPC alone struggles with heavily occluded tasks.

Hierarchical control improves manipulation success.

Abstract

In this paper, we study the implementation of a model predictive controller (MPC) for the task of object manipulation in a highly uncertain environment (e.g., picking objects from a semi-flexible array of densely packed bins). As a real-time perception-driven feedback controller, MPC is robust to the uncertainties in this environment. However, our experiment shows MPC cannot control a robot to complete a sequence of motions in a heavily occluded environment due to its myopic nature. It will benefit from adding a high-level policy that adaptively adjusts the optimization problem for MPC.