Online state vector reduction during model predictive control with gradient-based trajectory optimisation

TL;DR

This paper introduces an online state vector reduction method for model predictive control that dynamically simplifies high-dimensional systems during trajectory optimisation, leading to faster planning and improved performance.

Contribution

It proposes a novel online state reduction technique based on gradient information to improve trajectory optimisation efficiency in high-dimensional MPC tasks.

Findings

Reduced planning times in high-dimensional systems

Improved control performance with online state reduction

Effective trajectory optimisation in cluttered and deformable environments

Abstract

Non-prehensile manipulation in high-dimensional systems is challenging for a variety of reasons. One of the main reasons is the computationally long planning times that come with a large state space. Trajectory optimisation algorithms have proved their utility in a wide variety of tasks, but, like most methods struggle scaling to the high dimensional systems ubiquitous to non-prehensile manipulation in clutter as well as deformable object manipulation. We reason that, during manipulation, different degrees of freedom will become more or less important to the task over time as the system evolves. We leverage this idea to reduce the number of degrees of freedom considered in a trajectory optimisation problem, to reduce planning times. This idea is particularly relevant in the context of model predictive control (MPC) where the cost landscape of the optimisation problem is constantly evolving. We provide simulation results under asynchronous MPC and show our methods are capable of achieving better overall performance due to the decreased policy lag whilst still being able to optimise trajectories effectively.