Differentiable Material Point Method for the Control of Deformable Objects

TL;DR

This paper introduces a differentiable Material Point Method (MPM) simulator that enables efficient control of deformable objects, achieving faster and more energy-efficient manipulation compared to baseline methods.

Contribution

The work develops a differentiable MPM simulator specifically for control tasks involving deformable objects, improving optimization speed and energy efficiency.

Findings

Simulator reduces kinetic energy of the rope by 20%.

Achieves 2x faster optimization than baseline MPPI.

Uses only 3% of the computation time of baseline methods.

Abstract

Controlling the deformation of flexible objects is challenging due to their non-linear dynamics and high-dimensional configuration space. This work presents a differentiable Material Point Method (MPM) simulator targeted at control applications. We exploit the differentiability of the simulator to optimize a control trajectory in an active damping problem for a hyperelastic rope. The simulator effectively minimizes the kinetic energy of the rope around 2$\times$ faster than a baseline MPPI method and to a 20% lower energy level, while using about 3% of the computation time.