STAMP: Differentiable Task and Motion Planning via Stein Variational Gradient Descent

Yewon Lee, Yizhou Huang, Krishna Murthy Jatavallabhula, Andrew Zou Li, Fabian Damken, Eric Heiden, Kevin A. Smith, Derek Nowrouzezahrai, Fabio Ramos, Florian Shkurti

Keywords: Task and Motion Planning, Stein Variational Gradient Descent, Differentiable Physics Simulators, Dynamic Motion Primitives

TL;DR: We present a differentiable TAMP algorithm that efficiently searches for multiple diverse solutions by leveraging parallelized differentiable physics simulators and a gradient-based inference algorithm.

Abstract: Planning for many manipulation tasks, such as using tools or assembling parts, often requires both symbolic and geometric reasoning. Task and Motion Planning (TAMP) algorithms typically solve these problems by conducting a tree search over high-level task sequences while checking for kinematic and dynamic feasibility. This can be inefficient as the width of the tree can grow exponentially with the number of possible actions and objects. In this paper, we propose a novel approach to TAMP that relaxes discrete-and-continuous TAMP problems into inference problems on a continuous domain. Our method, Stein Task and Motion Planning (STAMP) subsequently solves this new problem using a gradient-based variational inference algorithm called Stein Variational Gradient Descent, by obtaining gradients from a parallelized differentiable physics simulator. By introducing relaxations to the discrete variables, leveraging parallelization, and approaching TAMP as an Bayesian inference problem, our method is able to efficiently find multiple diverse plans in a single optimization run. We demonstrate our method on two TAMP problems and benchmark them against existing TAMP baselines.

Submission Number: 21