Differentiable GPU-Parallelized Task and Motion Planning

TL;DR

This paper introduces a GPU-accelerated bilevel Task and Motion Planning algorithm that efficiently explores and optimizes thousands of candidate solutions simultaneously, enabling rapid planning for complex robotic manipulation tasks.

Contribution

It presents a novel GPU-parallelized TAMP algorithm that significantly improves solution speed and quality for highly constrained, non-convex planning problems in robotics.

Findings

Solves complex TAMP problems in seconds

Outperforms serial TAMP methods

Validated on multiple real-world robots

Abstract

Planning long-horizon robot manipulation requires making discrete decisions about which objects to interact with and continuous decisions about how to interact with them. A robot planner must select grasps, placements, and motions that are feasible and safe. This class of problems falls under Task and Motion Planning (TAMP) and poses significant computational challenges in terms of algorithm runtime and solution quality, particularly when the solution space is highly constrained. To address these challenges, we propose a new bilevel TAMP algorithm that leverages GPU parallelism to efficiently explore thousands of candidate continuous solutions simultaneously. Our approach uses GPU parallelism to sample an initial batch of solution seeds for a plan skeleton and to apply differentiable optimization on this batch to satisfy plan constraints and minimize solution cost with respect to soft objectives. We demonstrate that our algorithm can effectively solve highly constrained problems with non-convex constraints in just seconds, substantially outperforming serial TAMP approaches, and validate our approach on multiple real-world robots. Project website and code: https://cutamp.github.io