ScheduleStream: Temporal Planning with Samplers for GPU-Accelerated Multi-Arm Task and Motion Planning & Scheduling

TL;DR

ScheduleStream is a novel framework that enables efficient parallel task scheduling for multi-arm robots by leveraging GPU-accelerated sampling, extending traditional TAMP algorithms to produce schedules with concurrent arm motions.

Contribution

It introduces ScheduleStream, a general-purpose, domain-independent framework for planning and scheduling with sampling operations, capable of producing parallel arm schedules in multi-arm robot tasks.

Findings

ScheduleStream produces more efficient solutions than ablated methods.

GPU acceleration significantly speeds up planning.

Successfully demonstrated on real-world bimanual robot tasks.

Abstract

Bimanual and humanoid robots are appealing because of their human-like ability to leverage multiple arms to efficiently complete tasks. However, controlling multiple arms at once is computationally challenging due to the growth in the hybrid discrete-continuous action space. Task and Motion Planning (TAMP) algorithms can efficiently plan in hybrid spaces but generally produce plans, where only one arm is moving at a time, rather than schedules that allow for parallel arm motion. In order to extend TAMP to produce schedules, we present ScheduleStream, the first general-purpose framework for planning & scheduling with sampling operations. ScheduleStream models temporal dynamics using hybrid durative actions, which can be started asynchronously and persist for a duration that's a function of their parameters. We propose domain-independent algorithms that solve ScheduleStream problems without any application-specific mechanisms. We apply ScheduleStream to Task and Motion Planning & Scheduling (TAMPAS), where we use GPU acceleration within samplers to expedite planning. We compare ScheduleStream algorithms to several ablations in simulation and find that they produce more efficient solutions. We demonstrate ScheduleStream on several real-world bimanual robot tasks at https://schedulestream.github.io.