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

2025-11-06

AI Summary

Multi-arm task and motion planning (TAMP) struggles to generate genuinely parallel execution schedules due to reliance on sequential, single-arm paradigms. Method: This paper introduces ScheduleStream—the first general-purpose TAMP planning and scheduling framework that integrates sampling-based mechanisms into the scheduling process. It supports asynchronous activation and variable-duration hybrid continuous actions, enabling true concurrency across multiple arms. Leveraging GPU-accelerated sampling and domain-agnostic algorithm design, ScheduleStream achieves efficient, scalable multi-arm coordinated planning. Contribution/Results: Evaluated within the Task and Motion Planning & Scheduling (TAMPAS) framework, ScheduleStream significantly outperforms multiple ablation baselines in simulation and demonstrates robust effectiveness and practicality across diverse real-world dual-arm robotic tasks.

Technology Category

• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Multiagent Systems: Multiagent Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

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.

Problem

• Extending TAMP to enable parallel arm motion scheduling for multi-arm robots
• Addressing computational challenges in hybrid discrete-continuous action spaces
• Developing GPU-accelerated planning for efficient bimanual robot task execution

Innovation

• GPU-accelerated sampling for parallel arm motion planning
• Hybrid durative actions modeling asynchronous temporal dynamics
• Domain-independent algorithms solving TAMPAS without application-specific mechanisms