Interleaving Scheduling and Motion Planning with Incremental Learning of Symbolic Space-Time Motion Abstractions

2026-03-11

AI Summary

This work addresses the challenge of coordinating multi-object task scheduling and motion planning in shared workspaces, where both temporal-spatial and resource constraints must be jointly satisfied to ensure safe and efficient execution. The paper proposes an incremental closed-loop framework that, for the first time, integrates off-the-shelf schedulers with sampling-based motion planners through a symbolic spatiotemporal abstraction. In this framework, the scheduler generates candidate plans, which are then verified by the motion planner for continuous-motion feasibility; the planner returns symbolic conflict information—such as spatial interference or required temporal adjustments—to guide the scheduler’s iterative refinement. Evaluated on logistics and job-shop benchmarks, the approach significantly improves the feasibility and efficiency of multi-agent cooperative planning, achieving effective synergy between discrete task scheduling and continuous motion execution.

Technology Category

• Planning, Routing, and Scheduling: Mixed Discrete/Continuous Planning
• Multiagent Systems: Multiagent Planning
• Intelligent Robots: Motion and Path Planning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Task and Motion Planning combines high-level task sequencing (what to do) with low-level motion planning (how to do it) to generate feasible, collision-free execution plans. However, in many real-world domains, such as automated warehouses, tasks are predefined, shifting the challenge to if, when, and how to execute them safely and efficiently under resource, time and motion constraints. In this paper, we formalize this as the Scheduling and Motion Planning problem for multi-object navigation in shared workspaces. We propose a novel solution framework that interleaves off-the-shelf schedulers and motion planners in an incremental learning loop. The scheduler generates candidate plans, while the motion planner checks feasibility and returns symbolic feedback, i.e., spatial conflicts and timing adjustments, to guide the scheduler towards motion-feasible solutions. We validate our proposal on logistics and job-shop scheduling benchmarks augmented with motion tasks, using state-of-the-art schedulers and sampling-based motion planners. Our results show the effectiveness of our framework in generating valid plans under complex temporal and spatial constraints, where synchronized motion is critical.

Problem

• Scheduling and Motion Planning
• multi-object navigation
• shared workspaces
• temporal and spatial constraints
• Task and Motion Planning

Innovation

• Interleaved Scheduling and Motion Planning
• Incremental Learning
• Symbolic Space-Time Abstractions
• Task and Motion Planning
• Multi-object Navigation