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

TL;DR

This paper introduces an integrated framework combining scheduling and motion planning with incremental learning to efficiently generate feasible plans in complex shared workspace scenarios.

Contribution

It presents a novel interleaving approach that uses symbolic feedback to guide scheduling and motion planning in a unified, incremental learning loop.

Findings

Effective in complex logistics and job-shop scenarios

Generates valid plans under tight temporal and spatial constraints

Outperforms traditional sequential planning methods

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.