Dynamic Multi-Agent Pickup and Delivery in Robotic Cellular Warehousing Systems

2026-06-03

AI Summary

This study addresses the challenge of real-time task replanning in robotic cellular warehouse systems, where dynamic order evolution—such as the addition of new SKUs during execution—necessitates adaptive multi-agent pickup and delivery coordination. The work presents the first formulation of a dynamic multi-agent pickup and delivery problem that explicitly accounts for intra-order evolution. To tackle this, an event-triggered online replanning algorithm based on a token-passing mechanism is proposed, integrating order decomposition, priority-based scheduling, and a collaborative idle-robot assistance strategy. This approach enables efficient local replanning while preventing inter-agent conflicts. Extensive simulations demonstrate that the proposed method significantly reduces order flow time and outperforms both static and non-collaborative baseline approaches.

Abstract

Robotic Cellular Warehousing Systems (RCWS) give rise to multi-agent pickup and delivery (MAPD) processes in which robots sequentially collect multiple stock-keeping units (SKUs) for each order. Unlike classical MAPD formulations that assume static tasks, real warehouse operations often involve dynamic order evolution, where new SKUs may be appended to an order while it is being executed. Motivated by this practical requirement, this letter formulates the Dynamic Multi-Agent Pickup and Delivery problem considering internal order evolution for the first time. Building on the token passing paradigm, we propose two event-triggered online replanning algorithms. The first, Dynamic Token Passing, performs localized replanning upon order updates through add-order decomposition and priority-based token scheduling while preserving collision-free execution. The second, Cooperative Token Passing, further enables idle robots to opportunistically assist newly added pickups, improving system-level efficiency. Simulation results in RCWS environments demonstrate that the proposed methods significantly reduce order flowtime compared with static and non-cooperative baselines.

Problem

• Dynamic Multi-Agent Pickup and Delivery
• Robotic Cellular Warehousing Systems
• order evolution
• dynamic tasks
• multi-agent systems

Innovation

• Dynamic MAPD
• Token Passing
• Online Replanning
• Order Evolution
• Robotic Cellular Warehousing