Lifelong Scalable Multi-Agent Realistic Testbed and A Comprehensive Study on Design Choices in Lifelong AGV Fleet Management Systems

2026-02-17

AI Summary

Existing research on Multi-Agent Path Finding (MAPF) and Lifelong MAPF (LMAPF) often relies on idealized assumptions that fail to capture critical challenges in real-world Automated Guided Vehicle (AGV) systems, such as concurrent planning and execution, communication delays, execution uncertainty, and fault recovery. To bridge this gap, this work proposes LSMART—an open-source, extensible simulation platform that, for the first time, integrates high-fidelity AGV dynamics, communication latency, execution uncertainty, and dynamic task scheduling into lifelong multi-agent path planning scenarios. LSMART supports heterogeneous planners, parallel planning-execution pipelines, and fault-tolerant recovery strategies, enabling systematic evaluation across three key design dimensions: planning timing, policy selection, and recovery mechanisms. Extensive experiments provide empirical insights for building efficient and robust centralized AGV fleet management systems, and the platform is publicly released to facilitate the translation of theoretical advances into practical deployment.

Technology Category

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

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

We present Lifelong Scalable Multi-Agent Realistic Testbed (LSMART), an open-source simulator to evaluate any Multi-Agent Path Finding (MAPF) algorithm in a Fleet Management System (FMS) with Automated Guided Vehicles (AGVs). MAPF aims to move a group of agents from their corresponding starting locations to their goals. Lifelong MAPF (LMAPF) is a variant of MAPF that continuously assigns new goals for agents to reach. LMAPF applications, such as autonomous warehouses, often require a centralized, lifelong system to coordinate the movement of a fleet of robots, typically AGVs. However, existing works on MAPF and LMAPF often assume simplified kinodynamic models, such as pebble motion, as well as perfect execution and communication for AGVs. Prior work has presented SMART, a software capable of evaluating any MAPF algorithms while considering agent kinodynamics, communication delays, and execution uncertainties. However, SMART is designed for MAPF, not LMAPF. Generalizing SMART to an FMS requires many more design choices. First, an FMS parallelizes planning and execution, raising the question of when to plan. Second, given planners with varying optimality and differing agent-model assumptions, one must decide how to plan. Third, when the planner fails to return valid solutions, the system must determine how to recover. In this paper, we first present LSMART, an open-source simulator that incorporates all these considerations to evaluate any MAPF algorithms in an FMS. We then provide experiment results based on state-of-the-art methods for each design choice, offering guidance on how to effectively design centralized lifelong AGV Fleet Management Systems. LSMART is available at https://smart-mapf.github.io/lifelong-smart.

Problem

• Lifelong MAPF
• AGV Fleet Management
• Multi-Agent Path Finding
• Realistic Simulation
• Design Choices

Innovation

• Lifelong MAPF
• AGV Fleet Management
• Realistic Simulation
• Kinodynamic Constraints
• Centralized Planning