Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Jingtian Yan, Yulun Zhang, Zhenting Liu, Han Zhang, He Jiang, Jingkai Chen, Stephen F. Smith, Jiaoyang Li

TL;DR

LSMART, an open-source simulator to evaluate any Multi-Agent Path Finding (MAPF) algorithm in a Fleet Management System with Automated Guided Vehicles (AGVs) with guidance on how to effectively design centralized lifelong AGV Fleet Management Systems is presented.

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.

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

TL;DR

LSMART, an open-source simulator to evaluate any Multi-Agent Path Finding (MAPF) algorithm in a Fleet Management System with Automated Guided Vehicles (AGVs) with guidance on how to effectively design centralized lifelong AGV Fleet Management Systems is presented.

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.
Paper Structure (43 sections, 15 figures, 3 tables)

This paper contains 43 sections, 15 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Background
  3. Lifelong MAPF and Its Design Choices
  4. Agent Models in Planning
  5. Execution Policy
  6. Planner Invocation Policy
  7. Duplicate Goals Resolution in Instance Generator
  8. Fail Policy
  9. FMS Software
  10. LSMART
  11. System Overview
  12. Planner Invocation Policy
  13. Instance Generator
  14. Fail Policy
  15. MAPF Planner
  16. ...and 28 more sections

Figures (15)

  • Figure 1: Detailed architecture of LSMART. Red boxes are user customizable modules, gray boxes are non-customizable modules, and yellow boxes are data structures used for communicating between modules. Black arrows indicates required flow, red arrows indicate flow when the MAPF planner successfully finds collision-free paths, and yellow arrows indicate flow when the planner fails and the system need to recover from failure.
  • Figure 2: Experiment results of instance generators (Experiment 1 in \ref{['tab:exp']}).
  • Figure 3: Experiment results of planner invocation policies (Experiment 2 in \ref{['tab:exp']}).
  • Figure 4: Experiment results of $P$ and $W$ (Experiment 3 in \ref{['tab:exp']}).
  • Figure 5: Experiment results of different $P$ with standard MAPF (Experiment 4 in \ref{['tab:exp']}).
  • ...and 10 more figures

Theorems & Definitions (5)

  • Definition 1: Pebble Motion Agent
  • Definition 2: Standard MAPF
  • Definition 3: Standard Lifelong MAPF
  • Definition 4: Automated Guided Vehicles (AGV)
  • Definition 5: AGV Fleet Management System (FMS)