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

cs.ROFeb 17, 2026

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

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

Organizations: Robotics Institute, Carnegie Mellon University · Symbotic

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.

Figures & tables

		Agent Model (Planning)	Agent Model (Execution)	Execution Policy	Planner Invocation Policy	Instance Generator	Fail Policy	Open-source
1	Hönig et al. (2019)	Pebble Motion	Differential Drive	ADG	Event-based	Distinct-One-Goal	N/A	✗
2	Varambally et al. (2022)	Pebble Motion	Differential Drive	ADG	Event-based	Windowed-Multi-Goals	N/A	✗
3	Li et al. (2021b)	Pebble Motion	Pebble Motion	N/A	Periodic	Windowed-Multi-Goals	LRGW	✓
4	Zhang et al. (2024a)	Pebble Motion	Pebble Motion	N/A	Periodic	Windowed-Multi-Goals	Generalized ADG	✓
5	Chan et al. (2024)	Rotation Motion	Rotation Motion	N/A	Periodic	Windowed-Multi-Goals	N/A	✓
6	Zhang et al. (2025a)	Pebble Motion	Pebble Motion	ADG, PIBT-Based	Periodic	Windowed-Multi-Goals	N/A	✓

Table 1: Overview of previous FMS software tools.

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.

Setup	Agent Model (Planning)	Planner	W (s)	P (s)	T (s)	Planner Invocation Policy	Instance Generator	Fail Policy
1	Pebble Motion	Standard PBS	$\infty$	1	1	Periodic	Distinct-One-Goal	PIBT
2	Pebble Motion	Standard PBS	$\infty$	N/A	1	Event-based	Distinct-One-Goal	PIBT
3	Pebble Motion	Windowed PBS	1	1	1	Periodic	Windowed-Multi-Goals	PIBT
4	Pebble Motion	Windowed PBS	1	N/A	1	Event-based	Windowed-Multi-Goals	PIBT
5	Pebble Motion	MAPF4L PBS	$\infty$	1	1	Periodic	One-Goal	PIBT
6	Pebble Motion	MAPF4L PBS	$\infty$	N/A	1	Event-based	One-Goal	PIBT

Table 2: Summary of LSMART setups used in the experiments.

W

is the planning window for windowed MAPF solvers,

P

is the period to invoke the planner for periodic invocation policy, and

T

is the runtime limit for one invocation of the MAPF planner, all given in seconds. The

\infty

sign indicates that the planner plans collision-free paths to all the given goals.

Section	Experiment	Setups
Section 4.2	1	1, 2, 3, 4, 5, 6
Section 4.3	2	3, 4, 7, 8
	3	3, 7, 9, 10
	4	11
Section 4.4	5	3, 7, 12, 13, 14, 15
Section 4.5	6	16, 17, 18, 19

Table 3: Summary of experiments and the setups being used.

Panel of Figure 2 — Figure 2: Experiment results of instance generators (Experiment 1 in Table 3 ).

Panel of Figure 3 — Figure 3: Experiment results of planner invocation policies (Experiment 2 in Table 3 ).

Panel of Figure 4 — Figure 4: Experiment results of $P$ and $W$ (Experiment 3 in Table 3 ).

Panel of Figure 5 — Figure 5: Experiment results of different $P$ with standard MAPF (Experiment 4 in Table 3 ).

Panel of Figure 6 — Figure 6: Experiment results of fail policies (Experiment 5 in Table 3 ).

Panel of Figure 7 — Figure 7: Experiment results of agent model accuracy and planner optimality (Experiment 6 in Table 3 ).

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 8: Logo of LSMART.

Panel of Figure 9 — Figure 9: Additional experiment results of instance generators (Experiment 1 in Table 3 ).

Panel of Figure 10 — Figure 10: Experiment results of planner invocation policies (Experiment 2 in Table 3 ).

Panel of Figure 11 — Figure 11: Additional Experiment results of $P$ and $W$ (Experiment 3 in Table 3 ).

Panel of Figure 12 — Figure 12: Additional experiment results of different invocation frequencies (Experiment 4 in Table 3 ).

Panel of Figure 13 — Figure 13: Additional experiment results of fail policies (Experiment 5 in Table 3 ).

Panel of Figure 14 — Figure 14: Additional experiment results of MAPF model accuracy and planner optimality (Experiment 6 in Table 3 ).

Panel of Figure 15 — Figure 15: Experiment results of MAPF planner optimality.

Multi-Robot Systems

Multi-robot systems coordinate teams of robots to plan, perceive, communicate, and act together in shared tasks and environments.

See all 205 papers

Lifelong LaCAM with Local Guidance for Lifelong MAPF
May 16, 2026Tomoki Arita, Keisuke OkumuraSequential Decision Making Robust MAPF
Keio University, Japan · National Institute of Advanced Industrial Science and Technology (AIST), Japan
From Gridworlds to Warehouses: Adapting Lightweight One-shot Multi-Agent Pathfinding for AGVs
May 15, 2026Hiroki Nagai, Keisuke OkumuraMulti-Robot Motion Planning Constrained Motion Planning
National Institute of Advanced Industrial Science and Technology (AIST), Japan
Scalable Long-Horizon Planning with Staggered Updates for Lifelong MAPF
Aug 7, 2026Vaibhav Sanjay, Jiaoyang LiMulti-Agent Coordination Robust MAPF
Robotics Institute, Carnegie Mellon University

May 16, 2026J/K move · Enter open · S save

Lifelong LaCAM with Local Guidance for Lifelong MAPF

Tomoki Arita, Keisuke Okumura

Keio University, Japan · National Institute of Advanced Industrial Science and Technology (AIST), Japan

Sequential Decision Making Robust MAPF Multi-Agent Path Finding

Open paper AskPDF arXiv

Local guidance has recently proven to be a powerful driver of empirical performance in real-time, suboptimal multi-agent pathfinding (MAPF), improving the scalable configuration-based solver LaCAM. By injecting informative spatiotemporal cues around each agent, local guidance mitigates congestion, reduces waiting, and remains scalable enough even with tight time budgets, yielding state-of-the-art performance for one-shot MAPF. This study asks whether the same benefits can be lifted to the lifelong setting (LMAPF), where tasks arrive continuously and improvements in per-step plans can increase task completion throughput over long horizons. We propose LLLG, a Lifelong version of LaCAM enhanced with Local Guidance, which employs a receding-horizon windowed planning framework and warm-starts guidance from the previous solution at each timestep. Our method scales effectively, maintains high throughput even in compact, dense environments, and surpasses existing planners, thereby pushing the frontier of real-time, lifelong MAPF.

Abstract

Multi-Robot Systems

Explore similar work

Lifelong LaCAM with Local Guidance for Lifelong MAPF

From Gridworlds to Warehouses: Adapting Lightweight One-shot Multi-Agent Pathfinding for AGVs

Scalable Long-Horizon Planning with Staggered Updates for Lifelong MAPF