IROS-26 Tutorial on Scalable Multi-Robot Planning: From MAPF Algorithms to Real Robotic Systems

Time: October 1st: 8:30AM - 12:30AM Eastern Time
Location: Room 321

Recording: https://www.youtube.com/watch?v=EkfmFfDh9N0

Coordinating large teams of robots is a fundamental challenge in modern robotics, with applications ranging from warehouse automation to robotic assembly. Multi-Agent Path Finding (MAPF) has emerged as a promising algorithmic framework for addressing this challenge and has been extensively studied over the past decade, with scalable algorithms capable of coordinating thousands of robots. However, most MAPF research has historically focused on grid-based environments with simplified robot models in simulation, leaving a gap between algorithmic advances and robotic deployment.

This tutorial aims to help bridge this gap by presenting recent advances that extend MAPF from simulated discrete-time grid worlds to real robotic systems in both research labs and industry. We will highlight three representative applications: automated warehouses, multi-drone coordination, and multi-arm manipulation. In particular, speakers from robotics companies will present how MAPF-based coordination is deployed in today’s warehouses with hundreds of robots and discuss practical challenges in transitioning MAPF algorithms from research prototypes to production environments. The tutorial will also include a hands-on session on LSMART, an open-source platform for benchmarking and executing MAPF plans on large fleets of automated guided vehicles, providing participants with practical experience in building MAPF-based coordination pipelines.

Although MAPF has become a highly active research area with numerous workshops, tutorials, and competitions at major robotics and AI conferences, most prior events have focused on algorithmic advances in simplified planning settings. To the best of our knowledge, this will be the first tutorial dedicated to advancing MAPF algorithms for real-world robotic applications, covering both research prototypes and large-scale industrial deployments.

Target audience and objectives

For multi-robot researchers and practitioners, this tutorial targets both (i) those who are already familiar with MAPF but may view it as primarily theoretical and limited to grid-based, discrete-time settings, and (ii) those who are new to MAPF and are seeking scalable and practical tools for coordinating large robot teams. The tutorial will present MAPF as a powerful and scalable algorithmic foundation for coordinating large robot teams and demonstrate how modern MAPF-based methods can be extended to handle robot dynamics, execution uncertainty, and real-world constraints, and how they can be deployed on various practical robotic platforms like ground robots, robot arms, and aerial robots.
For AI and MAPF researchers, this tutorial will highlight the importance of real-robot deployment for MAPF research and present key open challenges and research opportunities that arise when bringing MAPF algorithms to real robots.
For both communities, this tutorial will provide an end-to-end view of multi-robot coordination—from planning and execution to learning and deployment—and clarify how recent MAPF advances translate into scalable, high-quality solutions for real robotic systems.
For students and developers, this tutorial will offer hands-on experience with state-of-the-art MAPF-based tools, enabling participants to directly experiment with scalable multi-robot planning and execution pipelines.

What You Can Expect To Learn

The diagram summarizes what you will take away from this tutorial. We begin with the MAPF problem and its core algorithms, then extend it toward real robots through dynamics-aware planning and robust plan execution, and see how it is deployed today in warehouses, drone fleets, and multi-arm systems. Eventually, you will build a MAPF coordination pipeline yourself in the hands-on LSMART session.