The Cambridge RoboMaster: An Agile Multi-Robot Research Platform

TL;DR

This paper introduces a versatile, compact multi-robot platform based on DJI Robomaster S1 vehicles, integrating hardware, control, and simulation software for research in multi-agent systems and reinforcement learning.

Contribution

The paper presents a novel integrated hardware and software platform that enables indoor multi-robot experiments with onboard autonomy and multi-agent reinforcement learning capabilities.

Findings

Demonstrated full onboard autonomy with ROS2 control stack

Validated multi-agent reinforcement learning in real-world experiments

Showcased versatility and reliability through various research case studies

Abstract

Compact robotic platforms with powerful compute and actuation capabilities are key enablers for practical, real-world deployments of multi-agent research. This article introduces a tightly integrated hardware, control, and simulation software stack on a fleet of holonomic ground robot platforms designed with this motivation. Our robots, a fleet of customised DJI Robomaster S1 vehicles, offer a balance between small robots that do not possess sufficient compute or actuation capabilities and larger robots that are unsuitable for indoor multi-robot tests. They run a modular ROS2-based optimal estimation and control stack for full onboard autonomy, contain ad-hoc peer-to-peer communication infrastructure, and can zero-shot run multi-agent reinforcement learning (MARL) policies trained in our vectorized multi-agent simulation framework. We present an in-depth review of other platforms currently available, showcase new experimental validation of our system's capabilities, and introduce case studies that highlight the versatility and reliability of our system as a testbed for a wide range of research demonstrations. Our system as well as supplementary material is available online. https://proroklab.github.io/cambridge-robomaster