The field of robotics is constantly evolving, with researchers seeking ways to push the boundaries of what robots can achieve. One area of particular interest is the use of teams of robots, which have the potential to tackle far more elaborate missions than individual robots. This includes covering long distances faster, visiting different sites simultaneously, or monitoring larger geographical areas. Platforms that combine reliable hardware and software for multi-robot applications could help advance research in this field, facilitating the testing of robot teams in specific real-world settings.
Recently, researchers at the University of Cambridge introduced the Cambridge RoboMaster, a promising platform for multi-robot research. This platform includes the design of a fleet of customized RoboMaster wheeled robots, along with software to simulate and train the robots on specific tasks. The mission of the team behind the Cambridge RoboMaster is to develop solutions for collective intelligence in multi-robot and multi-agent systems. This research incorporates methods from machine learning, planning, and control, with applications including automated transport, logistics, environmental monitoring, and search and rescue.
The researchers behind the Cambridge RoboMaster set out to develop a multi-robot research platform that met specific requirements, including state-of-the-art computing power, speed, agility, and durability. They decided to use customized versions of DJI RoboMaster S1 robots, small wheeled robots originally designed for high school and university-level competitions. Over the past three years, the team has continued to work on enhancing this robotic platform, adding more capable computers, sensors, and control software. This has allowed them to use the platform in multiple projects and competitions.
The Cambridge RoboMaster, built on the foundation of the DJI RoboMaster S1, has been enhanced to include a more capable main computer and custom controller. This has pushed the platform to its physical limits, allowing it to reach a top speed of 4.5 m/s. The platform is highly agile and effective for multi-robot experiments in indoor environments. It offers a perfect balance between robot size and capabilities, overcoming the limitations of both smaller, less powerful robots, and larger, more expensive robots that are impractical for indoor use.
One of the greatest advantages of the Cambridge RoboMaster is its cost-effectiveness, with a price tag of around $700, making it accessible for researchers. The platform includes a control stack for full on-board autonomy, peer-to-peer communication, and the ability to run multi-agent reinforcement learning policies directly from a simulation framework. Its combination of affordability, advanced capabilities, and versatility makes it an ideal tool for a wide range of research demonstrations and practical applications in multi-agent systems.
The Cambridge RoboMaster robots have been tested in various scenarios, demonstrating their power-efficiency and versatility in navigating both indoor and outdoor environments. While not intended for direct use in real-world settings, the platform serves as an ideal proxy and research tool for testing algorithms applicable in multi-agent navigation. Future plans for the platform include improving on-board sensing, decentralized communication, and control, as well as exploring its potential for research in drones. By continually enhancing and expanding the capabilities of the platform, the researchers aim to push the limits of multi-robot and multi-agent systems research.
Leave a Reply