University of Cambridge > Talks.cam > Machine Learning @ CUED > Graph neural network approach for decentralized multi-robot coordination

Graph neural network approach for decentralized multi-robot coordination

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Hong Ge.

Effective communication is key to successful, decentralized, multi-robot path planning. Yet, it is far from obvious what information is crucial to the task at hand, and how and when it must be shared among robots. To side-step these issues and move beyond hand-crafted heuristics, we propose a combined model that automatically synthesizes local communication and decision-making policies for robots navigating in constrained workspaces. Our architecture is composed of a convolutional neural network (CNN) that extracts adequate features from local observations, and a graph neural network (GNN) that communicates these features among robots. We train the model to imitate an expert algorithm, and use the resulting model online in decentralized planning involving only local communication and local observations. We evaluate our method in simulations by navigating teams of robots to their destinations in 2D cluttered workspaces. We measure the success rates and sum of costs over the planned paths. The results show a performance close to that of our expert algorithm, demonstrating the validity of our approach. In particular, we show our model’s capability to generalize to previously unseen cases (involving larger environments and larger robot teams). In Today’s talk, the speaker will present his work from proof of concept in simulation into the real-world robotics systems toward the fully decentralized system.

Speaker’s Bio:

Qingbiao Li is a final year PhD student at Prorok Lab in the Digital Technology Group (DTG) at the University of Cambridge under the supervision of Dr Amanda Prorok. During his PhD, he focuses on communication-aware motion planning for multi-robot coordination. He is investigating Graph Neural Networks (GNN) to build communication channels for multi-agent and multi-robot systems so that they can learn how to communicate between each other explicitly. His research can be applied to mobility-on-demand systems, automated warehouses, and smart cities.

Prior to joining Cambridge, he was working in the Hamlyn Centre at Imperial College London, founded by Prof Guang-Zhong Yang and the Lord Ara Darzi, in the field of medical robotics and healthcare to earn my MRes in Medical Robotics and Image-Guided Intervention. He was supervised by Prof Daniel Elson for an eight-month research project about oxygen saturation (StO2) estimation, and graduated with a distinction. He also held an MEng degree in Mechanical Engineering from the University of Edinburgh.

Homepage: http://qingbiaoli.github.io/

This talk is part of the Machine Learning @ CUED series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2022 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity