All intelligence is collective intelligence… Our research builds on this premise, and focuses on synthesizing decentralized agent controllers and interaction policies that lead to cooperative and collaborative systems. Many of our methods build on Graph Neural Network (GNN) architectures, which provide a well-suited inductive bias for networked multi-agent teams and swarms. We are also interested in developing data-driven or hybrid approaches that find near-optimal solutions to hard coordination problems involving resource allocation, path finding, or graph optimization. Our solutions enable fast on-line decision-making, as typically required in robotics applications. As part of our work, we develop sim-to-real methods that facilitate the transfer of policies learned in simulation to real world systems.

M Bettini, R Kortvelesy, A Prorok, Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning, ICML 2024

J Blumenkamp, S Morad, J Gielis, A Prorok, CoViS-Net: A Cooperative Visual Spatial Foundation Model for Multi-Robot Applications, CoRL 2024

M. Bettini, A. Shankar,  A. Prorok, Heterogeneous Multi-Robot Reinforcement Learning, AAMAS 2023

Z. Gao, A. Prorok, Environment Optimization for Multi-Agent Navigation, IEEE ICRA 2023

J. Blumenkamp, Q. Li, B. Wang, Z. Liu, A. Prorok, See What the Robot Can’t See: Learning Cooperative Perception for Visual Navigation, IEEE/RSJ IROS 2023

Research Assistant/Associate position in Machine Learning for Robot Co-Design

Apply Now

TEDxOxford talk by Amanda Prorok January 2024

Watch here

Best Paper Award at ICRA 2023 workshop for Jan Blumenkamp

Read More

Follow us on YouTube

Sign Up

Follow us on Twitter

Sign Up

Find us on Github

Here