Control and Learning for Multi-Agent Autonomy

Interdisciplinary Areas: Autonomous and Connected Systems, Others

Project Description

Multi-Agent Systems (MAS) are collections of autonomous agents, where each agent has sensing, computation, and decision-making capabilities. By working as a cohesive whole, large-scale MAS can achieve complex missions that are well beyond the capabilities of individual systems, such as exploration of the unknown, monitoring a large city, and search and rescue. Different from systems with a centralized coordinator, large-scale MAS operate in a distributed way, and achieve global objectives through only local coordination among neighboring agents.

The objective of this project is to establish cutting-edge algorithms and design principles for MAS to coordinate in an unknown, time-varying or even hostile environment. New methods will be developed for robustness, safety, resilience of MAS. We are particularly interested in integration of control with machine learning, i.e. how to leverage new techniques from machine learning to control systems with unknown dynamics, and how to employ classical control theories to solve fundamental problems in machine learning.


Start Date

August 15, 2024


Postdoc Qualifications

Solid mathematical skills and background in relevant areas, such as networks, control, optimization, or machine learning.

Passion and interest to solve challenging research problems using methodologies from multiple areas.

Good communication and writing skills (English).

Ability to thrive in a collaborative environment.



Shaoshuai Mou, , School of Aeronautics and Astronautics,

Shreyas Sundaram,, Elmore Family School of Electrical and Computer Engineering,


Short Bibliography

o   X. Wang, S. Mou, S. Sundaram. A Resilient Convex Combination for consensus-based distributed algorithms. Numerical Algebra, Control and Optimizations, 9(3), 269-281, 2019.

o   S. Sundaram, B. Gharesifard. Distributed optimization under adversarial nodes. IEEE Transactions on Automatic Control. 64(3), 1063-1076, 2019.

o   A. Mitra, S. Sundaram. Byzantine-resilient distributed observers for LTI systems. Automatica, 108, 2019.

o   W. Jin, Z. Wang, Z. Yang, S. Mou. Pontryagin Differentiable Programming: An End-to-End Learning and Control Framework. Proceedings of Advances in Neural Information Processing Systems (NeurIPS). 2020.

o   W. Jin, S. Mou, G. J. Pappas. Safe Pontryagin Differentiable Programming. Proceedings of Advances in Neural Information Processing Systems (NeurIPS). 2021.