Project

Project 1. Cooperative Control, Sensing and Learning in Multi-Agent Systems (MAS)

Multi-Agent Systems (MAS) are widely used in various fields (e.g., Search and Rescue Operations, intelligent transportation systems, etc.) due to their tremendous advantages, such as flexibility, scalability and usability. However, they bring with them new challenges, such as network imperfections and system uncertainties.

My proposed approaches, are numerically and experimentally validated at the Unmanned Systems Laboratory from the University of Nevada Reno, on a team of aerial robots correspond to the Bepob drone, manufactured by Parrot where these results demonstrated the effectiveness of my proposed approaches, as well as their applicability to real-time systems. Ultimately, I proved that my proposed methodologies guarantee the convergence to intelligent optimal control of MAS asymptotically.

Related Publications

[A14] Jafari, M., Xu, H., & Garcia Carrillo, L. R. (2020). A biologically-inspired reinforcement learning based intelligent distributed flocking control for Multi-Agent Systems in presence of uncertain system and dynamic environment, IFAC Journal of Systems and Control, 13, 100096.

[A13] Jafari, M., & Xu, H. (2019). A biologically-inspired distributed fault tolerant flocking control for multi-agent system in presence of uncertain dynamics and unknown disturbance. Engineering applications of artificial intelligence, 79, 1-12.

[A12] Jafari, M. (2018). Distributed Control Of Multi-Agent Systems Using Biologically-Inspired Reinforcement Learning (Doctoral dissertation).

[A11] Jafari, M., & Xu, H. (2018, November). A game theoretic based biologically-inspired distributed intelligent flocking control for multi-uav systems with network imperfections. In 2018 IEEE Symposium Series on Computational Intelligence (SSCI) (pp. 1138-1144). IEEE.

[A10 Jafari, M., & Xu, H. (2018). Biologically-inspired intelligent flocking control for networked multi-UAS with uncertain network imperfections. Drones, 2(4), 33.

[A9] Jafari, M., & Xu, H. (2018, June). A biologically-inspired distributed intelligent flocking control for networked multi-uas with uncertain network imperfections. In 2018 International Conference on Unmanned Aircraft Systems (ICUAS) (pp. 15-21). IEEE.

[A8] Nguyen, T., La, H. M., Le, T. D., & Jafari, M. (2017). Formation control and obstacle avoidance of multiple rectangular agents with limited communication ranges. IEEE Transactions on Control of Network Systems, 4(4), 680-691.

[A7] Jafari, M., & Xu, H. (2017, September). A biologically-inspired distributed resilient flocking control for multi-agent system with uncertain dynamics and unknown disturbances. In 2017 Resilience Week (RWS) (pp. 71-76). IEEE.

[A6] Jafari, M., Fehr, R., Carrillo, L. R. G., Quesada, E. S. E., & Xu, H. (2017, July). Implementation of brain emotional learning-based intelligent controller for flocking of multi-agent systems. IFAC-PapersOnLine, 50(1), 6934-6939.

[A5] Fehr, R., Boles, K., Jafari, M., Xu, H., & Carrillo, L. R. G. (2017, June). A low-computation distributed connectivity control for coordinated multi-uas. In 2017 International Conference on Unmanned Aircraft Systems (ICUAS) (pp. 1181-1188). IEEE.

[A4] Jafari, M., Xu, H., & Carrillo, L. R. G. (2017, May). Brain emotional learning-based intelligent controller for flocking of multi-agent systems. In 2017 American Control Conference (ACC) (pp. 1996-2001). IEEE.

[A3] Jafari, M. (2015). On the cooperative control and obstacle avoidance of multi-vehicle systems (Master's thesis).

[A2] Jafari, M., Sengupta, S., & La, H. M. (2015, December). Adaptive flocking control of multiple unmanned ground vehicles by using a uav. In International Symposium on Visual Computing (pp. 628-637). Springer, Cham.

[A1] Nguyen, T., La, H. M., & Jafari, M. (2015, June). On the formation control of a multi vehicle system. In ISSAT International Conference on Modeling of Complex Systems and Environments.