Project Description

Autonomous systems, operating across land, air, space, and sea, hold significant promise for revolutionizing society. In emergency, adversarial, or competitive scenarios, these systems are pushed to their performance limits; thus, there is a critical need to ensure provably-safe control and planning for these systems in these extreme regimes. This project will establish foundational techniques and theory to address this need, leveraging the Indy Autonomous Challenge as an exciting testbed for the research. This challenge involves racing a fully autonomous Indylights car at speeds of up to 190mph on professional racetracks, including overtaking other fully autonomous racecars from top international teams. Addressing this challenge will require the Gilbreth fellow to contribute to new control strategies, path planning algorithms, and behavior prediction algorithms that account for the dynamics of the vehicle while pushing it to its operating limits. Of particular interest is the creation of new safe control and planning algorithms, leveraging both classical model-based techniques and emerging data-driven methodologies, to push beyond the state of the art and enable groundbreaking capabilities for high-speed autonomous systems. 

Start Date

Spring 2025

Post Doc Qualifications

- PhD in Electrical Engineering, Mechanical Engineering, Computer Engineering, Applied Mathematics, or a related discipline
- Solid understanding of control systems, with publications in top relevant venues
- Knowledge and experience in vehicle dynamics, path planning, safety-constrained control, autonomous systems, game theory, or multi-agent systems would be a benefit
- Strong oral and written communication skills
- Ability to work both independently and as part of an interdisciplinary team to tackle research challenges

Co-Advisors

Shreyas Sundaram (sundara2@purdue.edu), Marie Gordon Professor of Electrical and Computer Engineering, Co-Director of the Institute for Control, Optimization and Networks, https://engineering.purdue.edu/~sundara2/

Greg Shaver (gshaver@purdue.edu), Professor of Mechanical Engineering, Director of Herrick Labs, https://gregshaver.com/ 

Bibliography

D. Metz and D. Williams, "Near time-optimal control of racing vehicles." Automatica 25, no. 6 (1989): 841-857.

L. Xin, G. Chiu and S. Sundaram, "Learning the Dynamics of Autonomous Linear Systems from Multiple Trajectories." Proceedings of the American Control Conference, 2022.

Alexander H. Taylor, Miles J. Droege, Gregory M. Shaver, Jairo A. Sandoval, Stephen Erlien and James Kuszmaul, "Capturing the Impact of Speed, Grade and Traffic on Class 8 Truck Platooning", IEEE Transactions on Vehicular Technology, volume 69, issue 10, July 2020.

M. Pirani, E. Hashemi, A. Khajepour, B. Fidan, B. Litkouhi, S.-K. Chen, and S. Sundaram, "Cooperative Vehicle Speed Fault Diagnosis and Correction." IEEE Transactions on Intelligent Transportation Systems, vol. 20, no. 2, pp. 783 - 789, Feb. 2019.

A. Pandy, N. Pathuri, P. Salunke, S. Subba and D. Williams, "A Practical Fail-Operational Steering Concept," SAE Int. J. Commer. Veh. 13(3):177-188, 2020.