We are developing model-predictive control (MPC) algorithms to integrate planning and motion control for autonomous vehicles. These algorithms are deployed using robot operating system (ROS) on the University of Waterloo “Autonomoose”. Vehicle and tire models are developed from experimental tests using our intelligent vehicle measurement system, and the controllers are evaluated in virtual simulations and hardware-in-loop experiments prior to vehicle testing.
• Model-Predictive Controllers
• Autonomous and Connected Vehicles
• Intelligent Vehicle Systems
• Automated Planning and Control
• Lin Y, McPhee J, and Azad NL. (2019). Longitudinal Dynamic versus Kinematic Models for Car-Following Control Using Deep Reinforcement Learning. IEEE Intelligent Transportation Systems Conference. arXiv:1905.08314.
• Batra M, McPhee J, and Azad NL. (2018). Real-Time Model Predictive Control of Connected Electric Vehicles. Vehicle System Dynamics: International Journal of Vehicle Mechanics and Mobility. DOI: 10.1080/00423114.2018.1552004.
• Maitland A and McPhee J. (2018). Towards Integrated Planning and Control of Autonomous Vehicles Using Nested MPCs. ASME 2018 Dynamic Systems and Control Conference. DOI: 10.1115/DSCC2018-9224.