Autonomous Driving in Urban Environments
The coming decades will see the creation of fully autonomous vehicles (AVs) capable of driving without human intervention. Among the expected benefits of AVs are a significant reduction in traffic incidents, congestion, and pollution, while dramatically improving cost-efficiency.
Creating a complete AV system is a tremendous technological and scientific challenge. A key aspect in any AV system is the ability to drive safely in the presence of other actors in the environment, including other vehicles and pedestrians. Driving safely relies crucially on the ability to make accurate predictions about the intentions and behaviours of other actors based on limited observations, and the ability to compute robust plans with specified safety-compliance under a limited compute budget. Several surveys provide a good introduction into this area of research and open problems [1-4].
The goal of this project is to develop novel algorithms for autonomous driving in urban environments, by integrating efficient prediction and planning under limited observations and compute budget. Open source platforms such as CARLA (http://carla.org/) can be used for testing and evaluation of the developed algorithms. The challenge task is to drive safely across an entire city with diverse interaction scenarios (junctions, roundabouts, traffic jams, etc).
 Amir Rasouli, John Tsotsos (2019).Autonomous Vehicles That Interact With Pedestrians: A Survey of Theory and Practice. IEEE Transactions on Intelligent Transportation Systems
 Wilko Schwarting, Javier Alonso-Mora, Daniela Rus (2018). Planning and Decision-Making for Autonomous Vehicles. Annual Review of Control, Robotics, and Autonomous Systems
 Pendleton et al (2017). Perception, Planning, Control, and Coordination for Autonomous Vehicles. Machines Journal
 Paden et al (2016). A Survey of Motion Planning and Control Techniques for Self-Driving Urban Vehicles. IEEE Transactions on Intelligent Vehicles