Trajectory planning with verifiable safety
Making safe vehicle decisions and planning of collision-free trajectories play a critical role on the widespread of autonomous vehicles. Decision making and trajectory planning layers constitute the uppermost layer of a typical autonomous vehicle system architecture and therefore, their input comprises a considerable amount of uncertainties that accumulate during perception and situation understanding computations. However, these layers must felicitously deal with these uncertainties and must make reasonable assumptions about the vehicle environment.
Making such assumptions is not a trivial task, as the sources of the uncertainties are diverse. Limited sensor range, harsh weather conditions diminishing the quality of the perception, and occluded objects in the environment are among the most ordinary problems. But furthermore, an autonomous vehicle must also be able to deal with the unexpected behaviour of other traffic participants, which sometimes even unobserve the traffic regulations. Although the state-of-the-art autonomous vehicles operate very well in sound conditions, they only can inadequately handle with these problems. The idea behind the EU Horizon 2020 RobustSENSE project (Robust and Reliable Environment Sensing and Situation Prediction for Advanced Driver Assistance Systems and Automated Driving) is to develop algorithms that alleviate these problems and ensure the operational safety of an autonomous vehicle.
My research in that context focuses on trajectory planning with provable safety. Using provided environment information, we perform research to investigate cases that a vehicle encounters in daily traffic and try to develop novel metrics that enable reliable evaluation of the criticality. Once the a quantitative evaluation is done, these metrics are expolited in a criticality-aware motion planner to plan cautious behaviour for the autonomous vehicle.
Although safety forms the core of my research, I am not limited with that. I am also interested in motion planning research, cooperative driving, vehicle motion planning at the limits of handling, vehicle control and identification, and decision making. Interested students with excellent records are always welcome to apply for a bachelors/masters thesis and assistantships.