Data-Driven Test Scenario Generation for Cooperative Maneuver Planning on Highways

Abstract

Future automated vehicles will have to meet the challenge of anticipating the intentions of other road users in order to plan their own behavior without compromising safety and efficiency of the surrounding road traffic. Therefore, the research area of cooperative driving deals with maneuver-planning algorithms that enable vehicles to behave cooperatively in interactive traffic scenarios. To prove the functionality of these algorithms, single test scenarios are used in the current body of literature. The use of a single, exemplary scenario bears the risk that the presented approach only works in the presented scenario and thus no general statement can be made about the performance of the algorithm. Furthermore, there is a risk that fictitious traffic scenarios may be solved which do not occur in reality. Therefore, we present a procedure for generating test scenarios based on real-world traffic datasets that require cooperation of at least one of the involved vehicles and thus are challenging from the perspective of cooperation. This procedure is applied to a large highway traffic dataset, resulting in a test scenario catalog that allows a comprehensive performance evaluation. The extracted scenarios are clustered according to the cooperative actions used to solve the respective scenario, which enables a more detailed understanding of the underlying cooperative mechanisms. In order to serve as a basis for making comparisons between different behavior planners and thus contribute to the development of future maneuver planning algorithms, a tool to extract the test scenarios from the used traffic dataset is made publicly available.

A Survey on Safety-Critical Driving Scenario Generation -- A Methodological Perspective

“…In addition, efficiently selecting the critical scenario from a huge number of scenarios is another problem. [16] extracts useful scenarios according to the cooperative actions for cooperative maneuver planning evaluation. In [15], the authors developed a method to select testing ground to accelerate the performance estimation of AVs performance on public streets, where the main contribution is describing the risk intensities of the traffic system in an area of interest with Non-Homogeneous Poisson Process model [96].…”

SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehicles

“…Existing AD algorithm evaluation approaches and platforms can be categorized into three types based on how the testing driving scenarios are generated. First, the data-driven based generation and testing approaches [49,34,15,17] focus on real-world data sampling and distribution density estimation. This line of research is able to model the real-world driving conditions, while requiring a large number of data collection to capture the "rare" safety-critical scenarios for testing.…”

Collaborative Autonomous Driving—A Survey of Solution Approaches and Future Challenges

“…Prominent work has been done on developing the solution approaches for various single test scenarios (i.e., platooning, intersection crossing, lane change and merge) of collaborative driving guiding vehicles on how to behave cooperatively in the given situations. The limitation of these solution approaches is that they work well for the scenarios for which they are developed, thus providing no general suggestions in other scenarios [ 1 , 88 ]. For example, an algorithm developed for cooperative lane change directs the vehicles on how to change the lane cooperatively, but, at the same time, the algorithm provides no recommendations when the vehicles cross the intersection.…”