Facilitating Automatic Setup in a Robotised Test Framework for Autonomous Vehicles by Path Planning and Real Time Trajectory Generation

Abstract: The research in the field of autonomous vehicles and self-driving cars is growing at a rapid pace and strong initiatives are being taken to verify the capability and functionality of such autonomous vehicles. With continuous development being carried out in the field of Advanced Driver Assist Systems (ADAS) and Autonomous drive (AD) functions, ensuring safety, robustness and reliability of these functions is challenging and it requires advanced ways of verification and testing before these functions are deployed on the vehicle and delivered to the customer. Testing of these modern features can be done either on test track, real driving roads or in simulations by Computer Aided Engineering (CAE). But testing a high-risk scenario in the real-world would be challenging due to safety concerns. Also, high regression and continuous testing requires a test framework where the development and testing can be done in an efficient way. At Volvo Cars, it is envisioned that the best approach to test the AD vehicles is by subjecting the vehicle under test to several high-risk scenarios by simulation based engineering and replicate the subset of these tests on a closed-loop test framework developed on the test track. This thesis is a part of FFI Funded Research Project called CHRONOS2 where Volvo Car Corporation and other project partners aim to develop the closed-loop test framework for verification of AD Vehicles. This thesis work focuses on ensuring efficient and reproducible testing in the said test framework by accurate path planning and trajectory generation to drive the multiple test objects to their starting positions in an unstructured test environment. The algorithm developed for path planning should also ensure the generation of a safe path in real-time for the test objects in case of failure or error in the test framework. The path-planning algorithm has been successfully implemented taking the unstructured environment and vehicle dimensions into consideration resulting in a safe path avoiding obstacles and satisfying non-holonomic constraints of the vehicle. The implemented architecture utilizes the parallel-processing framework of Robot Operation System (ROS) and results in an algorithm which can run in real-time.