Project Details
[Return to Previous Page]Orchestrated control of drones for EuroNCAP vehicle scenarios - GLOBAL WITH CHALMERS UNIVERSITY
Company: AstaZero AB
Major(s):
Primary: CMPSC
Secondary: CMPEN
Optional: ME
Non-Disclosure Agreement: NO
Intellectual Property: YES
AstaZero is a proving ground located deep in the forests outside Gothenburg, Sweden built for testing of advanced automated driving, driver-assistance and active safety systems in road vehicles. AstaZero is a non-profit organization owned indirectly by the Swedish government and performs independent testing, verification and certification for its customers. An example of an active safety system could be the autonomous emergency brake system commonly found in modern vehicles. To show their customers the reliability of the safety functions, automotive companies regularly benchmark their systems in relation to the competitors’ systems - a task normally done by an independent party such as AstaZero, for example in the framework of Euro NCAP. The execution of such benchmarking tests can currently be performed with the open-source control software “Autonomous vehicle Testing Operating System” (ATOS). This system controls test participants such as the vehicle under test, crash targets, and surrounding infrastructure. However, one of the requirements of Euro NCAP tests video documentation. Today the documentation is performed manually with a static camera on a stand and, if the test area is very large, by piloted drone video documentation. Goal The aim of this project is therefore to automate the video documentation of a Euro NCAP test by use of drones. At project’s end a design showcase will be made on the AstaZero proving ground. It will demonstrate a situation where three automated drones follow the vehicle under test from different angles as the test is performed. The three drones’ camera views can be accessed via tablets by a test driver in the vehicle under test. To increase robustness to e.g. wind influence or difference in vehicle speeds, the drones’ cameras will be controlled by an object detection algorithm ensuring that the cameras are constantly pointing directly at the vehicle under test. The task In this global project students from Pennsylvania State University will collaborate with students from Chalmers University of Technology in achieving the goal. Your task will be to automate the drone movements. 1. Perform a cost-benefit analysis on automated video documentation of automated driving tests. 2. Make a technical plan for how to integrate the different parts of the system. 3. Based on the planned ground vehicle path, generate drone missions and commands such that the test execution is captured on video. Supporting information about the vehicle movement and planned path is available through ATOS.