A Value-Driven Design approach for the virtual verification and validation of autonomous vehicle solutions
Editor: Kevin Otto, Boris Eisenbart, Claudia Eckert, Benoit Eynard, Dieter Krause, Josef Oehmen, Nad
Author: Bertoni, Marco (1); Thorn, Stefan (2)
Institution: 1: Blekinge Institute of Technology; 2: Volvo Autonomous Solutions
Section: Design Methods
DOI number: https://doi.org/10.1017/pds.2023.44
Autonomous vehicle solutions (AVS) are regarded as a major enabling technology to support the realization of 'total site solutions' in the construction equipment industry. Their full-scale deployment is hindered today by the need to test autonomous driving capabilities against the varying conditions an AVS is expected to be exposed to during its lifetime. Therefore, using virtual simulation environments is common to overcome the cost and time limitations of physical testing. A caveat in this virtual verification and validation (V&V) work is how to trade off the ‘realism’ of the V&V output (using high-fidelity models across many scenarios) against computational time. This research investigates expectations and needs for value-driven decision support in the virtual V&V process, proposing an approach and a tool to raise awareness among decision-makers about the value associated with using selected simulation models/components in the virtual verification and validation task for AVS. Verification activities performed on the initial prototype show that its main benefit lies in facilitating cross-domain negotiations and knowledge sharing when negotiating the desired features of the virtual simulation environment.