Collaborative Virtual Validation Platform for ADAS/AD at KIT (ValKIT)
- Contact:
Qais Hamarneh, Maike Schwammberger
- Funding:
KIT Matching Fund
- Startdate:
01.01.24
- Enddate:
31.12.24
Motivation
Due to the increasing level of automation in vehicles, the complexity of the interaction between the vehicle and its surrounding systems is increasing towards a System of Systems (SoS). The validation of such systems, particularly their interactions, poses a significant challenge for the development of automated vehicles (AVs). To ensure safety of all traffic participants, an identification and analysis of critical driving scenarios at design time is of the utmost importance to ensure safety and acceptance of AVs. Virtual validation platforms are crucial in addressing this challenge, offering scalability, user-friendliness, and safety for individuals. They enable comprehensive simulation of a vehicle, encompassing its surroundings, including Vulnerable Road Users (VRUs), infrastructure, and other traffic participants. Integrating numerous components into the virtual platform is an intricate, cross-domain task, often beyond the capacity of a single researcher. To streamline this process, our goal is to establish a shared and collaborative virtual validation platform at KIT, utilizing existing and openly available components and enabling swarm testing as shown in. This project aims to establish the groundwork for a versatile validation platform, poised to serve as a cornerstone for numerous strategic projects in the future, while also allowing for further expansion of its capabilities.
Objectives:
- Development of a versatile and virtual platform for the development and validation of mobility systems (e.g. AVs) as well as for the creation of load collectives and user scenarios. The platform should be open, modular and will be available for all members of the center.
- Enabling swarm testing and fostering collaborative work in the virtual environment.
- Showcasing the shared and collaborative virtual platforms potential through two key use cases that leverage swarm testing:
- Gathering and analyzing conflict scenarios. A state is considered as a conflict if an agent, albeit human or autonomous, cannot choose an action (e.g. turning at an intersection, accelerating, braking…) without violating existing rules.
- Creating critical conflict scenarios through a gamification approach in the shared environment, and subsequently resolving them automatedly or via teleoperation in AR/VR/MR