1.5 KiB
| categories | date | description | layout | slug | tags | title | persons | presentation | recording | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2023-05-11T20:31:43+02:00 | event-talk | Rix Groenboom - Validation of AI: Towards a Driving Exam for OpenPilot |
|
|
|
Abstract
We present practical results of testing the OpenPilot ADAS software (the core of the Comma3 [https://comma.ai/]). OpenPilot consists of C/C++ and Python code to handle most of the logic involved in driving a car. Also, Machine Learning models are employed for various detection tasks, such as road line detection.
To test the functional behavior (“Is OpenPilot able to handle certain traffic situations?”), we are implementing a framework that generates test scenarios from traffic laws. For the non-functional aspect, we have looked at the robustness of the implemented ML models, as part of analysis for Trustworthy AI (“Can OpenPilot be fooled by modifying the input images?”).
We will present the outcomes, discuss the results, and give pointers for further research on ADAS testing.
Biography
Rix Groenboom leads the research group New Business & ICT within the Hanze University of Applied Science; with innovation in Artificial Intelligence, Connectivity (5G), Cyber Security, and Smart Industry. He has over 25 years of experience in SW quality in academic, commercial, and industrial environments.