Autonomous vehicles (AVs) such as self-driving cars and unmanned aerial vehicles are complex systems that use artificial intelligence (AI) and machine learning (ML) to make real-time navigational decisions. Ensuring the dependability of AVs in terms of robustness, correctness, reliability, and safety is critical for their mass deployment and public adoption. However, it is challenging to assess and ensure the dependability of these systems due to their complexity both in terms of software and hardware and in terms of the inherent stochasticity and uncertainty in the sensor data and ML/AI algorithms. In this chapter, we design and develop novel assessment techniques to rigorously validate the AV system, including its runtime operational characteristics. The developed assessment techniques address the challenges mentioned above and significantly outperform the current state-of-the-art assessment techniques. We demonstrate our developed techniques and scientific contributions using self-driving cars as a motivating example.
Assessing Dependability of Autonomous Vehicles
Springer Ser Reliab Eng
26.07.2022
17 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Dependability for declarative mechanisms: neural networks in autonomous vehicles decision making.
BASE | 2023
|Dependability of Avionics Unmanned Aerial Vehicles
IEEE | 2019
|