ADEX – Autonomous Driving Examiner

Smart mobility is one of the grand technological challenges of cyber-physical systems in the era of AI and IoT. Autonomous driving (AD) promises to dramatically reduce human

fatalities and pollution. While many advances have already been achieved over the past decade, several accidents of some autonomous cars expose the vulnerabilities

of the current state-of-the-art. Highly automated vehicles appear to ignore some of accepted principles for the design of fault-tolerant systems; certification of objectrecognition

techniques is causing major concerns, and the psychology of pedestrians and car drivers in mixed-traffic with autonomous cars is largely unexplored.

Human drivers must prove their abilities to a driving examiner, before being allowed to drive. Following this analogy, ADEX adopts a multidisciplinary approach to the design

and synthesis of a comprehensive, human-centric, autonomous-driving examination, which is agnostic to the particular design (underlying concept) of an AD controller, to expose its vulnerabilities or unknown flaws. The driving examination consists of realistically simulated traffic situations, called scenarios, with various configurations of road users, weather and road conditions. While the analysis and testing of the behavior of

the AD controller in normal traffic conditions plays a very important role, special emphasis is put on edge cases rarely occurring in normal traffic, to uncover hidden issues.

For the AD system such edge cases might represent limiting situations. Analysis of real-world traffic accidents is used to synthetically generate new, realistic and critical

traffic scenarios for testing. Causes of accidents are often resulting from the interaction of technical and human (psychological and physiological) factors. Both are studied

using holistic accident analysis on hot spots.

The work is driven by an interdisciplinary consortium, with experts in AI, safety, faulttolerant design, cyber-physical systems, accident analysis, psychology and standardization in AD. ADEX aims at developing a trustworthy framework for automatically

examining autonomous-driving controllers.