Correct-by-Construction Advanced Driver Assistance Systems based on a Cognitive Architecture
This addresses safety for autonomous and semi-autonomous vehicles, but is incremental as it builds on existing formal methods and cognitive architectures.
The paper tackled the safety verification of human driver models and design of correct-by-construction Advanced Driver Assistance Systems (ADAS) by integrating the ACT-R cognitive architecture with formal methods and an abstraction technique for finite representation as a Markov process, applied to a multi-lane highway scenario with efficacy demonstrated in two case studies.
Research into safety in autonomous and semi-autonomous vehicles has, so far, largely been focused on testing and validation through simulation. Due to the fact that failure of these autonomous systems is potentially life-endangering, formal methods arise as a complementary approach. This paper studies the application of formal methods to the verification of a human driver model built using the cognitive architecture ACT-R, and to the design of correct-by-construction Advanced Driver Assistance Systems (ADAS). The novelty lies in the integration of ACT-R in the formal analysis and an abstraction technique that enables finite representation of a large dimensional, continuous system in the form of a Markov process. The situation considered is a multi-lane highway driving scenario and the interactions that arise. The efficacy of the method is illustrated in two case studies with various driving conditions.