English

Correct-by-Construction Advanced Driver Assistance Systems based on a Cognitive Architecture

Robotics 2020-03-26 v1 Logic in Computer Science

Abstract

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.

Keywords

Cite

@article{arxiv.1907.09603,
  title  = {Correct-by-Construction Advanced Driver Assistance Systems based on a Cognitive Architecture},
  author = {Francisco Eiras and Morteza Lahijanian and Marta Kwiatkowska},
  journal= {arXiv preprint arXiv:1907.09603},
  year   = {2020}
}

Comments

Proceedings at IEEE CAVS 2019

R2 v1 2026-06-23T10:27:44.331Z