Towards Provably Correct Driver Assistance Systems through Stochastic Cognitive ModelingDownload PDF

Francisco Eiras, Morteza Lahijanian

28 May 2019 (modified: 05 May 2023)RSS 2019Readers: Everyone
Keywords: Cognitive Architecture, Driving Assistance System, Formal Methods, Formal Verification, Human Driver Model, Probabilistic Modeling, Semi Autonomous Driving, Temporal Logic, Multi-Objective Specifications
TL;DR: Verification of a human driver model based on a cognitive architecture and synthesis of a correct-by-construction ADAS from it.
Abstract: The aim of this study is to introduce a formal framework for analysis and synthesis of driver assistance systems. It applies formal methods to the verification of a stochastic human driver model built using the cognitive architecture ACT-R, and then bootstraps safety in semi-autonomous vehicles through the design of provably correct Advanced Driver Assistance Systems. The main contributions include the integration of probabilistic ACT-R models in the formal analysis of semi-autonomous systems and an abstraction technique that enables a finite representation of a large dimensional, continuous system in the form of a Markov model. The effectiveness of the method is illustrated in several case studies under various conditions.
0 Replies

Loading