The contribution of machine learning to analyze and evaluate the safety of automated transport systems

Abstract

This paper presents our contribution to the improvement of the usual methods of analysis and safety assessment used as part of the certification of automatic guided land transport systems. This contribution, based on the use of artificial intelligence techniques, including machine learning, has been realized by the development of several approaches and tools for modeling, capitalization and evaluation Knowledge of safety. The software tool presented in this article called REXCAS has two main purposes: first to check in and perpetuate the experience in security analysis and second to help those involved in the development and certification of transport systems in their arduous task of assessing safety studies.