Machine Learning-Assisted Cognition of Driving Context and Avoidance of Road Obstacles
In the vehicle of the future, an intelligent vehicle should be able to recognize the driving context so as it would be able to perform the necessary actions to continue the trip up to its intended destination. Moreover, such intelli-gent vehicle should also be able to detect and recognize road obstacles, as it is the failure to recognize an obstacle and avoid it that often lead to road accident, normally causing human fatalities. In this paper, knowledge engineering related to the cognitive processes of driving context detection, perception, decision and optimal action related to the driving context and avoiding road obstacles. Ontol-ogy and formal specifications are used to describe such mechanism. Different supervised learning algorithms are used for cognition of driving context and in recognizing and classifying obstacles. The avoidance of obstacles is implemented using reinforcement learning. The work is validated using driving simulator in the laboratory. This work is a contribution to the ongoing research in safe driving, and the application of machine learning leading to prevention of road accidents.
- Titre de l'ouvrage Machine Learning-Assisted Cognition of Driving Context and Avoidance of Road Obstacles
- Editeur(s) Institute for Systems and Technologies of Information, Control and Communication
- Co-auteur(s) HINA M., Ortalda A., Soukane A., Randame-Cherif A.
- Année de parution 2019
- Page(s) 25 pages
- Coordination du chapitre d'ouvrage Springer CCIS Series book entitled “Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2018, Revised Selected Papers”
Signal Processing, Control and Coordination in an Intelligent Connected Vehicle
In this paper, we present the functionalities of an intelligent connected vehicle. It is equipped with various sensors and connected objects that enable communication between the driver and its environment. This system provides assistance towards safe and green driving. The driving assistance may be directed towards the driver (semi-autonomous vehicle) or completely towards the vehicle (self-driving, autonomous vehicle). The assistance is based on the driving context which is the fusion of parameters representing the context of the driver, the vehi-cle and the environment. This cyber-physical vehicle has three main components: the embedded system, the networking and real-time system and the intelligent system. The architecture for data transfer within the connected vehicle is imple-mented through publish-subscribed infrastructure in which services are trans-ferred and controlled in an orderly manner. These functionalities are tested both in the laboratory and on the road with satisfactory results. This is the fruit of labor of a consortium composed of five industrial and two academic partners.
- Titre de l'ouvrage Signal Processing, Control and Coordination in an Intelligent Connected Vehicle
- Editeur(s) Zitouni R., Agueh M.
- Co-auteur(s) HINA M., Dourlens S., Soukane A., Ramdane-Cherif A.
- Année de parution 2018
- Page(s) 32 - 43
- Coordination du chapitre d'ouvrage Springer Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 260)