Safety awareness for intelligent transportation systems: Cooperative perception for a network of autonomous vehicles

The golf region including Oman and Quatar are categorized among the countries that have the highest Road Traffic Accident (RTA) related fatality rates worldwide. Due to increasing employment and more people obtaining driving licenses, it is likely that the rate of RTA related fatalities will further increase in coming few years if no decisive measurements are taken on to reduce this rate. It has been shown in recent studies that the occurrence of RTA is mainly caused by the inability of human drivers to predict and quickly react to imminent collision threats because human drivers are susceptible to distraction, fatigue, substance abuse and inherent limitations in prediction and reaction capabilities. This explains the longstanding interest among the industry and government experts for the development of Advanced Driver Assistance Systems (ADAS) and Fully Autonomous Vehicles (FAV) to facilitate on one hand active safety while operating with a ?human in the loop? and attempt to oppose human only when doing otherwise would lead to a potential collision or loss of control. On the other hand to solve other traffic problems such as time and space inefficiency and waste of fuel due to congestion. Fully autonomous maneuvering of cars has the potential of drastically reducing traffic accidents thanks to high-performance sensing and reasoning. The objective of this project is to provide solutions and recommendations on designing new driver assistance system technology that seeks to prevent collision with other vehicles and avoid accident with pedestrians. This is done by means of establishing cooperative driving process between the driver and the vehicle and between vehicles to other vehicles. The autonomous mode of a vehicle can therefore be intelligently or manually activated to accommodate with any situation awareness (SA). Taking advantages of the autonomous features on the road, we propose to design a framework for cooperative perception and trajectory planning for autonomous driving vehicles that focuses on safely sharing far-sight traffic information ahead on the road with other enabled autonomous vehicles or human-driven vehicles. This project proposes practical solutions that deploy unmanned aerial vehicles capable of taking off any autonomous vehicle, flying at a far range distance from the current vehicle?s spot gatherthering useful information from blind spot, broadcasting selected data to connected vehicles then land back on the its hosted vehicle right after the mission is terminated. Meanwhile, decision-making and planning methods are generated for the autonomous vehicles so that the vehicles navigate in a coordinated fashion using perception capability provided by the UAVs to ensure traffic safety and efficient motion on the road.