Autonomous vehicles require sophisticated software controllers to maintain vehicle performance in the presence of vehicle faults. The test and evaluation of complex software controllers is a challenging task. The goal of this eeort is to apply machine learning techniques to the general problem of evaluating an intelligent controller for an autonomous vehicle. The approach involves subjecting a ...

A neural network model reference adaptive controller for trajectory tracking of nonlinear systems is developed. The proposed control algorithm uses a single layer neural network that bypasses the need for information about the system’s dynamic structure and characteristics and provides portability. Numerical simulations are performed using nonlinear dynamic models of marine vehicles. Results ar...

This thesis presents the system architecture for landing an Unmanned Aerial Vehicle (UAV) from a hovering position without the intervention of a human operator. Through the use of feedback information from a height sensor, the UAV is commanded to perform controlled descent with the desired landing parameters by implementation of the flight control laws. The plant model of the system was determi...

This thesis examines the design and implementation of a vision system for an autonomous underwater vehicle. The vision system consists of three cameras, two being a stereo pair, and the third being attached to a pan/tilt unit to allow it to track moving targets. The goals for the development of the vision system were to: • Design and build all of the hardware for the vision system. The main foc...

An autonomous vehicle can navigate by measuring the light intensity in a known environment, using a prediction and correction cycle. This navigation method is not trivial, so I developed, implemented and tested two different navigation algorithms. The simple navigation function works well, except at some locations which depend on te light illumination function. The advanced algorithm is slower,...

The advent of autonomous vehicles is envisaged to disrupt the auto insurance liability model. Unlike the current model, wherein in the event of an accident, the liability is largely attributed to the driver, autonomous vehicles necessitate the consideration of other entities in the automotive ecosystem such as the auto manufacturer, software provider, service technician and the vehicle owner fo...

Context As autonomous driving technology matures towards series production, it is necessary to take a deeper look at various aspects of electrical/electronic (E/E) architectures for autonomous driving. Objective This paper describes a functional reference architecture for autonomous driving, along with various considerations that influence such an architecture. The functionality is described at...

A system for a real-time estimation of vehicle accident potential damages is proposed with the aim of facilitating autonomous vehicle's embedded computer system to come to the least harmful possible decision if it realizes that an accident is unavoidable. The system analyzes all the possible crashes so the autonomous vehicle will make a decision what the least destructive option is.

The rising popularity of self-driving cars has led to the emergence a new research field in recent years: Autonomous racing. Researchers are developing software and hardware for high performance race vehicles which aim operate autonomously on edge limits: High speeds, accelerations, low reaction times, highly uncertain, dynamic adversarial environments. This paper represents first holistic surv...