This thesis is to study the optimisation problems in autonomous vehicles, especially the modelling and optimisation of collision avoidance, and to develop some optimisation algorithms based on genetic algorithms and neural networks to operate autonomous vehicles without any collision. Autonomous vehicles, also called self-driving vehicles or driverless vehicles are completely robotised driving frameworks to allow the vehicle to react to outside conditions within a bunch of calculations to play out the undertakings. This thesis summarised artificial intelligence and optimisation techniques for autonomous driving systems in the literature.
The optimisation problems related to autonomous vehicles are categorised into four groups: lane change, motion planner, collision avoidance, and artificial intelligence. A chart had been developed to summarise those research and related optimisation methods to help future researchers in the selection of optimisation methods Collision Avoidance is one of streamlining issues in autonomous vehicles. Several sensors had been used to identify position and dangers and collision avoidance algorithms had been developed to analyse the dangers and to use vehicles to avoid a collision. In this thesis, the current research on collision avoidance has been reviewed and some challenges and future works were presented to select the research direction of this thesis, the aim of this research will be the development of optimisation methods to avoid collisions in a predefined environment.
The contributions of this thesis are that (1) a simulation model had been developed using Matlab for collision avoidance and serval scenarios were proposed and experimented with. The sensors are used as the inputs to determine collision in the learning preparation of the algorithm; (2) a neural network was used for collision avoidance of autonomous vehicles; (3) a new method was proposed with the combination of genetic algorithm and neural network. In the proposed frame, the neural network is used for decision making and a genetic algorithm is used for the training of the neural network. The results and experimentation show that the proposed strategies are well in the designed environment.
| Identifer | oai:union.ndltd.org:BRADFORD/oai:bradscholars.brad.ac.uk:10454/19799 |
| Date | January 2022 |
| Creators | Gadinaik, Yogesh Y. |
| Contributors | Not named |
| Publisher | University of Bradford, Faculty of Engineering and Informatics |
| Source Sets | Bradford Scholars |
| Language | English |
| Detected Language | English |
| Type | Thesis, doctoral, MPhil |
| Rights | <a rel="license" href="http://creativecommons.org/licenses/by-nc-nd/3.0/"><img alt="Creative Commons License" style="border-width:0" src="http://i.creativecommons.org/l/by-nc-nd/3.0/88x31.png" /></a><br />The University of Bradford theses are licenced under a <a rel="license" href="http://creativecommons.org/licenses/by-nc-nd/3.0/">Creative Commons Licence</a>. |
Page generated in 0.0024 seconds