Survey on Autonomous Vehicles using Artificial Intelligence

With large-scale expansion in the field of Artificial Intelligence, there has been an increase in the attempt to study and implement said concept into the development of Autonomous Vehicles (AVs). It has been documented that Autonomous Vehicles have the potential to rapidly decrease the human tendency to cause manual errors that may result in accidents. Therefore, one of the sole purposes of introducing an efficient Autonomous mechanism towards the driving process is to provide a convenient and accident-free vehicle-riding experience. While several surveys led to the discovery of various techniques such as Deep Learning, Q-Learning and so on for the development of AVs, these techniques also come with their own set of pros and cons. However, there is also a need for the investigation into the efficiency of these algorithms, in terms of parameter volume, latency, ability to handle hard tasks and various other factors. It has also been observed that the vast majority of these approaches employed the usage of cameras fitted on the exteriors of vehicles in order to recreate the various scenarios, terrains and riding-circumstances that may be encountered under real-time commutation.