A Survey of Deep Learning Applications to Autonomous Vehicle Control

Abstract

Designing a controller for autonomous vehicles capable of providing adequate performance in all driving scenarios is challenging due to the highly complex environment and inability to test the system in the wide variety of scenarios which it may encounter after deployment. However, deep learning methods have shown great promise in not only providing excellent performance for complex and non-linear control problems, but also in generalising previously learned rules to new scenarios. For these reasons, the use of deep learning for vehicle control is becoming increasingly popular. Although important advancements have been achieved in this field, these works have not been fully summarised. This paper surveys a wide range of research works reported in the literature which aim to control a vehicle through deep learning methods. Although there exists overlap between control and perception, the focus of this paper is on vehicle control, rather than the wider perception problem which includes tasks such as semantic segmentation and object detection. The paper identifies the strengths and limitations of available deep learning methods through comparative analysis and discusses the research challenges in terms of computation, architecture selection, goal specification, generalisation, verification and validation, as well as safety. Overall, this survey brings timely and topical information to a rapidly evolving field relevant to intelligent transportation systems.

A Low-Cost Platform for Modeling and Controlling the Yaw Dynamics of an Agricultural Tractor to Gain Autonomy

“…where (21) being positive shows that it is continuously decreasing along any path and its negative derivative, ensuring asymptotic stability as shown below…”

“…In [19,20], discussions are presented regarding the state of the art in autonomous driving vehicles focused on the top 20 countries in the world, dividing the autonomy into six levels based on the difficulty to be handled in the design of driverless vehicles, including different technologies equipped such as sensing, positioning, vision, and vehicular networks. Another survey is presented in [21], focusing on deep learning methods for autonomous vehicle control.…”

A Mental Simulation Approach for Learning Neural-Network Predictive Control (in Self-Driving Cars)

“…A survey of Deep Learning methods for vehicle control has been recently proposed [16]. The review acknowledges two broad categories: supervised learning and reinforcement learning.…”

“…Furthermore, if a model is required to create a safe training environment, that same model could be, in principle, exploited in a much more efficient way than trial and error. So far, no example of high-quality low-level vehicle control transferred to real vehicles is given in [16].…”

A Deep Learning Approach Towards Railway Safety Risk Assessment

“…In this section, we attempt to assign the previous works to various subsections; however, their topics are scattered across many fields and include a variety of perspectives. CNNs have been widely applied in a wide range of visual computing applications, including signal processing [34], [35], speech recognition [36], medical imaging [37]- [42], object detection [43]- [47], face recognition [48]- [51], robot control [52], [53], autonomous driving (AD) and control [53]- [55] crash detection, risk estimation and traffic monitoring [56], [57]. Some models have even been implemented on mobile devices, such as Google's FaceNet [58] and Facebook's DeepFace [59], which are used for face recognition [60], [61].…”