Steering Angle Prediction Techniques for Autonomous Ground Vehicles: A Review

Abstract

Unintentional lane departure accidents are one of the biggest reasons for the causalities that occur due to human errors. By incorporating lane-keeping features in vehicles, many accidents can be avoided. The lane-keeping system operates by auto-steering the vehicle in order to keep it within the desired lane, despite of changes in road conditions and other interferences. Accurate steering angle prediction is crucial to keep the vehicle within the road boundaries, which is a challenging task. The main difficulty in this regard is to identify the drivable road area on heterogeneous road types varying in color, texture, illumination conditions, and lane marking types. This strenuous problem can be addressed by two approaches, namely, 'computer-vision-based approach' and 'imitation-learning-based approach'. To the best of our knowledge, at present, there is no such detailed review study covering both the approaches and their related optimization techniques. This comprehensive review attempts to provide a clear picture of both approaches of steering angle prediction in the form of step by step procedures. The taxonomy of steering angle prediction has been presented in the paper for a better comprehension of the problem. We have also discussed open research problems at the end of the paper to help the researchers of this area to discover new research horizons.

Dự Đoán Góc Lái Xe Tự Hành Sử Dụng Mạng Noron Tích Chập Tiên Tiến

“…Thiết kế kiến trúc mạng và tinh chỉnh siêu tham số trong mạng CNN để đạt kết quả tối ưu là vấn đề đang được nhiều nhà nghiên cứu khoa học quan tâm [9]. Năm 2016, nhóm NVIDIA đã nghiên cứu thiết kế mô hình xe tự lái, nhóm huấn luyện sử dụng kiến trúc mạng LeNet, bổ sung hàm kích hoạt, chứa 9 lớp bao gồm 1 lớp chuẩn hóa, 5 lớp tích chập và 3 lớp kết nối đầy đủ [10].…”

How Many Features is an Image Worth? Multi-Channel CNN for Steering Angle Prediction in Autonomous Vehicles

“…Various methods of steering angle predictions of autonomous vehicles have been researched in recent years that include the use of computer vision and deep neural networks [23]. Though the end goal is the same, the approaches differ dramatically.…”

Real-Time Experimental Evaluation and Analysis of PID and MPC Controllers Using HIL Setup for Robust Steering System of Autonomous Vehicles

“…Takagi-Sugeno (T-S) fuzzy model based on a fuzzy Lyapunov control framework for automatic lane keeping under varying system constraints such as unknown crosswinds and varying road curvatures is presented in [12]. Artificial neural networks such as Convolution Neural Network (CNN) and Long-Short-Term-Memory Network are used to predict the steering angle for lane keeping even during poor visibility conditions [13]. A novel algorithm is proposed for automated lane changing using yaw rate, steering angular position, and steering wheel feedback torque from the electric power steering (EPS) system [14].…”