Yaw stability control system plays a significant role in vehicle lateral dynamics in order to improve the vehicle handling and stability performances. However, not many researches have been focused on the transient performances improvement of vehicle yaw rate and sideslip tracking control. This paper reviews the vital elements for control system design of an active yaw stability control system; the vehicle dynamic models, control objectives, active chassis control, and control strategies with the focus on identifying suitable criteria for improved transient performances. Each element is discussed and compared in terms of their underlying theory, strengths, weaknesses, and applicability. Based on this, we conclude that the sliding mode control with nonlinear sliding surface based on composite nonlinear feedback is a potential control strategy for improving the transient performances of yaw rate and sideslip tracking control.

No abstract

Active steering control is one of the approach that can be used to improve the vehicle's lateral and yaw stability. By combining active front steering and active rear steering control, the vehicle's handling and stability can be improved via four wheel active steering (4WAS) control. In this paper, a robust control algorithm of sliding mode control is designed for 4WAS vehicle. Single track 2 d.o.f linear model is utilized for controller design and simulation purpose. Simulation for 4WAS and front steering (AFS) is carried out in Simulink for step steer and double lane change maneuver to verify the effectiveness of the proposed control system. The result shows that the 4WAS perform better than the AFS in tracking the desired response trajectory.

No abstract

Tracking an object in night surveillance video is a challenging task as the quality of the captured image is normally poor with low brightness and contrast. The task becomes harder for a small object as fewer features are apparent. Traditional approach is based on improving the image quality before tracking is performed. In this paper, a single object tracking algorithm based on deep-learning approach is proposed to exploit its outstanding capability of modelling object’s appearance even during night. The algorithm uses pre-trained convolutional neural networks coupled with fully connected layers, which are trained online during the tracking so that it is able to cater for appearance changes as the object moves around. Various learning hyperparameters for the optimization function, learning rate and ratio of training samples are tested to find optimal setup for tracking in night scenarios. Fourteen night surveillance videos are collected for validation purpose, which are captured from three viewing angles. The results show that the best accuracy is obtained by using Adam optimizer with learning rate of 0.00075 and sampling ratio of 2:1 for positive and negative training data. This algorithm is suitable to be implemented in higher level surveillance applications such as abnormal behavioral recognition.