Vision-Based Adaptive Cruise Control in Vehicle Platooning Navigation

Abstract

The vehicle platoon can significantly slow down the traffic congestion and improve the traffic efficiency, the driving safety and fuel economy. It is an important means to solve traffic safety problems. The monocular cameras can be used in the vehicle platoon systems for determining the distance to a front vehicle. The distance is used in the vehicle controller to control the vehicle platoon. Removing the background is an effective way to improve the accuracy and speed of detecting the vehicle or license plates. The cameras are installed on the vehicle, so the object detection algorithms for dynamic scenes is crucial. The vison-based front distance measurement method is effective in creating low-cost systems or as a failsafe method to provide system reliability under sensor failure. Since vehicle platoon control system has uncertain and nonlinear, it is significant to study the cooperative control problem of uncertain nonlinear vehicle platoon systems. The consensus and containment are two fundamental problems in cooperative control. The main research works of this dissertation are summarized as follows: A fast and effective moving object detection method for a moving camera is proposed. The global motion is estimated through tracking the grid-based key points using optical flow. After the motion compensation, the background model, candidate background model and candidate age are used for the background modelling. Then the local pixel difference and the consistency of local changes between the current frame and the background model are used for the background subtraction. The lighting influence threshold and the local pixel difference between the current frame and two previous aligned frames are used to reduce the lighting influences. Finally, Gaussian filter, connected-components analysis, erosion and dilation are used to refine the results. The performance evaluation shows that this proposed method works very fast in real time and has competitive results compared with others in the public dataset. A front vehicle distance measurement method is proposed. It locates the license plate of the front vehicle in the moving object area after removing the background. The license plate is positioned by extracting the texture in the vertical direction of the license plate area. The front vehicle distance is estimated from the observed license plate height by using the logarithmic equation with three fixed parameters. An adaptive consensus control method of second-order nonlinear systems with output constraints is proposed. It guided by an active leader. Backstepping design combining with fuzzy approximate technique is employed in the consensus control design. A command governor is introduced to generate an optimal virtual control signal, which is able to balance the virtual control law and the actual velocity signal. The optimization problem is solved via a recurrent neural network. A barrier Lyapunov function is utilized to guarantee the uniformly ultimately bounded control of the closed-loop systems without violating the output constraints. A containment control method for uncertain nonlinear multi-agent systems is proposed. The followers are governed by nonlinear systems with unknown dynamics while the multiple leaders are neighbors of a subset of the followers. Fuzzy logic systems (FLSs) are used to identify the unknown dynamics and a distributed state feedback containment control protocol is proposed. This result is extended to the output feedback case, where observers are designed to estimate the unmeasurable states. Then, an output feedback containment control scheme is presented. The developed state feedback and output feedback containment controllers guarantee that the states of all followers converge to the convex hull spanned by the dynamic leaders.