Youchun Xu

A method of stereo obstacle detection based on image symmetrical move

A stereo obstacle detection method based on images symmetrical move and cell partition is presented in this paper. This algorithm gets each cells optimum offset by calculating the minimum non-similarity of cell, and merges Cell of Interests (COIs) to calculate obstacles in the most probably obstacle regions, and gives information of these obstacles. The paper introduces the perspective projection model at first, and then gives two conclusions which are the basic of the algorithm, the part of cell partition and cell optimum offset calculation are presented. Finally, algorithm performance tested by experiment on the test vehicle JJUV-I is shown in the paper.

Traveling path tracking algorithm in virtual coordinate system for intelligent vehicle

This paper proposes a real-time traveling path tracking algorithm for intelligent vehicle. Two encoders are installed on the left and right wheels to measure the rolling distances of the wheels. A virtual coordinate system fixed to the ground is constructed. The calculating algorithm of vehicle position and heading angle in the virtual coordinate system based on the recorded data from encoders is presented. The proposed algorithm is independent on external reference object or the global positioning system and unaffected by culverts, tall buildings, illumination, fog, rain etc. The experimental results show the efficiency of the proposed algorithm.

Study on intelligent vehicle's steering control system using BP neural networks

Using the neural networks algorithms to control automatically is one important direction in intelligent vehicles steering control. This paper presents the installation, mechanical design and processing of intelligent vehicle electronic steering control system. According to the characteristics of intelligent vehicle, the neural networks steering control model is designed, programmed and implemented on computer. Experiments testify the efficiency of the proposed neural networks control algorithms.

A hardware-in-loop simulation test-platform for the intelligent vehicle's steering control system

During the research of intelligent vehicle steering control algorithm, it is extremely dangerous for the intelligent vehicle to do solid trial under high-speed circumstance. According to the Visual C++ and Matlab, a hardware-in-loop simulation test-platform (HILSTP) for the intelligent vehicles steering system has been set up. The test-platform which is designed on the basis of the steering system of the vehicle can manipulate directly the steering mechanism, so it is able to simulate accurately the steering control of the intelligence vehicle under high-speed circumstance. HILSTP can expediently analyze the steering control algorithm, decrease the trial expenses and trial risk, and improve the development efficiency.