|
|
International Journal of Automotive Technology 2002;3(2): 71-77. |
| LATERAL CONTROL OF AUTONOMOUS VEHICLE USING LEVENBERG-MARQUARDT NEURAL NETWORK ALGORITHM |
| K. B. Lee, Y.J. Kim, O. S. Ahn, Y. B. Kim |
| Chonnam National University |
|
|
|
|
|
| ABSTRACT |
|
A new control method for vision-based autonomous vehicle is proposed to determine navigation direction by analyzing lane information from a camera and to naigate a vehicle. In this paper, characteristic featured data points are extracted from lane images using a lane recognition algorithm. Then the vehicle is controlled using new Levenberg-Marquardt neural network algorithm. To verify the usefulness of the algorithm, another algorithm, which utilizes the geometric relation of a camera and vehicle, is introduced. The second one involves transformation from an image coordinate to a vehicle coordinate, then steering is determined from Ackermann angle. The steering schme using Ackermann angle is heavily depends on correct geometric data of a vehicle and a camera. Meanwhile, the proposed neural network algorithm does not need geometric relations and it depends on the driving style of human driver. The proposed method is superior than other referenced neural network algorithms such as conjugate gradient method or gradient decent one in autonomous lateral control. |
| Key Words:
Back-propagation algorithm, Levenberg-marquardt algorithm, Sobel method, Autonomous vehicle, Lateral control, Vision system, Ackermann angle |
|
|
|
Preview
Full text via DOI 
Download Citation 
Print 
