This article presents a real-time control system for an agricultural mobile machine (vehicle) based on an on-board vision system using a single camera. This system has been designed to help humans in repetitive and difficult tasks in the agricultural domain. The aim of the robotics applicaton concerns the control of the vehicle with regard to the reap limit detected in image space. The perception aspect in relation to the application has been described in previous work, and here we deal with the control aspect. We integrate image features issued from the modeling of the scene in the control loop to perform an image-based servoing technique. The vehicle behavior described here concerns bicycle and neural models, and three control laws are then synthesized. The first and the second are modeling approaches and use an interaction between the scene and the image space. They are based on the regulation of a task function. The third is a "black-box modeling" technique, and is based on a neural network. Finally, experimental results obtained with these different control laws in different conditions are presented and discussed.