Search Results

This paper describes a longitudinal control method with an Adaptive Cruise Control (ACC) system using a wheel torque management technique. The wheel torque management technique can control vehicular speed by the following procedure without tuning parameters. First, the ACC module calculates a command speed from a desired headway distance and from output data of the radar sensor. Secondly, it calculates a required wheel torque to take the command speed, current speed and running resistance into consideration. Thirdly, the management module controls actuators based on the command wheel torque and characteristics of each vehicle. If the required wheel torque is positive, the management module orders adjustment of the throttle opening position and a change of the gear ratio in the automatic transmission. If the command wheel torque is negative, the management module activates the electronic brake in accordance with the magnitude of the command wheel torque.

A new automotive vision platform has been developed for practical applications. The vision platform simultaneously realizes high-performance computing power and reliability for automotive use by using a newly developed dedicated image processor. The developed processor has specialized and novel hardware allowing it to process a large amount of image data at high speed under a moderate clock frequency. The vision platform has enough capability to process multiple applications at the same time. In this paper, we describe the unified memory architecture in the vision platform. We introduce specific functional units for various applications such as the edge analysis unit. We report results from experiments with a real-time on-board lane recognition system.