This paper proposes an approach to designing an intelligent vehicle controller for partially supporting the driver's operation of a vehicle. Driving can be thought of as a system formed by the interaction between the driving environment, vehicle behavior and the driver's expectations of vehicle behavior. This interaction analysis incorporates the driver's intention model representing knowledge of the driver's particular cognitive characteristics. This model infers driver's intention to accelerate and decelerate. The reasoning method is based on a multipurpose decision-making technique that allows explicit treatment of the driving environment, vehicle behavior and the driver's intentions. Moreover reasoning engine can deal with the difference of driver's individual characteristics for generating intention to decelerate by using both the fuzzy integral and the fuzzy measure. As an example, a control procedure designed with the proposed model is applied to automatic transmission control. The simulation results show good agreement with driving test results.

View full abstract

In this paper a novel system for license plate recognition is presented. To acquire fine images of fast passing vehicles under the illumination condition varied greatly, a sensing aparatus, which is composed of lens, a prism beam splitter, two CCD cameras and a shutter control board, with wide dynamic range has been developed. This aparatus can be applied to fast passing vehicles over a speed of 100km/h in scenes with a 1.5×10⁴ dynamic range. The performance of the developed system has been investigated on passing vehicles under the illumination condition including from the twilight to the sunlight at noon. Obtaining recognition rate 98%, thus the developed system is effective for license plates recognition.

View full abstract

This improvement on functions and performances of exhaust gas sensor should be indispensable to qualify the emission regulation of ULEV. The tubular zirconia cell with limited diffusion layer laminated platinum foil heater on it have been prepared for sensor. The electronic module mainly consists of an ASIC and a single-chip micro-computer. By time shared (4msec) feed back control for constant electromotive force (0.5V) and constant cell temperature (700°C), it have been achieved frequency response (20Hz), warm-up time (5sec) and required on board durability.

View full abstract

This paper describes the preceding vehicle recognition and road-lane recognition methods for the rear-end collision avoidance system (RCAS) which we are developing. These methods are using an edge histogram method based on modelbased vision. The edge histogram method can detect line elements of the objects stably with low calculation cost. When the region of interests for the preceding vehicle and road lanes in the image are established and their projected edge histograms are observed in time series order, we can recognize the positions of the vehicle and the lane. Furthermore, we apply Kalman Filter to their motions and predict their locations for time series detection. Using this stable recognition, we derive a collision time to control the on-board brake system. We show the performance of these methods by experimental results

View full abstract

Air to fuel ratio sensor is used for emission control system of three-way catalyst, and constitutes the important functional part of combustion control system.
For further precise combustion control application, universal air to fuel ratio heated exhaust gas oxygen sensor (UEGO sensor) has been developed.
This paper introduces heater control system for constant element temperature of UEGO sensor.
By the heater wattage feedback control of sensing cell impedance, the change of sensor element temperature is decreased.

View full abstract

This study deals with a method for detection of angular rate by using three set of three-dimensional acceleration sensors. Though the direction of angular rate vector can not be decided, by calculation from centrifugal forces at multiple points the angular rate vector can be obtained. In this paper, the method of calculaton, the error from calculation, and the numerical example of detection are shown. As a result, the method using acceleration sensors for detecting angular rate is not practical in micro sensing system.

View full abstract