Keiji Aoki

Neural network control for automatic braking control system

Abstract We have developed an automatic braking control system for automobiles applying a three-layer neural network model. This system enables the vehicle to decelerate smoothly and to stop at the specified position behind the vehicle ahead. This paper focuses on the use of the three-layer neural network model in the automatic braking control system. Because vehicle dynamics is varied by the variations in road conditions or vehicle characteristics, it cannot be represented accurately by mathematical models. According to this reason, the conventional control methods, such as proportional integrative derivative (PID) control, cannot achieve satisfactory control performance. Therefore, we have constructed the neural network adaptive control system based on the feedback error learning method. This learning method enables the system to adapt to the changes in road grade and vehicle weight without using any specific sensors. Experimental results show satisfactory control performance and reveal that the neural network adaptive control system based on the feedback error learning method is available for the automatic braking control system.

TOYOTA'S NEW SINGLE-CHIP MICROCOMPUTER BASED ENGINE AND TRANSMISSION CONTROL SYSTEM

Toyota succeeded in the fall of 1984 in manufacturing a complex engine and transmission control system using a newly developed single-chip microcomputer. This microcomputer, equipped with an 8K-byte ROM (Read Only Memory) and a 256-byte RAM (Random Access Memory), a powerful real time processing function, and a high-speed optimum instruction set, is better suited for automobiles. Application of the latest CMOS technology has enabled lower power consumption and improved noise immunity. The new system, which includes a new function, the electronic spark advance with knock control in addition to the conventional sophisticated system, has greatly improved the performance and driveability of vehicles. The newly designed electronic control unit (ECU) has been greatly improved in reliability and has not changed in its size with the adoption of the highly integrated new microcomputer, which is due to the fact that it uses fewer LSIs (Large Scale Integrated circuits) than the conventional ECU, although it includes the great additional function.

A Preview Steering Control Strategy Based on Computer Vision for Automated Vehicle Highway Systems

This paper describes how a vision based lane tracking control system using a correlation image processing was developed for an automated vehicle highway system. Successful lane tracking during curved roadway was made by preview steering control strategy based on an LZ feedback control and adaptive feedforward control with a neural network.

ELECTRONIC ENGINE CONTROL SYSTEMS FOR THE SMALLER PASSENGER CAR

The objective of this study is to clarify the requirements for an engine control unit and a control strategy in case these systems are applied to smaller engines and smaller vehicles and where high accuracy of control is needed. An experimental control unit has been developed. Both transient and steady state compensation controls for fuel injection and ignition timing have been investigated. The requirements for conversion time of the analog to digital converter, the interpolation logic for crank angle signal, and the compensation circuitry have been clarified. The effectiveness of the compensation control, asynchronous fuel injection, and the adaptive control of air to fuel ratio have been demonstrated.