Yukiyo Kuriyagawa

A RESEARCH ON ANALYTICAL METHOD OF DRIVER-VEHICLE-ENVIRONMENT SYSTEM FOR CONSTRUCTION OF INTELLIGENT DRIVER SUPPORT SYSTEM

In this study, a driver model with the multiple regression and the neural network is constructed to analyze the relationship between the drivers control action and the information that includes data of vehicle behavior and environment. Using these models, effectiveness of the information to control the action of a driver is examined. To evaluate the intelligent driver support systems, Mental Work Load (MWL) model is constructed with the multiple regression and the neural network. MWL is expressed as Heart Rate Variability (HRV). Measured HRV data and calculated HRV data with MWL model show good agreement. Effectiveness of information is examined using the MWL model. From these results, it is shown that the analytical method with the drivers MWL can be used to assess and improve the intelligent driver support systems as the next stage of this research.

A modeling of heart rate variability to estimate mental work load

Recently, many kinds of machines have been introduced in various fields in our society. We are touching machine systems everyday at various times. Therefore, we need to establish a method of evaluation of comfortable and safe operating conditions in human-machine systems. The authors consider the modeling of heart rate variability to estimate mental work load during driving.

HR Changes in Driving Scenes with Danger and Difficulties Using Driving Simulator

To provide a safe and comfortable driving environment, extracting a variety of stress scenes experienced by drivers and utilizing them for investigating actual causes and ways to assist drivers is effective. To find scenes that could be investigated efficiently in this way, we proposed a method based on changes in a drivers physiological indices that emotional changes may have caused. In this paper, we examined the possibility of applying this method to experimental situations using a driving simulator (DS). An experiment using a DS has an advantage over one done in a real life situation in that the experimental parameters can be controlled. This paper examines the relationship between a drivers emotional changes and physiological changes during driving. As a result, we suggest that whether an event is recognized and how much emotion it caused can be estimated by combining measurements of changes in heart rate (HR), skin conductance (SC), and respiration.

Calculation algorithm for motion control target for the platooning of autonomous heavy vehicles

In this study, we develop an algorithm for the realtime generation of a trajectory for a control target to realize the autonomous steering control needed to realise a platooning system for heavy trucks. The proposed algorithm consists of a driver model, which considers the risk potential, and a vehicle dynamics model. This algorithm was validated through simulations using a vehicle dynamics model with multiple degrees of freedom. In addition, the feasibility of real-time processing for the control target was determined through field tests in which the proposed algorithm was implemented on the control hardware of an experimental vehicle.