Search Results

Recently, a number of researches on detecting such inattentive driving have been carried out, and various detection methods have been proposed. In this paper, using driving data which can be measured with existing on-board vehicle sensors, the authors focus on headway distance behavior which relates to rear-end collision as well as the steering behavior which can be used to detect driver drowsiness. The emphasis of this study is that the inattentive driving can be potentially detected from the driving behavior deviated from the normative characteristics considering the transfer function from the environment to the driving operation. Therefore, intrusive measurement methods such as physiological measurement are not required. In addition, to detect the inattentive state by the criterion of the individual driver, the driver assistance system can be realized in the way that it can be adapted not only to various types of drivers, but also to the driver real-time driving state.

This paper describes the classification algorithm of the driving steering intention based on brain-computer interface (BCI) using electroencephalogram (EEG). The classification algorithm of the driving steering intention was examined and developed. Experiments were conducted with 3 able-bodied subjects using driving simulator (DS). The drivers were instructed to operate the vehicle according to the series of three kinds of instructions (right steer, left steer, and straight running). Those instructions were given to the subject with random order, after the operation trigger had been signaled. The off-line analytical result shows that the driver's steering intention can be classified at the averaged probability of about 80%.

In Japan, the number of occupant fatalities has decreased at high ratio due to the development of passive and active safety technology in recent years. However, the pedestrian fatality is still the major proportion of fatalities according to the statistics of traffic accident. Therefore, it is important to study and develop active safety technologies which target to pedestrian. By analyzing the traffic accident statistics, narrow road in urban area is one of the dangerous parts for pedestrian. And the dangerous case that pedestrian often gets into an accident is while crossing road outside of crosswalk. This study focuses on accidents which are caused by pedestrians suddenly crossing narrow urban roads. In such cases, drivers need to drive carefully, preparing for sudden crossing or unexpected dangerous behavior of pedestrians. Therefore, it is important for drivers to predict the accident risk due to the crossing pedestrian behavior in such narrow roads.

Existing driver assistance systems are based on averaged characteristics of drivers, so the systems may cause sense of discomfort to some drivers and the effectiveness on accident prevention degrades due to low system acceptance. To deal with this issue, an individual adaptive hurry driving detection system is proposed in this research. We proposed the detection method of hurry driving using hierarchical Bayesian model. Urban driving data are collected by a continuous-logging drive recorder (DR). Features of hurry driving behavior extracted by hierarchical Bayesian method. The probability of hurry driving state is estimated by using this model using this model.

Although wandering phenomenon of passenger and commercial cars is often experienced on damaged and dented roads, this phenomenon has not been theoretically studied so far. The objectives of this paper are to show, using linear stability theory, how and why the wandering phenomenon occurs. Firstly, the fourth order characteristic equation of a car running on a damaged road surface, taking the cross profile into account, is derived to theoretically analyze the running stability. Secondly, according to root locus analysis of the characteristic equation, it is clearly found that the vehicle body fluctuation on dented roads is much influenced by the forward velocity, the wheel track depth, and the vehicle parameters. Thirdly, a first order preview driver model is introduced to discuss the performance of the closed-loop system of driver-vehicle during lane changes.

This study focuses on the scene that a vehicle overtakes a pedestrian in a narrow road in an urban area and proposes the safety index that shows the appropriate driving behavior in the target scene. Moreover, this study evaluates the validity of the index by experiments. In the target scenes, drivers need to drive carefully, preparing for the latent risk that the pedestrians may start crossing the roads suddenly. In other word, the vehicles must reduce the speed in order to be ready to avoid accidental contacts with pedestrians in case the pedestrians start crossing the road suddenly. However, according to the pedestrian model proposed by the authors in the previous study, the crossing angles of pedestrians are unpredictable. Therefore, the drivers must drive with such speed that the vehicle can avoid an accidental contact by braking even if the pedestrian start crossing the road at any angle.

This study aims to clarify the principal causes of head-on collisions and to establish a reference model when passing through unsignalized intersections without the right of way. The experiment was conducted on the test course using the experimental vehicle to collect driving data of expert drivers. The relation between the vehicle velocity and the face angle versus distance from the stop line was clarified and the characteristics of the safety confirmation behavior were obtained by analyzing driving data considering with driver's eye gaze.

This paper aimes to develop a driver model describing driver's decision and control process during right-turning at signalized intersections from the standpoint of Man-Machine Interaction. Based on the results of accident analysis and experiments, a driver model described by Fuzzy Theory, which consists of linguistic If-Then Rules and Membership Functions, is developed to simulate the decision and control process of drivers. The major results are (1) the right-turning accidents are mainly due to driver errors of recognition or evaluation for opposing-through vehicles, (2) the fuzzy driver model, which consists of membership functions for subjective recognition and judgement and control rules for forward speed, is capable to simulate the real driver behavior, and (3) the characteristics of the driver's fuzziness of vehicular controls are shown by membership functions compared with experimental results.

Steering reaction torque is one of the most important types of information for drivers since it has significant influence on vehicle maneuverability. Even with today's advanced simulation technology, however, it is very difficult to accurately simulate steering feeling. The purpose of this study is to develop a steering Hardware-in-the-Loop (HIL) simulator that can quantitatively evaluate steering systems. This simulator can control the force on the tie rod with simple mechanism. The validity of this HIL simulator has been ascertained by comparing the simulation results with those obtained during actual vehicle testing.The preliminary research concerning the advanced simulators based on the developed HIL simulator is also reported.

This study proposes a method for presenting maneuver request information of accelerator pedal to a driver via the accelerator pedal itself. By applying periodic force like vibration on an accelerator pedal, information is transferred to the driver without displacing the accelerator pedal. In this study, the authors focus on a saw-tooth wave as the periodic force. When the saw-tooth-waved force is applied on the accelerator pedal, a human driver feels as if the accelerator pedal is knocked by someone periodically. In addition, information about the quantity of requested maneuver can be transferred by the amplitude of the saw-tooth wave. Based on these facts, the saw-tooth wave is modified and optimized empirically with ten human drivers so that the information of direction is transferred most reliably. In addition, the relationship between the amplitude of the saw-tooth wave and requested quantity of the pedal maneuver that the drivers feel is formulated.