Search Results

The purpose of this study is to develop a method for evaluating the safety of the braking control algorithm for automated driving under mixed traffic flow of automated driving system and vehicles driven by drivers. We consider that the automated driving system should be controlled such that it blends in with mixed traffic. Therefore, in evaluating the safety of braking control for the automated driving system when following, the influence of the automated driving system on the driver of the following vehicle is an important evaluation index. First, we analyzed past traffic accidents in Japan to determine a suitable traffic environment for evaluating the safety of the braking control algorithm for the automated driving system when following. Second, the driver’s braking operations were measured using actual vehicles in this situation. We developed a method of generating sample algorithms of braking control based on the driver’s braking operations.

Most driving assist systems are uniformly controlled without considering differences in characteristics of individual drivers. Drivers may feel discomfort, nuisance, and stress if the system functions differently from their characteristics. The present study reduced these side effects for systems with a highly accurate driver model. The model was constructed using Nonlinear AutoregRessive with eXogeous inputs (NARX), which has a learning function and estimates the driving action of a driver. The model was constructed for one driving condition yet can be applied to other driving conditions. If one model can be applied to many driving conditions, a system can construct as minimum requirements. The driver decelerated while approaching the target at the tail of a traffic jam on a highway. A driver model was constructed for the driver’s braking action. The experimental condition was 11 data measurements from 50 to 130 km/h made at intervals of 10 km/h.

Two experiments were carried out to clarify the characteristics of manual driving when the task of vehicle control is transferred from an autonomous driving system at SAE levels 3 and 5 to manual driving. The first experiment involved another vehicle merging into the lane of the host vehicle from the left side of a highway. This experiment simulated the functional limit of a level 3 system with the driver in a situation of low alertness. When the other vehicle changed lane in front of the host vehicle, the driving task was transferred from the system to the driver. The second experiment simulated a driver travelling along a city road with manual driving after the driver used the system in a situation of sleeping on a highway. In this experiment, a pedestrian emerges from a blind spot along a city road, and the driver needs to brake having recently awaken. In the first experiment, the driver with low alertness could not control the vehicle when manually driving.

SAE International defines six levels of autonomous driving system, four of which include a change of control from the system to the driver in certain conditions. When vehicle control changes from the system to a human driver, a safe transition time is necessary. The present study focuses on level 3 automation, in which the system controls driving in ordinary conditions, but the human driver is expected to intervene in emergency situations. The aim of this study was to investigate the relationship between driver posture and transition time. Driver posture included four components: backrest angle, seat position, foot position, and arm position. These were adjusted to investigate a total of 30 posture patterns. In addition, the situation in which the driver was not watching the road, but instead using a tablet computer was investigated. The driver’s braking and steering reaction times were measured for a highway-driving scenario in which a truck dropped cargo in front of the vehicle.

A vehicle-to-vehicle communication system (V2V) sends and receives vehicle information by wireless communication and assists safe driving. The present study investigated the activation timings of collision information support, collision caution support, and collision warning support provided by a V2V in an experiment using a driving simulator for four situations of (1) assistance in braking, (2) assistance in accelerating, (3) assistance in making a right turn, and (4) assistance in making a left turn at a blind intersection. The four situations are common scenarios of traffic accidents in Japan. Safety margins for collision information support and collision warning support were the time required for the driver to fully apply the brake pedal, while the safety margin for collision caution support was the time required for the driver to begin applying the brake pedal. The study investigated the effects of adding safety margins to standard activation timings.

Collision avoidance systems for rear-end collisions have been researched and developed. It is necessary to activate collision warnings and automatic braking systems with appropriate timing determined by a monitoring system of a driver's braking action. Although there are various systems to monitor driving behavior, this study aims to create a monitoring system using a driver model. This study was intended to construct a model of a driver's braking action with the Time Delay Neural Network (TDNN). An experimental scenario focuses on rear-end collisions on a highway, such as the driver of a host vehicle controlling the brake to avoid a collision into a leading vehicle in a stationary condition caused by a traffic jam. In order to examine the accuracy of the TDNN model, this study used four parameters: the number of learning, the number of neurons in the hidden layer, the sampling time with 0.01 second as a minimum value, and the number of the delay time.