Naohisa Hashimoto

The Application of RTK-GPS and Steer-By-Wire Technology to the Automatic Driving of Vehicles and an Evaluation of Driver Behavior

Automatic vehicle driving has long been the subject of research efforts designed to improve the safety and efficiency of automobile transportation. In recent years, increasingly sophisticated sensors and automobiles have brought automatic driving systems closer to reality. In this paper we describe an attempt to apply real-time kinematic GPS (RTK-GPS), a highly precise positioning system, and steer-by-wire body technology, which has advanced greatly in recent years, to automatic driving. In addition, we also describe the results of research into human factors related to automatic driving, which will become more and more important as automatic driving is put to practical use.(A)

Spectral Collaborative Representation based Classification for hand gestures recognition on electromyography signals

In this study, we introduce a novel variant and application of the Collaborative Representation based Classification in spectral domain for recognition of the hand gestures using the raw surface Electromyography signals. The intuitive use of spectral features are explained via circulant matrices. The proposed Spectral Collaborative Representation based Classification (SCRC) is able to recognize gestures with higher levels of accuracy for a fairly rich gesture set. The worst recognition result which is the best in the literature is obtained as 97.3\% among the four sets of the experiments for each hand gestures. The recognition results are reported with a substantial number of experiments and labeling computation.

An experimental study on vehicle behavior to wheel chairs and standing-type vehicles at intersection

Many researchers have been trying to solve the traffic problems. One solution to these problems seems to reduce traffic volume in urban area. In order to reduce it, people should consider the modal shift to the public transportation and personal mobility. As new personal mobility is developed and spread into the real world traffic, we need to estimate the effect of personal mobility on vehicle drivers and systems. Also, some traffic accidents at intersections lead to fatal accidents. One of the large percentages of fatal accidents is that the vehicle which is turning right in an intersection (turning left in Japan), hits a pedestrian crossing at the crosswalk. The objective of this research is to investigate the behavior of vehicle drivers to personal mobility at the intersection. Four personal vehicles, which can be used on crosswalk, were employed as personal mobility. We measured the distances between the vehicle, which is turning left, and a personal vehicle at the intersection when a personal vehicle crosses at the crosswalk. The multiple experiments were performed in the public area. Experimental result shows that the distance drivers would like to keep to pedestrian is the minimum in comparing to the distances to other personal vehicles. From this result, it is assumed that drivers might be confused about small personal vehicles, and stop own vehicles shorter, and would like to keep longer distance than usual. This experimental data is valuable for pedestrian and personal vehicle detection system and human machine interface.

Automated Vehicle Mobile Guidance System for Parking Assistance

A new concept that a vehicle, which does not have fully automated functions but has partial intelligent functions, is manually or automatically guided to an assigned destination position with a guidance system has been proposed. This paper describes the concept of the system and reports the experimental results of the guidance to a parking space with the proposed system. The experimental study has been conducted to show the feasibility of the system proposed. In the experiments, a vehicle was guided with a mobile guidance system that measures the position and the heading of a guided vehicle to instruct it the steering and the velocity to its goal. The system is featured by that a few intelligent mobile guidance systems will assist many ordinary vehicles in dedicated areas including parking lots.

Smartphone-based two-wheeled self-balancing vehicles rider assistant

This paper presents an approach to a driver assistant system for a two-wheeled self-balancing mobility vehicles in particular for a Segway. The approach is aimed for the readily available mobile devices, which become a part of our daily life such as a smartphone or a tablet. If a mobile device is well-positioned on a mobility vehicle, its front and rear cameras can be utilized as sensors to capture the ride related information about the riders intention(s) and the interaction of the rider with the environment. In addition, attached to the handle bar of the mobility vehicle, this mobile device can be used to alert the driver using the motion and location sensor as well as cameras and gather ride characteristics. In this study, we describe a context-aware system that continuously observes both the rider and the dynamical characteristics of the ride and provides alerts to the rider anticipating the hazards, collision, the route of the other public road users, and the stability of the current ride characteristics.

A Cooperative Assistance System Between Vehicles for Elderly Drivers

In this paper, the authors propose a cooperative driver assistance system for elderly drivers. The proposed system involves the assisted vehicle, referred to as the guest vehicle, and the assisting vehicle, known as the host or escort vehicle. Using vehicle to vehicle communications, the host vehicle, typically driven by an experienced driver, assists the the guest vehicle, which is usually driven by an elderly driver. The paper discusses the characteristics of elderly drivers, the concepts of assistance and the cooperative driver assistance, as well as the experiments and their evaluations.

Elderly Driver Assistance Systems with Cooperation between Vehicles: the Concept and Experiments

This paper proposes a new concept of elderly driver assistance systems, which performs the assistance by the cooperative driving between two vehicles, and describes some experiments with elderly drivers. The assistance consists of one vehicle driven by an elderly driver called a guest vehicle and the other driven by a assisting driver called a host vehicle, and the host vehicle assists or escorts the guest vehicle through the inter-vehicle communications. The functions of the systems installed on a single-seat electric vehicle are highly evaluated by subjects of elderly drivers in virtual streets on a test track.

A signal pattern recognition approach for mobile devices and its application to braking state classification on robotic mobility devices

Personal Mobility Robots, such as the Seqway may be the remedy for the transportation related problems in the congested environment, especially for the last and first mile problems of the elderly people. However, the vehicle segmentation issues for the mobility robots, impede the use of these devices on the shared paths. The mobility reports can only be used in the designated areas and private facilities. The traffic regulatory institutions lack robot-society interaction database. In this study, we proposed methods and algorithms which can be employed on a widespread computing device, such as an Android tablet, to gather travel information and rider behavior making use of the motion and position sensors of the tablet PC. The methods we developed, first filter the noisy sensor readings using a complementary filter, then align the body coordinate system of the device to the Segways motion coordinate. A couple of state of the art classification methods are integrated to classify the braking states of the Segway. The classification algorithms are not limited to classification of the braking states, but they can be used for other motion related maneuvers on the road surfaces. The detected braking states and the other classified features related to the motion are reflected to the screen of the Android tablet to inform the rider about the riding and motion conditions. The developed Android application also gathers these travel information to build a National database for further statistical analysis of the robot-society interaction. A mobile application is developed for classification of braking states.The Sparse and Collaborative Representation based Classifications are used.The developed signal filtering and classification modules is accurate and robust.The application can be used to classify different dynamical maneuvers of mobility devices.

A framework of fault detection algorithm for intelligent vehicle by using real experimental data

Automated vehicles have a possibility to contribute more capacity, safety, low emission and high efficiency to transportation. However, unstable conditions of the automated system can cause serious problem, thus the automated vehicle requires high reliability. The objective of this research is to develop algorithms of fault (unstable condition) detection for automated vehicles, and to improve the overall reliability of the system. In this study, we initially solved and updated identification of some pattern of data constellations under normal and unstable conditions through the experiments in a real world. The multiple experiments were done in the public area (course distance is about 1.1[km]) with some times, where some pedestrian, bicycles and other robots coexisted. The method of detecting faults utilizes mahalanobis distance, correlation coefficient and linearization in order to improve the reliability of detecting the faults correctly, because real experimental conditions include some random noises, and the method must be robust for the changing conditions. The feature of this study is to utilize the experiment results in real world, construct the algorithms and evaluate it. The simulations were done with the real experimental data, in order to evaluate it. The simulation result shows that the proposed system detects faults correctly, and it proves the validity of the proposed method proved.

Application for a Personal Mobility Sharing System Using Two-Wheeled Self-balancing Vehicles

To solve urban area traffic problems, one potential solution is to reduce traffic volumes. In order to do so, a modal shift from conventional passenger vehicles to public transportation and eco-vehicles, including personal vehicles, should be considered. We propose a personal mobility sharing system using the Segway. To evaluate this system, it is necessary to perform experiments under real conditions and gather experimental data for a social pilot study. This study introduces an application for a personal mobility sharing system using the Segway-type vehicle. The main feature of the proposed application is to gather and store experimental data on mobility sharing, and to assist a driver to use the Segway-type personal vehicle safely. Each vehicle is equipped with a tablet, on which the application is installed.