Toshiyuki Haramaki

A Device Identification Method for AR-based Network Topology Visualization

It is a crucial issue for a network administrator to quickly and accurately acquire up-to-data network topology information for installing new devices, changing existing routes, and fixing communication failures. In this paper, we propose a network topology visualization system based on mobile AR (Augmented Reality) for assisting the administrator in real working environments. A focus to effectively support him/her is to provide a way for automatically identifying a specific network device he/she is working on and present its latest topology information without interrupting his/her administration tasks. The proposed device identification method estimates the administrators physical location using the signal strength of wireless APs (access points) receivable at the location and makes a guess for candidate target devices such as a group of routers and switches. Next, it narrows down to a specific device among the candidates using a vision-based object identification technique. Then, the system graphically visualizes the network topology information of the identified device through an HMD (Head Mounted Display) device worn by the administrator. The system supports not only senior administrators to efficiently performing complex management tasks, but also juniors and trainees to acquire practical knowledge and skills on network administration.

A Network Topology Visualization System Based on Mobile AR Technology

Effectively managing network infrastructure requires administrators to appropriately understand up-to-data network system status. Accurate understandings are especially crucial when installing new communication equipment and fixing network failures. In this paper, we propose a network topology visualization system based on AR (Augmented Reality) for assisting an administrator in real working environments. The proposed system graphically visualizes network configuration information and physical cabling structure related to a specific network node such as a router or a switch through an HMD (Head Mounted Display) device worn by the administrator. The system supports not only the administrator to efficiently performing the network management task but also trainees to acquire practical knowledge and skills on network administration.

An Edge Computer Based Driver Monitoring System for Assisting Safety Driving.

Driver Monitoring System (DMS) is a promising IoT application in Intelligent Transport Systems (ITS) research field. DMS assists car drivers by monitoring their driving activities, sensing incidents to cause possible dangers, and alerting the drivers to prevent accidents. We aim to realize a new DMS that is inexpensive and highly effective. This paper proposes a method for detecting any incidents based on machine learning. The proposed method firstly configures a detector by training in-car environment data and driver’s vital signs gathered from multiple sensors. Then, the detector is embedded in a self-contained edge computer for monitoring a driver in a car. The device is always connected to the information communication network by radio waves. Those data obtained by monitoring are stored in the cloud server. The server learns and analyzes the stored data using processing such as machine learning. As a result, we acquire knowledge leading to safe driving. The edge computer uses these knowledge to process the sensor data in real time, observe the driver, sense the danger, and call attention. These mechanisms prevent occurrence of troubles such as traffic accidents. The paper describes the proposed system overview, implementation method, and initial evaluations.

A Mobile AR Assistant for Campus Area Network Management

Network infrastructure needs to be managed in response to frequent revisions of organization. VLAN (Virtual LAN) is a key technology for flexibly configuring the network. It enables to reconfigure the network without changing physical cabling for accommodating it to the current organizational structure. Accurately configuring VLAN structure, however, is a complicated task and highly-skilled administrators can only perform the task. In this paper, we propose a mobile assistant for visually administering VLAN configuration using AR (Augmented Reality). When an administrator simply looks at a specific switch device, the proposed system acquires the latest configuration information about the device and graphically superimposes the result. The administrator can also invoke some commands to validate the configuration result without typing them by using the system. It can assist even less-experienced administrators to easily grasp the VLAN configuration and perform some basic management tasks.

A Robot Assistant in an Edge-Computing-Based Safe Driving Support System

In this paper, we describe a robot-based interface for presenting important information to assist safety driving. We have been developing a safe driving support system consisting of various devices for sensing the in-vehicle environment and driver’s vital signals, a set of edge computing nodes for analyzing the sensed data, and actuators for presenting the analyzed results to the driver. Because visual and auditory messages are commonly used in an instrumental panel, an audio system, and a navigation system in the car, adding similar notification methods may hinder the driver’s safety driving operations. We, therefore, propose to use robot motions with voice messages as a new way of delivering important information to the driver. We designed and implemented two sets of the driver assisting methods using a real robot placed in a vehicle and a visual robot aid moving on a monitor screen. We conducted a comparative experiment among the methods to verify their effectiveness and practicality.

A Safe Driving Support Method Using Olfactory Stimuli

Recent progress of IoT technology becomes remarkable and driver monitoring systems with in-vehicle devices is one of promising application field. In this paper, we propose a method for constantly monitoring a driver’s line of sight and warning him/her by sound and scent when it detects a dangerous state due to inattentive driving. Sound is an effective method for instantly alerting some state, but it may become a factor for hindering the driver’s concentration. Therefore, we devised a method for gently presenting the warning as a background information by scent. We developed a driving simulator and conducted experiments for verifying the effectiveness of the proposed method.

A Mobile Wireless Network Visualizer for Assisting Administrators

As a performance index of wireless network, a heat map function for visualizing the distribution of signal strengths received from APs (Access Points) is a useful tool. Existing technologies, however, have some problems such as insufficient automation for acquiring signal information to visualize and inflexibility for dealing with on-demand monitoring requests issued by administrators on site. We propose a practical method for stably monitoring signal conditions in a managed site and efficiently visualizing the observation results. We implement the proposed method based on a light-weight publisher-subscriber communication framework applicable for various IoT applications. It can handle the on-demand monitoring requests for immediately visualizing the latest condition while it is constantly monitoring whole area as a background process. In this paper, we describe background and purpose, implementation detail, and preliminary evaluations of the proposed system.

A Robot Gesture Framework for Watching and Alerting the Elderly

Watching and medical care for the elderly is one of promising application fields of IoT. Humanoid robots are considered to be useful agents for not only relaxing the elderly but also watching and alerting them in a daily life. Detecting and preventing the risk of indoor heat stroke is an important issue especially for the elderly who live alone. A method for reliably conveying the possible danger of the indoor heat stroke to the elderly is a crucial factor to implement a practical system. In this paper, we describe the system for informing unusual conditions to the elderly by using a communication robot that normally gives users healing. We designed and implemented a set of normal and special motions for a desktop humanoid robot and evaluated whether the robot motions effectively make users aware of abnormal situations.

A Real-Time Robot Motion Generation System Based on Human Gesture

When a communication robot conveys some messages to human users, showing some motions matching with the messages is an effective way in human robot interaction. Designing and implementing a set of useful robot motions, however, is a difficult problem. It requires developers to describe instructions for accurately controlling motors embedded in the robot. In this paper, we propose a method for generating robot motions by using human gestures as input. The proposed method captures human gestures in real time by using motion sensors, converting the acquired data to robot motion instructions, and applying them to a physical robot. We developed a prototype system targeted at supporting different motion sensors and robots with lightweight data communication between a control node and a robot. We conducted experiments for controlling the robots by human gestures to verify the effectiveness of the proposed method. It can promote better human robot communication environments with reducing labors in robot motion development.

A Device Status Visualization System Based on Mobile Markerless AR Technology

In order to effectively manage computer and network infrastructure, administrators need to appropriately understand the latest state of the whole system. When managing new servers and communication equipment, accurately grasping current situation is particularly important. In this paper, we propose a status visualization system based on AR (Augmented Reality) which supports administrators in actual management work environments. The proposed system graphically visualizes state information of a specific device such as a server or a network switch via a head mounted display (HMD) worn by a system administrator. It also visualizes logical and physical network structures consisting of servers and switches. This system assists the administrators for efficiently executing computer device management tasks. In addition, it helps them to master practical knowledge and skills related to servers and networks.