Yuichi Yaguchi

• Doctor of Philosophy (Computer Science and Engineering)
• Professor (Associate) at University of Aizu

The accurate 3-D map construction applicable to a robot navigation on outdoor irregular terrains is promising technology for future disaster response. We have performed the experiments of the 3-D mapping of such irregular terrains equipped in Fukushima Robot Test Field using the man-powered movable wagon. The 3-D maps are constructed by LIDAR-SLAM...

This research proposed to develop a rover system that follows a human and runs in a platoon for the disaster response. In the case of this system, we need non-collision route planning avoidance actions to prevent collisions and know the route accurately. In this paper, we developed a system that uses a flocking algorithm to prevent collisions and R...

This research aims to discuss how to obtain the number of commands needed to control a mind drone from Electroencephalogram (EEG) signals. The brain-computer interface (BCI) analyzes brain waves to identify human emotions and brain perception and control locations. To use this technology, when a specific thought or stimulus is received, its brain w...

The purpose of this research is to verify the construction of a large-scale simulator, which is necessary when verifying an unmanned air traffic control system that manages a large number of UAVs. Therefore, in this study, we connected a number of systems that simulate actual aircraft with ROS to the simulator built with Gazebo, and verified how ma...

We are currently facing a “labor crisis,” particularly in the field of logistics, because of reductions in the labor force. Therefore, industries must make their logistics more efficient by utilizing autonomous mobile robotics technologies. This paper proposes a hierarchized map concept that makes unmanned delivery tasks which use multiple autonomo...

This paper discusses security development methods for the development of unmanned aircraft systems. By organizing the cases of unseen flights and comparing the standards of manned aircraft and remote control systems, we explore the procedures of security development that contribute to the development of unmanned aircraft systems. We will also defin...

We propose the development of a coverage flight planner that solves the domain coverage problem for the use of multicopters in wide-area surveys and other applications. In such multicopter application cases, collision-free and efficient coverage flight path planning is necessary. In this paper, two approaches to domain decomposition are separated a...

The 3-D mapping data are necessary information for autonomous robot navigation. We progress a study to construct a 3-D point cloud map with extensive range and high resolution using two LIDARs which cover horizontal and vertical ranges. In this paper, we target construction of a calibration method to obtain parameters of coordinate conversion to in...

The IoRT (Internet of Robotic Things) system is a “system of systems” consisting of multiple layers such as robots, cloud, and networks. In most cases, separate solutions are used for each elemental system. On the other hand, the ZeroMQ messaging middleware enables us to develop each elemental system in an IoRT system comprehensively with a single...

In this research, we construct a lightweight and highly reliable flight reservation system of autonomous distributed unmanned aerial vehicle traffic management system (UTM) using Blockchain technology on a small PC such as Raspberry Pi. The current UTM system is almost centralized, but it needs so much data size should the system control which is c...

We are now facing labor crisis especially in logistics area because of the quickly shrinking population of working-age. Therefore, we must make logistics more efficient by utilizing robotics technologies. This paper proposes a method to plan local and global paths more effectively using hierarchized “maps”. By using this method, an autonomous mobil...

This paper proposed a case study of robotization using OpenRTM-AIST for the cloud observation system as Internet of things. We target to construct a remote management system for agricultural settlement sewage treatment facility in this study. We have already constructed cloud based remote observation system for them, and we try to add some remote s...

The autonomous navigation of multiple robots for application in disaster and accident areas and services such as delivery is important topic. For the navigation, a robot should have map data to identify surrounding environment and the obstacles and plan the robot path. Then, sharing of the map data among multiple robots through access to common ser...

On Internet of Robotic Things (IoRT), various robot systems are connected through the Internet. We need a transforming gateway to exchange data between heterogeneous robot systems to build IoRT systems. Generally, the gateway functions are integrated into robot systems or IoRT platforms. However, the incorporation of gateway functions requires a lo...

With the large number of web services now available via the internet, web service discovery has become a challenging and time-consuming task. Organizing web services into similar clusters is a very efficient approach to reducing the search space. A principal issue for clustering is computing the semantic similarity between services. Current approac...

In mobile robot navigation, restoration of the environment around the robot in a 3-D map is necessary for self-location, route planning, and detecting surrounding obstacles. We construct the 3-D color environmental map using both camera images and laser scanner (LIDAR) point cloud data. In the map, the RGB values are provided to the LIDAR point clo...

This paper proposes a waypoint navigation method with collision avoidance using an artificial potential method on random priority. To establish a multi-robot navigation system that consists of various tasks, the navigation system needs to avoid collisions by communicating with each robot path on-site. Robots have an autopilot system that includes w...

We report on the study of 27 drones to do the same work in one place at the same time on the basis of 'mesoscale meteorological measurement by 27 unit drone fleets' by project for promoting business Provincial Reconstruction practical development, Fukushima innovation coast. In this fiscal year's verification, at the Fukushima Robot Test Field, we...

The main objective of our research is to construct an evaluation scheme for a use case of mind drone interface (MDI). Moreover, in order to judge whether the evaluation scheme is appropriate, we would like to consider the safety margin of MDI at the time of approaching the crisis. Several research work and projects have already proposed MDI, but st...

MQTT is a very simple messaging protocol. This causes messaging systems to get high performance and low power consumption, and therefore MQTT protocol is suitable to construct IoT/IoR systems. However, the messaging performance is not only objective for IoT/IoR systems. In some cases, the quality of messaging service is more important than the mess...

Since 2018, we have a project the "Developing the high altitude drone fleet for gathering 3-D mesoscale meteorological information" adopted as a subsidy for Fukushima Innovation Coast Concept Promotion Facility Development. In this research, we develop a telemetry and command communication system for inexpensively manufacturing 920 MHz low power sm...

Acquisition of the 3-D environmental map via a cloud system is an important topic to operate multiple robots under the environment because the existing map can be shared for self-location of the robot, route planning and detection of obstacles without creating a new map. We have developed the system loaded on the movable robot to acquire the 3-D en...

Drones are being increasingly used to create new services and support the expansion of existing applications based on communication networks due to their flexibility and potential coverage. However, drone control and safety guarantees are difficult to attain, especially when drones fly beyond visual line of sight. To address this problem, we consid...

RTSystemEditor is the main standard management tool for RT systems on OpenRTM-aist. It is very easy for beginners to use the tool because it has GUI. However, it takes time from startup of the editor to activation of RT systems. Thus the tool has both merits and demerits for users. Moreover, it is very difficult to manage multiple RT systems distri...

This paper proposes a study of secure development design for cloud based UAS. Drones are now widely usage for industries, but still UAS and drones are less consideration of the secure development method or design for the machine, communication and application. We survey some relative researches for security design of IoT and connected vehicles, the...

We have constructed a system to visualize situation of a falling accident of the unmanned aerial vehicle (UAV) and a surrounding environment along an orbit of the UAV. In the system, the orbit of the UAV is displayed using the positional and attitudinal data recorded in the flight recorder. The color of the orbit varies depending on some parameters...

To develop a measure of streaming video quality for remotely operated robots, we need to know the critical factors for the quality of control. Controlling robots remotely is crucial for disaster response, and many attempts have been made to create such systems. Wireless communication, which is used in remote-control systems for unmanned vehicles, c...

Our goal was to analyze accidents of unmanned aerial vehicles (UAVs) by replicating their circumstances, using data obtained from the sensors and flight recorder installed on the UAVs. In this paper, we investigated the performance of three tools for 3-D mapping to reproduce the surrounding environment along the path of the UAV, and found that LIDA...

Networked robotics involves a collection of robots working together to perform complex tasks such as search and rescue task in disaster management. Because such tasks are beyond the capacity of a single powerful robot, networked robotics has been widely researched. However, the modes of cooperation in traditional networked robotics have been restri...

Current solutions of computation offloading for cloud robotics face challenges: 1) traditional approaches do not consider the characteristics of networked cloud robotics (NCR)(e.g., heterogeneity and robotic cooperation); 2) they fail to capture the characteristics of tasks in a robotic streaming workflow (RSW) (e.g., strict latency requirements an...

Latency is one of the most important factors to the overall performance of cloud robotics. In this paper, we propose a latency-aware computation-offloading algorithm for cloud robotics. We first propose a novel framework of networked cloud robotics. Then we formulate the latency-aware computation-offloading problem, and develop a MILP-based algorit...

We propose that cloud base RTM for improve usability and reduce number of steps for learning cost. In this paper, we build a RTM environment for Raspberry Pi with cloud RTM environment that environment can be automatically deployed to Raspberry Pi. We suggest auto deploy with Web UI make better for building RTM environment.

If an accident happens on the drone flight, the flight recorder system is helpful for finding causality of crush. However, the general flight recorder system can not restore flight route in detail because it is not monitored environments by the camera. In this paper, we will propose to restore a system which uses 3D scenes using a monocular camera....

In this research, we investigate what camera settings are effective for an indoor automatic search system. We recommend installing RGB cameras with depth sensors like the Kinect and show how they should be installed to facilitate searches in indoor environments such as buildings with multiple floors. To validate camera configurations, the RTA* algo...

This paper proposes to construct the software components for robot prototyping support using the FaBo sensors. The Fabo sensors are prepare for the prototyping and studying Internet of Things, and these sensors are useful to use robotics to implement as Internet of Robots or Cloud Robotics. We implement this sensor on the OpenRTM-Aist, robot middle...

In this research, we construct a generalized interface for drones from each manufacturer using OpenRTM-aist. We can then assemble these drones and establish formation flight by using a virtual leader--follower system. The leader and the follower positions are calculated by using speed and rotation data from feedback information such as the GPS, vel...

Although CORBA interfaces are ordinarily used in building robot systems on OpenRTM-aist, there are some cases in which it is difficult to build robot systems just using these interfaces. By using brokered Pub/Sub messaging interfaces instead of the CORBA interfaces partially, you may be able to solve the problems. Additionally, you can also enhance...

Since late 2000’s, Japanese astrobiologists have started to be involved more into space experiments and missions associated with sample returns and subsequent micro-analyses. Their efforts have resulted in the successful start of the in-orbit operation of the “TANPOPO” mission, named after dandelion, a grass whose seeds with floss are spread by the...

The main purpose of this research is to specify articulation difference between native and non-native speakers by digitizing tongue motions and analyzing the difference between utterances. Differences in tongue motion directly influence speaker’s pronunciation; therefore, it may be possible to improve non-native speaker’s efficiency of pronunciatio...

The Internet of Things(IoT) is one of the most important domains in the network society. Drones are effective devices for IoT. However they are weak in the joint ownership of observation data because their communication protocol can connect only as peer communication, and they are always connected to specific devices. OpenRTM-aist is able to unifie...

We report the recognition in video streams of isolated alphabetic characters and connected cursive textual characters, such as alphabetic, hiragana and kanji characters, that are drawn in the air. This topic involves a number of difficult problems in computer vision, such as the segmentation and recognition of complex motion on videos. We use an al...

Web service filtering is an efficient approach to address some big challenges in service computing, such as discovery, clustering and recommendation. The key operation of the filtering process is measuring the similarity of services. Several methods are used in current similarity calculation approaches such as string-based, corpus-based, knowledge-...

Social network services (SNSs) serve numerous users with large amounts of information of different kinds. On an SNS, information will propagate on a user network, which is represented as a complex network in general but can be reformed as a tree by using the direction of propagation and allowing duplication. Our goal in this study was to show the p...

In this paper, we propose an approach to publish services based on Linked data principles and discover services by service cluster with visualization for reducing the using thresholds. First, we propose Linked social service which is published on the open web by following Linked data principles with social link, then, a spatial clustering algorithm...

Web service clustering is an efficient approach to address some challenges in service computing area such as discovering and recommending. To cluster the Web services we need to filter the similar services. Key operation in filtering process is measuring the similarity of services. There are several methods used in current similarity calculation ap...

The main purpose of this research is specifying the articulation difference between L1 and L2 speakers by digitizing tongue motions and analyzing their differences between utterances. Differences in tongue motion directly influence speakers' pronunciation, so it may be possible to determine a speaker's L1 from tongue motion data. By comparing L1 an...

To extract temporal variations in the relation between two or more words in a large time-series script, we propose three procedures for adoption by the existing Associated Keyword Space system, as follows. First, we begin the calculations from a previous state. Second, we add a random seed if a new object was present in the previous state. Thrid, w...

This paper presents a comparative analysis of the color models. It used when identifying human skin in a gesture recognition system. The recognition system was based on time-space continuous dynamic programming (TSCDP). TSCDP performs optimal matching between point trajectories and video images. A point trajectory is a sequential pattern of pixels...

This paper proposes to aid the search for images by visualization of the image data on a spherical surface. Many photographs were lost in the Tohoku tsunami, and those that were eventually found are now being scanned. However, the owners of the lost photographs are finding it difficult to search for their images within a large set of scanned images...

Web service clustering is one of a very efficient approach to discover Web services efficiently. Current clustering approaches use traditional clustering algorithms such as agglomerative as the clustering algorithm. The algorithms have not provided visualization of service clusters that gives inspiration for a specific domain from visual feedback a...

Categorical classification for real-world images is a typical problem in the field of computer vision. This task is extremely easy for a human due to our visual cortex systems. However, developing a similarity recognition model for computer is still a difficult issue. Although numerous approaches have been proposed for solving the tough issue, litt...

To support the development of pronunciation training systems for non-native (L2) speakers, past research has proposed visualization of a speaker's tongue using ultrasound as feedback showing differences between L2 and native (L1) speakers. However, there has been little or no quantitative assessment combining temporal variation of speech sounds and...

We propose an efficient hardware accelerator for the calculation of accumulated values of two-dimensional continuous dynamic programming (2DCDP). The 2DCDP is a powerful optimal pixel-matching algorithm between input and reference images which can be applied to image processing, such as image recognition, image search, feature tracking, 3D reconstr...

Supporting the development of a pronunciation learning system, this paper reports an inspection of the trajectory of speech sentences in a feature space that is constructed from midsagittal tongue images and frame-wise speech sounds. One objective of this research is to estimate tongue shape and position from speech sounds, so we focus on determini...

We propose an easy framework for automatically constructing spatial ontologies that locate related concepts together in a space. The conventional graph representation is strong in showing direct relationships between entities, but it is difficult to process its topology when extracting features from the network, because similarity between networks...

This paper proposes to aid the search for images by visualization of the image data on a spherical surface. Many photographs were lost in the Tohoku tsunami, and those that were eventually found are now being scanned. However, the owners of the lost photographs are finding it difficult to search for their images within a large set of scanned images...

A collaborative filtering recommends a list of items to a given user, to which he is expected to prefer to, considering a history of purchase items of the user and those of other users, and it is applied to many web shopping sites. On the other hand, although many people often reserve accommodation facilities from web pages, it is difficult to appl...

We propose a novel method for the segmentation of deformable objects and the extraction of motion features for tracking objects in video data. The method adopts an algorithm called two-dimensional continuous dynamic programming (2DCDP) for extracting pixel-wise trajectories. A clustering algorithm is applied to a set of pixel trajectories to determ...

We propose an implementation of a model-based free-viewpoint TV (FTV) system using only three un-calibrated cameras. FTV is next-generation media that enables us to see a scene from any viewpoint. A model-based approach for realizing FTV requires real-time 3D object capture using multiple cameras. Here, we pro-pose a system for reconstructing 3D ob...

This paper proposes a method for reconstructing a 3D surface landscape from an aerial image sequence captured by a single noncalibrated camera. Reconstructing a 3D surface landscape is more difficult than constructing a landscape of buildings or objects in a room because of the lack of available information about camera parameters, the need for mos...

This paper presents a new method for categorical classification. A method called two-dimensional continuous dynamic programming (2DCDP) is adopted to optimally capture the corresponding pixels within nonlinearly matched areas in an input image and a reference image representing an object without advance segmentation procedure. Then an image can be...

We consider the optimization problem of object recognition for real world images. Although several approaches have been proposed, this paper aims to improve the recognition rate with our novel method. In this paper, a full pixel matching based object recognition method in which no advance segmentation procedure is occurred during matching procedure...

A two-dimensional continuous dynamic programming (2DCDP) method is proposed for two-dimensional (2D) spotting recognition of images. Spotting recognition is the simultaneous segmentation and recognition of an image by optimal pixel matching between a reference image and an input image. The proposed method performs optimal pixel-wise image matching...

We propose a novel method for the segmentation of objects and the extraction of motion features for moving objects in video data. The method adopts an algorithm called two-dimensional continuous dynamic programming (2DCDP) for extracting pixel-wise trajectories. A clustering algorithm is applied to a set of pixel trajectories to determine objects e...

This paper proposes an approach to reconstruct 3D object from a sequence of 2D images using 2D Continuous Dynamic Programming algorithm (2DCDP) as full pixel matching technique. To avoid using both calibrated images and fundamental matrix in reconstructing 3D objects, the study uses the same approach with Factorization but aims to demonstrate the e...

A two-dimensional continuous dynamic programming (2DCDP) method is proposed for two-dimensional spotting recognition of images. Spotting recognition is simultaneous segmentation and recognition of an image by optimal pixel matching between a reference and an input image. The proposed method performs optimal pixel-wise image matching and two-dimensi...

This paper proposes a method to analyze and determine the unified similarity of various data, such as movies, images, sound, and text. Items from these sources of data have various relative-similarity properties, which are specified by quantitative methods, and these similarities can be represented by physical distances in a multidimensional scalin...

We present a novel method for recognizing an object in an image using full pixel matching between a reference image and an input image without advance segmentation of the image. A method called two-dimensional continuous dynamic programming (2DCDP) is adopted to optimally calculate the accumulated local distances of all corresponding pixels in nonl...

The clustering and recognition of Web video content play an important role in multimedia information retrieval. This paper proposes a method for both clustering and recognizing Web video content using a histogram of phoneme symbols (HoPS). HoPS contains information about speech and sound intervals. In this study, three experiments were conducted.Th...

This paper proposes an approach to extract motion features from sequences of images of human behavior.A novel algorithm called two-dimensional continuous dynamic programming (2DCDP) is proposed, which can obtain a set of correspondence data for all pixels between sequential images.The 2DCDP algorithm performs segmentation-free detection of objects...

To detect and observe the location and angle of electrical feeder lines in galloping movies, the observer must recognize the relation of two red balls acting as spacers for pairs of lines. This research proposes and develops a system to detect these balls using color recognition in image processing. Our experiments, show that this system is success...

Spotting recognition is the simultaneous realization of both recognition and segmentation. It is able to extract suitable information from an input dataset satisfying a query, and has developed into a research topic known as word spotting that uses dynamic programming or hidden Markov models. Continuous dynamic programming (CDP) is a promising meth...

This paper proposes a novel search system for speech and song segments. The amount of accumulated video data in the World Wide Web is expanding and its content is varied. Video content includes natural voices and singing voices, and these differ in their phoneme lengths. Our system uses frame-wise phoneme recognition and Continuous Dynamic Programm...

A novel approach is presented for a retrieval method that is useful for waveforms of songs with accompaniment. Audio signals of songs have some different acoustical characteristics from speech signals. Furthermore, the length per mora of signals is longer than that of speech. Therefore, the authors suggest a sound retrieval system for application t...

The purpose of this research is to acquire new knowledge about the meanings of words by arranging the words in space. We allocated the words and displayed their relationship with each other in a three-dimensional space with a method called Associated Keyword Space (ASKS). In the experiment, the data obtained by ASKS were compared with Thesaurus.com...

We propose a novel method for mining knowledge from linked Web pages. Unlike most conventional methods for extracting knowledge from linked data, which are based on graph theory, the proposed method is based on our associated keyword space (ASKS), which is a nonlinear version of linear multidimensional scaling (MDS), such as quantification method t...

We propose a song wave retrieval method. Both song wave data and a query wave for song wave data are transformed into phoneme sequences by frame-wise labeling of each frame feature. By applying a search algorithm, called Continuous Dynamic Programming (CDP), to these phoneme sequences, we can detect a set of similar parts in a song database, each o...