加藤 由花

Robot simulators are generally used in the research and development of autonomous mobile robots in human-robot coexistence environments. These simulators require to implement moving pedestrians as dynamic obstacles, and often use various crowd models developed in the field of crowd simulation research. However, existing crowd simulations make assumptions that all virtual agents comprising the crowd are controlled in the same manner and that each virtual agent has full knowledge of the surrounding environment. The validity of these assumptions is not clear in robot navigation simulators. In this paper, we analyze existing crowd simulations for use in a simulator for autonomous mobile robot navigation. We also conduct simulation experiments using a simple crowd model to evaluate the impact of environmental differences on the performance of the crowd simulations.

In recent years, many navigation methods using deep reinforcement learning for autonomous mobile robots have been proposed to apply to various dynamic environments. However, since the learning results depend on the simulation environment, it may be inappropriate to apply them directly to the real environments from the standpoint of safety and efficiency. To solve the problem, in this paper, we propose a multi-policy switching method that enables safe and efficient navigation for autonomous mobile robots that share space with humans in various real-world environments, such as dense and crowded situations. Specifically, the method switches the navigation rule among four policies including deep reinforcement learning-based policy according to the size of the target robot's movable space (i.e., unoccupied area around the robot). We verify the effectiveness of the proposed method by conducting navigation experiments with computer simulation. The results show that the proposed method improves collision avoidance rate in a narrow space where the robot tends to halt or oscillate by existing methods.

In Japan, where the labour force has decreased in recent years, robots have got a lot of attention to supplement the workforce. In the reception and response control system using the robot 'ApriPoco™', measuring the walking trajectory using a laser rangefinder has been studied, but it cannot measure accurately because the trajectory overlaps. In this paper, we propose a system that predicts trajectories in real-time using Gaussian process regression. We experimented by checking the operation of the non-real-time trajectory prediction system. The proposed system improved the probability of obtaining correct data from about 7.4% compared with the previous system. Based on this result, we conducted a demonstration experiment with a real-time prediction system. As a result, the number of coordinate data points was reduced, and the accuracy decreased. We aim to improve the accuracy of the real-time prediction system in the future.

情報処理学会マルチメディア通信と分散処理研究会の関連研究領域において，研究者はどのような研究論文を「良い」論文であると考えているのかについて，自己の論文と他者の論文に分けて第1次調査としてアンケート調査を行い，その結果を分析した．アンケートはシニア研究者を対象に実施し，通常の新規性や有用性等の論文査読基準だけでは測定できない研究論文の価値や，研究論文執筆において研究者が重要と考えている要素を抽出した．さらに，意識調査の活用を目的として，分析結果と考察を当該研究コミュニティのワークショップにおいて研究発表し，意見交換を行った．その後，第2次調査として，研究コミュニティの「良い」論文を送り出す役割についての意識調査を実施した．本研究によって，当該研究領域における「良い」論文価値の共有を図るきっかけが得られたことと，「良い」論文を送り出すためにこのような意識調査が活用でき，継続的に必要であると考えられることが確認できた．

<p>Large volumes of data are typically used during analyses. Data preprocessing, which involves detecting outliers, handling missing data, data formatting, integration, and normalization, is essential for achieving accurate results. Many tools and methods are available for reducing preprocessing time. However, most analysts face difficulties when using them. This paper proposes a method for handling outliers and missing data, called Automated PRE-Processing for Sensor Data (APREP-S). For reducing analysis resources, we combine programming by example and machine learning via Bayesian inference, inputting human knowledge to APREP-S as an example and calculating a proper proportion by machine learning via Bayesian inference. We also define k-Shape as the calculation of the rate of similarity of time-series data. In evaluation, we use sensor data of temperature and humidity and compare the sum of the square of the errors of four methods, between original data and outputs of each methods, (1) APREP-S, (2) mean of the entire data, (3) mean of the around-the-target imputation data, and (4) spline interpolation. It is verified that APREP-S is a more suitable method for humidity data than temperature data. preprocessing method. we consider the reason is that humidity data have more changing points.</p>

© 2019 IEEE. It has recently become possible to analyze integrated data obtained from sensors or wearable devices in the field of Information Technology (IT). Well-known examples include behavioral patterns of customers in a shop, the autonomous motion of robots, and fault prediction. It is known that the pre-processing of data-before it is input into the analysis model-is essential to achieve accurate results. However, this task requires 80% of the resources in the analysis process. As an improvement to the pre-processing of outliers and missing data, we had previously proposed 'APREP-S' based on Bayesian inference with Programming by Example. In this paper, we expand APREP-S and define the timing of model generation for increased interactivity between analysts and APREP-S. We calculate the accuracy of the new APREP-S and compared it to that of existing methods. Based on our results, we conclude that APREP-S is the most effective imputation method for time-series data.

The need for analyzing data is increasing at an unprecedented rate. Well-known examples include customer behavioral patterns in shops, the autonomous motion of robots, and fault prediction. Pre-processing of data is essential for achieving accurate results. This includes detecting outliers, handling missing data, and data formatting, integration, and normalization. Pre-processing is necessary for eliminating ambiguities and inconsistencies. We here propose a framework called APREP-DM (for the Automated PRE-Processing for Data Mining) applicable to data analysis, including using sensor data. We evaluate two types of perspectives: (1) considering pre-processing in a test-case scenario involving pedestrian trajectory tracking, and (2) comparing APREP-DM with the outcomes of other existing frameworks from four different perspectives. We conclude that APREP-DM is suitable for analyzing sensor data.

In recent year, there has been increasing interest in communication robots, and a variety of services including voice guidance are expected for such robots. For providing those services, state estimation of robot users is required. From the background, we have been studying a method to predict the walking direction of a pedestrian who heads toward a robot in order to provide suitable voice guidance to him/her by a communication robot installed at the reception desk of a public facility. In this paper, we verify the effectiveness of the proposed method by using actual observed data. Here, we measure pedestrian trajectories using a laser range scanner installed on a tripod and predict the branching direction using pre-trained predictor models by a machine learning algorithm. In this paper, we generated two predictor models using an open dataset of pedestrian trajectories in a shopping mall. By conducting evaluation experiments using the models, we found out that one model can predict the direction with practical accuracy but the accuracy of another one is not sufficient. The result shows that using robust and adequate predictor models are important for our target system.

In this paper, we propose a method robustly predicting the destination of a pedestrian heading toward a robot in order to provide suitable voice guidance to him/her by communication robots installed at the reception desks of public facilities. For this purpose, we measure a pedestrian trajectory with a laser range scanner attached to the robot, and predict the destination among more than three branches by cascading multiple predictor models for two branches pre-trained by a machine learning algorithm. In order to verify the effectiveness of the proposed method, we conduct experiments using a dataset of tracking pedestrians at a shopping mall, and data observed in the real environment. The result shows that our method can predict three branch destinations with an accuracy of about 80%.

我々はこれまで，測域センサで測定された各人の位置情報を基に，インタフェースロボットの応答制御を行い，挨拶などのコミュニケーションに利用する研究を進めてきた．ここでは，人の腰の高さに設置したセンサで人までの距離を時系列データとして取得し，ある時刻の人の位置を確率分布として推定する手法を用いてきた．本稿では，この手法を拡張し，測定位置を足首に変えることで，人の位置だけではなく，人属性を合わせて推定する手法を提案する．人属性推定としては，高齢者/若年者の弁別を対象に，機械学習アルゴリズムを用いて予測器を構築する．ここでは，「歩幅」「歩速」「歩行加速度」など7種類の歩行データの平均値と標準偏差を特徴量とすることで，単一の測域センサから取得した歩行データのみで，属性弁別が可能であることを示す．Until now, we have studied a dialog control method for interface robots based on human location data measured by a laser range scanner as a human-robot interaction scheme. In this method, we have obtained distance data from the sensor at waist level to the target human as time series data, and have estimated the human location at a time as a probability distribution. This paper enhances the scheme and proposes an estimation method of human attributes in addition to their locations by measuring motion data of human legs at the time of walking. As human attributes, we focus on a classification method of elderly and young people, and construct the prediction model by using a machine learning algorithm. In this paper, we also verify that the attribute classification using walking data obtained from a single laser range scanner becomes possible by adopting seven types of features of walking data, such as strides, velocity and acceleration, for the model.

It is known that there is a strong correlation between daily lifestyle and health condition. Lifestyle-related diseases are one example of them and the action of preventing them is very important topics of discussion. Recently, various devices, which are worn anytime and are able to collect vital information, are widely used. Consequently, many studies using these devices for health management have been made. From these backgrounds, this study proposes a method estimating a stress state by using the instantaneous pulse rate obtaining from wearable devices in order to identify long-term stress factors in daily life. Here, we formulate Stress and Relaxed Value (SRV) as a QOL (Quality of Life) indicator with considering both stress and relaxed state, and verify that SRV can be associated with lifestyle factors. For the method, we use LF/HF (Low Frequency/High Frequency), which is derived from the fluctuation of the peak intervals of heartbeat and is an indicator of the psychological stress state. In this study, we calculate SRV by combining LF/HF with HF, which correlates relaxed states. In addition, we verify the effectiveness of the proposed method by conducting evaluation experiments using a wearable device.

本稿では，情報処理学会におけるダイバーシティ推進の取り組みとして，2016年4月に発足したInfo-WorkPlace委員会の活動を紹介する．本委員会は，女子学生，女性技術者・研究者の活動を支援し，学会の一層の発展を図ることを目的に設立されたが，委員会名にあえて「女性」という言葉を入れていない．これは，性別・年齢などの属性を問わず，私たちのワークプレイスを新たにデザインしていくことを目指したい，という思いが込められているためである．女性支援活動は重要な取り組みといわれながらも，一部の女性だけが活発に活動していて広がりがない，女性というだけで半ば強制的に参加させられるなど，本来の意味で機能していない事例も見受けられる．我々は，参加することにメリットがあり，参加したくなる場づくりを目指した，新しい形の活動を模索している．本稿では，委員会設立までの経緯，現在の活動内容を紹介することにより，ダイバーシティ推進活動の今後の方向性について考察する．

「男性の働き方を変えないと女性の働き方も変えられない」．日本の夫婦共働きの世帯が1,100世帯を超え，多くの若い世代が育児と仕事との両立という問題に直面し，悪戦苦闘・試行錯誤しています．ダイバーシティ社会の推進において，ワークプレースはどうあるべきか？ ICTでどう支援できるか？ 2016年9月に富山大学で開催されたFIT2016において，情報処理学会Info-WorkPlace委員会とデジタルプラクティス編集委員会との共同企画イベントとして実施したパネル討論の内容をまとめました．

Recently, lifestyle-related diseases, which are caused by accumulated disordered lifestyle, have been a considerable problem. Though someone might be able to change such lifestyle by becoming aware of the style problems, it is not easy to be always conscious of health in everyday life and also to visualize their lifestyle individually. Currently, we can use various sensor devices to solve these problems. Improving of sensing technologies makes it possible to collect various kinds of vital information daily and easily. From these backgrounds, we have studied on a Quality of Life (QOL) visualization system, whose target is to improve our lifestyle on a daily basis by using vital information collected from wearable devices. In this paper, we propose a QOL indicator called SRV (Stress and Relaxed Value) as one of the functions of the QOL visualization system. That is an estimation model on stress and relaxed states by using the instantaneous pulse rate. We also verify the effectiveness of the proposed model by conducting evaluation experiments using a pulse sensor.

We have studied a dialog control method for interface robots by using location data of persons measured by a Laser Range Scanner as a human-robot interaction technology. In the method, we measured the distance between a sensor and a person with the sensor placed at human waist height as a time series data and estimated the position coordinates of the person at a time as a probability distribution. This paper extends the scheme and proposes a method estimating person attributes in addition to the location data by monitoring the movement of legs while the person is walking. As for person attributes, we focus on the age and classify persons as the elderly and the young. At that time, we construct a prediction model of age groups based on machine learning mechanisms. In this paper, we use seven feature values, these are the step length, the step width, the velocity of leg 1, the velocity of leg 2, the velocity of body, the acceleration of leg 1 and the acceleration of leg 2 for the model. By conducting experiments, we verify that classification accuracy improves particularly using acceleration and standard deviation of the data.

In this paper, we discuss the effect of network delay on remote navigation for low-cost simple robots using cloud environments. First, we conduct the experiment of remote navigation using a robot simulator and show the result which does not navigate a robot adequately under the network condition with pseudo-delay. Then, from the result, we derive the necessity of the control model in considering network delay and design the delay-conscious control model in slowing the observation and quickening the control according to the pre-defined delay model.

This paper proposes a method for estimating a stress state by using pulse sensor obtaining from wearable devices in order to identify long-term stress factors in daily life. For the method, we use LF/HF (Low Frequency / High Frequency), which is derived from the fluctuation of the peak intervals of heartbeat, and is an indicator of the psychological stress state. The proposed method estimates LF/HF by using a pulse instead of the heartbeat, and formulates Stress and Relaxed Value (SRV) as a Quality of Life (QOL) indicator on the basis of LF/HF. In addition, we conduct an experiment comparing pulse data, obtaining from pulse sensor and pulse wave obtaining from the pulse wave monitor. The experimental result shows that the same trend can be recognized on these data.

This paper proposes a remote navigation system for a simple tele-presence robot. In general, robot functions of tele-presence robots are limited, and visual angle of the camera on robots is narrow, so they are unsuitable to use navigation services. The proposed system overcomes the difficulty by adopting system architecture in which robots are controlled remotely via a server located in the Internet, by using well-designed virtual reality techniques for robot control and by implementing almost all robot navigation functions into the server. In this paper, we also implemented Remote Open Campus System (ROCS) as a prototype system, and by using that, we confirmed the effectiveness and usefulness of the proposed system.

本稿では,ロボットサービス向けプロトコル仕様であるRSNP (Robot Service Network Protocol)を利用したロボットサービス/ロボット技術の解説を行う.RSNPは,業界団体であるロボットサービスイニシアチブ(RSi:Robot Service initiative)により策定されたオープンな仕様であり,Webサービス基盤をベースにしていることから,インターネットと整合性の高い標準化された機能を利用可能である.連載後編の今回は,応用編として,RSNPに基づくロボットサービス/ロボットの実例を紹介する.

日本の競争力の比較的強い分野とされているロボット分野だが,インターネットやクラウドサービスと連携する時代へと進みつつあり,ソフトウェア技術やシステム化が鍵になっている.本稿では,ロボットサービスのプラットホームの仕様として業界団体ロボットサービスイニシアティブ(RSi)においてフォーラム標準として策定しているRSNP(Robot Service Network Protocol)仕様を取り上げ,RSNPの技術と,これを活用したロボットやサービスについて2回にわたって解説する.RSNPの具体的なプログラミングや応用システムについて述べることで,情報通信分野の研究者や技術者にも本分野へ関心を高めて頂きたいと考えている.第1回は,RSNPのアーキテクチャ・ロボットサービスのプログラミングモデルについて紹介する.

本稿では，多種多様なロボットと，環境側に設置する簡易な目印を使って，ロボットの遠隔操作サービスを構築するためのサービスプラットフォームを提案する．本プラットフォームは，インターネット経由で遠隔地の案内を行う「案内サービス」を対象としており，ロボットの存在する実環境に対する処理をプラットフォーム内に隠蔽することにより，ロボット工学の知識を持たないソフトウェアプログラマでも容易にシステムの構築が実現できる．提案するプラットフォームは，ロールプレイングゲーム開発で利用される表現技法を利用している点に特徴があり，ソフトウェアプログラマは，APIの呼び出しとリスナによるイベント取得により，ロボット遠隔操作プログラムを構築することができる．本稿では，プラットフォームの利用例として，大学のキャンパス案内を対象にしたRemote Open Campus System（ROCS）を構築し，プラットフォームの有用性，有効性を検証する．This paper proposes a service platform for developing remote control services of mobile robots by using various kinds of robots and simple markers set on remote environments. The target of the platform is "Guide Services" via the Internet. Even software programmers without the knowledge of robotics can easily develop such systems by encapsulating robot processes conducting on the real world into the platform. A feature of the platform is to use a expression form and technique used for computer role playing games, and software programmer implements remote control programs for robots by calling APIs and using event listeners. In this paper, we implement Remote Open Campus System (ROCS) for university campus guide services as a usage sample, and as a result, we confirm the usefullness and effectiveness of the platform.

This paper proposes a mapping method with the virtual world and the real world for robot remote controlling via the internet. Server isolates a user operation side in the virtual world and a robot working side in the real world. We use a GameEngine for creating the virtual world. The GameEngine handles user operation and user side view. This view is used for the reference for comparing matching level with the real world view which is taken by robots in the real world and current intensity level comparing with measured intensity concurrently. These comparing processes are done on the server. We validate efficiency of the method for applying to campus guidance service.

When we discuss operability and convenience of remote control robot systems, it was usual to focus on user interfaces to operate robots. In this paper, we propose to improve methods of service providing based on the different operation types, e.g. operation which requires realtime response, operation which allows delay between user operation and robot movement via networks.

我々は，ロボットサービスのインターネット化を実現するための研究開発環境RSi-Cloud（RSi Resaserch Cloud）の研究を進めている．これまで，Webブラウザ経由でロボットカメラの画像を監視する見守りサービスを構築し，RSNP（Robot Service Network Protocol）を実装したロボットからの接続を実現してきた．今回，RSi-Cloud上に，ロボットのためのソフトウェア部品（RTコンポーネントなど）を，RSNPを実装したロボットと同様に扱う仕組みを実現したのでその結果を報告する．この仕組みを利用すると，サービス機能をサーバ上にデプロイする必要がなく，またファイアウォール内に配備可能になるため，ロボットサービス開発の拡充が期待できる．本稿では，RTコンポーネントであるVisionModuleを組み込んだプロトタイプシステムを開発し，提案手法の有効性を検証する．We have proposed the RSi Research Cloud (RSi-Cloud), which enables integration of robot services with internet services. Until now, we have developed a surveillance service using robot cameras via Web browsers, and have realized internet connection from robots implemented with RSNP (Robot Service Network Protocol). This paper reports an implementation result of the mechanism which treats software components for robots (such as RT Components) by the same way as RSNP robot clients. The mechanism makes it possible to provide service components without deploying in a server side, and to deploy the components within firewall systems, and as a result, a robot service expansion can be expected. In this paper, we develop a prototype system using an RT Component, VisionModule, and verify the effectiveness and usefulness of the proposed method.

Recently, there are increasing interests of integration between robot technologies and Internet services, and various cloud-based service platforms for robots are proposed. From these backgrounds, in this paper, we propose a virtual campus tour service which enables remote users to control robots in school campuses via the Internet. In implementing the service, we use Robot Service Network Protocol (RSNP), which is a common protocol specification for robot services. Therefore, users can operate various remote robots in various campuses via the proposed service. Furthermore, we conduct subjective and objective assessments on camera functions for the service, and verify the effectiveness of the proposed one.

Internet and cloud-based robot services and their platforms are becoming attractive. Many related works have been also done, such as DAvinCi, ROS on Android, and RoboEarth. However, when robot services are provided via computer networks, very reliable services are required to deal with short/long-term disconnection between services and robots due to wireless LAN disconnection, robot service problems, system error on robots, and so on. In this paper, we adopt Robot Service Network Protocol (RSNP) as a robot service platform in order to integrate robot services with Internet services. In addition, we propose a method and architecture to realize reliable cloud-based robot services for RSNP in a communication view point.

Recently, there are increasing interests of integration between robot services and the Internet, and many remote control services using robots have been proposed. In order to control robots remotely, we generally use images and videos captured by robot cameras and fixed cameras, but image quality is fluctuating with a change of network condition. The fluctuation has an effect on operational accuracy of remote control robots. In this paper, we propose the method controlling quality of camera images according as network condition for a virtual campus tour service using robots.

Recently, many ICT companies as well as researchers are taking an increasing interest in robot services using cloud computing, and various service platforms for them have been proposed. From these backgrounds, we have proposed a distributed service framework using Robot Service Network Protocol (RSNP) to integrate various devices including robots with internet services. The key mechanism of the proposed framework is a robot assignment function, which discovers distributed robot resources and assign the requested tasks by end users to suitable robots. In this paper, we implement a prototype system on the proposed framework, and conduct implementation evaluation using the system.

With the rapid advance of the integration of internet and robot areas, various service platforms are proposed that assume cloud environments. For robot services, as the numbers of devices and their types increase, a mechanism that enables the entry of developers in various areas is required. However, existing platforms are insufficient to the problem. In this paper, we developed a distributed service framework that realizes the coordination of various devices, robots, and service functions based on RSNP (Robot Service Network Protocol), a protocol specification for robot services. Furthermore, we implement a pet-sitting service as a prototype system that uses a proposed framework and verify the effectiveness of the framework.