Yasushi Nakauchi

A Social Robot that Stands in Line

Recent research in mobile robot navigation make it feasible to utilize autonomous robots in service fields. But, such applications require more than just navigation. To operate in a peopled environment, robots should recognize and act according to human social behavior. In this paper, we present the design and implementation of one such social behavior: a robot that stands in line much as people do. The system employs stereo vision to recognize lines of people, and uses the concept of personal space for modeling the social behavior. Personal space is used both to detect the end of a line and to determine how much space to leave between the robot and the person in front of it. Our model of personal space is based on measurements from people forming lines. We demonstrate our ideas with a mobile robot navigation system that can purchase a cup of coffee, even if people are waiting in line for service.

Intelligent kitchen: cooking support by LCD and mobile robot with IC-labeled objects

Recent development of information technology is making electric household appliances computerized and networked. If the environments surrounding us could recognize our activities indirectly by sensors, the novel services, which respect our activities, can be possible. In this paper, we propose human activity recognition system, which infers the next human action by taking account of the past human behaviors observed so far. We also developed cooking support system by using an LCD touch panel on the kitchen counter and a mobile robot on the floor, which suggest what the human should do next by voice and gestures. Experimental results confirmed the feasibility of the inference system and the quality of support.

A social robot that stands in line

Recent research results on mobile robot navigation systems make it promising to utilize them in service fields. But in order to utilize the robot in a peopled environment, it should recognize and respond to peoples social behaviors. In this paper, we describe a social robot that stands in line as people do. Our system uses the concept of personal space for modeling a line of people and we have experimentally measured the actual size of the personal space when people form lines. The system employs stereo vision to recognize lines of people. We demonstrate our ideas with a mobile robot navigation system that can purchase a cup of coffee, even if people are waiting in line for service.

Multi-agent interface architecture for human-robot cooperation

One of the important factors required to realize personal robots is mutual cooperation between humans and robots. To support human cooperative work based on asynchronous communication, the authors had developed a groupware toolkit called Michele. They propose a multi-agent interface architecture called RT-Michele. A prototype of RT-Michele was implemented, and autonomous mobile robots were developed. RT-Michele was applied to office automation, where it provided not only asynchronous communication, but also real-time interactive communication for cooperative work among humans and mobile robots.<<ETX>>

Cooking Procedure Recognition and Support by Ubiquitous Sensors

This paper proposes cooking support using ubiquitous sensors. We developed a machine learning algorithm that recognizes cooking procedures by taking into account widely varying sensor information and user behavior. To provide appropriate instructions to users, we developed a Markov-model-based behavior prediction algorithm. Using these algorithms, we developed cooking support automatically displaying cooking instruction videos based on user progress. Experiments and experimental results confirmed the feasibility of our proposed cooking support.

Social behavioral robot that stands in line

Recent research results on mobile robot navigation systems make them seem promising for utilization in service fields, but in order to utilize the robot in a peopled environment, it should recognize and obey the peoples social behavior. In this paper, we propose a social behavioral robot that stands in line as people do. We have employed the notion of personal space for modeling a line of people and developed a stereo vision system to recognize them. We have also developed a mobile robot navigation system that can purchase a cup of coffee even if people are waiting for service in line.

Dosing monitoring system using iMec and ubiquitous sensors

Recently, the number of senior citizens who are living alone and taking medicine is increasing due to population aging. Since these people have many risks of incorrect dosing, their caretakers living at a distance are concerned about their health. Therefore, we developed iMec (intelligent medicine case) and propose iMec system that is composed of iMec and ubiquitous sensors. The system can support correct dosing of recipient and dosing monitoring of their caretakers. The iMec is a medicine case that not only detects medicine in the medicine case by image processing but also notifies about dosing timing and dosage by touch display and speaker. The ubiquitous sensors assist the iMec to decide dosing timing. We have confirmed the validity of the image processing methods by experiments.

Sequential Human Behavior Recognition for Cooking-Support Robots

Recent advances in information technology are making electric household appliances computerized and networked. If our environments could intuit our activities, e.g., by sensors, novel services taking anticipated actions into account would become possible. We propose activity recognition that infers a subject’s next action based on previously observed behaviors. We developed a cooking-support robot that suggests by voice and gesture what the subject may want to do next. Experimental results confirmed feasibility of the inference and the quality of support.

Human behavior recognition for cooking support robot

The recent development in information technology is making electrical household appliances computerized and networked. If the environment surrounding us could recognize our activities indirectly by sensors, novel services, which respect our activities, can be possible. In this paper, we propose a human activity recognition system, which infers the next human action by taking into account past human behavior, observed so far. We also developed a cooking support robot, which suggests what the human should do next, by voice and gesture.

Cooking procedure recognition and support system by intelligent environments

In this paper, we propose cooking support system by using ubiquitous sensors. We developed machine learning algorithm that recognizes cooking procedures by taking account of various and numerous sensor information and past human behaviors. In order to provide appropriate instructions to a user, we also developed Markov-model based human behavior prediction algorithm. By employing these algorithms, we developed cooking support system that automatically displays cooking instruction movies according to users progresses. We conducted experiments with subjects and the experimental results confirmed the feasibility of the proposed cooking support system.