We have developed the person following robot "ApriAttendatrade". This robot can accompany a person using vision based target detection and avoid obstacles with ultrasonic sensors while following the person. The robot first identifies an individual with its image processing system by detecting a person's region and recognizing the registered color and texture of his/her clothes. Usually, the person following robot has to detect and recognize the specified person and calculate his/her position in a complicated real-life environment of fixed objects and moving people. Our newly developed algorithm allows the robot to extract a particular individual from a cluttered background, and to find and reconnect with the person if it loses visual contact. Tracking people with stereo vision was realized by systematizing visual and motion control with a robust algorithm that utilizes various characteristics of the image data. The developed algorithm uses several analyses to extract information on the distance to each feature point, speed of target, color and texture of clothes for a stable tracking in many situations including changes of view due to self motion, shifts in lighting and objects similar to the target. The person following robot ApriAttendatrade has been exhibited at Aichi EXPO 2005, and its robust functions and smooth person following capability were successfully demonstrated
1 January 2017 in International Journal on Smart Sensing and Intelligent Systems
This paper describes the relationship between visual attention and eye blink frequency. In an experiment, we prompted the activation of a subject’s visual attention and examined the influence of visual attention (as measured using electrodermal activity (EDA), which is meaningfully correlated with visual attention) on the subject’s eye blink frequency. Experimental results show that engagement of visual attention decreased eye blink frequency and that when visual attention was not activated, eye blink frequency increased. Knowledge of this relationship provides a technique using EDA to objectively determining a subject’s visual attention status.
The paper describes a 2D sound source mapping system for a mobile robot. We developed a multiple sound sources localization method for a mobile robot with a 32 channel concentric microphone array. The system can separate multiple moving sound sources using direction localization. Directional localization and separation of different pressure sound sources is achieved using the delay and sum beam forming (DSBF) and the frequency band selection (FBS) algorithm. Sound sources were mapped by using a wheeled robot equipped with the microphone array. The robot localizes sounds direction on the move and estimates sound sources position using triangulation. Assuming the movement of sound sources, the system set a time limit and uses only the last few seconds data. By using the random sample consensus (RANSAC) algorithm for position estimation, we achieved 2D multiple sound source mapping from time limited data with high accuracy. Also, moving sound source separation is experimentally demonstrated with segments of the DSBF enhanced signal derived from the localization process
Death due to drowning accounts for about 30% of unintentional injuries of 1 to 4 year-old infants in Japan. A system for preventing infant drowning is strongly required. This paper describes a newly developed system for preventing infants 1G drowning injury at home. The prototype of infant drowning prevention system developed by the authors is presented. The developed system can measure the wave motion of water in the bathtub using a triaxial accelerometer, detect the abnormal wave motion, and give a warning to guardians with a radio communication. In this paper, the details of the system and the experimental results on abnormal wave motion detection are shown.
A wearable sensor technology enables us to conduct scientific research on our everyday lives by measuring everyday phenomena quantitatively. For example, observing and understanding infant's behavior in everyday lives is required for developing preventive measures of infant's injuries. This paper describes a wearable electromyography (EMG) sensor for measuring grasping behavior in a daily living space. The prototype system of a wearable EMG sensor developed by the authors is presented. This paper proposes a method for counting grasping behavior using the developed system. The results of the experiment conducted for an adult show that the system can estimate grasping times within an error of 25%. This paper also presents a downsized wearable EMG sensor for an infant and reports an EMG map, which visualizes the events related to arm motions with location, as one of applications of the developed EMG sensor.