Ubiquitous Experience Media

We exploit recorded activities as a good source of human-human and human-robot communication for sharing experience, memory, and knowledge. In particular, we're interested in audiovisual, ubiquitous, and wearable-experience-capturing technology as interaction-grounded lifelong tools. We've developed several devices - such as a wearable interaction tracker - that facilitate an indexed recording of human experiences     

Accelerating Robot Development Through Integral Analysis of Human–Robot Interaction

The development of interactive robots is a complicated process, involving a plethora of psychological, technical, and contextual influences. To design a robot capable of operating ldquointelligentlyrdquo in everyday situations, one needs a profound understanding of human-robot interaction (HRI). We propose an approach based on integral analysis of multimodal data to pursue this understanding and support interdisciplinary research and development in the field of robotics. To adopt this approach, a software tool named interaction debugger was developed that features user-friendly navigation, browsing, searching, viewing, and annotation of data; it enables fine-grained inspection of the HRI. In four case studies, we demonstrated how our analysis approach aids the development process of interactive robots.     

Interfacial crosslinking and diffusion via extensional rheometry

When a coextruded multilayer sheet is pulled in a uniaxial extensional rheometer the interfacial area per unit volume increases, amplifying interfacial effects. To investigate interfacial reaction, a pair of functional and miscible polyethylenes were co‐extruded into multilayer sheets (256 layers). One polyethylene contained 8 wt% glycidyl methacrylate comonomer the other 4 wt% anhydride grafts. The extensional force to pull the molten multilayer sheet was measured via a rotating clamp extensional rheometer (RME, Rheometric Scientific). Owing to the reaction in the interfacial region before and during the extension, the measured extensional force increased dramatically. The interfacial stress was extracted and correlated to the extent of interfacial crosslinking. The rate of interfacial crosslinking was found to exceed the rate of area generation at extension rates < 0.01 s^?1. By annealing samples and then stretching them, the growth rate of the interlayer was determined, and a diffusion coefficient estimated.     

Scalable and robust multi-people head tracking by combining distributed multiple sensors

In this paper, we present a robust 3D human-head tracking method. 3D head positions are essential for robots interacting with people. Natural interaction behaviors such as making eye contacts require head positions. Past researches with laser range finder (LRF) have been successful in tracking 2D human position with high accuracy in real time. However, LRF trackers cannot track multiple 3D head positions. On the other hand, trackers with multi-viewpoint images can obtain 3D head position. However, vision-based trackers generally lack robustness and scalability, especially in open environments where lightening conditions vary by time. To achieve 3D robust real-time tracking, here we propose a new method that combines LRF tracker and multi-camera tracker. We combine the results from trackers using the LRF results as maintenance information toward multi-camera tracker. Through an experiment in a real environment, we show that our method outperforms toward existing methods, both in its robustness and scalability.     

Social acceptance toward a childcare support robot system: web-based cultural differences investigation and a field study in Japan

This paper investigates people’s social acceptance of a childcare support robot system and compares it with existing childcare technologies (anesthesia during labor and baby food, i.e. processed food and formula milk) through web-based questionnaires between Japan and USA and a field study in Japan. We investigated social acceptance through four scales: intention to use, safety and trustworthiness, negative attitudes, and decreasing workload. For this paper, our participants included 400 people (200 from each country) in Japan and USA located through a web-based survey who answered questionnaires about the four scales to investigate their social acceptance of childcare support technologies. Our web-based survey results indicate that our system’s concept was evaluated lower than current childcare support technologies in both Japan and USA. We also conducted a field trial with 30 additional people in Japan and through their actual experiences investigated their evaluations of the prototype of our childcare support robot system.     

Automatic calibration of laser range finder positions for pedestrian tracking based on social group detections

Laser range finders (LRF’s) are non-invasive sensors which can be used for high-precision and anonymous tracking of pedestrians in social environments. Such sensor networks can be used in robotics to assist in navigation and human–robot interaction. Typically, multiple LRF’s are used together for such tasks, and the relative positions of these sensors must be precisely calibrated. We propose a technique for estimating relative LRF positions using observations of social groups in the pedestrian flow as keypoint features for determining coarse estimates of relative sensor offsets. The most likely offset is estimated using a generalized Hough transform and used to identify sets of possible shared observations of individual pedestrians between pairs of sensors. Outliers are rejected using the RANSAC technique, and the resulting shared observations from each sensor pair are combined into a constraint matrix for the sensor network, which is solved using least-squares minimization. Results show calibration accuracy of sensor positions within 34?mm and 0.51°, and an analysis of pedestrian data collected from ubiquitous networks in three public and commercial spaces shows that the proposed calibration technique enables pedestrian tracking within 11?cm accuracy.     

Text-line extraction and character recognition of documentheadlines with graphical designs using complementary similarity measure

A method for recognizing characters on graphical designs is proposed. A new projection feature that separates text-line regions from backgrounds, and adaptive thresholding in displacement matching are introduced. Experimental results for newspaper headlines with graphical designs show a recognition rate of 97.7 percent     

Interactive Humanoid Robots for a Science Museum

One objective of the Intelligent Robotics and Communication Laboratories is to develop an intelligent communication robot that supports people in an open everyday environment by interacting with them. A humanoid robot can help achieve this objective because its physical structure lets it interact through human-like body movements such as shaking hands, greeting, and pointing. Both adults and children are more likely to understand such interactions than interactions with an electronic interface such as a touch panel or buttons. To behave intelligently during an interaction, a robot requires many types of information about its environment and the people with whom it interacts. However, in open everyday environments, simple recognition functions such as identifying an individual are difficult because the presence and movement of a large number of people as well as unfavorable illumination and background conditions affect the robot's sensing ability. We integrated humanoid robots and ubiquitous sensors in an autonomous system to assist visitors at an Osaka Science Museum exhibit     

Image Compression and Reconstruction Using pi<Subscript><Emphasis Type="Italic">t</Emphasis></Subscript>-Sigma Neural Networks

A high-order feedforward neural architecture, called pi _t -sigma (π _t σ) neural network, is proposed for lossy digital image compression and reconstruction problems. The π _t σ network architecture is composed of an input layer, a single hidden layer, and an output layer. The hidden layer is composed of classical additive neurons, whereas the output layer is composed of translated multiplicative neurons (π _t -neurons). A two-stage learning algorithm is proposed to adjust the parameters of the π _t σ network: first, a genetic algorithm (GA) is used to avoid premature convergence to poor local minima; in the second stage, a conjugate gradient method is used to fine-tune the solution found by GA. Experiments using the Standard Image Database and infrared satellite images show that the proposed π _t σ network performs better than classical multilayer perceptron, improving the reconstruction precision (measured by the mean squared error) in about 56%, on average.