Toshihiro Matsui

Jijo-2: an office robot that communicates and learns

Describes how the authors have combined speech recognition, dialogue management, and statistical learning procedures to develop Jijo-2; an office robot that can communicate with humans and learn about its environment.

Sound source localization and signal separation for office robot "JiJo-2"

A method of sound source localization and source separation for the sound sources in the near-field range is described in this paper. For the sound localization, the subspace method was employed to obtain a high resolution which is necessary for the range estimation with a small-sized array. The modified MVBF with the estimated localization information was used for signal separation. In an experiment conducted in a middle-sized meeting room, 60-70% of word recognition rate was achieved.

Roll-over Detection and Sleep Quality Measurement using a Wearable Sensor

Mental health management in the workplace has attracted increasing attention in recent years. As sleep is an essential physiological function that is strongly related to mental condition, easy and daily sleep management is considered essential for maintaining good mental health. In this paper, we detected roll-over movements during sleep using a wearable armband-shaped sensor, SenseWear Pro2 Armband. We then classified sleep depth into two stages, light sleep and deep sleep, based on roll-over frequency. We also propose a new index designated the Sleep Quality Score (SQS). Finally, we performed long-term measurement and compared SQS in healthy people and patients with major depression disorder.

Combining probabilistic map and dialog for robust life-long office navigation

A design of mobile robot for robust life-long navigation in office environment is proposed and evaluated. The key idea is combining probabilistic map and dialog with humans for reducing the location uncertainty. Bayesian inference with the map represented by probabilistic automata is used in order to reduce the number of queries and to evaluate the success rate of planned paths. We experimentally implemented the design using a simple Bayesian network with continuous nodes and demonstrated its effectiveness in a real environment.

An event-driven architecture for controlling behaviors of the office conversant mobile robot, Jijo-2

In order for our office conversant robot to take robust actions according to events rising from different kind of sensors, a layered process network architecture based on an event-driven control model is presented. In this architecture, high level modules are freed from time consuming checking of sensors, and are able to follow multiple scenario-driven consistent behaviors, allowing interruption from human and environment. Programs are written as series of event-action pairs, which are also effective to keep reactiveness and modularity high.

Natural dialogue with the Jijo-2 office robot

This paper reports on our work on the spoken dialogue interface to Jijo-2, an autonomous mobile office robot. We propose an attentional state model for office robot dialogue based on the centering model [2]. We give details of the implementation of Jijo-2s language components and give our algorithm for reducing the ambiguity of dialogues by identifying pronoun referents.

Partitioning An Assembly For Infinitesimal Motions In Translation And Rotation

The problem of partitioning an assembly into two subassemblies that can be separated arises in assembly planning. We consider assemblies of rigid parts whose contacts are equivalent, in terms of motion constraints, to finite sets of point-plane contact constraints. This type of contact includes all stable contacts between polyhedra as well as the large majority of contacts seen in industrial assemblies. For such assemblies, we describe a general algorithm to And a subassembly that is free to rotate and translate a small distance from the rest of the assembly. For assemblies with m contacts described as k point-plane constraints, the algorithm has a worst-case time bound of 0(~k5).

Prototypes of teleoperation systems via a standard protocol with a standard human interface

We have been developing prototypes of teleoperation systems via a standard protocol with a standard human interface, where VRML2.0 is employed as the protocol and a Web browser as the human interface. Using a Web browser, an operator can plan motions of objects interactively on a manipulation simulator with a world model which was sent from a remote site via VRML. The employment of a standard protocol and human interface enables our teleoperation system to be used by non-specialists from any Internet site, or by anyone from anywhere, without installing any specific software on the client side a priori.

An integrated tele-robotics system with a geometric environment model and manipulation skills

Describes an integrated tele-robotics system for remote execution of assembly and disassembly of mechanical components in hazardous environments such as nuclear power plants, undersea and space. The key concept of this system integration consists of the combination of manipulation skills with an environment model. The model provides the geometric structure and physical properties of the objects in the environment. The manipulation skills enable reliable task execution in the presence of unavoidable errors and uncertainties. Based on the model and skills, the system autonomously executes specified tasks. In addition, the system provides the operator with a 1-DOF bilateral control dial as an intervention tool for real-time remote assistance of manipulator movement for error avoidance and recovery. With these features, robustness and reliability in remote task execution has been achieved.<<ETX>>

Distributed real-time processing for humanoid robots

A humanoid robot is a real-time system controlled by a complex computer system that requires huge computing power for perception and planning, high energy efficiency for self-contained control, reduction of physical dimensions, and high reliability. This paper proposes a distributed architecture for the humanoid robot control substituting conventional centralized control architectures. In addition to the parallelism that provides scalable computing power at low clock namely at low energy, the distributed architecture contributes to reliable operations by replacing many fragile analog signal wires with a digital network with redundant routes. In order to accomplish a real-time control over the network, RMTP (responsive multi-threaded processor) for parallel and real-time computation has been newly designed. RMTP can synchronize more than thirty nodes distributed over a robot body in less than 5 micro second with a real time network called the responsive link (RL). Architectures of RMTP, RL and Linux-based real-time system software are presented.