Robots should listen to and recognize speeches with their own ears under noisy environments and simultaneous speeches to attain smooth communications with people in a real world. This paper presents three simultaneous...
详细信息
Robots should listen to and recognize speeches with their own ears under noisy environments and simultaneous speeches to attain smooth communications with people in a real world. This paper presents three simultaneous speech recognition based on active audition which integrates audition with motion. Our robot audition system consists of three modules - a real-time human tracking system, an active direction-pass filter (ADPF) and a speech recognition system using multiple acoustic models. The real-time human tracking realizes robust and accurate sound source localization and tracking by audio-visual integration. The performance of localization shows that the resolution of the center of the robot is much higher than that of the peripheral. We call this phenomenon "auditory fovea" because it is similar to visual fovea (high resolution in the center of the human eye). Active motions such as being directed at the sound source improve localization because of making the best use if the auditory fovea. The ADPF realizes accurate and fast sound separation by using a pair of microphones. The ADPF separates sounds originating from the specified direction obtained by the real-time human tracking system. Because the performance of separation depends on the accuracy of localization, the extraction of sound from the front direction is more accurate than that of sound from the periphery. This means that the pass range of ADPF should be narrower in the front direction than in periphery. In other words, such active pass range control improves sound separation. The separated speech is recognized by the speech recognition using multiple acoustic models that integrates multiple results to output the result with the maximum likelihood. Active motions such as being directed at a sound source improve speech recognition because it realizes not only improvement of sound extraction but also easier integration of the results using face ID by face recognition. The robot audition system improved
An adaptive gain smooth sliding controller, based on a smooth sliding observer, is developed to control nonlinear SISO affine systems with uncertain parameters and state functions. Furthermore, an adaptively updated p...
详细信息
An adaptive gain smooth sliding controller, based on a smooth sliding observer, is developed to control nonlinear SISO affine systems with uncertain parameters and state functions. Furthermore, an adaptively updated parameter term is introduced in the steady state space model of the controlled system in order to obtain useful information despite fault detection. Using a sliding observer with smooth switching function and adaptive gain increases the robustness w.r.t. uncertainties. The adaptive gains smooth sliding observer and controller are designed to fulfill the attractiveness condition on the corresponding switching surfaces. An application to a single arm, flexible joint robot is presented. In order to alleviate chattering in the observer and the controller, a parameterized tangent hyperbolic is used as a switching function, instead of a pure relay one. The gain of the switching function is adaptively updated, depending on the estimation error or on tracking error.
An overview is given on the integration of product modeling with robot control. A method to enhance application of geometric and other product and production equipment related information in robot control is introduce...
详细信息
An overview is given on the integration of product modeling with robot control. A method to enhance application of geometric and other product and production equipment related information in robot control is introduced. Focus is on creation and application of model data information understandable by robot controls, on communication of model data with robot environments through the Internet, and finally on some related telerobotics issues.
In this paper, we introduce a new control method of quasi-passive dynamic walking for a biped walking robot. The control low uses actuators just only to maintain the passive walking. First, focusing on the contact pha...
详细信息
ISBN:
(纸本)9810474806
In this paper, we introduce a new control method of quasi-passive dynamic walking for a biped walking robot. The control low uses actuators just only to maintain the passive walking. First, focusing on the contact phase of swing leg, the stability analysis of passive walking robot is performed through a discrete-time system of the robot. Second, we propose a new control method of semi-passive walking based on delayed feedback control, which do not require any reference trajectory for walking. Finally, the effectiveness of the control law is shown through several simulations.
In this paper, we provide a theoretical basis for a modified IMC-PID controller and its associated set-point response and disturbance rejection tradeoff as presented in a recent conference. We show that, while the mod...
详细信息
ISBN:
(纸本)9810474806
In this paper, we provide a theoretical basis for a modified IMC-PID controller and its associated set-point response and disturbance rejection tradeoff as presented in a recent conference. We show that, while the modified IMC-PID controller can achieve set-point response and disturbance rejection tradeoff, the nominal stability property of the resulting closed-loop system can no longer be guaranteed. We then present a generalised PID controller which not only allows set-point response and disturbance rejection tradeoff to be achieved, but also possesses a guaranteed closed-loop nominal stability property. We illustrate by two simulation examples how generalised PID controllers and their associated tuning procedure can be applied to control first-order plus dead-time processes.
In this paper we describe the implementation of a Medical Image Aid system designed for fast access to images based on their semantic content. The raw and processed images are grouped according to image type and image...
详细信息
ISBN:
(纸本)9810474806
In this paper we describe the implementation of a Medical Image Aid system designed for fast access to images based on their semantic content. The raw and processed images are grouped according to image type and image content and are organized in a hierarchy. The data organization in the system consists of a collection of such hierarchies that are used to efficiently store images and other related knowledge. The novelty of our system is that it accepts an arbitrary number of userdefined attributes and other features that characterise the image, as well as image processing algorithms for feature extraction. The system supports different query types and it is capable of searching images using multiple levels of symbolic and quantitative descriptions. This system provides a platform for future research on linking knowledge-based image understanding with content-based image retrieval.
This paper presents a novel application of the Bayesian Shape Model (BSM) for facial feature extraction. First, a full-face model is designed to describe the shape of a face, and the PCA is used to estimate the shape ...
详细信息
ISBN:
(纸本)9810474806
This paper presents a novel application of the Bayesian Shape Model (BSM) for facial feature extraction. First, a full-face model is designed to describe the shape of a face, and the PCA is used to estimate the shape variance of the face model. Then, the BSM is applied to match and extract the face patch from input face images. Finally, using the face model, the extracted face patches are easily warped or normalized to a standard view. Applications of this facial feature extraction algorithm include face recognition, face video coding and retrieval, face animation and multi-media.
The mean objective of this project is to develop an expert system module that uses the clinical decision criteria of experts in the neonatology field to advice paramedical and semi-skilled personnel who require guidan...
详细信息
ISBN:
(纸本)9810483643
The mean objective of this project is to develop an expert system module that uses the clinical decision criteria of experts in the neonatology field to advice paramedical and semi-skilled personnel who require guidance to diagnose the etiology of neonatal jaundice. The project was developed with a commercially available software package EXSYS (Multilogic Inc.). In this project, we have used a rule-based system to build the decision tree that would aid the paramedical personnel to arrive at a appropriate etiology for hyperbilirubinemia in a neonate. The project is field tested in India, where the residents are asked to come up with the correct diagnosis given the clinical tests. The disadvantage of this model is that there is the problem of it becoming obsolete in a few years time unless it is constantly being updated by developers. There is also the problem that this system cannot train or learn by itself unlike an artificial neural network.
As the actuators of active magnetic bearings (AMB) are open loop unstable a feedback control system is essential for their successful operation and for ensuring good performance. In addition, when rotor systems utiliz...
详细信息
ISBN:
(纸本)9810474806
As the actuators of active magnetic bearings (AMB) are open loop unstable a feedback control system is essential for their successful operation and for ensuring good performance. In addition, when rotor systems utilizing AMBs are operated at high speeds there will be synchronous vibrations due to unavoidable rotor mass unbalances, which generate synchronous disturbance forces. These forces and vibrations can often lead to severe problems in rotating machines including collision with the touchdown bearings at high speed and the possible risk of causing damage to the internal parts of the machines. In this paper, a new "direct" adaptive feedforward algorithm is proposed for minimizing selected vibration performance measures which is based on the filtered-x LMS adaptive filter algorithm. This new adaptive algorithm has been used for adjusting the amplitude and phase of a synchronous signal injected at the summing junction of the bearing feedback control loop. The experimental results reported in this work show the effectiveness of the proposed method.
Java with its large number of application programming interfaces (APIs) which includes provisions for database connectivity, signal processing and advanced security features is ideally suited for enterprise-wide biome...
详细信息
ISBN:
(纸本)9810483643
Java with its large number of application programming interfaces (APIs) which includes provisions for database connectivity, signal processing and advanced security features is ideally suited for enterprise-wide biomedical applications. In this paper we report the use of some of the Java APIs used in developing a clinical database system with Java speech interfaces. To speed up storage, retrieval and processing of patient information it would be useful to have a speech/voice interface to the clinical information system serving as the repository for the patient information. But voice recognition software as it comes out of the box is not adequate for professionals such as physicians who need additional highly specialized vocabulary specific to their subject matter. Once such a vocabulary is created and setup it is imperative to develop a voice based search for the terms, definitions or information such as images, acquired signals etc. pertaining to specific medical content. In this paper we report the design and implementation of a one such system, namely the Medical Speech Interface System (MSI) for specialized users (in this case Respiratory Specialists) to do point of care information transaction processing with voice technology.
暂无评论