Robotic manipulators require contact force sensing capabilities to sense the contact force between the manipulator and an object. Specifically, for humans and robots to coexist in the work environment, the robot must be able to detect an external force applied by a human. This study presents a new intrinsic force sensing method for robot manipulators that can obtain accurate information of the external force applied by a human during human–robot interaction. The method employs a robot cover, which is typically utilized in robot manipulators. Unlike conventional force sensing methods, a six-axis force/torque sensor is placed between the cover and the link of the robot manipulator. As a result, the proposed method provides information of the three-axis contact force applied to the cover surface and its contact location. Therefore, the cover itself becomes a sensorized cover based on the intrinsic force sensing method. To evaluate its sensing performance, the sensorized cover is experimentally validated using reference sensors. Finally, an experiment is performed in which the robot successfully recognizes letters written on the cover, indicating a high level of contact force sensing performance.

This paper proposes a muscle-like SMA (Shape Memory Alloy) actuator with an active cooling system for efficient response. An SMA coil spring is embedded into a stretchable coolant vascular for soften structure of robots. In order to design a flexible, lightweight, and fast-response soft actuator with the SMA coil spring and coolant circulation system, a modeling based approach has been conducted. Analysis of coolant effects has been conducted in aspects of heating speed, cooling speed, and energy consumption based on both theoretical and empirical studies. From thermomechanical and heat transfer model between SMA and coolant, the actuation times in the case of heating and cooling phase have been estimated. From experimental results, Mineral oil is selected as the optimal coolant, and the maximum actuation frequency was measured as 0.5Hz for 40% contraction lifting 1kg.

Owing to the singularity of the within-class scatter, linear discriminant analysis (LDA) becomes ill-posed for small sample size (SSS) problems. Null-space-based LDA (NLDA), which is an extension of LDA, provides good discriminant performances for SSS problems. Yet, as the original scheme for the feature extractor (FE) of NLDA suffers from a complexity burden, a few modified schemes have since been proposed for complexity reduction. In this brief, by transforming the problem of finding the FE of NLDA into a linear equation problem, a novel scheme is derived, offering a further reduction of the complexity.

A class of recurrent neural networks is proposed and proven to be capable of identifying any discrete-time dynamical system. The application of the proposed network is addressed in the encoding, identification, and extraction of finite state automata (FSAs). Simulation results show that the identification of FSAs using the proposed network, trained by the hybrid greedy simulated annealing with a modified cost function in the training stage, generally exhibits better performance than the conventional identification procedures.

We propose a novel stochastic optimization algorithm, hybrid simulated annealing (SA), to train hidden Markov models (HMMs) for visual speech recognition. In our algorithm, SA is combined with a local optimization operator that substitutes a better solution for the current one to improve the convergence speed and the quality of solutions. We mathematically prove that the sequence of the objective values converges in probability to the global optimum in the algorithm. The algorithm is applied to train HMMs that are used as visual speech recognizers. While the popular training method of HMMs, the expectation-maximization algorithm, achieves only local optima in the parameter space, the proposed method can perform global optimization of the parameters of HMMs and thereby obtain solutions yielding improved recognition performance. The superiority of the proposed algorithm to the conventional ones is demonstrated via isolated word recognition experiments.

Audio-visual speech recognition (AVSR) using acoustic and visual signals of speech has received attention because of its robustness in noisy environments. In this paper, we present a late integration scheme-based AVSR system whose robustness under various noise conditions is improved by enhancing the performance of the three parts composing the system. First, we improve the performance of the visual subsystem by using the stochastic optimization method for the hidden Markov models as the speech recognizer. Second, we propose a new method of considering dynamic characteristics of speech for improved robustness of the acoustic subsystem. Third, the acoustic and the visual subsystems are effectively integrated to produce final robust recognition results by using neural networks. We demonstrate the performance of the proposed methods via speaker-independent isolated word recognition experiments. The results show that the proposed system improves robustness over the conventional system under various noise conditions without a priori knowledge about the noise contained in the speech.

This paper presents a single-objective and a multiobjective stochastic optimization algorithms for global training of neural networks based on simulated annealing. The algorithms overcome the limitation of local optimization by the conventional gradient-based training methods and perform global optimization of the weights of the neural networks. Especially, the multiobjective training algorithm is designed to enhance generalization capability of the trained networks by minimizing the training error and the dynamic range of the network weights simulataneously. For fast convergence and good solution quality of the algorithms, we suggest the hybrid simulated annealing algorithm with the gradient-based local optimization method. Experimental results show that the performance of the trained networks by the proposed methods is better than that by the gradient-based local training algorithm and, moreover, the generalization capability of the networks is significantly improved by preventing overfitting phenomena.

The use of visual information of speech has been shown to be effective for compensating for performance degradation of acoustic speech recognition in noisy environments. However, visual noise is usually ignored in most of audio-visual speech recognition systems, while it can be included in visual speech signals during acquisition or transmission of the signals. In this paper, we present a new temporal filtering technique for extraction of noise-robust visual features. In the proposed method, a carefully designed band-pass filter is applied to the temporal pixel value sequences of lip region images in order to remove unwanted temporal variations due to visual noise, illumination conditions or speakers' appearances. We demonstrate that the method can improve not only visual speech recognition performance for clean and noisy images but also audio-visual speech recognition performance in both acoustically and visually noisy conditions.

This paper presents a novel training algorithm of hidden Markov models (HMMs) for visual speech recognition based on a modified simulated annealing (SA) algorithm, hybrid simulated annealing, where SA is combined with a local optimization technique to improve the convergence speed and the solution quality. While the popular training method of HMMs, the expectation-maximization (EM) algorithm, only achieves local optima in the parameter space, the proposed algorithm performs global search and thus obtains solutions giving improved recognition performance. The effectiveness of the proposed method is demonstrated via isolated word recognition experiments.

We have implemented the sequential HGASA on a Sun Workstation machine; its performance seems to be very good in finding the global optimum of a sample function optimization problem as compared with some sequential optimization algorithms that offer low efficiency and limited reliability. However, the sequential HGASA generally needs a long run time cost. So we implemented a parallel HGASA using message passing interface (MPI) on a high performance computer and performed many tests using a set of frequently used function optimization problems. The performance analysis of this parallel approach has been done on IBM Beowulf PCs cluster in terms of program execution time, relative speed up and efficiency

This paper proposes a novel discriminative training algorithm of hidden Markov models (HMMs) based on the multiobjective optimization for visual speech recognition. We develop a new criterion composed of two minimization objectives for training HMMs discriminatively and a global multiobjective optimization algorithm based on the simulated annealing algorithm to find the Pareto solutions of the optimization problem. We demonstrate the effectiveness of the proposed method via an isolated digit recognition experiment. The results show that the proposed method is superior to the conventional maximum likelihood estimation and the popular discriminative training algorithms.

We investigate optimal and suboptimal decision rules for parallel code acquisition in chip-asynchronous direct-sequence spread-spectrum (DS/SS) systems. The conventional decision rule for parallel acquisition is to choose the largest correlator output of a receiver. However, such a scheme is optimum only for chip-synchronous models. In this letter, an optimal decision rule is derived based on the maximum-likelihood criterion for chip-asynchronous models. A simpler suboptimal decision rule is also discussed. The performance of the optimum and suboptimum decision rules is compared to that of the conventional decision rule. Numerical results show, that for chip-asynchronous models, both the optimal and suboptimal decision rules outperform the conventional decision rule.

This paper presents an application of evolutionary programming to parameter optimization in the design of a voltage reference circuit. Designing circuits consists of two steps: topological design and parameter determination. After designing a topology suitable for the circuit, the designer selects an appropriate value for each circuit element from a circuit analysis and his experience. This step is difficult and time consuming because the designer must consider many factors simultaneously. As more precise circuits are required, parameter optimization becomes more complex. The voltage reference circuit, which requires a precise reference voltage independent of power fluctuation and temperature change, is such an example. In this paper, evolutionary programming is used as an effective method of finding good parameter values for the elements of the voltage reference circuit. Simulation results show that this method provides good performance and can be used as an effective method for circuit design.

In the above paper by Kuntanapreeda-Fullmer (ibid., vol.7, no.3 (1996)) a training method for a neural-network control system which guarantees local closed-loop stability is proposed based on a Lyapunov function and a modified standard backpropagation training rule. In this letter, we show that the proof of Proposition 1 and the proposed stability condition as training constraints are not correct and therefore that the stability of the neural-network control system is not quite right. We suggest a modified version of the proposition with its proof and comment on another problem of the paper. In reply, Kuntanapreeda-Fullmer maintain the proof in the original paper is correct. Rather than identifying an error, they believe Park et al. have made a significant extension of the proof for application to stable online training networks.

This paper investigates a neurocontroller for nonminimum phase systems which is trained off-line with genetic algorithm (GA) and is combined in parallel with a conventional linear controller of proportional plus integral plus derivative (PID) type. Training of this kind of a neuro-genetic controller provides a solution under a given global evaluation function, which is devised based on the desired control performance during the whole training time interval. Empirical simulation results illustrate the efficacy of the proposed controller compared with a conventional linear controller in point of learning capability of adaptation and improvement of performances of a step response like fast settling time, small undershoot, and small overshoot.