Although optical flow is useful for tracking of a moving object, estimation by the gradient method is ill-posed problem. In order to avoid ill-posedness, we have proposed a tracking method via one dimensional optical flow (1D flow), which is calculated on the straight line (calculation axis). The calculation axes are spanned several direction based on the estimated motion. This method votes with the number of positive 1D flow and updates the calculation axes depending on the voting result. We update these axes every five frames to achieve stable estimation of motion. Hence, it is impossible to track a object which moves fast because this object moves to the outside of the region of interest. If the calculation axes are updated every frame to track a object which moves fast, then this method tends to estimate the wrong direction due to vibration of the camera or partial occlusion. We propose a tracking method via 1D flow using queue. We prepare queues of which the length is five for each direction. The number of positive flow is enqueued. Direction which has maximum value is regarded as the moving direction. We can achieve stable tracking even if a object moves fast, because the calculation axes are updated every frame and estimation of the moving direction is based on the information of the past five frames. In experiment for real image sequences, the proposed method can track a object which moves fast.

The human communication exists in various situations of our daily life. For human-robot communication or robot-robot communication, it is useful to design a communication model based on communication principal that is an entrainment phenomenon of nonlinear dynamics. In this paper, we focus on the robot motion synchronization for robot-robot communication. The robots are controlled to be entrained to an orbit attractor that corresponds to a robot motion. By exchanging the state variables of each robot, the robots are controlled to entrain one attractor that is possible for both robots and synchronize each other. The results of this paper represent the communication principal by an entrainment phenomenon of nonlinear dynamics.

The optical flow is a useful tool for the tracking of a moving object. Estimation of the optical flow based on the gradient method is an ill-posed problem. In order to avoid this ill-posed problem, we proposed a tracking method using a one-dimensional optical flow, which is calculated on a straight line (called the calculation axis) spanning several directions. However, the motion of the observer was not considered. In this paper, we propose object tracking by a one-dimensional optical flow under a rotating observer. The apparent motion of a stationary environment object should be eliminated for calculating the one-dimensional optical flow. Hence, we introduce the detection method of a moving object by mapping, which converts the motion of a stationary environment object into a linear signal trajectory. We calculate the one-dimensional optical flow by using pixels, which belong to the moving object, to eliminate the apparent motion of the stationary environment object. In order to verify the efficacy of the proposed method, simulation is performed using synthesized images. The proposed method successfully tracks the moving object when the observer rotates at a constant angular velocity

Estimation of an inverse kinematics model is important in robot manipulator control. Multilayered neural networks that can express a nonlinear mapping are applied in order to acquire the inverse kinematics model. Several estimation methods using neural networks have been proposed, and we herein consider the forward-propagation (FP) rule. This method is based on the following steps. First, the goal signal, which corresponds to the supervisor signal at the hidden layer and the output layer, is derived by the Newton-like method. Second, the updating of weights is realized by linear multiple regression. The regression coefficients express the adding correction of the weights. In the FP rule, it is important to realize the goal signal exactly. However, it is difficult to realize this requirement because the correction of the goal signal in the hidden layer, which corresponds to the objective variable, is expressed by the linear combination of the desired trajectory, which corresponds to the describing variable, because the neurons in the input layer are decided by the number of control outputs. In this paper, we propose the FP rule with a high-order term. The layer, which is constructed with the high-order term of the input to the neural network, is inserted between the input layer and the hidden layer. In addition, we derive the goal signal in this scheme. In order to verify the efficacy of the FP rule with a high-order term, we apply this rule to the inverse kinematics problem for the two-link manipulator, which moves on the horizontal plane. The simulation results show that the proposed method obtains a more accurate inverse kinematics model, compared to the FP rule without the high-order term

A novel associative memory model is proposed in which both the stable and optimal (minimum error) association are realized even when noisy input key vectors are given. The performance of the model is compared with that of typical associative memory models (Kohonen's model and the stabilized model) theoretically and experimentally (by computer simulation). The proposed model takes full consideration of the input noise conditions (magnitude of noise). Since the relationship between the proposed model and Kohonen's model is similar to that between the Wiener filter and the inverse filter, the proposed associative memory model is more practical than Kohonen's model.>

An improvement of the Moore-Penrose generalized inverse associative memory method is presented. It is known that for noisy input key vectors the associative memory is extremely sensitive (unstable) and association errors become unacceptably large, particularly as the number of vectors approaches the number of components per vector. Using singular value decomposition the association behavior of the associative memory is analyzed theoretically and its association error is shown to consist of two kinds of errors. One is due to the linear dependency of the key vectors (dependency error), and the other is due to the input additive noise (noise error). For noisy input key vectors the noise error is greatly increased when at least one small eigenvalue of the key space exists. It is found that the noise error can be changed to the dependency error by eliminating the corresponding eigenvalues. Therefore, if the eigenvalues are appropriately eliminated, stable association behavior can be realized and the association error reduced. In the proposed improvement method an elimination condition of the eigenvalues is given. The proposed method is greatly effective for noisy input key vectors.

The purpose of this correspondence is to propose a new construction method of distributed associative memory which operates with discrete-valued signals. In this method, memorized pairs of vectors (cue vectors and data vectors) are recorded in the form of a matrix W and a vector T. From an input vector X, the data vector is recalled by an operation u(XW + T) where X is a cue vector or a noisy cue vector. and u is a quantizing function. The methods of memorization and recall are similar to the Associatron; however, the proposed model can recall the data vectors optimally in Bayesian sense even when noisy cue vectors are given as the input vectors.