Recently, the demand for a man-machine cooperative system, where the machine assists the human operator, is rapidly growing in the industrial fields. To meet this demand, the human model is required to design the suitable assist controller in the man-machine cooperative system. This paper presents a new human behavior model based on a piece-wise affine model which is a class of hybrid dynamical system, and apply it to a sliding task. Since the human behavior is considered to consist of several primitive motions expressed by continuous dynamics and a decision-making expressed by the discrete switch, it seems to be natural to introduce the hybrid system modeling. Particularly, the decision strategy for the number of discrete modes is addressed by using a hierarchical clustering technique, and the measured data are classified into several modes. Then, each primitive motion in each mode is identified based on the affine model. Finally, the switching conditions among modes are identified by applying support vector machine to the classified data. The obtained piece-wise affine model can quantitatively represent both primitive motions and decision-making in the human behavior

This paper presents the development of a mathematical model of the human decision making. The main contributions of this paper are introduction of the logistic regression model as the mathematical model of the decision, development of the real time prediction of the decision based on the model, and proposal of some useful quantified measures to evaluate the characteristics of the human behavior. The proposed modeling and analysis strategies are applied to the driving behavior, in particular, focusing on the turn-right task in the intersections. Furthermore, two quantified measures “decision entropy” and “decision aggressiveness” are defined based on the estimated parameters in the logistic regression model. The objective evaluation made by these measures agrees well with the subjective evaluation made by the questionnaires.

This paper presents the development of the modeling and recognition of human driving behavior based on a stochastic switched autoregressive exogenous (SS-ARX) model. First, a parameter estimation algorithm for the SS-ARX model with multiple measured input-output sequences is developed based on the expectation-maximization algorithm. This can be achieved by extending the parameter estimation technique for the conventional hidden Markov model. Second, the developed parameter estimation algorithm is applied to driving data with the focus being on driver's collision avoidance behavior. The driving data were collected using a driving simulator based on the cave automatic virtual environment, which is a stereoscopic immersive virtual reality system. Then, the parameter set for each driver is obtained, and certain driving characteristics are identified from the viewpoint of switched control mechanism. Finally, the performance of the SS-ARX model as a behavior recognizer is examined. The results show that the SS-ARX model holds remarkable potential to function as a behavior recognizer.

This paper presents a new mathematical model for the human behavior called stochastic switched linear dynamical (SS-LD) model. The SS-LD model can be regarded as a natural extension of the conventional hidden Markov model (HMM), where different linear dynamical model is allocated to each discrete state of the HMM to represent continuous dynamics. Then, the parameter identification technique for SS-LD model is developed based on the EM algorithm. Finally, we apply the proposed behavior model to a typical man-machine cooperative system, and the usefulness of the proposed model is verified through some experiments

This paper presents a development of the modeling of the human driving behavior based on the expression as hybrid dynamical system (HDS) focusing on the driver's collision avoidance behavior. The driving data are collected by using the three-dimensional driving simulator based on CAVE, which provides stereoscopic immersive vision. In our modeling, the relationship between the measured information such as the sensory information of range between cars, range rate and lateral displacement between cars and the output of driver of the steering amount are expressed by the piecewise linear (PWL) model, which is a class of HDS. Then, we solve the identification problem for the PWL model by using the combination of data clustering and support vector machine. By introducing the PWL model, it becomes possible to find not only coefficients in each submodel but also parameters in the logical (switching) conditions from the measured driving data. From the obtained results, it is found that the driver appropriately switches the 'control law' according to the sensory information. This enables us to capture not only the physical meaning of the driving skill, but also the decision-making aspect (switching conditions) in the driver's collision avoidance behavior.

This paper presents a modeling strategy of human driving behavior based on the controller switching model focusing on the driver's collision avoidance maneuver. The driving data are collected by using the three-dimensional (3-D) driving simulator based on the CAVE Automatic Virtual Environment (CAVE), which provides stereoscopic immersive virtual environment. In our modeling, the control scenario of the human driver, that is, the mapping from the driver's sensory information to the operation of the driver such as acceleration, braking, and steering, is expressed by Piecewise Polynomial (PWP) model. Since the PWP model includes both continuous behaviors given by polynomials and discrete logical conditions, it can be regarded as a class of Hybrid Dynamical System (HDS). The identification problem for the PWP model is formulated as the Mixed Integer Linear Programming (MILP) by transforming the switching conditions into binary variables. From the obtained results, it is found that the driver appropriately switches the "control law" according to the sensory information. In addition, the driving characteristics of the beginner driver and the expert driver are compared and discussed. These results enable us to capture not only the physical meaning of the driving skill but the decision-making aspect (switching conditions) in the driver's collision avoidance maneuver as well.

In this paper, we discuss a method to achieve safe autonomous robot system coexistence (or Kyozon in Japanese). First, we clarify human pain tolerance and point out that a robot working next to an operator should be covered with a soft material. Thus, we propose a concept and a design method of covering a robot with a viscoelastic material to achieve both impact force attenuation and contact sensitivity, keeping within the human pain tolerance limit. We stress the necessity of a simple robot system from the viewpoint of reliability. We provide a method of sensing contact force without any force sensors by monitoring the direct drive motor current and velocity of the robot. Finally, we covered a two-link arm manipulator with the optimum soft covering material, and applied the developed manipulator system to practical coexistence tasks.

It is very difficult to place tactile sensors around revolute joints of manipulators, since those joints and surrounding surfaces are not stationary and thus they remain insensitive to contact with obstacles. This interferes with the introduction of sensors for collision avoidance control in manipulators. This paper deals with a tactile sensor system for universal joint sections of manipulators in order to detect collisions with obstacles. Its unique characteristic is the ability to detect, in one sampling period, the positions of more than one collision despite having only one signal line. It is achieved by making use of the resonance phenomenon of the sensor circuit, and all sensor elements can be distinguished from one another by frequency division. The structure of the sensor and the method to detect the label number and position of the sensor elements that are in contact with obstacles are described, followed by analysis of the circuits and experimental results of the sensor system.>

Deals with a multi-sensor system for controlling a two-fingered hand to grasp various objects. The multiple sensors are grasping force sensors, a friction coefficient sensor, and a weight sensor, which are mounted on the hand. Algorithms to recognize objects and to control grasping force of the hand by integrating the detected sensory information are also presented. Experimental results of case studies show that the ability to detect grasping force of wide dynamic range, friction coefficient, and weight allows a hand to grasp many different objects.>