Kunitoshi Sato

Learn More
This paper describes the practical control of non-friction mechanism for precision positioning. Non-friction mechanism is often used for precision positioning. Even though it has a simple structure, still, plant identification is compulsory needed during designing a conventional controller. This makes the controller non-user-friendly and non-practical-used(More)
This paper considers an adaptive H<sup>infin</sup> control method with link frictions compensation and external disturbances rejection for robotic systems. It is assumed that all the system parameters for friction model and robot are unknown. The proposed method ensures that the unknown parameters are estimated and approximation errors of friction model and(More)
In this paper an adaptive tracking control of a servo mechanism with friction is developed, based on the notion of H<sup>infin</sup> optimality. It is assumed that the friction dynamics can be described by the LuGre model. The nonlinear characteristic function of the LuGre model is parameterized by a neural-network (NN). In general, friction parameters and(More)
We have developed Interaction Builder (IB), a rapid prototyping tool for constructing web-based Multi-Modal Interaction (MMI) applications. The goal of IB is making it easy to develop MMI applications with speech recognition, lifelike agent, speech synthesis, web browsing, etc. For this purpose, IB supports the following interface and functions: (1) GUI for(More)
This paper proposes an adaptive control method for robotic manipulators with input toque uncertainties. For each link of manipulators, it is assumed that the input torque uncertainties can be divided into unknown parameters term and bounded disturbance term. In addition, all the parameters for input torque uncertainties and robot are unknown. The proposed(More)
This paper presents an unsupervised learning-based object category formation and recognition method for mobile robot vision. Our method has the following features: detection of feature points and description of features using a scale-invariant feature transform (SIFT), selection of target feature points using one class support vector machines (OC-SVMs),(More)
In order to sufficiently represent and recognize human gestures, one needs, in the first place, to know at what frame rate a gesture should be sampled. To investigate the temporal-domain problems on gesture recognition, a framework is proposed that recognizes arbitrary gestures at multiple frame rate by running recognition processes in parallel. In our(More)
An adaptive H<sup>&#x0221E;</sup> control for positioning mechanism with input nonlinearity is proposed in this paper. It is assumed that the input nonlinearity can be described as unknown parameters term and bounded disturbance term, an adaptive H<sup>&#x0221E;</sup> control method is given. Proposed control strategy does not include a discontinuous(More)
  • 1