This paper proposes a trajectory tracking control for non-holonomic systems using dynamic feedback linearization based on piecewise multi-linear (PML) models. The approximated model is fully parametric. Input-output (I/O) dynamic feedback linearization is applied to stabilize PML control system. Although the controller is simpler than the conventional I/O feedback linearization controller, the control performance based on PML model is the same as the conventional one. The proposed methods are applied to a tricycle robot and a quadrotor helicopter. Examples are shown to confirm the feasibility of our proposals by computer simulations.

We propose a scenario-based approach to solve and analyze complex problems. It is a variation of linguistic information processings. Human beings use macroscopic methods which is constructed from an abstract data structure, soft processing and powerful prediction, to solve several complex problems. Making and using the scenario are realized by linguistic information processing. We defined the scenario as a combined notion of sequence and its meanings which are described by linguistic labels. For application, scenario making and analysis of the game of GO playing system are shown

This paper describes an intelligent unmanned helicopter system as an aerial robot developed by the author and his research students in the past ten years. This helicopter can make free flights with linguistic commands transmitted from a ground station. It can be also navigated by GPS signals. This paper first introduces the hardware and software control systems of the developed helicopter. Then it mainly discusses image-feedback control with a CCD camera. Based on image information, the helicopter can hover over an arbitrary field, land on an assigned landing spot, and track a moving object. Copyright (C) 2001 IFAC.

The domain of comonotonically additive and monotone functionals on the class of continuous functions with compact support is extended in a natural way. A necessary and sufficient condition for which the extended functional is comonotonically additive and monotone is presented. It is shown that the extended functional can be represented by a Choquet integral when the extended functional is comonotonically additive and monotone.

The relations between a comonotonically additive and monotone functional I and the induced fuzzy measures mu (+)(I) and mu (-)(I) are discussed. We present a necessary and sufficient condition of the functional I for mu (+)(I)(X) < , mu (-)(I)(X) < and mu (+)(l)(X) = mu (-)(I)(X). (C) 2001 Elsevier Science B.V. All rights reserved.

This paper discusses the functional I defined on the class of continuous functions, which is comonotonically additive and monotone. The notion of regular fuzzy measure is proposed and the uniqueness theorem of regular fuzzy measure is shown. It is also shown that I can be represented by the difference of two Choquet integrals with respect to regular fuzzy measures when the universal set X is a locally compact Hausdorff space, and that I can be represented by one Choquet integral with respect to a regular fuzzy measure when X is a compact Hausdorff space.

This paper discusses multiattribute preference relations compatible with a value/utility function represented by the Choquet integral with respect to a fuzzy measure, and shows that the additivity of the fuzzy measure is equivalent to each of mutual preferential independence, mutual weak difference independence, mutual difference independence, mutual utility independence, and additive independence.

In this paper, we introduce a concept of computing with texts for realizing intelligent computing. In the computing we propose a way of dealing with the meaning of texts based on the concept of a meaning base defined in systemic functional linguistic theory and show a concrete example of how meaning is exchanged in a dialogue of travel consultation. Then we show the structure of a prototype system for travel consultation which processes meaning.

A hierarchical autoregressive model of time series using fuzzy measures and the Choquet integral is presented. The fitting and forecasting quality of the presented model is analysed by applying it to well-known time series data (the sunspot series) and compared with the forecasting qualities of other conventional models.

Human activity naturally contains ambiguities and contradictions that cannot be solved mathematically or logically. We think that human intelligence is closely related to the use of language. Therefore, in order to achieve intelligent computing as human beings do, we need to realize the architecture in which language is used as an information medium on a computer. In this paper we study on the development of a travel consultation system based on the above architecture as an example of information processing in intelligent computing, and show how language functions in information processing.

The authors propose a consistent and bias corrected extension of Akaike's information criterion (AIC), AIC(bc). Empirical performances of the AIC(bc) are studied. The AIC(bc) was found to result in relatively better model order choices of a linear regression model using a Monte Carlo experiment.

This paper presents a Takagi-Sugeno-Kang (TSK) fuzzy controller based on a TSK fuzzy model consisting of TSK fuzzy rules of which consequents are a state equation and have a constant term. The proposed controller consists of TSK fuzzy rules and guarantees the stability of the closed loop system. The pole placement and the integral control developed for linear control systems are used for the TSK fuzzy controller. The behaviour of the closed loop system controlled by the suggested fuzzy controller is the same as the linear system of which state transition matrix is the desired one. This paper deals with both the continuous systems and the discrete systems

In this paper, we provide the necessary and sufficient condition for a Choquet integral model to be decomposable into a canonical hierarchical Choquet integral model constructed by hierarchical combinations of some ordinary Choquet integral models. This condition is characterized by the pre-Znclusion-Exclusion Covering (pre-IEC). Moreover, we show that the pre-IEC is the subdivision of an IEC and that the additive hierarchical structure is the most fundamental one on considering a hierarchical decomposition of the Choquet integral model.

The concept of outer regular fuzzy measures is proposed, and it is shown that a functional of certain type on the cone of positive continuous functions with compact supports is represented as a Choquet integral with respect to a outer regular fuzzy measure. It is also shown that the Choquet integral of positive continuous functions with compact supports is represented as a Lebesgue integral with the same integrands. This representation is a generalization of certain previous results of others, which are useful for computation of the upper and lower expected value.

It is shown that the autocontinuity is equivalent to the property that the convergence in measure implies the convergence in distribution. This result is applied to Denneberg's dominated convergence theorem for the Choquet integral.

Attributed graphs (AG) or attributed relational graphs (ARG) and fuzzy attributed graphs (FAG) have been used for representing objects or scenes in image understanding. Based on, matching of two AGs or FAGs, similarity between two objects or two scenes can be measured. Since the matching belongs to a NP-hard problem, there have been many attempts to reduce the computational complexity of the matching. This paper uses FAGs to represent objects and gives several algorithms to measure the similarity of two FAGs. Its approach for matching is based on Eshera and Fu's method (1984). Our algorithm is extended to the case of FAGs and is simpler and reasonable. As an example, some line drawings of chairs are used for verifications. A method for representing a line drawing with a FAG is given. With two indexes for similarity and compatibility between two FAGs, identification and inclusion relations between two line drawings are studied

In this paper we give representation results for nonlinear functionals in arbitrary spaces, as fuzzy integrals. The main assumption is that of comonotonic maxitivity (i.e. I(f ∨ g) = If ∨ Ig for comonotonic f, g). Under the more restrictive condition of stochastic dominance, we prove a more specific representation as a fuzzy integral with respect to a distorted probability measure. We discuss the particular cases of possibility measures and upper fuzzy expectations. Some partial Randon-Nikodym results are proved for both the Choquet and the fuzzy integrals. Finally an example is shown where the fuzzy integral representation is useful.