Abstract not found

Intelligent agents embedded in a dynamic, uncertain environment should incorporate capabilities for both planned and reactive behavior. Many current solutions to this dual need focus on one aspect, and treat the other one as secondary. We propose an approach for integrating planning and control based on behavior schemas, which link physical movements to abstract action descriptions. Behavior schemas describe behaviors of an agent, expressed as trajectories of control actions in an environment, and goals can be defined as predicates on these trajectories. Goals and behaviors can be combined to produce conjoint goals and complex controls. The ability of multivalued logics to represent graded preferences allows us to formulate tradeoffs in the combination. Two composition theorems relate complex controls to complex goals, and provide the key to using standard knowledge-based deliberation techniques to generate complex controllers. We report experiments in planning and execution on a mobi...

Controlling the movement of an autonomous mobile robot requires the ability to pursue strategic goals in a highly reactive way. We describe a fuzzy controller for such a mobile robot that can take abstract goals into consideration. Through the use of fuzzy logic, reactive behavior (e.g., avoiding obstacles on the way) and goaloriented behavior (e.g., trying to reach a given location) are smoothly blended into one sequence of control actions. The fuzzy controller has been implemented on the SRI robot Flakey. I. Introduction Autonomous operation of a mobile robot in a real environment poses a series of problems. In the general case, knowledge of the environment is partial and approximate; sensing is noisy; the dynamics of the environment can only be partially predicted; and robot's hardware execution is not completely reliable. Though, the robot must take decisions and execute actions at the time-scale of the environment. Classical planning approaches have been criticized for not being...

We propose a classification of measures enabling to compare fuzzy characterizations of objects, according to their properties and the purpose of their utilization. We establish

The term Soft Computing (SC) represents the combination of emerging problem-solving technologies such as Fuzzy Logic (FL), Probabilistic Reasoning (PR), Neural Networks (NNs), and Genetic Algorithms (GAs). Each of these technologies provide us with complementary reasoning and searching methods to solve complex, real-world problems. After a brief description of each of these technologies, we will analyze some of their most useful combinations, such as the use of FL to control GAs and NNs parameters; the application of GAs to evolve NNs (topologies or weights) or to tune FL controllers; and the implementation of FL controllers as NNs tuned by backpropagation-type algorithms.

Fuzzy rules have been advocated as a key tool for expressing pieces of knowledge in "fuzzy logic". However, there does not exist a unique kind of fuzzy rules, nor is there only one type of "fuzzy logic". This diversity has caused many a misunderstanding in the literature of fuzzy control. The paper is a survey of different possible semantics for a fuzzy rule and shows how they can be captured in the framework of fuzzy set and possibility theory. It is pointed out that the interpretation of fuzzy rules dictates the way the fuzzy rules should be combined. The various kinds of fuzzy rules considered in the paper (gradual rules, certainty rules, possibility rules, and others) have different inference behaviors and correspond to various intended uses and applications. The representation of fuzzy unless-rules is briefly investigated on the basis of their intended meaning. The problem of defining and checking the coherence of a block of parallel fuzzy rules is also briefly addressed. This iss...

This chapter presents a review of various interpretations of the fuzzy membership function together with ways of obtaining a membership function. We emphasize that different interpretations of the membership function call for different elicitation methods. We try to make this distinction clear using techniques from measurement theory.

This papers aims at clarifying the meaning of different interpretations of the Max-Min or, more generally, the Max-t-norm rule in fuzzy systems. It turns out that basically two distinct approaches play an important role in fuzzy logic and its applications: fuzzy interpolation on the basis of an imprecisely known function and logical inference in the presence of fuzzy information. Keywords: Fuzzy logic; fuzzy control; Max-Min rule, fuzzy interpolation. 1 Introduction This is a synthesizing paper which returns to the question, what is the role of the Max-Min (Max-t-norm) rule in fuzzy logic from the viewpoint of logical inference. We aim at demonstrating that two basic, more or less complementary approaches in fuzzy logic and its applications can be distinguished, namely: fuzzy interpolation of a fuzzily specified precise function and logical inference in the presence of fuzzy information. The first task is solved using the Max-t-norm rule which essentially leads to search of a fuzzy...

> none of the above types of knowledge is accurate. More to the point, most of the inaccuracy is inherent to the problem, and cannot be overcome by building a more sophisticated machine. The accuracy of the agent's knowledge about its environment is bounded by the noise and limited range of its sensors, and by the precision and granularity of the prior information. This is true, in particular, of agent's knowledge about its own location, and about the location of the target position. The complexity of the environment and the presence of other agents may cause unpredictable changes, and knowledge of the current state cannot be safely projected, whatever its quality. The effect of each action is muddled by errors in the On leave from Iridia, Universit'e Libre de Bruxelles, Brussels, Belgium. effectors, as well as by the weakness of the knowledge about the situation where it is performed. Finally, the agent's knowledge about its very goals may be inaccurate: e.g.,

: The development of techniques for autonomous operation in realworld, unstructured environments constitutes one of the major trends in the current research on mobile robotics. In spite of recent advances, a number of fundamental difficulties remain. In this chapter, we discuss how fuzzy logic techniques can be used to address some of these difficulties. To illustrate the discussion, we describe the fuzzy-logic solutions developed on Flakey, the mobile robot of SRI International. 5.1 INTRODUCTION Chapter 5 of the International Handbook of Fuzzy Sets D. Dubois, H. Prade and H. Zimmermann, editors Kluwer Academic Publisher, forthcoming in 1999 Contact: http://iridia.ulb.ac.be/saffiotti/ The operation of an autonomous mobile robot in a real-world unstructured environment requires consideration of multiple issues. First, the controller must be able to operate under conditions of imprecision and uncertainty. For example, prior knowledge about the environment is, in general, incomplete, unc...