Search

Fuzzy classifier systems (FCS) implement a mapping from real numbers to real numbers, through fuzzy interpretation of input and output. Reinforcement learning (RL) algorithms can be successfully applied to develop learning FCS analogously to what can be done with learning classifier systems (LCS). The author motivates this approach and presents a methodology to extend straightforwardly reinforcement distribution algorithms originally designed for crisp input and output to fully exploit the features of FCS.

Models that are constructed within the bounds of a single paradigm are not sufficient for modeling all aspects of complex systems. Therefore, even though reasoning and simulation systems that utilize a single modeling paradigm are the current norm, we explore a multimodel approach in this paper. A multimodel approach is defined as one in which more than one model-each derived from a different perspective, and utilizing correspondingly distinct reasoning and simulation strategies-are employed. By describing four models which illustrate the use of different modeling techniques, we show how a multimodel approach can enrich the modeling environment and make it correspond better with real world information. Our models come from many sources-Systems and Simulation literature for the modeling of natural phenomena and artificial devices, and Artificial Intelligence and Cognitive Science for the modeling of human intuition and expertise in reasoning. Generalizing from these four models, we suggest that modeling complex systems may best be approached from an integrated architectural viewpoint which combines multiple modeling paradigms. >

We present S-ELF, an evolutionary algorithm that we have developed to learn the context of activation of fuzzy logic controllers implementing fuzzy behaviors for an autonomous agent. S-ELF learns context metarules that are used to coordinate basic behaviors in order to perform complex tasks in a partially and imprecisely known environment. Context metarules are expressed in terms of positive and negated fuzzy predicates. We also show how S-ELF can learn robust and portable behaviors, thus reducing the time and effort to design behavior-based agents.

In this paper, we propose a modeling paradigm that uses fuzzy sets to represent concepts on which control modules of a behavior-based autonomous robot operate. The primitives defined in the modeling paradigm are expressive enough to represent the knowledge needed by planning, coordination, and reactive control of a multi-robot control system. At the same time, it provides a well-founded tool to represent in a compact way the data interpretations needed to reason effectively about what is happening in the world and what is desired to happen. This modeling paradigm makes the design of behavior, planning, and coordination modules easy, since its primitives are simple and expressive. Moreover, it provides a sound framework to deal with uncertainty in sensing and world modeling.

Coordination, planning, and reactivity are important for successful teams of autonomous robots, in dynamic adversarial domains. In this paper, we propose a fuzzy cognitive model to integrate coordination, planning and reactive behaviors in a team of cooperating robots. In our architecture, behavioral modules are used as high-level macro-actions that compose structured plans defined by a flexible multi-agent coordination system. The use of an unifying cognitive model provides an effective tool for seamless integration of reactive and deliberative components in the robots, gaining as much as possible from the presence of different skills and competencies in the team. The control model is designed to be tuned and adapted on-line so that the team strategies and the role of robots in the control schemata can be automatically modified to face different opponent teams, and changes in robot capabilities.

Diagnosis of industrial plants is a complex task, usually performed by systems provided with the plant itself. However, these diagnostic systems are not reliable when the working conditions are different from those expected at design time. In this paper, we present OMISSYS (Opportunistic Model-based diagnosIS SYStem), a system that can diagnose faults in plants whose components are imperfectly described, and where data are affected by uncertainty and imprecision. OMISSYS exploits the available knowledge and data to obtain a suboptimal diagnosis for the detected fault. We represent imperfection using uncertain-fuzzy numbers, a formalism that can represent both uncertainty and imprecision. OMISSYS was tested on realistic examples and it efficiently produced satisfactory diagnoses.

We discuss some guidelines to cope with problems that arise when using cheap and simple sensors on mobile, autonomous, robotic agents. In particular we focus on the perceptual aliasing problem and on the possibility to perform active sensor data acquisition. We present a robotic architecture that we have implemented on a real robot following the proposed guidelines. The obtained mobile robot satisfies the design specifications, navigating autonomously in an unstructured environment.

We present an, omnidirectional vision system me have implemented to provide our mobile robot (Polyphemus"the one with only one eye) with a fast tracking capability. Polyphemus has to recognize elements in a semi-structured environment (the soccer field of Robocup) at a rate close to 20 Hz. We have designed a multi-shaped mirror to optimize the resolution of the image and its vertical coverage. The interpretation system is based on focused, multi-level, and opportunistic procedures.

In this paper, we present a dead reckoning sensor to support reliable odometry on mobile robots. This sensor is based on a pair of optical mice rigidly connected to the robot body and its main advantages are 1) this localization system is independent from the kinematics of the robot, 2) the measurement given by the mice is not subject to slipping, since they are independent from the traction wheels, nor to crawling, since they measure displacements in any direction 3) it is a low-cost solution with a precision comparable to classical shaft encoders. We present the mathematical model of the sensor, its implementation, and some experimental evaluations using the standard UMBmark benchmark for odometry.

Presents OMISSYS (Opportunistic Multimodel-based diagnosIS SYStem), an approach to diagnosis where all the available knowledge is framed into different types of models, belonging to a space defined by: level of abstraction, uncertainty, and epistemological type. All the knowledge is represented using possibly qualitative relationships among variables and possibly approximated values. OMISSYS uses the so-framed incomplete, uncertain, and approximate knowledge to diagnose a complex artifact, such as an industrial plant. It navigates opportunistically through an arbitrary set of models to reach a predefined diagnosis goal. >

The application of Reinforcement Learning (RL) algorithms to learn tasks for robots is often limited by the large dimension of the state space, which may make prohibitive its application on a tabular model. In this paper, we describe LEAP (Learning Entities Adaptive Partitioning), a model-free learning algorithm that uses overlapping partitions which are dynamically modified to learn near-optimal policies with a small number of parameters. Starting from a coarse aggregation of the state space, LEAP generates refined partitions whenever it detects an incoherencebetween the current action values and the actual rewards from the environment. Since in highly stochastic problems the adaptive process can lead to over-refinement, we introduce a mechanism that prunesthe macrostates without affecting the learned policy. Through refinement and pruning, LEAP builds a multi-resolution state representation specialized only where it is actually needed. In the last section, we present some experimental evaluation on a grid world and a complex simulated robotic soccer task.

This article reports on the Sixth Robot World Cup Competition and Conference (RoboCup-2002) Fukuoka/Busan, which took place from 19 to 25 June in Fukuoka, Japan. It was the largest Robo- Cup since 1997 and held the first humanoid league competition in the world. Further, the first ROBOTREX (robot trade and exhibitions) was held with about 50 companies, universities, and institutes represented. A total of 117,000 spectators witnessed this marvelous event. To the best of our knowledge, this was the largest robotic event in history.

Fuzzy rules cooperate in a fuzzy logic controller (FLC) to produce the best action for a given situation. If we have a population of fuzzy rules controlling a device, and we would like to evolve the population to obtain optimal performance by reinforcement learning, rules should compete each other, since we would like to judge their proposals. Therefore, in this approach, cooperation and competition are two opposite, desired activities done by the population members. This may be a problem, if we consider that the evaluation function may be biased, as it may happen, for instance, when we are designing a controlled device such as an autonomous agent. The problem becomes even harder if we would like to learn general rules, i.e., rules containing don't care symbols in their antecedents, thus competing with many groups of other rules, in many different situations. We discuss these issues, and present a solution, implemented in ELF (evolutionary learning of fuzzy rules). We successfully applied ELF to develop autonomous agents, and other fuzzy controlled devices. >

International audience; Due to the complexity and sophistication of the skills needed in real world tasks, the development of autonomous robot controllers requires an ever increasing application of learning techniques. To date, however, learning steps are mainly executed in isolation and only the learned code pieces become part of the controller. This approach has several drawbacks: the learning steps themselves are undocumented and not executable. In this paper, we extend an existing control language with constructs for specifying control tasks, process models, learning problems, exploration strategies, etc. Using these constructs, the learning problems can be represented explicitly and transparently and, as they are part of the overall program implementation, become executable. With the extended language we rationally reconstruct large parts of the action selection module of the AGILO2001 autonomous soccer robots.