Mauricio Figueiredo

Design of fuzzy systems using neurofuzzy networks

This paper introduces a systematic approach for fuzzy system design based on a class of neural fuzzy networks built upon a general neuron model. The network structure is such that it encodes the knowledge learned in the form of if-then fuzzy rules and processes data following fuzzy reasoning principles. The technique provides a mechanism to obtain rules covering the whole input/output space as well as the membership functions (including their shapes) for each input variable. Such characteristics are of utmost importance in fuzzy systems design and application. In addition, after learning, it is very simple to extract fuzzy rules in the linguistic form. The network has universal approximation capability, a property very useful in, e.g., modeling and control applications. Here we focus on function approximation problems as a vehicle to illustrate its usefulness and to evaluate its performance. Comparisons with alternative approaches are also included. Both, nonnoisy and noisy data have been studied and considered in the computational experiments. The neural fuzzy network developed here and, consequently, the underlying approach, has shown to provide good results from the accuracy, complexity, and system design points of view.

Comparison of Yager's level set method for fuzzy logic control with Mamdani's and Larsen's methods

A new fuzzy reasoning method for fuzzy control recently proposed by R. Yager is investigated. A comparison with the most useful fuzzy control schemes, for a first-order with time delay process, is carried out. The results obtained show that Yagers method is superior from the point of view of both computational burden and control system behavior. >

Learning algorithms for a class of neurofuzzy network and application

A class of neurofuzzy networks and a constructive, competition-based learning procedure is introduced. Given a set of training data, the learning procedure automatically adjusts the input space portion to cover the whole space and finds membership functions parameters for each input variable. The network processes data following fuzzy reasoning principles and, due to its structure, it is dual to a rule-based fuzzy inference system. The neurofuzzy model is used to forecast seasonal streamflow, a key step to plan and operate hydroelectric power plants and to price energy. A database of average monthly inflows of three Brazilian hydroelectric plants located at different river basins was used as source of training and test data. The performance of the neurofuzzy network is compared with period regression, a standard approach used by the electric power industry to forecast streamflows. Comparisons with multilayer perceptron, radial basis network and adaptive neural-fuzzy inference system are also included. The results show that the neurofuzzy network provides better one-step-ahead streamflow forecasting, with forecasting errors significantly lower than the other approaches.

Simultaneous emergence of conflicting basic behaviors and their coordination in an evolutionary autonomous navigation system

An evolutionary autonomous navigation system is described that evolves two basic, conflicting behaviors, namely, obstacle avoidance and target seeking, as the system acquires skill to coordinate them (behavior emergence and coordination skill acquisition happen simultaneously). Simulation experiments show promising results: the number of target captures increases and the number of collisions stabilizes, as generations proceed. They confirm the evolutionary learning capacity of the reactive navigation system proposed.

Autonomous navigation system applied to collective robotics with ant-inspired communication

Research in collective robotics is motivated mainly by the possibility of achieving an efficient solution to multi-objective navigation tasks when multiple robots are employed, instead of a single robot. Several approaches have already been tried in multi-robot systems, but the bio-inspired ones are the most frequent. This paper proposes to augment an autonomous navigation system based on learning classifier systems for using in collective robotics, introducing an inter-robot communication mechanism inspired by ant stigmergy, with each robot acting independently and cooperatively. The navigation system has no innate basic behavior and all knowledge necessary to compose the decision-making artifact is evolved as a function of the environmental feedback only, during navigation. Repulsive and/or attractive pheromone trails are produced by the robots along navigation, following very simple rules. Basically, each robot has to perform obstacle avoidance and target search, and the status of the pheromone level at the position currently occupied by each robot will influence the coordination of the two fundamental behaviors. Experiments are performed in simulation, with comparative results indicating that the presence of the pheromone trails is responsible for significant improvements in the capture rate and in the length of the route adopted by each robot.

A classifier system in real applications for robot navigation

This paper presents an autonomous evolutionary system applied to control a mobile robot in unknown environments. The navigation system learns efficiently to deal with situations where the robot must capture targets avoiding collisions with obstacles. Toward this end, robot direction and speed must be properly defined. The evolutionary approach is based on a version of classifier systems, responsible for the proposition of a competitive process involving rules of elementary behaviour. A virtual environment is used to evolve the controller, a Khepera II robot is submitted to real navigation tasks, with no significant degradation in performance. As an additional experiment, the controller is also evolved in a real environment, and validated in a different and more complex environment, not previously experimented, attesting the generalization capability of the proposal.

Modular Neural Network and Classical Reinforcement Learning for Autonomous Robot Navigation: Inhibiting Undesirable Behaviors

Classical reinforcement learning mechanisms and a modular neural network are unified for conceiving an intelligent autonomous system for mobile robot navigation. The conception aims at inhibiting two common navigation deficiencies: generation of unsuitable cyclic trajectories and ineffectiveness in risky configurations. Distinct design apparatuses are considered for tackling these navigation difficulties, for instance: 1) neuron parameter for memorizing neuron activities (also functioning as a learning factor), 2) reinforcement learning mechanisms for adjusting neuron parameters (not only synapse weights), and 3) a inner-triggered reinforcement. Simulation results show that the proposed system circumvents difficulties caused by specific environment configurations, improving the relation between collisions and captures.

A hierarchical neuro-fuzzy approach to autonomous navigation

This work proposes a fuzzy-neural-network-based controller that considers the direction and velocity of navigation as controllable terms. The controller is composed of a number of in-born modules responsible for instant actions at each step of navigation. These in-born modules are then coordinated by a neuro-fuzzy module which exhibits learning. The learning processes take place after collisions against obstacles, after targets are reached and, due to a special memory structure, a learning process may also occur due to a remembering process. Thus, the model proposed carries a high degree of autonomy since the controller learns on its own how to coordinate its basic behaviors, while the navigation occurs.

Intelligent autonomous navigation for mobile robots: spatial concept acquisition and object discrimination

An autonomous system able to construct its own navigation strategy for mobile robots is proposed. The navigation strategy is molded from navigation experiences (succeeding as the robot navigates) according to a classical reinforcement learning procedure. The autonomous system is based on modular hierarchical neural networks. Initially, the navigation performance is poor (many collisions occur). Computer simulations show that after a period of learning, the autonomous system generates efficient obstacle avoidance and target seeking behaviors. Experiments also offer support for concluding that the autonomous system develops a variety of object discrimination capability and of spatial concepts.

Adaptive neuro-fuzzy modeling

A new class of adaptive neural fuzzy networks for fuzzy modeling is introduced in this paper. It learns the essential parameters to model a fuzzy system such as fuzzy rules and membership functions. Fuzzy rules are easily encoded and decoded from its structure. These neural fuzzy networks also rigorously emulate fuzzy reasoning mechanisms. Because of their knowledge representation and computational features we can see the proposed system either as a neural fuzzy network or a fuzzy system. Thus, linguistic models are easily extracted from their structure. Simulation results and comparison analysis show that the proposed network has good performance considering two criteria: accuracy and number of rules derived.