A 3D object grasping point learning system is proposed in this paper, which contains object coordinate construction and grasping point learning. A RGBD Convolutional Neural Network (RGBD-CNN) is proposed to classify the orientation type of objects. An object model and the iterative closest point algorithm (ICP) are then applied to estimate the object pose. Hence, the object coordinate can be constructed in the end. The object's normal vector and depth images are obtained first for learning the object grasping region. Then, the grasping range of the end effector (palm) will be simulated on these images. Finally, Convolutional Autoencoder (CAE) is applied to encode the physical characteristics of the simulated palm image. The proposed method can evaluate the grasping points by comparing the features of the simulated palm in the database through a 3D KD-tree. The robot plans a suitable grasping point based on the appointed task by integrating object coordinates and learned grasping points. It is worth mentioning that most research only emphasizes object orientation justification or grasp points generation. However, this research considers the problem of object pose estimation and grasping points generation together. Therefore, the robot can adapt to different task situations in real time. Real experiments demonstrate that the proposed method can recognize various kinds of shapes.

Premature convergence is a critical issue of Particle Swarm Optimization (PSO). The weak global search capability causes particles trapped in local minima at early stage of learning process. There is several research dedicate to solve this problem over the decade. This paper proposes a new algorithm combined Isolation Forest and Particle Swarm Optimization called Isolation Forest Backward Particle Swarm Optimization (IFB-PSO). The proposed new learning scheme helps particles escaping from local minima. The particle will jump backward to the targeted position when the particle trapped over specific iterations. The destination is precisely selected by Isolation Forest to endow the backward particle hopeful future. IFB-PSO is evaluated by a classic benchmark suite, cart-pole problem, and mountain car problem. Experimental results show that IFB-PSO gets competitive results on the benchmark suite with different dimensions and two control problems in comparison with 11 well-known optimization algorithms. The behavior of backward particles is also analyzed to inspect the utility and efficiency of the backward process.

This paper presents an intuitive human-robot interface system (iHRIS), where the deep deterministic policy gradient (DDPG) with hindsight experience replay (HER) training method is proposed to accelerate model training. The system consists of a motion capture system and a motion learning network. The motion capture system includes an RGB-D camera and an operating glove. The position of the human operator's hand is estimated by Openpose using the RGB-D images, while the hand's posture is determined by the information captured by the glove. An inertial measurement unit (IMU) and a microprocessor are equipped on the glove. The IMU data is calibrated using the Recursive Least Squares (RLS) method and computed using Madgwick's algorithm. Based on the observed position and posture of the human operator's hand, a motion can be generated. This motion is then trained using the DDPG network with the Reverse Curriculum Generation (RCG) method. The network has an Actor-Critic structure and a replay experience buffer, which makes it more feasible and helps avoid overfitting. Furthermore, HER is integrated into the network to enhance convergence speed and performance. Finally, the experiments demonstrate that the proposed iHRIS enables real-time imitation of the human operator by the robot, and the imitated motion can be learned by the DDPG network.

In this article, the adaptive-network-based fuzzy inference system (ANFIS) is combined with the double deepQ-network (DDQN) to realize a fuzzy DDQN (FDDQN) such that a humanoid robot can generate a linear inverted pendulum model-based gait pattern in real time. The FDDQN not only allows the humanoid robot to correct the gait pattern instantly but also improves its stability. The proposed scheme is designed and implemented in a toddler-sized humanoid robot called Louis. First, four pressure sensors are installed on the bottom of the sole and one inertial measurement unit is set up on the trunk of the robot. A wireless communication chip is employed to transfer the data to a computer to determine the required parameters for the robot. Next, a control system based on the Linux operating system is developed. The values of the center of pressure and acceleration obtained with the ANFIS are adopted to train the DDQN. The proposed neural network comprises four layers, and the model is cautiously selected to avoid overfitting. The proposed scheme is verified using a robot simulator and then real-time-tested on Louis. The experimental results indicate that the FDDQN can provide the robot timely feedback during walking as well as helps it in adjusting the gait pattern independently. The balancing of the robot through effective dynamic feedback is similar to the balancing ability of an infant learning to walk.

Inspired by the self-exploring learning approach, this paper proposes an object-learning system in which a robot interacts with objects to obtain their features and construct object concepts. The system consists of three kinds of features: interaction features, visual features, and intrinsic features. When the robot interacts with an object, it observes the changes in the object to obtain its interaction features. At the same time, the robot learns the visual features of the object. The intrinsic features are the properties of the object. Models of the relationships among the three kinds of features are constructed through an Artificial Bee Colony based Random Forest algorithm and a Convolutional Neural Network. The established models help the robot to predict the properties of new objects and to make decisions. Two experiments are constructed in this paper: the service-providing task and the stacking task. In the former, the robot decides on an appropriate object, using the object concept models, to accomplish an appointed task. In the second experiment, the robot uses a Gated Recurrent Neural Network to learn the stacking sequence of various objects. All the experimental results demonstrate that the robot can build object concept models by interacting with objects, and can utilize these models to accomplish various tasks.

This paper presents a Human Partner System (HPS) that is composed of three sub-systems: a hearing system, a speaking system, and a vision system. Coordinated with these systems, HPS can recognize people and dialog with them. To attract a human's attention for interaction, this paper combines the difference image method and the GrabCut algorithm for HPS. To assist humans in their daily lives and to enhance their interactive fun, HPS has a short-term memory function and can read out new email when a known person appears in her line of sight. To allow HPS to search for a target object in a complicated environment, this paper proposes the double peak continuously adaptive mean shift (DPCAMS) algorithm, which combines the contours and color information of target object. This algorithm is easy to implement and the experimental result demonstrates that this algorithm is faster than the speeded up robust features (SURF) algorithm.

This paper proposes a 3D vision based object grasping posture learning system. In this system, the robot recognizes the orientation of the object to decide the grasping posture, whereas selects a feasible grasping point by detecting the surrounding. When the planned posture is not good enough, the proposed learning system adjusts the position of the end effector real time. The learning system is inspired by a book entitled, Thinking, Fast and Slow, and consists of two subsystems. The subsystem I judges whether the pose of the object is learned before, and plans a grasping posture by past experience. When the pose of the object is not learned before, the subsystem II learns a position adjustment by the real time information form the motor angels and the images. Finally, the method proposed in this paper is applied to the home service robot and is proven the feasibility by the experimental results.

Inverse kinematics is a general method for defining the joint angles of the robot arm. This method provides an efficient way to control the robot arm for several tasks. However, the server motors or the mechanism design of the robot arm may not always be ideal. If the motor consumption is existed, the error of the final position of the robot arm will be increased. In order to solve this problem, this paper proposes an intelligent method for the posture calibration of the robot arm. In this paper, the particle swarm optimization (PSO) algorithm and the proposed neural network model are integrated to calibrate the kinematics of the robot arm. The experimental results show that the control error can be reduced by applying the proposed method. The feasibility and practicality of the proposed method are also validated in the experiments.

This paper presents a recognition system for understanding the words of home-service-related sign language. Because the data received from a sensor are sequential, the hidden Markov model (HMM) that has been successfully applied to speech signals is chosen as a classifier. However, the number of states in the HMM model should be decided upon first before constructing the HMM classifier. To solve this problem, an entropy-based K -means algorithm is proposed to evaluate the number of states in the HMM model with an entropy diagram. Four real datasets are utilized to verify the developed entropy-based K -means algorithm. Moreover, a data-driven method is given to combine the artificial bee colony algorithm with the Baum-Welch algorithm to determine the structure of HMM. The database contains 11 home-service-related Taiwan sign language words and each word is performed ten times, five males and five females are invited to perform such words. Finally, the recognition system is established by 11 HMM models, and the cross-validation demonstrates an average recognition rate of 91.3%.

This paper proposes a control method that improves the ability of adult-sized humanoid robots to adapt to weightlifting situations. In order to achieve the goal of having humanoid robots automatically balance their motion for weight-lifting situations, feedback control is added to the motion control system. The feedback sensors include a three-axis accelerometer and a three-axis gyroscopic, which would be processed by Kalman filter, as well as eight force sensors providing the zero moment point (ZMP) information on the robot. These feedback signals are used as the input of a Fuzzy Q-learning controller, which adjusts the motions to keep the stabilization of the robot. The Fuzzy Q-learning controller consists of two stages: one is the stage of fitting the output weights of each pose in motion patterns, and the second is training the rule-table of the controller. The experiment shows that the controller allows the adult-sized robot to walk stably in weight-lifting situation. Thus, the developed controller indeed keeps the balance of the robot in different situations, which gives the robot the ability to adapt to various environments in the manner of human beings.

This paper proposes an artificial DNA assisted queen bee genetic algorithm (DNA+QBGA) to learn the gains, control structures, membership functions, and rules of the fuzzy controller. The queen bee genetic algorithm (QBGA) possesses simple and fast evolution process to figure out the best parameters and the DNA computing is adopted to determine the structure of fuzzy controller. Each fuzzy control structure can be defined by a different bee hive, which contains the control structure and dimension of the gain. The presented DNA+QBGA can make the membership functions and rules communicate with one another among different control structures. Moreover, a novel three-step crossover operation is investigated such that the crossover between different odd dimensions of membership functions can be made. Step one is that the dimensions of parents (queen and drone) and the offspring (brood) are expanded to the same dimension resolved by their least common multiple. Step two is to randomly select the genes from the parents in the corresponding space. Step three is that the offspring gene is calculated by the real-code crossover between their parents. Finally, the simulation results of the fuzzy controlled cart-pole and chaotic systems demonstrate the feasibility and effectiveness of the proposed schemes.

A fast color information setup based on evolutionary programming (EP) like particles swarm optimization (EPSO) for the manipulator control system is examined in this paper. The first step for a manipulator to grasp and place color objects into the correct location is to correctly identify the RGB or the corresponding hue, saturation, value (HSV) color model. The commonly used method to determine the thresholds of HSV range is manual tuning, but it is time-consuming to find the best boundary to segment the color image. This paper proposes a new method to learn color information, which is executed by semiautomatic learning. At first, the watershed algorithm incorporates user interactions to segment the color image and obtain the target image. Then, the comparison between the target image and the original image is utilized to build a lookup table (LUT) of color information, where three HSV thresholds are learned by PSO methods. Because the convergence speed of well-known PSO algorithms is slow and may be stuck in the local minimum, we present the EPSO method realized by applying EP to the PSO method. Moreover, a novel approach is investigated to escape the local minimum supposing the particles are stuck in the local minimum. Finally, both the numerical and experimental results demonstrate that the developed approach can not only rapidly learn the thresholds to segment a color image but can also jump out the local minimum.

The design and implementation of particle swarm optimization (PSO) gait learning method for adult-sized humanoid robots is proposed in this paper. In order to reduce the motor damage and let train motions more convenient, a robotics simulator system for humanoid robots is designed. This robotics simulator system is established by an open source software-Open Dynamics Engine (ODE). The model of David developed by aiRobots laboratory is a combination of rigid bodies and joints. The humanoid robot is trained on the robotics simulator system with PSO method, which chooses the trajectory of robot's center of mass as the fitness value to learn faster and stable gait automatically. The results of the experiment show that the motions which play on the robotics simulator system are very similar to the real motions, so it can be utilized as the motion training platform. The result of the PSO gait learning method has great performance on the robotics simulator system. The humanoid robot learns gait pattern from marking time to moving center of mass and swing its legs. Finally, this gait let the real humanoid robot walk forward at 14.5 cm/s.

In this paper, a novel computing methodology called DNA-RGA computing algorithm, which combines the characteristics of DNA and Real Coded Genetic algorithm, is proposed to design fuzzy controller and to improve the performance of systems. In order to explore the major merit of DNA-RGA computing algorithm in the field of control systems, this paper presents a variable PID-like fuzzy controller design based on aforementioned methodology to attain the proper types of controllers, such as P-like, PD-like, PI-like, or PID-like fuzzy controllers, corresponding to different plants. Finally, the simulation results demonstrate the validity and feasibility of the proposed methodology.

In this paper, a novel observer-based adaptive fuzzy neural network (FNN) control scheme for robotic systems is proposed for tracking performance and to suppress the effects caused by uncertainties, and disturbances. A PSO-SA based adaptive FNN system is used to approximate an unknown system from the manipulation of the model following tracking errors. The proposed scheme uses an observer, which allows for identifying the state of an unknown state in the system, simultaneously. It is shown that the proposed control scheme can guarantee the better tracking performance and suppress internal uncertainties or external disturbance. Simulations are given to show the validity and confirm the performance of the proposed scheme.

This paper proposes the implementation of fuzzy motion control based on reinforcement learning (RL) and Lagrange polynomial interpolation (LPI) for gait synthesis of biped robots. First, the procedure of a walking gait is redefined into three states, and the parameters of this designed walking gait are determined. Then, the machine learning approach applied to adjusting the walking parameters is policy gradient RL (PGRL), which can execute real-time performance and directly modify the policy without calculating the dynamic function. Given a parameterized walking motion designed for biped robots, the PGRL algorithm automatically searches the set of possible parameters and finds the fastest possible walking motion. The reward function mainly considered is first the walking speed, which can be estimated from the vision system. However, the experiment illustrates that there are some stability problems in this kind of learning process. To solve these problems, the desired zero moment point trajectory is added to the reward function. The results show that the robot not only has more stable walking but also increases its walking speed after learning. This is more effective and attractive than manual trial-and-error tuning. LPI, moreover, is employed to transform the existing motions to the motion which has a revised angle determined by the fuzzy motion controller. Then, the biped robot can continuously walk in any desired direction through this fuzzy motion control. Finally, the fuzzy-based gait synthesis control is demonstrated by tasks and point- and line-target tracking. The experiments show the feasibility and effectiveness of gait learning with PGRL and the practicability of the proposed fuzzy motion control scheme.

The main goal of this study is to design a full-car active suspension controller with a reduced order observer for vehicles so as to improve ride comfort and reduce the suspension deflection. The proposed fuzzy sliding-mode control (FSMC) consists of the sliding-mode control (SMC) and the fuzzy logic control (FLC), where the SMC can decrease the suspension deflection of the car and the FLC can improve the ride comfort of the passengers. The full-car model of an automobile is firstly examined in this paper. The stability property of the fuzzy sliding-mode controlled active suspension system is confirmed by the Lyapunov stability analysis. In order to make comparison, we also introduce the optimal active suspension control (OASC) scheme. Three kinds of road profiles, a bump road, a random white noise and a power spectral density road profile, are exploited to test the performance. All the computer simulations demonstrate that the proposed FSMC can provide the best ride comfort and the least suspension deflection among all the examined controllers under all these road profiles.

In this paper, a combined intelligent technique is introduced for the trajectory tracking control of a nonholonomic wheeled mobile robot (WMR), which comprises an interval type-2 fuzzy kinematic control (IT2-FKC) and an interval type-2 fuzzy terminal sliding-mode dynamic control (IT2-FTSMDC). Firstly, an interval type-2 fuzzy logic controller designed for the kinematic model of the WMR is introduced, and then the IT2-FTSMDC is developed for the dynamic model of the WMR, which is a combination of the interval type-2 fuzzy logic control (IT2-FLC) and the terminal sliding-mode dynamic control (TSMDC). The validity of the proposed method is demonstrated via computer simulations. The simulation results show that the tracking performance of the IT2-FTSMDC is better than that of the FTSMDC.

The observer-based integral adaptive fuzzy sliding mode controllers are developed for a class of uncertain nonlinear systems. By designing the state observer, the fuzzy systems, which are used to approach any unknown functions, it can be constructed using the state observer-based estimations. Based on Lyapunov stability theorem, the proposed integral adaptive fuzzy sliding mode control system can guarantee the stability of the whole closed-loop systems and obtain good tracking performance as well. The proposed methods are applied to an inverted pendulum system achieve satisfactory simulation results.

This paper mainly covers the development of a FPGA-based fuzzy controller and image processing system for a small-sized humanoid robot. All the computations are operated on an FPGA board including the real-time image processing and the fuzzy logic controller design for PK event in FIRA RoboWorld cup. At first, the specification of the hardware is introduced. The image processing is then employed for target recognition. The control strategy system for PK event is also developed. Finally the experiments are demonstrated to verify feasibility of the proposed control system.

This paper presents a robust H∞fuzzy controller for a class of T-S time-delay discrete fuzzy bilinear system (DFBS). Firstly, a discrete robust H∞fuzzy controller is proposed to stabilize the T-S time-delay DFBS with disturbance. Secondly, based on the Schur complement and some variable transformation, the stability conditions of the overall fuzzy control system are formulated by linear matrix inequalities (LMIs). Finally, a numerical example is utilized to demonstrate the validity and effectiveness of the proposed control scheme.

The motivation of this paper is to confer the study of omni-directional trajectory motion control implemented by the SOPC system. In the hardware architecture, four mutual orthogonal omni-directional wheels are horizontally established on the plane of the chassis and four optical encoders are equipped with DC motors to read the data of angular velocity and compute the posture of the surveillance and security robot (SSR). The robot will track the desired trajectory which has been generated by the trajectory generation system. We present a fully-fuzzy trajectory tracking system which can compensate for the errors of the velocity and regulate the errors of the position based on the dynamic model. After dealing with the information, the correct trajectory motion can be determined. Finally, the experimental results indicate that the proposed omni-directional trajectory control scheme can be successfully applied to the SSR.

The main theme of this paper is to present robust fuzzy controllers for a class of discrete fuzzy bilinear systems. First, the parallel distributed compensation method is utilized to design a fuzzy controller, which ensures the robust asymptotic stability of the closed-loop system and guarantees an H(infinity) norm-bound constraint on disturbance attenuation for all admissible uncertainties. Second, based on the Schur complement and some variable transformations, the stability conditions of the overall fuzzy control system are formulated by linear matrix inequalities. Finally, the validity and applicability of the proposed schemes are demonstrated by a numerical simulation and the Van de Vusse example.

This paper describes a methodology to determine optimum design parameters of the fuzzy logic control (FLC) for active suspension system (ASS) with full-car model using the evolutionary programming (EP) method. The ASS for full-car model design is a difficult problem especially when the system’s multi-objectives are simultaneously considered. In the conventional FLC, parameters adjustment is done by the system response, expert knowledge or trial-and-error scheme. In this paper, EP algorithm is adopted to search the optimum parameters of the FLC for ASS by minimizing a fitness function that composed of all the desired performance of a full-car model. In order to make comparison, we also introduce the optimal active suspension control (OASC) scheme. Two kinds of road profiles, a bumped road and a white noise random road, are exploited to test the performance. All the computer simulations demonstrate that the proposed EP-based FLC can provide the best ride comfort and the least suspension deflection among all the examined controllers under all these road profiles.

This paper presents the composite fuzzy control to stabilize the nonlinear singularly perturbed (NSP) systems with guaranteed Hinfincontrol performance. We use the Takagi-Sugeno (T-S) fuzzy model to construct the singularly perturbed fuzzy (SPF) systems. The corresponding fuzzy slow and fast subsystems of the original SPF system are also obtained. At first, a set of common positive-define matrices and the controller gains are determined by the Lyapunov stability theorem and linear matrix inequality (LMI) approach. Then, a sufficient condition is derived for the robust stabilization of NSP systems. The composite fuzzy control will stabilize the original NSP systems for all epsivisin(0,epsiv*) and the allowable perturbation bound epsiv*can be determined via some algebra inequalities. A practice example is adopted to demonstrate the feasibility and effectiveness of the proposed control scheme

This paper proposes a fuzzy bilinear model for a class of nonlinear systems and a fuzzy controller to stabilize such systems. By examination of a modeling problem, we describe how to transform a nonlinear system into a bilinear one via Taylor's series expansion and then we adopt the Takagi-Sugeno (T-S) fuzzy modeling technique to construct a fuzzy bilinear model. For controller design, the parallel distributed compensation (PDC) method is utilized to stabilize the fuzzy bilinear system (FBS), and some sufficient conditions are derived to guarantee the stability of the overall fuzzy control system via linear matrix inequalities (LMIs). Moreover, we propound some sufficient conditions for robust stabilization of the FBS with parametric uncertainties. Finally, a numerical example and the Van de Vusse model are utilized to demonstrate the validity and effectiveness of the proposed FBS.

In this paper, we propose a novel interval type-2 fuzzy logic controller (IT2FLC) for interval system. The precise mathematical model of the controlled plant is not required to design this IT2FLC. Design procedure of the IT2FLC is explored in detail. A typical linear interval system with 50% parameter variations is adopted to demonstrate the effectiveness of the proposed IT2FLC. For better understanding the performance of IT2FLC, numerous shapes of membership functions and variation of rule numbers of rule table are evaluated for simulation thoroughly. The simulation results are compared with those from type-1 fuzzy logic controller (T1FLC) under same conditions. It shows that the performance of IT2FLC is much better than that of T1FLC if the number of rule is reduced.

The theme of this paper is to design a real-time fuzzy target tracking control scheme for autonomous mobile robots by using infrared sensors. At first two mobile robots are setup in the target tracking problem, where one is the target mobile robot with infrared transmitters and the other one is the tracker mobile robot with infrared receivers and reflective sensors. The former is designed to drive in a specific trajectory. The latter is designed to track the target mobile robot. Then we address the design of the fuzzy target tracking control unit, which consists of a behavior network and a gate network. The behavior network possesses the fuzzy wall following control (FWFC) mode, fuzzy target tracking control (FTTC) mode, and two fixed control modes to deal with different situations in real applications. Both the FWFC and FTTC are realized by the fuzzy sliding-mode control scheme. A gate network is used to address the fusion of measurements of two infrared sensors and is developed to recognize which situation is belonged to and which action should be executed. Moreover, the target tracking control with obstacle avoidance is also investigated in this paper. Both computer simulations and real-time implementation experiments of autonomous target tracking control demonstrate the effectiveness and feasibility of the proposed control schemes.

This paper presents some novel results for stabilizing singularly perturbed (SP) nonlinear systems with guaranteed control performance. By using Takagi-Sugeno fuzzy model, we construct the SP fuzzy (SPF) systems. The corresponding fuzzy slow and fast subsystems of the original SPF system are also obtained. Two fuzzy control designs are explored. In the first design method, we propose the composite fuzzy control to stabilize the SPF subsystem with H/sup /spl infin// control performance. Based on the Lyapunov stability theorem, the stability conditions are reduced to the linear matrix inequality (LMI) problem. The composite fuzzy control will stabilize the original SP nonlinear systems for all /spl epsiv//spl isin/(0,/spl epsiv//sup */) and the upper bound /spl epsiv//sup */ can be determined. For the second design method, we present a direct fuzzy control scheme to stabilize the SP nonlinear system with H/sup /spl infin// control performance. By utilizing the Lyapunov stability theorem, the direct fuzzy control can guarantee the stability of the original SP nonlinear systems for a given interval /spl epsiv//spl isin/[/spl epsiv/_,/spl epsiv/~]. The stability conditions are also expressed in the LMIs. Two SP nonlinear systems are adopted to demonstrate the feasibility and effectiveness of the proposed control schemes.

In this paper, the concepts of car maneuvers, fuzzy logic control (FLC), and sensor-based behavior are merged to implement the human-like driving skills in the garage-parking task by an autonomous car-like mobile robot (CLMR). We decompose the garage-parking control into four modes to synthesize the fuzzy garage parking control (FGPC). Computer simulation results illustrate the effectiveness of the proposed control schemes. The setup of the CLMR is provided, where the FGPC is implemented on a field-programmable gate array (FPGA) chip. Finally, the real-time experiments of the FPGA-based CLMR for the garage-parking task demonstrate the feasibility in a practical car maneuvering.

This paper is devoted to design and implement a car-like mobile robot (CLMR) that possesses autonomous garage-parking and parallel-parking capability by using real-time image processing. For fuzzy garage-parking control (FGPC) and fuzzy parallel-parking control (FPPC), feasible reference trajectories are provided for the fuzzy logic controller to maneuver the steering angle of the CLMR. We propose two FGPC methods and two FPPC methods to back-drive or head-in the CLMR to the garage and the parking lot, respectively. Simulation results illustrate the effectiveness of the developed schemes. The overall experimental setup of the parking system developed in this paper is composed of a host computer, a communication module, a CLMR, and a vision system. Finally, the image-based real-time implementation experiments of the CLMR demonstrate the feasibility and effectiveness of the proposed schemes.

This paper is devoted to designing and implementing a behavior based fuzzy logic controller for a one-on-one robot soccer system, which can be considered as a visual servoing system. Both the behavioral assemblage and fuzzy motion control of the soccer robot will be addressed in detail. Finally, both computer simulations and practical experiments are used to demonstrate the feasibility and effectiveness of the proposed control.

This paper presents a control scheme for the speed controller in a 2-mass motor drive system. The speed controller is based on state feedback compensation. The state observer obtains unmeasured states for this system. It is not only accuracte but also fast by utilizing the integrated fuzzy observer. The optimal controller configuration is composed by a load compensator and a linear quadratic (LQ) regulator including an integrator. The load disturbance is directly compensated by the estimated load. Simulation results show that the proposed integrated fuzzy observer provide the better estimation performance than that of the Kalman filter and the proposed control scheme can effectively track the desired speed in the presence of load disturbance.

The aim of the paper is to determine optimal motion planning for an autonomous mobile robot (AMR) moving in an environment with obstacles. We propose two motion planning methods, one is the linear vertex decision mechanism (LVDM) and the other is the fuzzy logic decision mechanism (FLDM). Computer simulations are explored to compare the performance of these two mechanisms. Furthermore, we apply genetic algorithms (GAs) to the LVDM to select the optimal weighting factor and we also adopt GAs in the FLDM such that the best membership function and/or the number of fuzzy control rules can be obtained. Computer simulations of the evolved LVDM and FLDM with GAs are also provided. All the simulations demonstrate that the proposed schemes can indeed guide the AMR even if the environment is filled with obstacles.

Fuzzy controllers implemented in hardware can operate with much higher performance than software implementations on standard microcontrollers. In this paper, a dynamic fuzzy logic controller (FLC) and its hardware architectures are proposed. The FLC is realized on a CLPD chip. The presented circuits can dynamically generate fuzzy inference results when they are activated, so there is no need to design a large scale of ROM to store the fuzzy rules. Even we increase the resolutions of input and output variables and the universes of discourses, the increments of the gate counts are very few. Finally, a garage parking control system is used to demonstrate the effectiveness of the developed chip.

A new application of fuzzy set theory to the state estimation problem is presented. The Lyapunov function here is utilized as a performance index to formulate the fuzzy inference rules. The proposed methodology not only has better state estimation in comparison with the traditional Kalman filter but the stability property is also guaranteed.