Sun Zengqi

Observer based adaptive controller design of flexible manipulators using time-delay neuro-fuzzy networks

In this paper, a dynamical time-delay neuro-fuzzy controller is proposed for the adaptive control of a flexible manipulator. It is assumed that the robotic manipulator has only joint angle position measurements. A linear observer is used to estimate the robot joint angle velocity. For a perfect tracking control of the robot, the output redefinition approach is used in the adaptive controller design using time-delay neuro-fuzzy networks. The time-delay neuro-fuzzy networks with the rule representation of the TSK type fuzzy system have better learning ability for complex dynamics as compared with existing neural networks. The novel control structure and learning algorithm are given, and a simulation for the trajectory tracking of a flexible manipulator illustrates the control performance of the proposed control approach.A dynamical time-delay neuro-fuzzy controller is proposed for the adaptive control of a flexible manipulator. It is assumed that the robotic manipulator has only joint angle position measurements. A linear observer is used to estimate the robot joint angle velocity. For perfect tracking control of the robot, an output redefinition approach is used in the adaptive controller design using time-delay neuro-fuzzy networks. The time-delay neuro-fuzzy networks with rule representation of a Takagi-Sugeno-Kang type fuzzy system have better learning ability for complex dynamics as compared with existing neural networks. The control structure and learning algorithm are given, and a simulation for the trajectory tracking of a flexible manipulator illustrates the control performance of the proposed control approach.

Transport layer protocol reconfiguration for network-based robot control system

Internet robot control system is a typical real-time network control system (NCS). The data stream of the NCS is comprised of crucial data and real-time data. The crucial data demands more reliability for the network protocol, which requires low error rate, low loss rate and high throughput. And the real-time data has more delay sensitivity, requiring minimal delay and delay jitter. However, the request of these two types of data is contrary. Now existing protocol, such as TCP or UDP, can cater for only one type of data. This paper presents a new transport layer protocol. The protocol can reconfigure itself to cater for both of crucial and real-time request.

A fuzzy neural network and its application to controls

A fuzzy neural network is presented. The network is composed of two parts: an antecedent network and a consequent network. The network acts as a fuzzy logic controller. The antecedent network matches the premises of the fuzzy rules and the consequent network implements the consequences of the rules. The network has similar structure to a CMAC. An example for mapping a nonlinear function shows a good results of the fuzzy neural network. A control structure based on the fuzzy neural network and a BP network is given, which has the same structure as the model reference adaptive control system.

Dynamic modeling, control and simulation of flexible dual-arm space robot

Flexible Multi-Arm Space Robot is a highly nonlinear and coupled dynamic system. Using the assumed mode method to describe the elastic deformation, the dynamic model of flexible dual-arm space robot is build by the Lagrange approach. The inversion dynamic control method is performed to solve the tracking problem. Then a serial of simulations of tracking control of two kinds of typical trajectory have done. Good tracking control results obtained at the simulations of the flexible dual-arm space robot.

Accurate and stable vision in robot soccer

Robot soccer requires vision to be fast, robust and accurate to capture environment situation. In this paper a new method to improve accuracy and stability of vision system in robot soccer is presented. The main topics are camera calibration and robot localization with colored patterns. The lens distortion is successfully compensated and image coordinates is correctly projected to real field, thus achieving a more accurate estimation of object detection. Stability of the position and orientation of a robot is significantly improved with well-chosen colored patterns. Both simulation and experiment results show that our method performs well to provide accurate and stable vision in robot soccer.

Reinforcement learning method-based stable gait synthesis for biped robot

A stable gait generation algorithm based on T-S type fuzzy learning net is proposed in this paper. Gait generation is divided into model construction and error learning. Reference gait model and dynamic model are firstly constructed with basic gait geometric knowledge. Then reinforcement learning method is introduced into T-S type fuzzy network to learn the gain parameters for hip trajectory adjustment. Few fuzzy rules with ZMP stable knowledge are needed to formulate the nonlinear relation between the ZMP curve and hip trajectory. The problem of finding multi-variables in continuous space is also simplified to searching independent action gains simultaneously. Results of simulation on a biped robot proved the feasibility.

Analysis and synthesis of fuzzy stochastic systems via LMI approach

This paper studied a general class of nonlinear stochastic systems, which can be approximated by T-S fuzzy model. The problem both the control and the state entering into the diffusion term is discussed here. A PDC state feedback controller is proposed to guarantee the mean-square stability of the closed-loop system. All the results are represented by the linear matrix inequalities.

Stable adaptive control for robot trajectory tracking using neural networks

Existing stable adaptive control approaches using neural networks have been developed mostly in continuous time systems for robot trajectory tracking. This paper investigates the discrete time case. A novel scheme for integrating a neural network (NN) approach with an adaptive implementation of the sliding mode control with the sector is developed. The sliding mode control with the sector serves two purposes, one is to provide the global stability of the closed loop system, the other is to improve the tracking performance. The whole system stability and tracking error convergence are proved by Lyapunov techniques which yield a NN weight tuning algorithm.

Mission Planning for Unmanned Aerial Vehicles

This article presents the implementation of mission planning for unmanned aerial vehicles (UAV). A safe-ring method for real-time path planning of UAV is proposed. Threat modeling, different types of reconnaissance are discussed before the algorithm is described. Kinematical constraints are satisfied with a model which has the same structure as the physical vehicle. A feasible state trajectory was generated, which can be followed by a standard autopilot. The demonstration of the mission planning system shows that the implementation is efficient and satisfying

Design and implementation of Scilab fuzzy logic toolbox

Scilab is a comprehensive scientific package freely distributed by INRIA. This paper presents the design and implementation of a fuzzy logic toolbox based on Scilab, which allows the user to solve his control problem using fuzzy logic with very little effort. The fuzzy logic toolbox is written in the Scilab language and Tcl/TK. It provides complete functions for inference, an easy to use graphical editor for building complex models of fuzzy logic systems, and a simulator for Scicos. Applications of fuzzy in systems and control, and the use of fuzzy toolbox are illustrated by a simple example