Hybrid control strategies for a five-finger robotic hand

This paper presents the fuzzy control of a five fingered robot hand by using the genetic algorithm and TMS320F2812 chip. Because of its high-speed performance, its support for multi-motor control and its low power consumption, TMS320F2812 DSP from TI demonstrates itself as an ideal candidate for the five fingered robot hand. There are five fingers and each finger has three degrees of freedom (DOF). All the actuators and electronics are integrated in the finger body and the palm. This robot has five fingers in which all joints are driven by DC motors. At the same time, the multisensory robot hand integrates position, force/torque and temperature sensors. The fuzzy controller dealing with the level of finger control is a multiple-input-multiple-output (MIMO) fuzzy learning controller and is implemented in AVRs microcontrollers. In this paper, the design of the fuzzy controller is base on the genetic algorithm. The whole weight of the hand is about 1.3Kg and the fingertip force can reach 8N.

2008

The strong dependence of the computed torque control of dynamic model of the robot manipulator makes this one very sensitive to uncertainties of modelling and to the external disturbances. In general, the vector of Coriolis torque, centrifugal and gravity is very complicated, consequently, very difficult to modelled. Fuzzy Logic Controller can very well describe the desired system behavior with simple "if-then" relations owing the designer to derive "if-then" rules manually by trial and error. On the other hand, Neural Networks perform function approximation of a system but cannot interpret the solution obtained neither check if its solution is plausible. The two approaches are complementary. Combining them, Neural Networks will allow learning capability while Fuzzy-Logic will bring knowledge representation (Neuro-Fuzzy). This paper presents the control of puma 600 robot arm using Adaptive Neuro Fuzzy Inference System (ANFIS) based computed torque controller (type PD). Numerical simulation using the dynamic model of puma 600 robot arm shows the effectiveness of the approach in improving the computed torque method. Comparative evaluation with Fuzzy computed torque (type PD) control is presented to validate the controller design. The results presented emphasize that a satisfactory trajectory tracking precision and stabilility could be achieved using ANFIS controller than Fuzzy controller.

Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, 2009

This paper presents a hybrid of a soft computing technique of adaptive neuro-fuzzy inference system (ANFIS) and a hard computing technique of adaptive control for a two-dimensional movement of a prosthetic hand with a thumb and index finger. In particular, ANFIS is used for inverse kinematics, and the adaptive control is used for linearized dynamics to minimize tracking error. The simulations of this hybrid controller, when compared with the proportional-integral-derivative (PID) controller showed enhanced performance. Work is in progress to extend this methodology to a five-fingered, three-dimensional prosthetic hand.

2011 3rd International Conference on Computer Research and Development, 2011

This paper presents the performances of different type fuzzy logic controllers which are adaptive neural-network based fuzzy logic (ANNFL) controller, hierarchical adaptive neural-network based fuzzy logic (HANNFL) controller and adaptive neural-network based interval type2 fuzzy logic (ANNIT2FL) controller. ANNFL, HANNFL and ANNIT2FL controllers are applied on flexible manipulator for both position and tip deflection control to learn which one satisfy us with it's performance according to desired goals. The performances of the proposed controllers are evaluated on the basis of the experimental results.

Hard computing based optimization algorithms usually require a lot of computational resources and generally do not have the ability to arrive at the global optimum solution. Soft computing algorithms on the other hand negate these deficiencies, by allowing for reduced computational loads and the ability to find global optimal solutions, even for complex cost surfaces. This paper presents fusion of soft computing or control technique of genetic algorithm (GA) and hard computing technique of proportional integral derivative (PID) control with application to prosthetic hand. An adaptive neuro-fuzzy inference system (ANFIS) is used for inverse kinematics of the three-link index finger, and feedback linearization is used for the dynamics of the hand and the GA is used to find the optimal parameters of the PID controller. Simulation results with practical data shows good results for the prosthetic hand to hold a square object with a two-link thumb and index finger.

INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY

This paper proposes a hybrid ANFIS (Adaptive Neuro-Fuzzy Inference System) controller with DMRAC (Direct Model Reference Adaptive Control) and mathematical modeling of the kinematic and dynamic solutions. The controller was hybrid with a classical controller, and was designed for a spherical-wristed 6-DOF elbow manipulator. The manipulator’s trajectory overshoot and settling time affect movement; their minimization was thus aimed for. The whole manipulator-controller system was modeled and simulated on MATLAB Version 2011a and Robotics Toolbox 9. To increase accuracy, the ANFIS controller was trained to use many paths in rules and memberships selection. A 3D display model for the manipulator was built in MATLAB. The simulation of the design had done by using the MATLAB/SIMULINK through connection the design with 3D model. Satisfactory results show the hybrid controller’s capacity for precision and speed, both of which are higher than a classical controller’s alone.

In this paper, an adaptive control strategy is developed for the 14 degrees of freedom (DOFs), five-fingered smart prosthetic hand with unknown mass and inertia of all the fingers. In particular, the forward and inverse kinematics of the system regarding the analytical relationship between the angular positions of joints and the positions and orientations of the end-effectors (fingertips) have been obtained using a desired orientation for three-link fingers. The simulations of the resulting adaptive controller with five-fingered prosthetic hand show enhanced performance.

Control of flexible manipulator is considering one of the great challenges for control engineering. The flexibility of the manipulator converts the system to a non-minimum phase system. Classical controllers cannot cope with the vibration suppression of the tip in addition to achieving the desired position of the manipulator. A Modified Proportional-Integral-Derivative (MPID) control is proposed to control the flexible manipulator. The main difficulty with the proposed MPID controller lies on the tuning of the vibration gain of the controller. The vibration control gain has been determined in an empirical way so far. It is a considerable time consuming process because the vibration control performance depends not only on the vibration control gain but also on the other parameters such as the payload, references and PD joint servo gains. Hence, the vibration control gain must be tuned considering the other parameters. A fuzzy logic tuning scheme is used in this paper to find optimal vibration control gain for the MPID controller. The proposed fuzzy logic scheme finds an optimum vibration control gain that minimizes the tip vibration for the end effector of the flexible manipulator. The effectiveness of using the fuzzy logic appears in the ability to tune the gain with different loading condition and input parameters. The tuned gain response results are compared with results for other types of gains and show a good ability to suppress the tip vibration of the flexible manipulation in addition achieving accurate joint angle position.

ANADOLU UNIVERSITY JOURNAL OF SCIENCE AND TECHNOLOGY A - Applied Sciences and Engineering

In this study, trajectory control of robotic arm which has two degrees of freedom (DOF) is conducted by using the control methods of Proportional-Derivative (PD), Adaptive Neuro Fuzzy System (Anfis), hybrid PD-Anfis and its performance analysis is carried out. In the design of the robot, forward kinematics, inverse kinematics and dynamic equations are used. Firstly, the PD controller is executed, and then the PD controller and Anfis controller are compared applying to a different controller approach with the Anfis of Matlab/Simulink software. The positive and negative sides of the Anfis controller are compared and hybrid PD-Anfis controller method is conducted as a different approach to eliminate the negative sides. While the system constants Kp and Kv are kept constant by the classical PD control method, the output of PD controller is trained with Anfis in the new method and the output value is adjusted according to the error and the change rate of the error. By this way, outputs which have less error rate and which are able to follow the reference better are obtained.