https://users.iit.demokritos.gr/~bgat/PatRec2006.pdf

Adaptive degraded document image binarization

A robust adaptive control approach is proposed to solve the consensus problem of multiagent systems. Compared with the previous work, the agent's dynamics includes the uncertainties and external disturbances, which is more practical in real-world applications. Due to the approximation capability of neural networks, the uncertain dynamics is compensated by the adaptive neural network scheme. The effects of the approximation error and external disturbances are counteracted by employing the robustness signal. The proposed algorithm is decentralized because the controller for each agent only utilizes the information of its neighbor agents. By the theoretical analysis, it is proved that the consensus error can be reduced as small as desired. The proposed method is then extended to two cases: agents form a prescribed formation, and agents have the higher order dynamics. Finally, simulation examples are given to demonstrate the satisfactory performance of the proposed method.

Decentralized Robust Adaptive Control for the Multiagent System Consensus Problem Using Neural Networks

A compensation scheme is presented for general nonlinear actuator deadzones of unknown width. The compensator uses two neural networks (NNs), one to estimate the unknown deadzone and another to provide adaptive compensation in the feedforward path. The compensator NN has a special augmented form containing extra neurons whose activation functions provide a "jump function basis set" for approximating piecewise continuous functions. Rigorous proofs of closed-loop stability for the deadzone compensator are provided and yield tuning algorithms for the weights of the two NNs. The technique provides a general procedure for using NNs to determine the preinverse of an unknown right-invertible function.

Deadzone compensation in motion control systems using neural networks

Most research so far in robot control has assumed either kinematics or Jacobian matrix of the robots from joint space to Cartesian space is known exactly. Unfortunately, no physical parameters can be derived exactly. In addition, when the robot picks up objects of uncertain lengths, orientations, or gripping points, the overall kinematics from the robot's base to the tip of the object becomes uncertain and changes according to different tasks. Consequently, it is unknown whether stability of the robot could be guaranteed in the presence of uncertain kinematics. In order to overcome these drawbacks, in this paper, we propose simple feedback control laws for setpoint control without exact knowledge of kinematics, Jacobian matrix, and dynamics. Lyapunov functions are presented for stability analysis of feedback control problem with uncertain kinematics. We shall show that the end-effector's position converges to a desired position in a finite task space even when the kinematics and Jacobian matrix are uncertain. Experimental results are presented to illustrate the performance of the proposed controllers.

Approximate Jacobian control for robots with uncertain kinematics and dynamics

Many concrete problems from engineering, economics, operations research, etc., can be formulated by an optimization problem of the type 

$$\displaystyle\begin{array}{rcl} \min f_{0}(a,x)& &{}\end{array}$$

(1.1a)



$$\displaystyle\begin{array}{rcl} \mbox{ s.t.}& & {}\\ & & {}\\ \end{array}$$



$$\displaystyle\begin{array}{rcl} f_{i}(a,x)& \leq & 0,i = 1,\ldots,m_{f}{}\end{array}$$

(1.1b)



$$\displaystyle\begin{array}{rcl} g_{i}(a,x)& =& 0,i = 1,\ldots,m_{g}{}\end{array}$$

(1.1c)



$$\displaystyle\begin{array}{rcl} x \in D_{0}.& &{}\end{array}$$

(1.1d)

Stochastic optimization methods

From the Publisher:
A complete overview of the fundamentals of robotics. Case study examples of educational, industrial and generic robots are discussed. Class demonstration software is provided with the laboratory manual. (vs. Craig, Fu, and Asada).

Robert J. Schilling

Papers

Fundamentals of Robotics : Analysis and Control