From the Publisher:
This graduate text provides an authoritative account of neural network (NN) controllers for robotics and nonlinear systems and gives the first textbook treatment of a general and streamlined design procedure for NN controllers. Stability proofs and performance guarantees are provided which illustrate the superior efficiency of the NN controllers over other design techniques when the system is unknown. New NN properties, such as robustness and passivity are introduced, and new weight tuning algorithms are presented. Neural Network Control of Robot Manipulators and Nonlinear Systems provides a welcome introduction to graduate students, and an invaluable reference to professional engineers and researchers in control systems.

/pdf/neural-network-control-of-robot-manipulators-and-nonlinear-2lgcy2ydnw.pdf

Neural Network Control of Robot Manipulators and Nonlinear Systems

The effective application of sliding mode control to mechanical systems is not straightforward because of the sensitivity of these systems to chattering. Higher-order sliding modes can counteract this phenomenon by confining the switching control to the higher derivatives of the mechanical control variable, so that the latter results are continuous. Generally, this approach requires the availability of a number of time derivatives of the sliding variable, and, in the presence of noise, this requirement could be a practical limitation. A class of second-order sliding mode controllers, guaranteeing finite-time convergence for systems with relative degree two between the sliding variable and the switching control, could be helpful both in reducing the number of differentiator stages in the controller and in dealing with unmodelled actuator dynamics. In this paper different second-order sliding mode controllers, previously presented in the literature, are shown to belong to the above cited class, and some cha...

A survey of applications of second-order sliding mode control to mechanical systems

Force/position control strategies provide an effective framework to deal with tasks involving interaction with the environment. In this paper the parallel approach to force/position control of robotic manipulators is presented. It shows a complete use of the available sensor measurements by operating the control action in a full-dimensional space without using selection matrices. Conflicting situations between the position and force tasks are managed using a priority strategy: the force control loop is designed to prevail over the position control loop. This choice ensures limited deviations from the prescribed force trajectory in every situation, guaranteeing automatic recovery from unplanned collisions. A dynamic force/position parallel control law is presented and its performance in presence of an elastic environment is analyzed; simplification of the dynamic control law is also discussed leading to a PID-type parallel controller. Two case studies are worked out that show the effectiveness of the approach in application to an industrial robot. >

The parallel approach to force/position control of robotic manipulators

A great many control schemes for a robot manipulator interacting with the environment have been developed in the literature. This paper is aimed at presenting a survey of robot interaction control schemes for a manipulator, the end effector of which comes in contact with a compliant surface. A salient feature of the work is the implementation of the schemes on an industrial robot with open control architecture equipped with a wrist force sensor. Two classes of control strategies are considered, namely, those based on static model-based compensation and those based on dynamic model-based compensation. The former provide a good steady-state behavior, while the latter enhance the behavior during the transient. The performance of the various schemes is compared in the light of disturbance rejection, and a thorough analysis is developed by means of a number of case studies.

/pdf/a-survey-of-robot-interaction-control-schemes-with-2mqkzor6rr.pdf

A survey of robot interaction control schemes with experimental comparison

The state of the art of force control for robot manipulators is surveyed in this article. An overview and a unified description of the two major approaches to force control are presented. Several research topics related to force control are also surveyed.

Force control of robot manipulators

Mathematical models for constrained robot dynamics, incorporating the effects of contact forces required to maintain satisfaction of the constraints, are used to develop explicit conditions for stabilization and tracking using feedback. The control structure allows feedback of displacements, velocities and the contact forces. Global conditions for tracking based on a modified computed torque controller are presented. These conditions provide a guarantee that the closed loop controlled robot is stable when performing tasks defined by the specified constraints.

Danwel Wang

Papers

Feedback Stabilization and Tracking of Constrained Robots