A. Almansa

Adaptive control of manipulators with supervision of the sampling rate and free-parameters of the adaptation algorithm

An adaptive neural control scheme for mechanical manipulators is proposed. A supervisor is used to improve the system performances during the adaptation transients. The supervisor exerts two supervisory actions. The first one consists basically in updating the free-design adaptive controller, the quadratic loss function is maintained sufficiently small. The second supervisory action consists basically of an online adjustment of the sampling period within an interval centered in a nominal value of the sampling period. The sampling period is selected so that the transient of the tracking error is improved.

Logical Formal Description of Expert Systems

The objective of expert systems is the use of Artificial Intelligence tools so as to solve problems within specific prefixed applications. Even when such systems are widely applied in diverse applications, as manufacturing or control systems, until now, there is an important gap in the development of a theory being applicable to a description of the involved problems in a unified way. This paper is an attempt in supplying a simple formal description of expert systems together with an application to a robot manipulator case.

Adaptive Stable Control of Manipulators with Improved Adaptation Transients by Using On-line Supervision of the Free-Parameters of the Adaptation Algorithm and Sampling Rate

An adaptive control scheme for mechanical manipulators is proposed. The control loop essentially consists of a network for learning the robots inverse dynamics and on-line generating the control signal. Some simulation results are provided to evaluate the design. A supervisor is used to improve the performances of the system during the adaptation transients. The supervisor exerts two supervisory actions. The first one consists basically of updating the free-design adaptive controller parameters so that the value of a quadratic loss function is maintained sufficiently small. Such a function involves past tracking errors and their predictions both on appropriate time hori- zons of low performances during the adaptation transients. The supervisor exerts two supervisory actions. The second supervisory action consists basically of a on-line adjustment of the sampling period within an interval centered in a nominal value of the sampling period. The sampling period is selected so that the transient of the tracking error is improved according to the simple intuitive rule of using a sampling rate faster as the tracking error changes faster.

ADAPTIVE CONTROL OF MANIPULATORS WITH IMPROVED ADAPTATION TRANSIENTS BY USING ON-LINE SUPERVISION OF THE FREE-PARAMETERS OF THE ADAPTATION ALGORITHM AND OF THE SAMPLING RATE

An adaptive control scheme for mechanical manipulators is proposed. The control loop essentially consists of a network for learning the robots inverse dynamics and on-line generating the control signal. Some simulation results are provided to evaluate the design. A supervisor is used to improve the systems performances during the adaptation transients. The supervisor exerts two supervisory actions. The first one consists basically in updating the free-design adaptive controller parameters so that the value of a quadratic loss function is maintained sufficiently small. Such a function involves past tracking errors and their predictions both on appropriate time horizons of low performances during the adaptation transients. The supervisor exerts two supervisory actions. The second supervisory action consists basically of a on-line adjustment of the sampling period within an interval centered in a nominal value of the sampling period. The sampling period is selected so that the transient of the tracking error is improved according to the simple intuitive rule of sampling faster as the tracking error changes faster.

Control of robotic manipulators via supervision of the free-design parameters and sampling rate

An adaptive control scheme for mechanical manipulators is proposed. The control loop consists of a network for learning the robot¿s inverse dynamics and online generating the control signal. Some simulation results are provided to evaluate the design. A supervisor is used to improve the performances of the system during the adaptation transients. The supervisor exerts two actions. The first one consists of updating the free-design adaptive controller parameters so that the value of a quadratic loss function is maintained sufficiently small. The second action consists of an on-line adjustment of the sampling period within an interval centered at its nominal value.

Stable adaptive control of manipulators with improved transients via supervision of the free-design parameters and sampling period

An adaptive control scheme for mechanical manipulators is proposed. The control loop consists of a network for learning the robots inverse dynamics and online generating the control signal. Some simulation results are provided to evaluate the design. A supervisor is used to improve the performances of the system during the adaptation transients. The supervisory exerts two actions. The first one consists of updating the free-design adaptive controller parameters so that the value of a quadratic loss function is maintained sufficiently small. The second action consists of an on-line adjustment of the sampling period within an interval centered at its nominal value.

Theoretical results for describing expert systems in the supervision of the adaptation transients of a planar robot

The objective of expert systems is the use of Artificial Intelligence tools so as to solve problems within specific prefixed applications. This paper deals with the development of an expert system valid to optimize the adaptation transients arising in adaptive control using a logic formalism previously described. Its structure is composed by a supervisor based on an expert network organization and designed to improve the transient performances in the adaptive control of a planar robot. Apart form the basic adaptation scheme consisting of an estimation algorithm plus an adaptive controller, two additional coordinated expert systems are used to update an adaptation gain and the sampling period with a master expert system coordinating both above expert systems.

Theoretical Results for Expert Systems in the Supervision of Adaptation Transients in a Planar Robot

This paper addresses the development of an expert system that is valid for optimization of transients arising in adaptive control via the use of a logicformal system. Practical experimentation leads to good applicability in a context of rule-based knowledge. A supervisor is designed to improve the transient performance in the adaptive control of a planar robot, based on an expert network organization. Apart from the basic adaptation scheme consisting o f an estimation algorithm plus an adaptive controller, two additional coordinated expert systems are used to update the adaptation gain and the sampling period, with a master expert system coordinating both expert systems.

Advanced control techniques based in artificial intelligence for robotics manipulators

The performance quality in nonlinear model based control of mechanical manipulators is conditioned to the reliability of the mathematical model and precision in the knowledge of all the involved parameters. Control methods based on artificial intelligence techniques (learning algorithms, system identification and neural networks) can be applied to improve its performance. A neural control scheme is proposed, consisting basically of a neural network for learning the robot inverse dynamics and online generating the control signal. Also an online supervision based on optimisation techniques is designed and implemented for such neural control. Simulation results are provided to evaluate the alternative variations to the proposed central scheme.