Intelligent control
Intelligent control is a class of control techniques, that use various AI computing approaches like neural networks, Bayesian probability, fuzzy logic, machine learning, evolutionary computation and genetic algorithms.Before we begin with what an intelligent control is, it is important to note what an intelligent agent essentially means. An intelligent or a rational agent is one who simply does the right things.This leads to a definition of an ideal rational agent: For each possible percept sequence, an AGENT ideal rational agent should do whatever action is expected to maximize its performance measure,on the basis of the evidence provided by the percept sequence and whatever built-in knowledge the agent has.Intelligent control achieves automation via the emulation of biological intelligence. It either seeks to replace a human who performs a control task (e.g., a chemical process operator) or it borrows ideas from how biological systems solve problems and applies them to the solution of control problems (e.g., the use of neural networks for control).
Overview
Intelligent control can be divided into the following major sub-domains:
- Neural network control
- Bayesian control
- Fuzzy (logic) control
- Neuro-fuzzy control
- Expert Systems
- Genetic control
- Intelligent agents (Cognitive/Conscious control)
New control techniques are created continuously as new models of intelligent behavior are created and computational methods developed to support them.
Neural network controllers
Neural networks have been used to solve problems in almost all spheres of science and technology. Neural network control basically involves two steps:
- System identification
- Control
It has been shown that a feedforward network with nonlinear, continuous and differentiable activation functions have universal approximation capability. Recurrent networks have also been used for system identification. Given, a set of input-output data pairs, system identification aims to form a mapping among these data pairs. Such a network is supposed to capture the dynamics of a system.
Fuzzy Logic controllers
Fuzzy control is a methodology to represent and implement a (smart) human’s knowledge about how to control a system. A fuzzy controller is shown in Figure 1. The fuzzy controller has several components:
• The rule-base is a set of rules about how to control.
• Fuzzification is the process of transforming the numeric inputs into a form that can be used by the inference mechanism.
• The inference mechanism uses information about the current inputs (formed by fuzzification), decides which rules apply in the current situation, and forms conclusions about what the plant input should be.
• Defuzzification converts the conclusions reached by the inference mechanism into a numeric input for the plant.
Genetic Control
To understand what Genetic control is, one must suffice oneself with the theory of genes and the importance of its study in an artificially intelligent machine
Genes are the blueprint of our bodies, a blueprint that creates the variety of proteins essential to any organisms survival. These proteins, which are used in countless ways by our bodies are produced by genetic sequences, i.e. our genes, as described in the cell biology section, protein synthesis pages. Utilization of Genetic Information All cells have originated from the single zygote cell that formed it, and therefore possess all the genetic information that was held in that zygote. This means that an organism could be cloned from the genetic information in the nucleus of one cell, regardless of the volume of cells that make the organism (be it one or billions).
However, this brings about the following question, how can cells become differentiated and specialised to perform a particular function if they are all the same? The answer to this is each cell performing its unique role has some of its genes 'switched on' and some 'switched off'.
In light of this, the cells in our body still contain the same genetic information, though only a partial amount of this information is being used in any one cell. Switched On and Switched Off Some genes are permanently switched on, because they contain the blueprint for vital metabolites (enzymes required for respiration etc). However, since cells become specialised in multi-cellular organisms such as ourselves, some genes become switched off because they are no longer required to be functional in that particular cell or tissue.
For instance, insulin is produced in pancreas cells, which must have the gene that codes for insulin switched on, and perhaps other genes that are un-related to the role of the pancreas can be switched off.
Some other genes that will be functional during specialisation determine the physical characteristics of the cell, i.e. long and smooth for a muscle cell or indented like a goblet cell.
Genetic control then transforms all of this available information into an algorithm to design and texture genes for avoiding mucotic growth and/or identifying probable threats to the proposed gene. This branch of science deals with protection, regeneration and transformation of the analytical information collected.
Bayesian controllers
Bayesian probability has produced a number of algorithms that are in common use in many advanced control systems, serving as state space estimators of some variables that are used in the controller.
The Kalman filter and the Particle filter are two examples of popular Bayesian control components. The Bayesian approach to controller design requires often an important effort in deriving the so-called system model and measurement model, which are the mathematical relationships linking the state variables to the sensor measurements available in the controlled system. In this respect, it is very closely linked to the system-theoretic approach to control design.
See also
- action selection
- artificial intelligence
- Function approximation
- genetic engineering
- robotics simulators
- http://en.wikibooks.org/wiki/Robotics_Kinematics_and_Dynamics
 | This article includes a list of references, related reading, or external links, but its sources remain unclear because it lacks inline citations. (April 2011) |
References
- Stengel, R.F. (1991). "Intelligent Failure Tolerant Control" (PDF). IEEE Control Systems Magazine. 11 (4): 14–23. doi:10.1109/37.88586.
- Stengel, R.F. (1993). "Toward Intelligent Flight Control" (PDF). IEEE Trans. Systems, Man, and Cybernetics. 23 (6): 1699–1717. doi:10.1109/21.257764.
- Antsaklis, P.J. (1993). An Introduction to Intelligent and Autonomous Control. Kluwer Academic Publishers. ISBN 0-7923-9267-1.
{{cite book}}: Unknown parameter|coauthors=ignored (|author=suggested) (help)
- Stuart Jonathan Russel, Norvig Peter. (2010). Artificial intelligence: a modern approach. Prentice Hall. ISBN 0-7923-9267-1.
Further reading
- Jeffrey T. Spooner, Manfredi Maggiore, Raul Ord onez, and Kevin M. Passino, Stable Adaptive Control and Estimation for Nonlinear Systems: Neural and Fuzzy Approximator Techniques, John Wiley & Sons, NY ;
- Farrell, J.A., Polycarpou, M.M. (2006). Adaptive Approximation Based Control: Unifying Neural, Fuzzy and Traditional Adaptive Approximation Approaches. Wiley. ISBN 978-0-471-72788-0.
{{cite book}}: CS1 maint: multiple names: authors list (link) - Schramm, G. (1998). Intelligent Flight Control - A Fuzzy Logic Approach. TU Delft Press. ISBN 90-9011924-8.