Cognitive approach through the neural network (NN) paradigm is a critical discipline that will help bring about autonomic computing (AC). NN-related research, some involving new ways to apply control theory and control laws, can provide insight into how to run complex systems that optimize to their environments. NN is one kind of AC systems that can embody human cognitive powers and can adapt, learn, and take over certain functions previously performed by humans. In recent years, artificial neural networks have received a great deal of attention for their ability to perform nonlinear mappings. In trajectory control of robotic devices, neural networks provide a fast method of autonomously learning the relation between a set of output states and a set of input states. In this chapter, we apply the cognitive approach to solve position controller problems using an inverse geometrical model. In order to control a robot manipulator in the accomplishment of a task, trajectory planning is required in advance or in real time. The desired trajectory is usually described in Cartesian coordinates and needs to be converted to joint space for the purpose of analyzing and controlling the system behavior. In this chapter, we use a memory neural network (MNN) to solve the optimization problem concerning the inverse of the direct geometrical model of the redundant manipulator when subject to constraints. Our approach offers substantially better accuracy, avoids the computation of the inverse or pseudoinverse Jacobian matrix, and does not produce problems such as singularity, redundancy, and considerably increased computational complexity.
TopIntroduction
Current research areas on theories and applications of Cognitive Informatics (Wang et al., 2005; Chiew, 2003; Wang, 2005) have demonstrated a consistent effort at applying cognitive informatics to real word problem domains such as autonomous computing. Almost all of the hard problems yet to be solved in this discipline are stemmed from the fundamental constraints of the brain and the understanding of its cognitive mechanisms and processes (Wang et al., 2002; Wang et al., 2003).
The autonomic computing (Wang, 2003) derives from the body’s autonomic nervous system, which controls key functions without conscious awareness or involvement. Autonomic controls use motor neurons to send indirect messages to organs at a sub-conscious level. These messages regulate temperature, breathing, and heart rate without conscious thought. The implications for computing are immediately evident; a NN, which computes joint positions for a robot and adapts itself under varying conditions without considerably increased computational complexity. In recent years, artificial neural networks have received a great deal of attention for their ability to perform nonlinear mappings. In trajectory control of robotic devices, neural networks provide a fast method of autonomously learning the relation between a set of output states and a set of input states (Guez et al., 1989; Kieffer et al., 1991; Hunt et al., 1992; Ramdane-Cherif et al., 1995).
In (Jung et al., 2000; Fang et al., 1993; Fang et al., 1998) several neural network inverse control techniques are applied for trajectory tracking of a PD controlled rigid robot and (Kawato et al., 1990) look ahead planning based on neural networks is successfully applied to real time control of a robot arm. the task is to touch a rolling ball with a robot arm
Traditional approaches to control redundant manipulators have centered on the Jacobian pseudoinverse (Klein et al., 1983) which is non intuitive, tiresome to compute and generates arbitrary joint position vectors in the neighborhood of singularities. These solutions are often inappropriate and result in unacceptable large joint velocities and accelerations.