Search

Robot manipulators are playing increasingly significant roles in scientific researches and engineering applications in recent years. Using manipulators to save labors and increase accuracies are becoming common practices in industry. Neural networks, which feature high-speed parallel distributed processing, and can be readily implemented by hardware, have been recognized as a powerful tool for real-time processing and successfully applied widely in various control systems. Particularly, using neural networks for the control of robot manipulators have attracted much attention and various related schemes and methods have been proposed and investigated. In this paper, we make a review of research progress about controlling manipulators by means of neural networks. The problem foundation of manipulator control and the theoretical ideas on using neural network to solve this problem are first analyzed and then the latest progresses on this topic in recent years are described and reviewed in detail. Finally, toward practical applications, some potential directions possibly deserving investigation in controlling manipulators by neural networks are pointed out and discussed. [ABSTRACT FROM AUTHOR]

The PID controller with constant feedback gains has withstood as the preferred choice for control of linear plants or linearized plants, and under certain conditions for non-linear ones, where the control of robotic arms excels. In this paper a model-free self-tuning PID controller is proposed for tracking tasks. The key idea is to exploit the passivity-based formulation for robotic arms in order to shape the damping injection to enforce dissipativity and to guarantee semiglobal exponential convergence in the sense of Lyapunov. It is shown that a neuro-fuzzy network can be used to tune dissipation rate gain through a self-tuning policy of a single gain. Experimental studies are presented to confirm the viability of the proposed approach. [ABSTRACT FROM AUTHOR]

Abstract: This paper describes the automation of a vibro-lance for ground improvement on a construction site. Here, a vibrating probe is lowered into the ground and penetrates downwards by means of a two-arm excavator, compacting the surrounding soil. The control system is straightforward to install on a conventional, hydraulically controlled excavator, such as the one utilised for the field tests reported in the paper. The new system supports the operator by automatically maintaining the verticality of the probe, increasing the speed of operation by a factor of three, whilst also yielding improved accuracy and, therefore, a potential increase in tool life. In particular, the research demonstrates the successful design and implementation of Proportional-Integral-Plus (PIP) control systems for joint control on-site. To the authors'' knowledge, this represents the first operational use of automation for vibro-lance ground compaction. [Copyright &y& Elsevier]

A description is presented of software and hardware components designed for enabling robots to perform interactive assembly tasks. Topics include architecture, functionality development tools, and the processes involving cognition, scheduling and execution.

Robust control of robots including motor dynamics is considered based on a dynamic game approach. The control law is composed of three main components. The first component utilizes feedback linearization to cancel the system''s nominal nonlinearity and achieve tracking via pole-placement. The discrepancy between the nominal functions used in feedback linearization and the true ones is compensated for using the second control component that is based on an adaptive hierarchical fuzzy algorithm. The third control component ensures robustness by attenuating the worst-case effect of both the residue due to fuzzy cancellation and the external disturbances. The main contribution of this work is the derivation of the hierarchical adaptive fuzzy algorithm to avoid the rule explosion phenomenon that characterizes traditional fuzzy systems. We also prove that the proposed control algorithm is locally stable. Simulation of a two-link manipulator illustrates a successful performance of our controller and investigates the effect of the design parameters. [Copyright &y& Elsevier]

The study presented a concept for integrating the control system of an anthropomorphic robot hand into the control system of an entire humanoid robot. It provided grasp skills to coordinate movements of hand and arm and determines grasp patterns, depending on the object to grasp and the task to execute.