Connectionist approaches to the control of manipulation robots at the executive hierarchical level: An overview

Abstract

Abstract. One of the most interesting and important properties of connectionist systems is their ability to control sophisticated manipulation robots, i.e. to produce a large number of efficient control commands in real-time. This paper represents an attempt to give a comprehensive report of the basic principles and concepts of conneetionism in robotics, with an outline of a number of recent algorithms used in learning control of a manipulation robot. A major concern in this paper is the application of neural networks for off-line and on-line learning of kinematic and dynamic relations used in robot control at the executive hierarchical level.

Intelligent Control of Robotic Systems

“…The area of possible applications of neural networks in robotics [28] [126], [195], [166]' [135], [347], [211], [91], [147] includes various purposes such as vision systems, appendage controllers for manufacturing, tactile sensing, tactile feedback gripper control, motion control systems, situation analysis, navigation of mobile robots, solution of the inverse kinematic problem, sensory-motor coordination, generation of limb trajectories, learning visuomotor coordination of the robot's arm in 3D, control of biped gait, etc. All these robotic tasks can be categorized according to the type of hierarchical control level of the robotic system, i.e., neural networks can be applied at the strategic control level (task planning), at the tactical control level (path planning) and at the executive control level (path control).…”

Strategic Control Level for Industrial Robotic Contact Tasks

“…A robotic control system usually represents a multilevel hierarchical structure with the strategic, tactical, and executive levels (Jocković et al, 1990;Katić, & Vukobratović, 1994). In fact, these levels are based on the principle of increasing accuracy with decreasing sophistication.…”