Thea Iberall

Human prehension and dexterous robot hands

The human hand is versatile in its interactions with the envi ronment, demonstrating skills that designers of dexterous robot hands would like to emulate. Various postures and features of the human hand combine to provide a great deal of functional ity. In this article, an analysis of human prehensile capability is presented, comparing a symbolic description of prehension to an opposition-space, parameterized framework. By pointing out features of the human hand in prehensile tasks, we hope to offer insights that designers can use for building more versatile robot and prosthetic hands.

Dextrous robot hands

Manipulation using dextrous robot hands has been an exciting yet frustrating research topic for the last several years. While significant progress has occurred in the design, construction, and low level control of robotic hands, researchers are up against fundamental problems in developing algorithms for real-time computations in multi-sensory processing and motor control. The aim of this book is to explore parallels in sensorimotor integration in dextrous robot and human hands, addressing the basic question of how the next generation of dextrous hands should evolve. By bringing together experimental psychologists, kinesiologists, computer scientists, electrical engineers, and mechanical engineers, the book covers topics that range from human hand usage in prehension and exploration, to the design and use of robotic sensors and multi-fingered hands, and to control and computational architectures for dextrous hand usage. While the ultimate goal of capturing human hand versatility remains elusive, this book makes an important contribution to the design and control of future dextrous robot hands through a simple underlying message: a topic as complex as dextrous manipulation would best be addressed by collaborative, interdisciplinary research, combining high level and low level views, drawing parallels between human studies and analytic approaches, and integrating sensory data with motor commands. As seen in this text, success has been made through the establishment of such collaborative efforts. The future will hold up to expectations only as researchers become aware of advances in parallel fields and as a common vocabulary emerges from integrated perceptions about manipulation.

Neural network architecture for robot hand control

A robot hand control system called GeSAM, which is under development at the University of Southern California, is described. The goal of the GeSAM architecture is to provide a generic robot hand controller that is based on a model of human prehensile function. It focuses on the relationship between geometric object primitives and the ways a hand can perform prehensile behaviors. It is shown how the relationship between object primitives and a useful set of grasp modes can be learned by an adaptive neural network. By adding training points as necessary, system performance can be improved, avoiding the tedious job of computing every relationship individually.<<ETX>>

Opposition space and human prehension

A problem that has plagued both motor psychologists in studying human behavior, and robot designers in reproducing it, is how to quantify that behavior. It has been argued that kinematic and dynamic models are inadequate for explaining human movement unless they also include both the performance constraints and the objectives that affect the neural and neuromuscular inputs. With a dextrous, multi-fingered hand, multiple grasping solutions are possible. This chapter addresses the question faced by the controller, that of how best to use features of the hand to achieve the task goals, given anticipated object properties and predictable interaction outcomes. The opposition space model takes into account the hand’s ability to apply task-related forces while gathering sensory information, in terms of its precision and power capabilities. By separating implementation details from functional goals, the study of human hand functionality can lead to the design of better dextrous robot hands and their controllers.

The multi-dimensional quality of task requirements for dextrous robot hand control

The authors identify four important task requirements for dextrous robot hand control. These requirements are stability, manipulability, torquability, and radial rotatability. High-level task descriptions, supplied by the user, are refined into detailed task descriptions that can be used to drive a robot hand. A knowledge-based approach for refining a reasonable set of tasks is used to infer values for a set of task attributes, which trigger several heuristics. Those heuristics are applied using a set of metaheuristics to determine good grasp postures and poses for the task. How to use this multidimensional grasping quality in grasp mode selection and performance evaluation is shown in an industrial assembly domain.<<ETX>>

A Neural Network for Planning Hand Shapes in Human Prehension

Quantifying human hand movement is a problem that interests both motor psychologists, in studying human behavior, and robot designers, in reproducing it. We attempt to capture the functionality of human prehensile movement using abstracted concepts such as virtual fingers and opposition space. We describe a neural network that maps object/task properties into a prehensile posture, relating the mapping to empirical evidence.

Neural Network Models for Selecting Hand Shapes

Publisher Summary The simple task of grasping objects has been studied to understand and duplicate the versatility of the human hand. The language of opposition space and virtual fingers provides a high-level language for describing such plans. Different hand postures offer different capabilities, and the selection of a posture is an important computation performed by the central nervous system. In order to model this selection, the five networks presented in this chapter offer examples of a neural style of processing. All involve computations performed through the interactions of a large number of simple processing elements, or units that had an activation state and were connected together through synapses in some pattern of connectivity. Units either excited or inhibited each other, and synaptic connections were represented by weight matrices. The use of neural models allows one to explore the implementation of planning processes, while incorporating experimental results from behavioral, anatomical, and neurophysiological studies. It is shown that the activation of the units in the middle layer demonstrates an internal representation for an opposition.

On the development of EMG control for a prosthesis using a robotic hand

The human hand is a complex end-effector capable of a large variety of postures. Multifingered robot hands, such as the Belgrade/USC hand, can approximate human hand functionality, and it is possible to consider their use in prosthetics. The authors have developed a system, PRESHAPE, that translates user commands into motor signals using the virtual finger concept. For control, electromyographic (EMG) signals from forearm muscles are used. The authors describe PRESHAPE and its use of EMG signals. Simulation results are presented.<<ETX>>

Control philosophy and simulation of a robotic hand as a model for prosthetic hands

Multi-fingered robotic hands are attempts to approximate human hand characteristics and functionality, and it is reasonable to consider their possible adaptation and use in prosthetics and rehabilitation. The Belgrade/USC robot hand is used as a prototype prosthetic hand in order to evaluate a system that translates task-level commands into motor commands. The system, PRESHAPE, uses the virtual finger concept for generating the free and guarded motions that occur during the phases of hand movements in prehensile and nonprehensile tasks. This paper describes the control philosophy of PRESHAPE and presents simulation results for various tasks.

R/sup 2/AD: rapid robotics application development environment

R/sup 2/AD, a flexible robotics application development environment, combines powerful graphical display features with tools that support the rapid development of application programs. The graphical interface allows researchers to monitor the system state variables during the dynamic execution of robot programs. This feature enhances the researchers efficiency in interpreting experimental results. Rapid development is supported by a virtual machine through the use of software engineering principles and object-oriented techniques. In addition to these features, the user is able to emulate a wide variety of robot computational paradigms. This allows experimentation with, and comparison of, various computational techniques (e.g., hierarchical versus heterarchical control process topologies). The utility of the R/sup 2/AD virtual machine is demonstrated through applications currently under development.<<ETX>>