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.>

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.

The majority of prosthetic hands available today make no pretense of approaching the versatility and functionality of the human hand. Available prostheses generally possess only one degree of freedom, which greatly reduces the manipulative ability of the device. Additional degrees of freedom are rarely added, because of the difficulty in controlling them naturally. The authors have developed a control philosophy based on minimum information transfer from the amputee and maximum local autonomy of the device. To test this philosophy, they have developed a graphical simulation of a five-fingered anthropomorphic device. The results presented show that this is a viable method for the control of a multifingered prosthetic hand.>

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 researcher's 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.>

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.>

A major question facing the development of sophisticated robotics systems is how to capture the functionality seen in versatile living systems. An approach that has proven useful in designing complex systems is to capture the explicit constraints in a knowledge based system. A knowledge-based planning system under development is reported which attempts to capture the versatility of human prehension. The goal is to model the relationship between perceptual and motor systems in human prehension as well as to develop a knowledge-based grasp planner able to control sophisticated, dextrous robot hands.>

The human hand is versatile in its interactions with the environment, demonstrating skills that designers of dextrous robot hands would like to emulate. From the many attempts that have been made to understand the use of the human hand and to establish classifications of prehensile activity, common themes emerge. Two key issues seem to be balanced in prehensile tasks: that of affixing the object in the hand, and that of gathering information about the state of the object during the task. In this paper, we show these being balanced through combinations of three basic methods of applying oppositions around obiects, and we show how these relate to the postures of standard prehensile classifications.