Title :
A connectionist model of human grasps and its application to robot grasping
Author :
Moussa, Medhat A. ; Kamel, Mohamed S.
Author_Institution :
Dept. of Syst. Design Eng., Waterloo Univ., Ont., Canada
Abstract :
Presents a connectionist model that can learn human grasping rules. The model domain is a taxonomy of manufacturing grasps. The input vector specifies task and object attributes such as dexterity and shape, and the model predicts the required grasp. Experiments show that the model is capable of learning grasping rules and predicting correct grasps for new objects that it has not been trained on. The authors finally discuss how this model can be used as part of a robotic system for grasping objects
Keywords :
biomechanics; learning (artificial intelligence); manipulators; neural nets; physiological models; connectionist model; dexterity; grasping rules; human grasps; manufacturing grasps; object attributes; robot grasping; shape; task attributes; Electrical equipment industry; Grippers; Humans; Neural networks; Predictive models; Robot control; Robot sensing systems; Service robots; Shape; Taxonomy;
Conference_Titel :
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2768-3
DOI :
10.1109/ICNN.1995.487810
