Accession Number : ADA259496


Title :   Pose Determination of a Grasped Object Using Limited Sensing


Descriptive Note : Technical rept.


Corporate Author : MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB


Personal Author(s) : Siegel, David M


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/a259496.pdf


Report Date : May 1991


Pagination or Media Count : 201


Abstract : This report explores methods for determining the pose of a grasped object using only limited sensor information. The problem of pose determination is to find the position of an object relative to the hand. The information is useful when grasped objects are being manipulated. The problem is hard because of the large space of grasp configurations and the large amount of uncertainty inherent in dexterous hand control. By studying limited sensing approaches, the problem's inherent constraints can be better understood. This understanding helps to show how additional sensor data can be used to make recognition methods more effective and robust. This report introduces three approaches for pose determination. The first is based on an interpretation tree representation of possible object feature placements on finger segments. The tree is built in real-time based on the hand's configuration and an object model. The method is highly efficient as it only explores consistent paths through the tree.


Descriptors :   *ROBOTICS , *RECOGNITION , UNCERTAINTY , CONTROL SYSTEMS , MODELS , REAL TIME , HANDS , FINGERS , APPROACH , DETERMINATION , PATHS , TIME , TREES , CONFIGURATIONS


Subject Categories : Cybernetics


Distribution Statement : APPROVED FOR PUBLIC RELEASE