[Prev][Next][Index][Thread]

Marcos Edited Version - Embodied



As the subject says, this is the position statement after Marcos
read it...

Daze,

	eMpTy


This research involves a method and system which integrates human-computer interaction with reactive planning to operate a telerobot for use as an assistive device. The Multimodal User Supervised Interface and Intelligent Control (MUSIIC) strategy is a novel approach for an intelligent assistive telerobotic system:  speech-deictic gesture control integrated with a knowledge-driven reactive planner and a stereo-vision system.  The system is intended to meet the needs of individuals with physical disabilities and operate in an unstructured environment, rather than in a structured workcell allowing the user considerable freedom and flexibility in terms of control and operating ease.  The strategy utilizes a stereo-vision system to determine the three-dimensional shape and pose of objects and surfaces which are in the immediate environment, and provides an object-oriented knowledge base and planning system which superimposes information about common objects in the three-dimensio!
 nal world.  This approach allows the user to identify objects and task via a multimodal user interface which interprets their deictic gestures and speech inputs.  The multimodal interface performs a critical disambiguation function by binding the spoken words to a locus in the physical work space. The spoken input is also used to supplant the need for general purpose object recognition. Instead, three-dimensional shape information is augmented by the users spoken word which may also invoke the appropriate inheritance of object properties using the adopted hierarchical object-oriented representation scheme.  To understand the intricacies and embodied meaning of the numerous modal inputs we have also designed a graphical simulation of the multimodal environment.  This simulation will allow us to study and better understand the interplay between the user and the MUSIIC system.  Additionally, the simulated environment will be an integral part of the actual MUSIIC system by prov!
 iding the user a visualization which depicts the planner's interpretat

ion of the information the system has gathered.  The MUSIIC system's ability to determine the superquadric shape representation of the scene from stereo vision enables the graphical simulation to dynamically model a variety of real world entities and objects.