6533b827fe1ef96bd1287199
RESEARCH PRODUCT
Intention recognition in manufacturing applications
Anthony PietromartireZeid KootballyCraig SchlenoffMarek FranaszekSebti Foufousubject
Human-robot collaborationOntologybusiness.industryComputer scienceGeneral MathematicsManufacturing kittingRoboticsIntention recognitionRoboticsOntology (information science)Industrial and Manufacturing EngineeringComputer Science ApplicationsDomain (software engineering)Task (project management)Spatial relationControl and Systems EngineeringHuman–computer interactionRobotArtificial intelligenceState recognitionbusinessRepresentation (mathematics)SoftwareCardinal directiondescription
In this article, we present a novel approach to intention recognition, based on the recognition and representation of state information in a cooperative human-robot environment. States are represented by a combination of spatial relations along with cardinal direction information. The output of the Intention Recognition Algorithms will allow a robot to help a human perform a perceived operation or, minimally, not cause an unsafe situation to occur. We compare the results of the Intention Recognition Algorithms to those of an experiment involving human subjects attempting to recognize the same intentions in a manufacturing kitting domain. In almost every case, results show that the Intention Recognition Algorithms performed as well, if not better, than a human performing the same activity. A novel approach to intention recognition based on state recognition.Applied to the manufacturing kitting domain.States use a combination of spatial relations and cardinal directions.Algorithms performed better than humans performing the same task.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2015-06-01 | Robotics and Computer-Integrated Manufacturing |