Search results

The paper presents an implementation of knowledge representation including the capabilities of the system, based on ontologies for a Visually Guided Bin Picking Task. The ontology based approach was used to define the work environment, the robot, the machine vision sys- tem, and the capabilities that are needed to be performed by the robotic system, to perform the bin-picking task. The work proposes a novel application framework that is able to locate the object to pick from the bin and place it in a cell from a kit. For that, the framework, delivers the task implementation (PDDL) files that should be executed by the robot. The method used to detect the objects is based on Chamfer Match (CM) and Oriented Chamfer Match (OCM) which take advantage of the image edge map. To complete the pose estimation problem the robot manipulator is equipped with a laser range finder that can measure the object height. The robotic system was validated experimentally with simulation. using the V-REP environment interfacing with ROS, where the knowledge representation and reasoning framework is implemented. The system showed its capability to correctly pick and place a specific object. Moreover, the ontology based approach was very useful to define the task, the actions to be performed by the robot, based on its capabilities.

(c) 2007 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.

To perform mitral valve contour extraction a software application is presented to support the surgeon in the implant size decision. The system is based on the application, to mitral valve surgery images, of active contour models. First, current repair surgery to mitral valve disease is discussed. Active contour models are presented and using different implementation approaches a comparison was done. The algorithms proposed by Kass, Amini, Cohen, Eviatar and Shah (Greedy algorithm) were implemented in test environment. The implementation to be used in the software application, is the one due to Kass with a few modifications related to Cohen’s approach. During surgery, the system needs to be calibrated and the active contour initialised. These processes are supported by a colour segmentation technique, tested with real images, using fuzzy sets. Real open-heart surgery images have been used to test the system developed.