Browsing by Author "Pinto, J.R. Caldas"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
- Knowledge and capabilities representation for visually guided robotic bin pickingPublication . Gonçalves, Paulo; Pinto, J.R. Caldas; Torres, FredericoThe 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.
- Mitral valve contour extraction using active contour modelsPublication . Gonçalves, Paulo; Pinto, J.R. Caldas; Ramalho, Mário; Melo, J. Queiroz eTo 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.
- Uncalibrated eye-to-hand visual servoing using inverse fuzzy modelsPublication . Gonçalves, Paulo; Mendonça, L.F.; Sousa, João M.C.; Pinto, J.R. CaldasA new uncalibrated eye-to-hand visual servoing based on inverse fuzzy modeling is proposed in this paper. In classical visual servoing, the Jacobian plays a decisive role in the convergence of the controller, as its analytical model depends on the selected image features. This Jacobian must also be inverted online. Fuzzy modeling is applied to obtain an inverse model of the mapping between image feature variations and joint velocities. This approach is independent from the robot's kinematic model or camera calibration and also avoids the necessity of inverting the Jacobian online. An inverse model is identified for the robot workspace, using measurement data of a robotic manipulator. This inverse model is directly used as a controller. The inverse fuzzy control scheme is applied to a robotic manipulator performing visual servoing for random positioning in the robot workspace. The obtained experimental results show the effectiveness of the proposed control scheme. The fuzzy controller can position the robotic manipulator at any point in the workspace with better accuracy than the classic visual servoing approach.