EHIRING: PhD StudentsThe University of Amsterdam (UvA) and TomTom are opening a new research lab called 'ATLAS Lab'. We are seeking for one PhD student. You can apply here
Participants: Rick Groenendijk
FlexCRAFT is a Dutch research program to advance Cognitive Robotics for Flexible Agro-Food Technology. The program is executed by an excellent team of robotic researchers from five universities in collaboration with fourteen companies and supported by NWO/TTW. The program revolves around three agro-food use-cases. The uses-cases give rise to generic robotic challenges in dealing with variation. Demonstrators for each of the use-cases will be developed in use-case projects
The project aims to construct the first prototype of outdoor garden trimming robots. The robot is an extension of the current commodity Bosch Indego lawnmower, which will navigate through varying types of terrains, identify the bushes of interest, and trim them to ideal shapes. The University of Amsterdam (UvA) is in charge of the vision workpackage which analyzes captured images and makes sense of them. There are four tasks that have been proposed: recovering albedo and illumination, recognizing garden proto-objects, garden traversability and missing data completion.
UvA is part of GRAVITATE, which stands for Geometric Reconstruction And noVel semantIc reunificaTion of culturAl heriTage objEcts. GRAVITATE is an H2020 project which addresses the world of Cultural Heritage and related science. The innovative aspect of the project is to create a digital platform that allows Re-Unification, Re-Association and Re-Assembly of heritage artifacts, based on 3D geometry, shape analysis, colour features, semantic metadata and natural language processing. The integration of these approaches into a single decision support platform, with a full suite of visualization tools provides a unique resource for the cultural heritage research community.
Within GRAVITATE, partner UvA is to produce two main algorithms: Faceting and Mating. The Faceting is the segmentation of the 3D fragment into meaningful regions (e.g: fracture, inside skin, outside skin). While, the mating is digitally gluing the fragments into one artifact by putting them into the best relative position.
A computer that recognises dangerous situations on security footage: this is possible with deep-learning automated systems. But before this kind of system can operate independently, you have to design it and then train it with a huge number of examples. In addition, you need considerable computing power to let the system make decisions. At the Efficient Deep Learning programme, researchers are going to make deep learning much more efficient by using examples from daily life. They want to make it possible to use the technique (Of: They want to make the technique applicable) for other automatic visual inspections, tissue analysis, smart maintenance of equipment and intelligent hearing aids that can handle noisy environments.