European Funded Projects
The Laboratory of Robotics and Automation possesses a long standing experience in collaborative projects in European level, with several renown industrial and academic partners across Europe. Moreover, it plays a central role in promoting and advancing Industry 4.0 concepts at Greek and European level.
- “Novelty Or Anomaly HUNTER (NOAH)”, ESA AO8627.
- “Cloud-based Simulation of Page Curling from Straight Images and Correction using Neural Networks (CURLO)”, 3rd Party to Fortissimo 2 H2020 Project.
- “Methods to Refine the Self-Localization of Planetary Rovers Using Orbital Imaging, ESA NPI 289‐2013″, European Space Agency, ESA/ESTEC.
So far the only available rover localisation methods are relative, with respect to a previous rover location, and not absolute with respect to specific coordinates on the planet. This research work will investigate
methods for absolute localisation of a rover on a planetary surface by combining the stereo images obtained by the rover while traversing with high resolution images from orbit. The targeted localisation accuracy is equal to the resolution of the orbital images.
This research aims to study and develop algorithms, that combine SLAM techniques with spatial and elevation information coming from orbital images. Most previous attempts to improve the localisation utilising orbital imagery concerned robots that operate in structured urban environments, by extracting the prominent patterns of the area (e.g. edge detection on orbital images that depicted buildings and roads). This has provided favourable conditions, as urban environments offer abundance of canonical formations. Space scenes lack such canonical formations and, as a result, a different -less texture dependent methods- will be investigated. Therefore, two different approaches will be considered depending on the available orbital information:
In case only orbital images are available:
Extraction of “space specific – non structured” salient characteristics (local features, custom patterns) on the orbital images.
Extraction of corresponding characteristics that stem from ground rover’s on-board sensors.
In case only orbital digital elevation maps (DEMs) are available:
Extraction of 3D morphologically prominent formations from the DEMs.
Extraction of the corresponding formations utilising ground rover sensory for the environment reconstruction.
The algorithms will also be correlated to the computational resources they require. To this two different operational scenarios will be baselined and
investigated independently for the absolute localisation scheme:
Onboard approach: The ground station will provide periodically (e.g. daily) pre-processed data stemming from orbital images. Algorithms will be investigated that run onboard and combine this data with the local imagery collected by the rover.
On-ground approach: The refinement of the localisation will be done on-ground using selected stereo imagery downloaded by the rover on each communication window.
- “Autonomous Vehicle Emergency Recovery Tool (AVERT), FP7-SEC-2011-1-285092″, European Commission – Information & Communication Technologies (ICT).
commercial real estate. Vehicles provide an ideal delivery mechanism because they can be meticulously
prepared well in advance of deployment and then brought in to the Area of Operations. Furthermore, a real and
present danger comes from the threat of Chemical, Radiological, Biological and Nuclear (CRBN) contamination.
Current methods of bomb disruption and neutralisation are hindered in the event that the device is shielded,
blocked or for whatever reason cannot be accessed for examination.
The Autonomous Vehicle Emergency Recovery Tool (AVERT) shall provide a unique capability to Police and
Armed Services to rapidly deploy, extract and remove both blocking and suspect vehicles from vulnerable
positions such as enclosed infrastructure spaces, tunnels, low bridges as well as under-building and
underground car parks. Vehicles can be removed from confined spaces with delicate handling, swiftly and in
any direction to a safer disposal point to reduce or eliminate collateral damage to infrastructure and personnel.
AVERT shall be commanded remotely and shall operate autonomously under its own power and sensor
awareness, as a critical tool alongside existing technologies, thereby enhancing bomb disposal response speed
- “Sparing Robotics Technologies for Autonomous Navigation (SPARTAN), E913-00MM”, European Space Agency, ESA/ESTEC.
1) The reduction of the overall budgets required by the SFR navigation function while improving on its performances (i.e. accuracy of terrain reconstruction, probability to find paths) so to make the system compatible with the requirements of a long traverse range capability device.
2) The implementation of the developed computer vision algorithms (3D Reconstruction, Visual Odometry, and Visual SLAM) for rover navigation, using custom-designed vectorial processing (by means of FPGAs).
- “Innovative and Novel First Responders Applications (INFRA), FP7-ICT-SEC-2007-1-225272″, European Commission – Information & Communication Technologies (ICT).
A. Create an open, standards based interoperability layer that will allow:
• Broadband access for high bandwidth applications (i.e. live video)
• Autonomous wireless broadband in underground tunnels and concrete buildings – a severe problem in CI sites such as Subway tunnels, targeted by terrorists.
• Full voice and data communication interoperability between all FR teams, their command posts and the CI site control centre
• Full interoperability of FR applications in use by the FR teams
B. Provide practical and useful novel applications for FR teams, all integrated within the open interoperability layer:
• Thermal imaging applications
• Video annotation
• Advanced fibre optic sensors
• Indoor navigation system
Both the communications interoperability layer and the FR applications in INFRA are novel and go well beyond the current state of the art for the technology currently in use by FR teams. Although the FR forces are quite fragmented and localised, achieving standardization on the issue of broadband applications for FR is of importance to all Europe, as it will allow significant cost reduction of FR equipment and cross region and cross border cooperation between FR units. In a similar manner, there is no standardization of CI sites. So FR teams cannot rely on a standardised environment that is common to all CI sites. This situation is quite typical in Europe and globally. Project INFRA will provide a major step towards a standard, seamless, effective and efficient FR environment, which will ensure interoperability with the CI control centre, will save lives and reduce the financial damages of catastrophic events in CI sites.
- “Autonomous Collaborative Robots to Swing and Work in Everyday EnviRonment (ACROBOTER), FP6-IST-2006-045530″, European Commission – Information Society Technologies (IST).
- “Vision and Chemiresistor Equipped Web-connected Finding Robots (VIEW-FINDER), FP6-IST-2006-045541″, European Commission – Information Society Technologies (IST).
Summary of objectives:
1. Inspection of fire or crisis grounds and chemicals and toxin detection 2. Map building and scene reconstruction 3. Interfacing and fusing local command information and external information sources 4. Human Interface, integrating information search and robot control 5. Autonomous robot navigation and multi robot cooperation 6. Human-Robot cooperation and interaction.
- “Improvement of the Emergency Risk Management through Secure Mobile Mechatronic Support to Bomb Disposal (RESCUER), FP6-IST-511492″, European Commission – Information Society Technologies (IST).
RESCUER is an intelligent mechatronic system capable of achieving given goals under conditions of uncertainty. In contrast to existing automated bomb disarming systems, which are, by definition, pre-programmed to deliver given behaviour and are therefore predictable, RESCUER may arrive at specified goals in an unpredictable manner. This is possible due to RESCUER’s improved flexibility, dexterity and intelligence comparable to a human rescue specialist. Flexibility means the capability of responding to frequent changes in the environment without being re-configured. Dexterity means the enhanced perception and manipulation capabilities have never been used in Explosive, Chemical or Biological Threat Disposal or in humanitarian rescue operation while intelligence means the ability of RESCUER to identify the risk and to decide on proper action.
RESCUER is endowed with flexibility, which means it is capable of responding to frequent changes in the environment. This qualitative difference in RESCUER behaviour from exiting systems is the result of the separation of the domain knowledge from the mechanism dedicated for problem solving.
National Funded Projects
- “Combination of conventional and machine vision sensing and failure mode prediction models, for optimal risk management and increased operating life of production assets, in the Factory of the Future, (PREDICT), Τ1ΕΔΚ-02433”, ΕΥΔΕ-ΕΤΑΚ.
- “Multirole portable UAS (MPU), Τ1ΕΔΚ-00737”, ΕΥΔΕ-ΕΤΑΚ.
- “Hellenic Civil Unmanned Air Vehicle – HCUAV”, Φορέας χρηματοδότησης ΓΓΕΤ , ΣΥΝΕΡΓΑΣΙΑ, ΕΥΔ-ΕΤΑΚ 11ΣΥΝ9 629.
• Broad area surveillance, on a 24h/7d basis patrol over segments of National borders.
• Forest regions surveillance, on a 24h/7d basis patrol operation.
Furthermore, the adopted design requirements will aim at extending the use of the UAV towards atmospheric data collection for cloud formation, aerosol, pollution/air quality measurements and weather forecast initialization data.
- “Ανάπτυξη και Υλοποίηση Νέων Αλγόριθμων Αναγνώρισης Προτύπων Βασισμένων σε Βιολογικά Εμπνευσμένα Μοντέλα και σε Ευφυή Συστήματα”, Φορέας χρηματοδότησης ΓΓΕΤ , ΠΕΝΕΔ.
1. Αυτόματη συναρμογή των τμημάτων των εφημερίδων, οι οποίες κατατμήθηκαν για να χωρούν στο σαρωτή, ώστε να είναι δυνατή η ψηφιοποίησή τους. 2. Αυτοματοποίηση της τμηματοποίησης της εικόνας, ώστε να διευκολυνθεί η διαδικασία της αναγνώρισης χαρακτήρων. Η αυτοματοποίηση αυτή περιλαμβάνει επιλογή καταλλήλων κατωφλίων, φίλτρων για απομάκρυνση θορύβου και τονισμό χαρακτηριστικών κλπ. 3. Εφαρμογή γρήγορων σθεναρών αλγορίθμων στην αναγνώριση χαρακτήρων. 4. Αναγνώριση των λέξεων κλειδιών σε ένα κείμενο, στο οποίο έχει γίνει οπτική αναγνώριση χαρακτήρων, ώστε να είναι δυνατή η δεικτοθέτισή του.
- “Development of new techniques for recognition and categorization”, Greece-Slovenia, Joint Research and Technology Programmes.