RAPP
Proyectos
RAPP is a 3-year research project (2013-2016) funded by the European Commission through its FP7 programme. The RAPP project will provide an open source software platform to support the creation and delivery of robotic applications. These robotic applications are in turn expected to increase the versatility and utility of service and assistive robots. The emphasis of this project will be on applications that will enable robots to understand and respond to the intentions and needs of people at risk of exclusion, and especially the elderly.
Objetives
The RAPP project’s overall objectives can be stated as follows:
- Provide the infrastructure for robotic application developers to easily build and include machine learning and personalization techniques to their applications
- Create a robotic application repository from which robots can download applications and upload useful monitoring information
- Develop a methodology for knowledge representation and reasoning in robotics and automation, to allow for unambiguous knowledge transfer and reuse among groups of humans, robots and other artificial systems
- Create robotic applications that take into account the needs of elderly people and respect their autonomy and privacy
- Verify and validate the envisaged approach by deploying appropriate pilot case applications
Results
The RAPP project aims to provide an integrated approach for designing and producing robotic applications for heterogeneous robotic platforms, while at the same time addressing the needs of the end-users, i.e. the elderly people. In order to achieve this, the first year was tightly focused on an incremental procedure, by diligently gathering requirements from the end users, transforming the user requirements into the respective technical specifications and ultimately producing an overall system architecture and design.
Following up from the work performed in the first year, the main effort put in Y2 of the project was applied towards the accomplishment of the following aspects: the technical implementation of all respective modules appearing in the designed RAPP architecture, the preparation of the pilot cases, as well as the development and evaluation of the early robotic applications (RApps). The conclusion of the second year of the RAPP project has been met with the completion of most of the software components and sub-systems, a fact that will allows for shift of focus during Y3 towards the creation of the final RApps that will be ultimately tested and evaluated in our user groups.
Specifically, one of the key achievements of RAPP in the second year is the release of the overall platform architecture, ranging from the components required to include the heterogeneous robotic platforms, to the particular communication protocols and the high-level cloud services. This novel architecture addresses both the technical specifications and the user requirements of the RAPP project, and has been extensively reviewed both in action and through external processes (including relevant publications and peer-reviewing).
With respect to the particular machine learning components, the second year focused on finalizing all the software AI modules residing in the RAPP Platform and / or each robot. Specifically, several image processing, path planning, navigation and speech-oriented algorithms were designed, implemented and tested, aiming to be used both by external developers of robotic applications, as well as by the final versions of RApps. Finally, the respected web services were developed utilizing HOP and standard web communication methods.
Apart from algorithmic development, the RAPP API was finalized in order for the robotic applications to be able to invoke services both in the cloud and in the actual robots. Even though the specified RAPP API programming languages were C++ and JS, we worked beyond the state of the art by supporting Python as well. It should be stated that the RAPP Platform and the RAPP API were publicly released as open source code, aiming to attract robotic applications developers and benefit from their input. Finally the RAPP Store was developed and is ready to accommodate and serve the early and final versions of RApps.
Moving on to the user aspects of RAPP, work has been performed towards finalizing the requirements and specifications of RApps. The early requirements and specifications led to the development of the early versions of RApps which were evaluated with the help of the involved user groups, after the definition of the use cases and their prioritization according to their limitations and feasibility. The lessons learned from the early evaluation were recorded in the respective deliverables and will significantly assist towards the applications’ enhancement during Y3.
Finally, dissemination activities cover a broad range of channels and actions: website, social media, newsletters and press releases, conferences and journal publications. Particular emphasis has been given towards attracting RAPP’s target audience, i.e. elderly people, with focused seminars and demos addressed to this group, and publications to journals relevant to the interested stakeholders. During the second year, RAPP partners have organised or participated in over 20 external events and meetings to promote the RAPP project and results (10 events during the first year). During the second year, 13 scientific papers acknowledging RAPP have been published and are listed on the RAPP website.
Consortium
The RAPP project can count on eight partners in five European countries (Greece, France, United Kingdom, Spain and Poland), including research institutes, universities, industries and SMEs. The RAPP consortium brings together pioneers in the fields of Assistive Robotics, Machine Learning and Data Analysis, Motion Planning and Image Recognition, Software Development and Integration, and Excluded People – all eager to take on the technical and social challenges set in the project. RAPP partners are committed to identify the best ways to train and adapt robots to serve and assist people with special needs. Eventually, our aspired success will be to open and widen a new ‘inclusion market’ segment in Europe.
CERTH
Aristotle University of Thessaloniki
Inria
Ormylia Foundation
Ortelio
Matia Instituto
Warsaw University of Technology