R3-COP - Resilient Reasoning Robotic Co-operating Systems
R3-COP (Resilient Reasoning Robotic Co-operating Systems) aims at providing European industry with new leading-edge innovation that will enable the production of advanced robust and safe cognitive, reasoning autonomous and co-operative robotic systems at reduced cost. The major objective is to achieve cross-sector reusability of building blocks, collected in a knowledge base, by developing and implementing a generic framework and platform with domain-specific instantiation, and use of a multi-purpose computing platform. The project is co-funded by ARTEMIS JU and for Danish partners by the Danish Agency for Science, Technology and Innovation.
Problem
Autonomous systems are a most promising evolving area for cross-domain use and deployment of embedded intelligence and systems, with focus on both properties, "embedded" and "intelligence". Robots, one incarnation of autonomous systems, are a backbone of European industry, in achieving cost-effective production and high quality. Europe has a rather good position in this area. For historical reasons, existing solutions are always somehow proprietary, which in the long term is very costly. The classical industrial robots markets stagnate, whereas newly emergent market sectors (domestic services, surveillance and security, healthcare, transport etc.) are becoming key to European industry, which is very fragmented, a severe concern of ARTEMIS. The challenges can only be met by a joint European effort to overcome the obvious obstacles which hamper the broad and economic application of autonomous robotic systems:
- Lack of a uniform platform that would provide a flexible framework to integrate components from various technology providers.
- Lack of appropriate verification and testing means for autonomous systems with complex behaviour in realistic environments.
- The current robotic systems lack a "broader" sense to understand the environment and sufficient reasoning capabilities.
- Non-availability of high-performance computational embedded platforms.
- Unavailability of integrated components for advanced image recognition/processing and other perception/recognition/reasoning capabilities.
Solution
In order to overcome or at least alleviate these obstacles, R3-COP plans to progress the current state-of-the-art of autonomous systems in two main directions: technology andmethodology.
With respect to technology, R3-COP will develop a new fault tolerant high performance embedded hardware platform based on a multi-core architecture taking into account autonomous systems' functional and non-functional requirements. In addition, R3-COP will provide innovative system components for robust perception of the environment including sensor fusion, for reasoning and reliable action control, and for communication and cooperation among autonomous vehicles.
With respect to methodology, R3-COP will address the first obstacle by establishing a methodology based development framework for autonomous systems. This will be built upon an extensible knowledge base comprising all state-of-the-art information about the enabling technologies (hardware, algorithms etc.) for robust autonomous systems. This will include a reference framework for reasoning. The application of this methodology will be supported by a tool platform, which will cover design, implementation, and verification/testing. This will make efficient development of reference platforms for various robotic application domains as well as dedicated solutions possible, with strong means for avoiding mistakes due to experience-based methodology behind.
Further, testing tools will support automatic test case generation for cooperating autonomous systems with complex behaviour using multidimensional and multimodal sensing. As a consequence, this tool platform will both help to reduce cost and improve dependability. And because of fostering the development of cross-domain reference platforms, long-term aspects like maintainability or reuse will also be positively influenced.
Finally, the mentioned achievements shall be applied in a series of ground-based, air-borne and underwater demonstrators. Therefore, the project has conceptually an orthogonal structure.
Value
R3-COP meets the overarching objective of ARTEMIS with respect to close the design productivity gap in order to advance Europe's competitive position on the world market:
Reduce the cost of system design from 2005 levels by 15% by 2013: A clear objective of R3-COP is considerable cost-reduction in development and validation & verification of resilient cooperative autonomous (robotic) systems, The common architectural approach (framework), platforms, and V&V technologies are expected to reduce development and validation cost by at least 20% while enabling faster time-to-market.
Achieve 15% reduction in development cycles, especially in sectors requiring qualification or certification by 2013: The qualification and certification aspect is specifically addresses by Validation and Verification, and the close interaction with Standardization, by 1) developing and integrating new V&V strategies and a V&V framework, and 2) providing input for standardization and certification.
Manage a complexity increase of 25% with 10% effort reduction by 2013, by choosing an appropriate design methodology and architectural framework for composition of domain/application specific systems from a knowledge-base of components, methods and tools of all enabling technologies (embedded HW, sensors, perception,...)
Reduce re-validation and re-certification effort and time by 15% by 2013, by component based composition and advanced V&V technology (automated test case generation)
Achieve cross-sectoral reusability, by developing and implementing a rather generic framework and platform with domain-specific instantiation, and use of multi-purpose computing platform
Market Innovation
The project aims to overcome the fragmentation of the robotic sector by creating a cross-domain platform of methods and tools for the design, development and validation of resilient and usable real world autonomous systems. These systems will be able to reason, learn and cooperate in different application domains such as surveillance and rescue, agriculture, people care, home environments and transport. Research will target resilient cooperation models and protocols, robust computer navigation and vision algorithms, semantic reasoning methods, methods and tools for the efficient testing and validating of dependable adaptive autonomous systems.
Technical Innovation
Technology
- Fault-tolerant, high-performance processing platform based on a multi-core architecture
- Developing new test strategies for mobile and adaptive systems with complex sensor input (vision) with measurable coverage
- Robust perception of the environment
- Reasoning, learning and reliable action control
Methodology
- Development framework with an underlying knowledge base
- Tool platform for guarded development and standardized testing
- Model-driven process for the compositional development of safe and robust robotic co-operating (autonomous) systems
- Demonstrators from ground-based, airborne and underwater domains, including domestic and manufacturing applications as well.
Project Data:
- Title: Resilient Reasoning Robotic Co-operating Systems
- Acronym: R3-COP
- EU-project number: 100233
- Partners: 26
- Duration: 3.5 years (42 months)
- Start date: 1/5-2010
- End date: 31/10-2013
- Project Web-site: http://www.r3-cop.eu/
Funding authorities:
- ARTEMIS JOINT UNDERTAKING
- Danish Agency for Science, Technology and Innovation (for Danish partners)
- Total Budget: €18.319.660
Partners:
- AIT Austrian Institute of Technology GmbH, AT
- Brno University of Technology, CZ
- Hellenic Aerospace Industry S.A., GR
- CAMEA, spol. S.r.o, CZ
- Technalia, ES
- Friedrich-Alexander Universität Erlangen-Nürnberg, DE
- National Technical University of Athens, GR
- Technical Research Centre of Finland (Valtion Teknillinen Tutkimuskeskus), FI
- Telecommunication Systems Institute, GR
- Budapest University of Technology and Economics, HU
- THALES ITALIA SPA, IT
- Friedrich-Schiller-Universität Jena, DE
- Fraunhofer Institutes FHG/IPA/FHG/IDMT, DE
- Acciona Infraestructuras S.A, ES
- Infineon Technologies AG, DE
- Innova S.p.a., IT
- Siemens AG (Munich), DE
- Inst. of Mathematics and Computer Science of the University of Latvia, LV
- Elettric 80 Spa, IT
- Danish Technological Institute, Robot Technology, DK
- TEKNOSAVO OY, FI
- Probot Ltd., FI
- Profin Oy, FI
- Philips, NL
- Technical University Eindhoven, NL
- Demcon, NL