ICT-2007.2.1 (ICT-2007.2.2): Cognitive Systems, Interaction, Robotics
Target outcome:
a) Artificial systems that fulfil one or both of the following requirements:
- they can achieve general goals in a largely unsupervised way, and persevere
under adverse or uncertain conditions; adapt, within reasonable constraints,
to changing service and performance requirements, without the need for external
re-programming, re-configuring, or re-adjusting.
- they communicate and co-operate with people or each other, based on a wellgrounded
understanding of the objects, events and processes in their environment, and
their own situation, competences and knowledge.
Work will result in demonstrators that operate largely autonomously in demanding
and open-ended environments which call for a suitable mix of capabilities for
sensing, data analysis, processing, control and acting; and for communication
and co-operation with people or machines or both. Where required, systems will
integrate high-level cognitive competencies; for example, for reasoning, planning
and decision-making, and for active environmental modelling.
Proposals satisfying the above requirements should focus on one of the following
areas:
- Robots handling, individually or jointly, tangible objects of different
shapes and sizes, and operating either fully autonomously (as for instance
in difficult terrains with a need for robust locomotion, navigation and obstacle
avoidance) or in co-operation with people in complex, dynamic spatial environments
(e.g. domestic environments).
- Robots, sensor networks and other artificial systems, monitoring and controlling
material and informational processes e.g. in industrial manufacturing or public
services domains. This may include information gathering and interpretation
in real-time emergency or hazardous situations (e.g. through multi-sensory
data-fusion) or in virtual spaces related to real world objects and people.
- Intuitive multimodal interfaces and interpersonal communication systems
providing personalised interactivity in real-world and virtual environments,
based on improved human interaction modelling and understanding of contextually-referred
communication, for example, by signs and signals in all modes (such as sound,
vision, touch) and modalities (such as natural language, both spoken and written),
through autonomous adaptation and by addressing user needs, intentions and
emotions.
Work proposed in any of these areas should, as appropriate:
- develop and apply engineering approaches that cater for real-time requirements
(if present) and systems modularity, and ensure the reliability, flexibility,
robustness,
scalability and, where relevant, also the safety of the resulting systems;
and develop criteria for benchmarking these properties;
- contribute to the theory and application of learning in artificial systems,
tackling issues related to the purposive and largely autonomous interpretation
of sensorgenerated data arising in different environments, and to novel design
and implementation principles of pertinent systems architectures.
- explore and validate the use of:
- advanced sensor, actuator, memory and control elements, components and
platforms, based on new, possibly bio-mimetic, materials and hardware
designs e.g. for the realisation of systems with greater structural
and functional diversity and modularity,
- new, possibly bio-inspired, information-processing paradigms, and of
models of natural cognition (including human mental and linguistic development),
adaptation, self-organisation, and emergence; and take account of the
role of systems embodiment and affordances.
- new ways of combining statistical, knowledge driven and cognitive approaches
to language understanding, generation, and translation by machines.
b) A principled approach to structuring research in relevant areas, addressing
in particular learning in artificial systems, the requirements for cognitive
capacities of
robotic, interactive and language support systems, and including the development
of experimental scenarios, the development or construction of resources for
experimentation, and the development of performance metrics and definitions
of autonomy levels for artificial systems.
c) Co-ordination with related national or regional research programmes or initiatives.
Expected impact:
- Leading-edge technology companies creating new products and services, and
enhancing existing ones.
- New markets such as: extending the industrial robotics market to flexible
small scale manufacturing, opening up services (professional and domestic)
markets to robots, novel functionalities for embedded systems and assistive
systems for interpersonal communications, such as support of dynamic translation,
and effective medical diagnostics and therapeutics.
- Robust and versatile behaviour of artificial systems in open-ended environments
providing intelligent response in unforeseen situations, and enhancing human-machine
interaction
- Extended capabilities of people to perform routine, dangerous or tiring
tasks in previously inaccessible, uncharted or remote spaces; saving critical
time in emergencies or hazardous situations.
- Leading-edge research in Europe through collaborative and multidisciplinary
experimentation with approaches to achieving machine intelligence and artificial
cognitive systems, and through investigation of what artificial and natural
cognitive systems can and cannot do.
Funding schemes a): CP; b): NoE; c) CSA (CA only)
Indicative budget distribution 82 M€:
- CP 74 M€ of which a minimum of 39 M€ to IP and a minimum of 13
M€ to STREP;
- NoE 7 M€;
- CSA 1M€ (CA only)