Objetivo
The proposed research is directed at developing advanced neural schemes for obj ect-oriented, adaptive, reaching, grasping and manipulation in robotics, with i ncreased stability and robustness. They will be oriented to robotic service app lications, and especially for helping people with motor disabilities. The scien tific objectives of the project are: - Transfer of fundamental biological princ iples from cognitive-motor behaviour to antropomorphic robotics. - Construction of a high level, hardware independent, adaptive and modular library of element ary hand gestures. - New neural schemes that mimic the known cooperation betwee n cerebral cortex and cerebellum/basal ganglia during cognitive motor behaviour in manipulation. - Specifications for a subsequent industrial research project to be carried out by the endorsers The technical objectives of the project ar e: - Biological neural networks capable of construct grasp plans in the face of both functional and objectspecific constraints. - A language of opposition spa ce and virtual finger, oriented to construct a sequence learning of self adapti ve elementary hand gestures with total independence of application and environm ent. - Adaptive neural controllers wich, tested within laboratory environment u sing computer simulation, will be capable of generalising their skills in the s caling-up process to different robotics hands. The present project will transfe r human planning processes to robotics, while incorporating experimental result s from behavioural, anatomical, and neurophysiological studies. A well-defined robust set of mathematical models, elementary library of gestures, behavioural modules, and a selection mechanism over them will produce a considerable improv ement in the building of flexible and robust control systems for robot hands. M oreover, it will imply a reduction of the time and efforts necessary in the sca ling-up from laboratory to service robotics and a reduction of danger where rob ots must interact with humans. The generic neural models for human-like, flexib le, adaptive manipulation are not limited to the robotic service industry. The results of the present project are applicable in the whole area of manufacturin g where compliance is desirable to interact with the changing environment.
Ámbito científico
CORDIS clasifica los proyectos con EuroSciVoc, una taxonomía plurilingüe de ámbitos científicos, mediante un proceso semiautomático basado en técnicas de procesamiento del lenguaje natural.
CORDIS clasifica los proyectos con EuroSciVoc, una taxonomía plurilingüe de ámbitos científicos, mediante un proceso semiautomático basado en técnicas de procesamiento del lenguaje natural.
- natural sciencesbiological sciencesneurobiology
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringcontrol systems
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringrobotics
- natural sciencesmathematicsapplied mathematicsmathematical model
- natural sciencescomputer and information sciencesartificial intelligencecomputational intelligence
Convocatoria de propuestas
Data not availableRégimen de financiación
CSC - Cost-sharing contractsCoordinador
47151 Valladolid
España