AMARSiProject reference: 248311
Funded under: FP7-ICT
Adaptive Modular Architecture for Rich Motor Skills [Print to PDF] [Print to RTF]
Total cost:EUR 9 208 448
EU contribution:EUR 6 997 978
Call for proposal:FP7-ICT-2009-4
Funding scheme:CP - Collaborative project (generic)
Richness of biological motor behavior in robotic systemsThe motor skills of today’s robots still must be qualified as poor. The AMARSi Integrated Project aims at a qualitative jump toward biological richness of robotic motor skills. To achieve this goal, a number of innovative scientific concepts and interdisciplinary research methods will be implemented.
Acquiring rich motor skills will change the role of robots in our human’s society in two fundamental ways. First, such robots will be much more versatile than today, with greatly expanded ranges of practical usages. And second, the naturalness and compliance of their motor behavior will make them blend into the everyday routines of human society, physically safe and psychologically acceptable.
Compared to animals and humans, the motor skills of today's robots still must be qualified as poor. Their behavioural repertoire is typically limited to a narrow set of carefully engineered motor patterns that operate a rigid mechanics and lack situated adaptivity, learnability and dynamical fusion of motor primitives into complex, task-oriented behavioural patterns.\nThe AMARSi Integrated Project aims at a qualitative jump toward biological richness of robotic motor skills, a jump to complex, task-oriented interaction sequences between a robot and a human caretaker.\nIt comprises leading groups from robot engineering, compliant mechanics, morphological computing, human motor research; biomechanics, theoretical biology, machine learning. The project deploys:\n- coordinated and simultaneous development of compliant mechanics, pervasive learning and dynamical-systems based control architectures, centered on the concept of adaptive modules;\n- mutually informing research in human motor behavior and robotics;\n- reliance on compliant mechanics and morphological computing for flexibility, computational and motoric speed, safety and damage-robust learning;\n- novel learning paradigms (unsupervised, reinforcement and imitation) drawing from principles of reservoir computing;\n- control architectures based on dynamical (neural) systems throughout, also on the higher cognitive levels.\nRobotic demonstration with a compliant version of the iCub robot and a compliant quadruped Cheetah platform will manifest progress. The robots will engage in an interaction with a human caretaker at the level of a young child playing open-ended in a cluttered and rough environment. Hardware and software solutions will be made publicly available as open sources.\nUltimately, the naturalness of such compliant robots will let them blend into the everyday routines of human society, physically safe and psychologically acceptable.
Tel.: +49 (0) 521 106-67109
Fax: +49 (0) 521 106-89042
Tel.: +32 92643 029
Fax: +32 92643 583
Tel.: +41 44635 2407
Fax: +41 44635 4507
Tel.: +49 421 200 4515
Fax: +49 421 200 49 4515
Fax: +972 8 934 4165
Tel.: +39 010 71781 490
Fax: +39 010 720321