Cognitive Systems, Interaction, Robotics Developing new cognitive architectural principles to allow intelligent agents to learn socio-communicative skills by observing and imitating people Automatic imitation learning of socio-communicative skills is an interesting research topic with significant potential benefits for future autonomous systems, robots and intelligent interfaces. HUMANOBS will develop new cognitive architectural principles that allow intelligent agents to learn socio-communicative skills by observing and imitating people. The resulting system will control a virtual humanoid television host, capable of conducting a simulated TV program and taking interviews with human users through speech and gesture (including face, body, arm and hand). The long-term framework is one in which humanoid agents and robots have autonomy for learning multimodal skills in dynamic social situations.
- HUMANOBS is funded by the Seventh Framework Programme of the European Union.
- Supported by the Programme ICT-2007.2.2 - Cognitive systems, interaction, robotics.
- Programme under grant agreement ID 231453.
- Funding period: 1 January 2009 – 31 December 2012.
- Coordinator: HASKOLINN I REYKJAVIK EHF (Reykjavik University)