Title :
Reactive perception for autonomous task manipulation in robotic agents
Author :
Kikuti, M. ; Akyama, M. ; Medeiros, M. ; Reis, M. ; Aranha, C. ; GonÇalves, L.
Author_Institution :
Univ. Estadual de Campinas, Sao Paulo, Brazil
Abstract :
We present a model for reactive perception that can be used in multi-robot systems. The model is based on information servoing mechanisms that abstract data from general sensors. We are developing an inherently reactive approach that combines an on-line learning strategy with a predicted plan to drive the robot behavior
Keywords :
learning (artificial intelligence); multi-robot systems; robot vision; Robot Soccer; attention control; autonomous task manipulation; data abstraction from general sensors; decision system; information servoing mechanisms; manipulation skills; multi-robot systems; on-line learning strategy; pattern categorization; predicted plan; reactive approach; reactive perception; reinforcement learning models; robotic agents; visual servoing; Control systems; Feature extraction; Feedback; Learning; Multirobot systems; Orbital robotics; Predictive models; Robot sensing systems; Strategic planning; Visual servoing;
Conference_Titel :
Computer Graphics and Image Processing, 2001 Proceedings of XIV Brazilian Symposium on
Conference_Location :
Florianopolis
Print_ISBN :
0-7695-1330-1
DOI :
10.1109/SIBGRAPI.2001.963109
