In this paper we present how, using a careful definition of a state function, long animation sequences can be created joining clips from a database. Each next clip is chosen in real-time by a controller optimizing a cost function on the state function; this allows the user interact in real-time with the digital character. We analyze here two possible cost functions, one that is based on the evaluation of the compatibility of the next clip and one based on reinforcement learning in which the global policy of the controller is evaluated.
Creating long gait animation sequences through Reinforcement Learning / M. Alamia, N.A. Borghese - In: Neural Nets WIRN 10 : proceedings of the 20th Italian workshop on neural nets / [a cura di] B. Apolloni, S. Bassis, A. Esposito, C.F. Morabito. - Amsterdam : IOS press, 2011. - ISBN 9781607506911. - pp. 144-151 (( Intervento presentato al 20. convegno Workshop Italiano Reti Neurali tenutosi a Vietri sul mare nel 2010.
Creating long gait animation sequences through Reinforcement Learning
N.A. BorgheseUltimo
2011
Abstract
In this paper we present how, using a careful definition of a state function, long animation sequences can be created joining clips from a database. Each next clip is chosen in real-time by a controller optimizing a cost function on the state function; this allows the user interact in real-time with the digital character. We analyze here two possible cost functions, one that is based on the evaluation of the compatibility of the next clip and one based on reinforcement learning in which the global policy of the controller is evaluated.Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.