作者: Kazuyoshi Yoshii , Kazuhiro Nakadai , Toyotaka Torii , Yuji Hasegawa , Hiroshi Tsujino
DOI: 10.1109/IROS.2007.4399244
关键词:
摘要: We aim at enabling a biped robot to interact with humans through real-world music in daily-life environments, e.g., autonomously keep its steps (stamps) time musical beats. To achieve this, the should be able robustly predict beat times real while listening performance own ears (head-embedded microphones). However, this has not previously been addressed most studies on music-synchronized robots due difficulty predicting music. solve problem, we implemented beat-tracking method developed field of information processing. The predicted are then used by feedback-control that adjusts robot's step intervals synchronize experimental results show can adjust as tempo changes. resulting needed about 25 [s] recognize change after it and steps.