The ability to navigate toward sound sources extends a robot's reach beyond its visual field, enabling response to auditory events in unknown environments. To equip robots with this capability, existing methods couple acoustic and visual information through joint audio-visual learning in acoustic simulators. However, a...
Yao-Zhong Kang, Jiang Wang, Takeshi Ashizawa et al.· IEEE International Symposium...· 0 citations
Vision-language-action policies fine-tuned on LIBERO are trained and evaluated on the same ten instruction strings, and rewording the instruction changes base OpenVLA's success by -38.0 points, although the stronger policies lose a much smaller fraction of it than base OpenVLA.
Han-Long Li, Si-Han Tan, Takeshi Ashizawa et al.· 0 citations
A humanoid with 5-DoF arms cannot track generic bimanual end-effector trajectories with its arms alone; pelvis and waist motion must be recruited, but which motion, and when, is not uniquely determined. On a Unitree R1 in fixed double support, the set of dynamically valid recruitment strategies (pelvis pose and waist t...
Han-Long Li, Si-Han Tan, Takeshi Ashizawa et al.· 0 citations
Text-to-audio (TTA) generation aims to synthesize realistic audio that faithfully reflects natural-language descriptions. Most TTA systems adopt a two-stage latent paradigm: an audio tokenizer is optimized for reconstruction and then frozen, after which a generative model is trained in the resulting latent space. Howev...
Run-Wu Shi, Kai Li, Yu-Jin Wang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.