From Pixel to Poses: Object-centric Tool Manipulation Learning from Human Demonstrations
P2P-T is introduced, from Pixel to Poses for Tool Manipulation, a data-efficient, object-centric framework that learns tool use directly from human demonstrations and achieves a 73% improvement over the previous state of the art in execution performance on complex, real-world tool manipulation tasks that currently rema...
Bang-Jun Wang, Long-Yan Wu, Yu-Kun Wei et al.
· 0 citations