Naming Objects for Vision-and-Language Manipulation
Published in arxiv preprint, 2023
We propose a robot system and method that incorporates naming with appearance of the objects in advance, so that in the later manipulation task, instruction can be performed with its unique name to disambiguate the objects easily.
Recommended citation: Nishikawa, T., Aoyama, K., Sekiguchi, S., Takayanagi, T., Wu, J., Ishihara, Y., Kojima, T. and Yokono, J.J., 2023. Naming Objects for Vision-and-Language Manipulation. arXiv preprint arXiv:2303.02871. https://arxiv.org/abs/2303.02871