Neural Feature Fields for Language-Guided Robot Manipulation
Self-supervised and language-supervised image models contain rich knowledge of the world that is important for generalization. Many robotic tasks, however, require a detailed understanding of 3D geometry, which is often lacking in 2D image features. This work bridges this 2D-to-3D gap for robotic ma...
Autore principale: | Shen, William |
---|---|
Altri autori: | Kaelbling, Leslie P. |
Natura: | Tesi |
Pubblicazione: |
Massachusetts Institute of Technology
2023
|
Accesso online: | https://hdl.handle.net/1721.1/152770 https://orcid.org/0009-0004-0227-1071 |
Documenti analoghi
Documenti analoghi
-
Tactile-guided robot manipulation
di: Thya, Lydia
Pubblicazione: (2022) -
Robust neural controller for robot manipulator
di: Lou, Jia Ming
Pubblicazione: (2011) -
Neural controller for flexible robotic manipulator
di: Raveendran, N.
Pubblicazione: (2008) -
RF-guided exploration for robotic manipulation
di: Leng, Junshan.
Pubblicazione: (2021) -
Neural network control of a robot manipulator
di: Liew, Kang Chew.
Pubblicazione: (2009)