Thesis
Object-centric generative models for robot perception and action
- Abstract:
-
The system of robot manipulation involves a pipeline consisting of the perception of objects in the environment and the planning of actions in 3D space. Deep learning approaches are employed to segment scenes into components of objects and then learn object-centric features to predict actions for downstream tasks. Despite having achieved promising performance in several manipulation tasks, supervised approaches lack inductive biases related to general properties of objects. Recent advances...
Expand abstract
Actions
Access Document
- Files:
-
-
(Preview, Dissemination version, pdf, 15.3MB, Terms of use)
-
Authors
Contributors
+ Posner, I
- Institution:
- University of Oxford
- Division:
- MPLS
- Department:
- Engineering Science
- Role:
- Supervisor
+ Rupprecht, C
- Institution:
- University of Oxford
- Division:
- MPLS
- Department:
- Computer Science
- Role:
- Examiner
+ Ahn , S
- Role:
- Examiner
- DOI:
- Type of award:
- DPhil
- Level of award:
- Doctoral
- Awarding institution:
- University of Oxford
- Language:
-
English
- Keywords:
- Subjects:
- Deposit date:
-
2024-02-08
- ARK identifier:
Terms of use
- Copyright holder:
- Wu, Y
- Copyright date:
- 2023
If you are the owner of this record, you can report an update to it here: Report update to this record