Back to search
Georgia Institute of Technology
Canonical mapping as a general purpose representation
Abstract
dc:description.abstractPerception is critical for robotic manipulation in open environments, where traditional approaches often produce task-specific predictions that are unsuitable for deformable objects or adaptation to other tasks. In this work, conducted within a USDA-funded initiative focused on automating the poultry processing industry, we propose canonical mapping as a near-universal and flexible object descriptor. Canonical mapping establishes correspondences between image pixels and a 3D mesh, enabling robust pose prediction for both rigid and deformable objects.
Degree
thesis:*- Level thesis:degree_level
- Masters
- Department dc:contributor.department
- Computer Science
- Grantor dc:publisher
- Georgia Institute of Technology
- Year dc:date.issued
- 2024
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Rmiche, Nabil
- Advisor dc:contributor.advisor
-
- Pradalier, Cédric
- Committee members dc:contributor.committeemember
-
- Zsolt, Kira
- Ha, Sehoon
Subjects
dc:subject × 3Rights
- Language dc:language.iso
- en_US
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- https://hdl.handle.net/1853/80139