WO2024201430 - VISUAL MEMORY IN AUTONOMOUS AGENTS
National phase entry is expected:
Publication Number
WO/2024/201430
Publication Date
03.10.2024
International Application No.
PCT/IB2024/053163
International Filing Date
02.04.2024
Title **
[English]
VISUAL MEMORY IN AUTONOMOUS AGENTS
[French]
MÉMOIRE VISUELLE DANS DES AGENTS AUTONOMES
Applicants **
SOUL MACHINES LIMITED
L1, 106 Customs St West
Auckland, 1010, NZ
Inventors
JEFFERSON, Josephine
c/o Level 1 106 Customs Street West Auckland Central Auckland 1010, NZ
SAGAR, Mark
7 Takarunga Road Devonport
Auckland, NZ
PAGES, Nathan
c/o Level 1 106 Customs Street West Auckland Central Auckland 1010 (NZ), NZ
CONDER, Jonathan
c/o Level 1 106 Customs Street West Auckland Central Auckland 1010 (NZ), NZ
NEJATI, Alireza
c/o Level 1 106 Customs Street West Auckland Central Auckland 1010 (NZ), NZ
Priority Data
798767
31.03.2023
NZ
Application details
| Total Number of Claims/PCT | * |
| Number of Independent Claims | * |
| Number of Priorities | * |
| Number of Multi-Dependent Claims | * |
| Number of Drawings | * |
| Pages for Publication | * |
| Number of Pages with Drawings | * |
| Pages of Specification | * |
| * | |
| * | |
International Searching Authority |
MOIP
* |
| Applicant's Legal Status |
Legal Entity
* |
| * | |
| * | |
| * | |
| * | |
| Entry into National Phase under |
Chapter I
* |
| Translation |
|
Recalculate
* The data is based on automatic recognition. Please verify and amend if necessary.
** IP-Coster compiles data from publicly available sources. If this data includes your personal information, you can contact us to request its removal.
Quotation for National Phase entry
| Country | Stages | Total | |
|---|---|---|---|
| China | Filing | 938 | |
| EPO | Filing, Examination | 6447 | |
| Japan | Filing | 531 | |
| South Korea | Filing | 575 | |
| USA | Filing, Examination | 2635 |
Total: 11126 USD
The term for entry into the National Phase has expired. This quotation is for informational purposes only
Abstract[English]
Embodiments described herein provide a method for autonomous agents (which may be situated, embodied agents) to learn new visual objects, and recognize the same objects within the same "runtime" / session / interaction, and be able to train a longer-term visual memory model on the object. A visual memory system stores templates of objects and compares images to these templates. An internal or external (to the agent) signal may determine which object/s to compare. The visual memory system stores new and unrecognized objects as "templates" and returns whether or not any region of the image is likely to contain a match for any of the stored templates. There is thus provided one-shot visual learning.[French]
Les modes de réalisation décrits dans les présentes concernent un procédé destiné à des agents autonomes (qui peuvent être situés, des agents incorporés) pour apprendre de nouveaux objets visuels, et reconnaître lesdits objets lors de la même « exécution »/session/interaction, et être capables d'entraîner un modèle de mémoire visuelle à plus long terme sur l'objet. Un système de mémoire visuelle stocke des modèles d'objets et compare des images auxdits modèles. Un signal interne ou externe (vers l'agent) peut déterminer le ou les objets à comparer. Le système de mémoire visuelle stocke de nouveaux objets non reconnus en tant que « modèles » et renvoie si une quelconque région de l'image est susceptible de contenir une correspondance pour l'un quelconque des modèles stockés. Est ainsi obtenu un apprentissage visuel en une fois.