Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
PROBABILISTIC APPROACH TO UNIFYING REPRESENTATIONS FOR ROBOTIC MAPPING
Document Type and Number:
WIPO Patent Application WO/2024/058618
Kind Code:
A1
Abstract:
The present disclosure provides methods, apparatuses, and computer-readable mediums for evaluating a reliability of three-dimensional shape predictions. In an embodiment, a method includes obtaining a scene representation including one or more images, estimating semantic information of partially-observed objects in the scene representation, based on geometric information extracted from the one or more images, determining segmented pointclouds of the partially-observed objects based on the semantic information and the geometric information, creating metric embeddings of the segmented pointclouds corresponding to the partially-observed objects, predicting completed shape pointclouds of the partially-observed objects, generating, using a probabilistic machine learning model, confidence scores for each point of the completed shape pointclouds, based on a correlation between the geometric information and the semantic information, and controlling a motion of a robot based on the confidence scores for each point of the completed shape pointclouds.

Inventors:
HONG JUNGSEOK (US)
GARG SUVEER (US)
ISLER IBRAHIM VOLKAN (US)
Application Number:
PCT/KR2023/013970
Publication Date:
March 21, 2024
Filing Date:
September 15, 2023
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
SAMSUNG ELECTRONICS CO LTD (KR)
International Classes:
G05B19/4093; B25J15/00; G06T7/50; G06V10/776; G06V20/40
Foreign References:
US20180144493A12018-05-24
US20200273138A12020-08-27
US20220292717A12022-09-15
KR102393345B12022-05-02
US9589368B22017-03-07
Attorney, Agent or Firm:
Y.P.LEE, MOCK & PARTNERS (KR)
Download PDF: