Invention Grant
- Patent Title: Vehicle location using combined inputs of redundant localization pipelines
-
Application No.: US17443433Application Date: 2021-07-26
-
Publication No.: US12054173B2Publication Date: 2024-08-06
- Inventor: Paul Schmitt , Yimu Wang
- Applicant: Motional AD LLC
- Applicant Address: US MA Boston
- Assignee: Motional AD LLC
- Current Assignee: Motional AD LLC
- Current Assignee Address: US MA Boston
- Agency: Knobbe, Martens, Olson & Bear, LLP
- Main IPC: B60W60/00
- IPC: B60W60/00 ; G01C21/16 ; G06F18/214 ; G06N20/00 ; H04W4/46

Abstract:
Provided are methods for semantic annotation of sensor data using unreliable map annotation inputs, which can include training a machine learning model to accept inputs including images representing sensor data for a geographic area and unreliable semantic annotations for the geographic area. The machine learning model can be trained against validated semantic annotations for the geographic area, such that subsequent to training, additional images representing sensor data and additional unreliable semantic annotations can be passed through the neural network to provide predicted semantic annotations for the additional images. Systems and computer program products are also provided.
Public/Granted literature
- US20230027369A1 VEHICLE LOCATION USING COMBINED INPUTS OF REDUNDANT LOCALIZATION PIPELINES Public/Granted day:2023-01-26
Information query