US 12,168,445 B1
Refining event triggers using machine learning model feedback
Sharan Srinivasan, Sunnyvale, CA (US); Brian Tuan, Cupertino, CA (US); John Bicket, Burlingame, CA (US); Jing Wang, Toronto (CA); Muhammad Ali Akhtar, Chicago, IL (US); Abner Ayala Acevedo, Orlando, FL (US); Bruce Kellerman, Atlanta, GA (US); and Vincent Shieh, San Francisco, CA (US)
Assigned to Samsara Inc., San Francisco, CA (US)
Filed by Samsara Inc., San Francisco, CA (US)
Filed on Aug. 11, 2023, as Appl. No. 18/448,760.
Application 18/448,760 is a continuation of application No. 17/661,689, filed on May 2, 2022, granted, now 11,780,446.
Application 17/661,689 is a continuation of application No. 17/454,773, filed on Nov. 12, 2021, granted, now 11,352,013, issued on Jun. 7, 2022.
Claims priority of provisional application 63/117,271, filed on Nov. 23, 2020.
Claims priority of provisional application 63/113,645, filed on Nov. 13, 2020.
This patent is subject to a terminal disclaimer.
Int. Cl. B60W 40/09 (2012.01); G06N 3/045 (2023.01); G06T 7/73 (2017.01); G06V 20/59 (2022.01)
CPC B60W 40/09 (2013.01) [G06N 3/045 (2023.01); G06T 7/73 (2017.01); G06V 20/597 (2022.01)] 20 Claims
OG exemplary drawing
 
2. A vehicle device comprising:
a computer readable storage medium having program instructions embodied therewith; and
one or more processors configured to execute the program instructions to cause the vehicle device to:
obtain sensor data associated with an image of a scene;
access a first neural network, wherein the first neural network is configured to output a first probability of an event associated with the image;
route the sensor data to a receiving server system using a network connection with the receiving server system, wherein the receiving server system comprises a second neural network, wherein the second neural network is configured to output a second probability of the event;
obtain an identifier of one or more operations to dynamically adjust how the vehicle device identifies the event, the one or more operations based on a comparison of the first probability of the event output by the first neural network and the second probability of the event output by the second neural network; and
automatically perform the one or more operations, wherein performance of the one or more operations increases an accuracy of the vehicle device in identifying the event.