US-20260128995-A1 - OPTIMIZING DATA TRANSMISSION IN LOCATION-AWARE SYSTEMS

US20260128995A1US 20260128995 A1US20260128995 A1US 20260128995A1US-20260128995-A1

Abstract

In various examples, a technique for managing data uploads from location-aware systems includes determining a set of attributes associated with a set of data uploaded using a set of location-aware systems in a geographic region. The technique also includes computing a set of upload control parameters for the geographic region based at least on the set of attributes. The technique further includes receiving, from a location-aware system, a request indicating the geographic region. The technique additionally includes sending, to the location-aware system in response to the request, the set of upload control parameters within one or more control layers included in map data for the geographic region, wherein the location-aware system controls upload of additional data associated with the geographic region based at least on the one or more control layers.

Inventors

Galen Collins
Michael Stanton Kron
Derik SCHROETER
Matthew Sammis Ashman
Vladimir Shestak

Assignees

NVIDIA CORPORATION

Dates

Publication Date: 20260507
Application Date: 20251229

Claims (1)

1 . A method comprising: determining a set of attributes associated with a set of data uploaded using a set of location-aware systems in a geographic region; computing a set of upload control parameters for the geographic region based at least on the set of attributes; receiving, from a location-aware system, a request indicating the geographic region; and sending, to the location-aware system in response to the request, the set of upload control parameters within one or more control layers included in map data for the geographic region, wherein the location-aware system controls upload of additional data associated with the geographic region based at least on the one or more control layers.

Description

CROSS REFERENCE TO RELATED APPLICATIONS This application claims the priority of co-pending xx United States Patent Application titled “OPTIMIZING DATA TRANSMISSION IN LOCATION-AWARE SYSTEMS”, filed on Feb. 1, 2024, and having application Ser. No. 18/430,500. The subject matter of this related application is hereby incorporated herein by reference. BACKGROUND Modern vehicles are commonly equipped with sensors and communication systems that collect and transmit data related to their surroundings. This data may include (but is not limited to) images, point clouds, road conditions, traffic patterns, weather conditions, and/or other information that can be used to evaluate and/or improve vehicle operation and navigation. For example, a fleet of autonomous or semi-autonomous vehicles or other machine types within a geographic or other physical area may continuously collect and transmit data to a central server. This data may be used to debug issues in the vehicles, train machine learning models used in the operation of the vehicles, and/or perform other tasks. However, the volume of data collected by a large fleet of vehicles can quickly exceed a limited bandwidth allocation for transmitting data from the fleet. When this bandwidth allocation is exceeded, additional data transmissions may be throttled or cut off. Additionally, the value or importance of a given set of collected data may vary depending on factors such as (but not limited to) the geographic location of the corresponding vehicle, the type of the collected data, use cases associated with the collected data, and/or duplication of the collected data in other vehicles. Consequently, selective transmission of data from vehicles in the fleet may be required to use available network bandwidth and/or other limited resources in an efficient and effective manner. Existing approaches to controlling data transmission from fleets of vehicles include a distributed configuration system that sends instructions for uploading various types and quantities of data to the vehicles via a push or pull mechanism. These existing approaches may also, or instead, involve evaluating data uploaded by the vehicles and sending messages to throttle additional uploads from the vehicles. However, these existing approaches entail frequent communication with the vehicles, which requires a resource-intensive online infrastructure that may be difficult to maintain and/or scale. These existing approaches may further involve the creation and definition of individual “campaigns” that represent different configurations or policies for uploading data from the vehicles. Each campaign may additionally require the creation and/or propagation of custom code, retry mechanisms, redundancies, databases, and/or caching layers to implement the campaign, which is both time-and resource-intensive. As such, a need exists for more effective techniques for managing data transmission in large-scale vehicle fleets. SUMMARY Embodiments of the present disclosure relate to optimizing data transmission in location-aware systems. The techniques described herein include determining a set of attributes associated with a set of data uploaded using a set of location-aware systems in a geographic region. The technique also includes computing a set of upload control parameters for the geographic region based at least on the set of attributes. The technique further includes receiving, from a location-aware system, a request indicating the geographic region. The technique additionally includes sending, to the location-aware system in response to the request, the set of upload control parameters within one or more control layers included in map data for the geographic region, wherein the location-aware system controls upload of additional data associated with the geographic region based at least on the one or more control layers. One technical advantage of the disclosed techniques relative to prior approaches is the ability to specify and implement various policies for controlling the upload of data from a fleet of vehicles, thereby allowing limited bandwidth allocated to these uploads to be used in an efficient, effective, and responsive manner. Additionally, the disclosed techniques allow portions of control layers for controlling data uploads to be selectively requested by the vehicles, which reduces communication with the vehicles and resource overhead associated with an online infrastructure for conducting this communication. Further, because schemas for the control layers are distributed with the control layers, the vehicles are able to adapt data uploads to parameters in the control layers without requiring custom code, retry mechanisms, redundancies, databases, and/or caching layers to be created and propagated. BRIEF DESCRIPTION OF THE DRAWINGS The present systems and methods for optimizing data transmission in location-aware systems are described in detail below with reference to the attached drawing figures, w