Map updates
In various examples, segmented map creation for autonomous and semi-autonomous systems and applications is described herein. For instance, systems and methods described herein may segment a map into various portions, where the systems and methods then update the map based at least on the segmentation. For instance, based at least on receiving instances of data from machines navigating with an environment associated with the HD map, the instances of data may be associated with various portions of the map. Additionally, metrics associated with the portions of the map may be updated, such as by indicating the numbers of instances of data that are associated with the portions of the map. As such, when a metric associated with a portion of a map is satisfied, such as by reaching a threshold, the portion of the map may be updated without updating one or more other portions of the map.
1 . A system comprising:
one or more processors to cause a machine to navigate between locations within an environment using at least a first portion of a map associated with a first portion of the environment, wherein the map is updated, at least, by:
storing first mapstreams representing the first portion of the environment that is associated with the first portion of the map and second mapstreams representing a second portion of the environment that is associated with a second portion of the map;
determining, based at least on associating the first mapstreams with the first portion of the map, at least a first total number of mapstreams that are associated with the first portion of the map;
determining, based at least on associating the second mapstreams with the second portion of the map, at least a second total number of mapstreams that are associated with the second portion of the map;
determining, based at least on the first total number of mapstreams being equal to or greater than a threshold number of mapstreams and the second total number of mapstreams being less the threshold number of mapstreams, to update the first portion of the map while refraining from updating the second portion of the map; and
causing the first portion of the map to be updated using at least a portion of the first mapstreams.
2 . The system of claim 1 , wherein the map is further updated by:
determining, based at least on associating one or more third mapstreams with the second portion of the map, a third number of mapstreams by increasing the second total number of mapstreams; and
determining, based at least on the third number of mapstreams being equal to or greater than the threshold number of mapstreams, to update the second portion of the map.
3 . The system of claim 1 , wherein the map is further updated by:
updating a first value associated with the first total number of mapstreams to a second value based at least on associating at least a portion of the first mapstreams with the first portion of the map; and
determining that the first total number of mapstreams is equal to or greater than the threshold number of mapstreams based at least on the second value being equal to or greater than a third value associated with the threshold number of mapstreams.
4 . The system of claim 1 , wherein the map is further updated by:
obtaining first location data associated with one or more second machines that obtained the first mapstreams and second location data associated with one or more third machines that obtained the second mapstreams;
determining, based at least on the first location data, that the first mapstreams are associated with the first portion of the map; and
determining, based at least on the second location data, that the second mapstreams are associated with the second portion of the map.
5 . The system of claim 1 , wherein a mapstream from the first mapstreams comprises one or more of:
sensor data representing the first portion of the environment that corresponds to the first portion of the map; or
processed data representing one or more locations of one or more objects located within the first portion of the environment.
6 . The system of claim 1 , wherein the map is further updated by:
determining that a threshold period of time has elapsed since a previous update associated with the second portion of the map; and
determining, based at least on the threshold period of time elapsing, to update the second portion of the map.
7 . The system of claim 1 , wherein the map is further updated by:
associating a plurality of mapstreams with the first portion of the map;
filtering the plurality of mapstreams using one or more criteria; and
identifying, based at least on the plurality of mapstreams being filtered, the first mapstreams from the plurality of mapstreams.
8 . The system of claim 1 , wherein the system is comprised in at least one of:
a control system for an autonomous or semi-autonomous machine;
a perception system for an autonomous or semi-autonomous machine;
a system for performing one or more simulation operations;
a system for performing one or more digital twin operations;
a system for performing light transport simulation;
a system for performing collaborative content creation for 3D assets;
a system for performing one or more deep learning operations;
a system implemented using an edge device;
a system implemented using a robot;
a system for performing one or more conversational AI operations;
a system implementing one or more large language models (LLMs);
a system for performing one or more generative AI operations;
a system for generating synthetic data;
a system incorporating one or more virtual machines (VMs);
a system implemented at least partially in a data center; or
a system implemented at least partially using cloud computing resources.
9 . One or more processors comprising processing circuitry to cause a machine to navigate using a first portion of a map associated with a first portion of an environment, wherein the map is updated, at least, by:
storing one or more first mapstreams representing the first portion of the environment that is associated with the first portion of the map and one or more second mapstreams representing a second portion of the environment that is associated with a second portion of the map;
determining, based at least on associating the one or more first mapstreams with the first portion of the map, at least first total number of mapstreams that are associated with the first portion of the map;
determining, based at least on associating the one or more second mapstreams with the second portion of the map, at least a second total number of mapstreams that are associated with the second portion of the map;
determining, based at least on the first total number of mapstreams being equal to or greater than a threshold number of mapstreams and the second total number of mapstreams being less the threshold number of mapstreams, to update the first portion of the map while refraining from updating the second portion of the map; and
causing the first portion of the map to be updated using at least the one or more first mapstreams.
10 . The one or more processors of claim 9 , wherein the one or more processors is comprised in at least one of:
a control system for an autonomous or semi-autonomous machine;
a perception system for an autonomous or semi-autonomous machine;
a system for performing one or more simulation operations;
a system for performing one or more digital twin operations;
a system for performing light transport simulation;
a system for performing collaborative content creation for 3D assets;
a system for performing one or more deep learning operations;
a system implemented using an edge device;
a system implemented using a robot;
a system for performing one or more conversational AI operations;
a system implementing one or more large language models (LLMs);
a system for performing one or more generative AI operations;
a system for generating synthetic data;
a system incorporating one or more virtual machines (VMs);
a system implemented at least partially in a data center; or
a system implemented at least partially using cloud computing resources.
11 . The system of claim 1 , wherein the one or more processors are further to receive, from one or more computing devices, data representing at least the first portion of the map as updated for navigating within at least the first portion of the environment.
12 . A method comprising:
causing a machine to navigate within an environment based at least on a first portion of a map representing a first portion of the environment, wherein the map is updated, at least, by:
storing one or more first mapstreams representing the first portion of the environment that is associated with the first portion of the map and one or more second mapstreams representing a second portion of the environment that is associated with a second portion of the map;
determining, based at least on associating the one or more first mapstreams with the first portion of the map, at least a first number of mapstreams associated with the first portion of the map;
determining, based at least on associating the one or more second mapstreams with the second portion of the map, at least a second number of mapstreams associated with the second portion of the map;
determining, based at least on the first number of mapstreams being equal to or greater than a threshold number of mapstreams and the second number of mapstreams being less the threshold number of mapstreams, to update the first portion of the map while refraining from updating the second portion of the map; and
causing the first portion of the map to be updated using at least the one or more first mapstreams.
13 . The method of claim 12 , wherein map is further updated by:
determining, based at least on associating one or more third mapstreams with the second portion of the map, a third number of mapstreams by increasing the second number of mapstreams; and
determining, based at least on the third number of mapstreams being equal to or greater than the threshold number of mapstreams, to update the second portion of the map.
14 . The method of claim 12 , wherein the map is further updated by:
updating a first value associated with the first number of mapstreams to a second value based at least on the associating the one or more first mapstreams with the first portion of the map; and
determining that the first number of mapstreams is equal to or greater than the threshold number of mapstreams based at least on the second value being equal to or greater than a third value associated with the threshold number of mapstreams.
15 . The method of claim 12 , wherein the map is further updated by:
obtaining first location data associated with one or more second machines that obtained the one or more first mapstreams and second location data associated with one or more third machines that obtained the one or more second mapstreams;
determining, based at least on the first location data, that the one or more first mapstreams are associated with the first portion of the map; and
determining, based at least on the second location data, that the one or more second mapstreams are associated with the second portion of the map.
16 . The method of claim 12 , wherein a mapstream from the one or more first mapstreams comprises one or more of:
sensor data representing the first portion of the environment that corresponds to the first portion of the map; or
processed data representing one or more locations of one or more objects located within the first portion of the environment.
17 . The method of claim 12 , wherein the map is further updated by:
determining that a threshold period of time has elapsed since a previous update associated with the second portion of the map; and
determining, based at least on the threshold period of time having elapsed, to update the second portion of the map.
18 . The method of claim 12 , wherein the map is further updated by:
associating a plurality of mapstreams with the first portion of the map;
filtering the plurality of mapstreams using one or more criteria; and
identifying, based at least on the filtering the plurality of mapstreams, the one or more first mapstreams from the plurality of mapstreams.
19 . The method of claim 12 , wherein the method is executed in at least one of:
a control system for an autonomous or semi-autonomous machine;
a perception system for an autonomous or semi-autonomous machine;
a system for performing one or more simulation operations;
a system for performing one or more digital twin operations;
a system for performing light transport simulation;
a system for performing collaborative content creation for 3D assets;
a system for performing one or more deep learning operations;
a system implemented using an edge device;
a system implemented using a robot;
a system for performing one or more conversational AI operations;
a system implementing one or more large language models (LLMs);
a system for performing one or more generative AI operations;
a system for generating synthetic data;
a system incorporating one or more virtual machines (VMs);
a system implemented at least partially in a data center; or
a system implemented at least partially using cloud computing resources.
20 . The method of claim 12 , wherein the map is further updated by determining at least the first portion of the map and the second portion of the map by at least dividing the map.