Sensor data based map creation for autonomous systems and applications
One or more embodiments of the present disclosure relate to generation of map data. In these or other embodiments, the generation of the map data may include determining whether objects indicated by the sensor data are static objects or dynamic objects. Additionally or alternatively, sensor data may be removed or included in the map data based on determinations as to whether it corresponds to static objects or dynamic objects.
1. A method comprising:
obtaining sensor data representative of a geographical area, the sensor data including one or more sensor data sets, at least one sensor data set of the one or more sensor data sets being obtained using one or more sensors disposed on a corresponding ego-machine of one or more ego-machines during traversal through the geographical area by the corresponding ego-machine; and
determining that an object indicated by the sensor data is a static object based at least on at least a threshold number of sensor data sets that individually indicate a presence of the object at a particular location in the geographical area.
2. The method of claim 1 , further comprising removing sensor data that corresponds to the object in response to determining that the object is not a static object.
3. The method of claim 1 , wherein the determining that the object is a static object includes determining that the object is indicated as being at the particular location by two or more sensor data sets that each correspond to a same track traversed by a same ego-machine through the geographical area.
4. The method of claim 1 , wherein the determining that the object is a static object includes determining that the object is indicated as being at the particular location by two or more sensor data sets that correspond to different tracks traversed through the geographical area.
5. The method of claim 1 , wherein the determining that the object is a static object further includes determining that the object is disposed along one or more tracks of the one or more ego-machines that correspond to one or more of the sensor data sets.
6. The method of claim 1 , wherein the determining that the object is a static object includes: performing a first determination that the object is a static object based at least on a first threshold number of first sensor data sets that indicate a presence of the object at the particular location, the first sensor data sets corresponding to a same track traversed by a same ego-machine through the geographical area; and
performing a second determination that the object is a static object based at least on a second threshold number of second sensor data sets that indicate a presence of the object at the particular location, the second sensor data sets each corresponding to different tracks traversed by two or more different ego-machines through the geographical area.
7. The method of claim 6 , wherein the second determination is performed in response to the first determination being that the object is a static object.
8. The method of claim 6 , wherein:
the second threshold number is larger than the first threshold number.
9. At least one processor comprising:
one or more circuits to:
obtain sensor data corresponding to a geographical area, the sensor data including one or more sensor data sets, at least one sensor data set of the one or more sensor data sets being obtained using one or more sensors disposed on a corresponding ego-machine of one or more ego-machines during traversal through the geographical area by the corresponding ego-machine; and
determine that an object indicated by the sensor data is a dynamic object based at least on a particular number of sensor data sets individually indicating a presence of the object at a particular location in the geographical area not satisfying one or more thresholds.
10. The at least one processor of claim 9 , wherein the one or more circuits are further to remove sensor data that corresponds to the object in response to determining that the object is a dynamic object.
11. The at least one processor of claim 9 , wherein the determining that the object is a dynamic object includes determining that the object is indicated as being at the particular location by less than a threshold number of sensor data sets that correspond to a same track traversed by a same ego-machine through the geographical area.
12. The at least one processor of claim 9 , wherein the determining that the object is a dynamic object includes determining that the object is indicated as being at the particular location by less than a threshold number of sensor data sets that correspond to different tracks traversed through the geographical area.
13. The at least one processor of claim 9 , wherein the determining that the object is a dynamic object is further based at least on the object being disposed along one or more tracks of the one or more ego-machines that correspond to one or more of the sensor data sets.
14. A system comprising:
one or more processors to:
obtain sensor data corresponding to a geographical area, the sensor data including a plurality of sensor data sets, at least one sensor data set of the plurality of sensor data sets being obtained using one or more sensors disposed on a corresponding ego-machine of one or more ego-machines during traversal through the geographical area by the corresponding ego-machine; and
determine that an object indicated by the sensor data is a static object based at least on a particular number of sensor data sets of the plurality of sensor data sets individually indicating a presence of the object at a particular location in the geographical area.
15. The system of claim 14 , wherein the determining that the object is a static object includes determining that the object is indicated as being at the particular location by a threshold number of sensor data sets that correspond to a same track traversed by a same ego-machine through the geographical area.
16. The system of claim 14 , wherein the determining that the object is a static object includes determining that the object is indicated as being at the particular location by a threshold number of sensor data sets that correspond to different tracks traversed through the geographical area.
17. The system of claim 14 , wherein the determining that the object is a static object is further based at least on whether the object is disposed along one or more tracks of the one or more ego-machines that correspond to one or more of the sensor data sets.
18. The system of claim 14 , wherein the determining that the object is a static object includes:
performing a first determination that the object is a static object based at least on a first number of first sensor data sets that indicate a presence of the object at the particular location, the first sensor data sets each corresponding to a same track traversed by a same ego-machine through the geographical area; and
performing a second determination that the object is a static object based at least on a second number of second sensor data sets that indicate a presence of the object at the particular location, the second sensor data sets each corresponding to different tracks traversed by two or more different ego-machines through the geographical area.
19. The system of claim 18 , wherein the second determination is performed in response to the first determination being that the object is a static object.
20. The system of claim 18 , wherein:
the first determination is based at least on the first number of first sensor data sets satisfying a first threshold; and
the second determination is based at least on the second number of second sensor data sets satisfying a second threshold that is greater than or equal to the first threshold.
21. The system of claim 14 , wherein the system is implemented in or is associated with one or more 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 simulation operations;
a system for performing deep learning operations;
a system for generating synthetic data;
a system for generating multi-dimensional assets using a collaborative content platform;
a system implemented using an edge device;
a system implemented using a robot;
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.