Occupancy map updates based on sensor data collected by autonomous vehicles
An online system builds a high definition (HD) map for a geographical region based on sensor data captured by a plurality of autonomous vehicles driving through a geographical region. The autonomous vehicles detect map discrepancies based on differences in the surroundings observed using sensor data compared to the high definition map and send messages describing these map discrepancies to the online system. The online system updates existing occupancy maps to improve the accuracy of the occupancy maps (OMaps), and to thereby improve passenger and pedestrian safety. While vehicles are in motion, they can continuously collect data about their surroundings. When new data is available from the various vehicles within a fleet, this can be updated in a local representation of the occupancy map and can be passed to the online HD map system (e.g., in the cloud) for updating the master occupancy map shared by all of the vehicles.
1. A method comprising:
receiving a first occupancy map corresponding to a geographical region and representing objects previously detected in the geographical region;
receiving sensor data corresponding to the geographical region and representing objects currently detected in the geographical region;
generating, based at least on the first occupancy map and the sensor data, a second occupancy map;
identifying a discrepancy between the first occupancy map and the second occupancy map, wherein the discrepancy includes one or more of:
an object identifiable in the second occupancy map that is not identifiable in the first occupancy map;
an object in the first occupancy map that is not identifiable in the second occupancy map; or
a representation of an object being different between the first occupancy map and the second occupancy map; and
responsive to a significance value associated with the discrepancy being greater than a threshold, providing additional data related to the discrepancy to a map system.
2. The method of claim 1 , wherein the additional data includes one or more of:
raw sensor data; or
a location associated with the discrepancy.
3. The method of claim 1 , wherein the additional data is obtained from one or more vehicles based at least on a prioritization of the one or more vehicles.
4. The method of claim 3 , wherein the prioritization of the one or more vehicles is based at least on one or more of:
an amount of data provided by the one or more vehicles;
a rate of the amount of data provided;
a communication bandwidth associated with the one or more vehicles;
an operating status of the one or more vehicles;
a speed of the one or more vehicles with respect to collection of the additional data; or
a time of day with respect to collection of the additional data by the one or more vehicles.
5. The method of claim 1 , wherein the second occupancy map is generated based at least on a location of a vehicle associated with the receiving of the sensor data.
6. The method of claim 5 , wherein the location is determined based at least on the sensor data.
7. The method of claim 1 , wherein the significance value is based at least on an effect of the discrepancy on an accuracy of matching the sensor data with respect to the first occupancy map.
8. The method of claim 1 , wherein the discrepancy is provided to the map system prior to providing a second discrepancy to the map system based at least on the significance value indicating that the discrepancy is more significant than the second discrepancy.
9. A system comprising:
one or more processors comprising processing circuitry to perform operations comprising:
receiving a first occupancy map corresponding to a geographical region and representing objects previously detected in the geographical region;
receiving sensor data corresponding to the geographical region and representing objects currently detected in the geographical region;
generating, based at least on the first occupancy map and the sensor data, a second occupancy map;
identifying a discrepancy between the first occupancy map and the second occupancy map, wherein the discrepancy includes one or more of:
an object identifiable in the second occupancy map that is not identifiable in the first occupancy map;
an object in the first occupancy map that is not identifiable in the second occupancy map; or
a representation of an object being different between the first occupancy map and the second occupancy map; and
responsive to a significance value associated with the discrepancy being greater than a threshold, providing additional data related to the discrepancy to a map system.
10. The system of claim 9 , wherein the additional data includes one or more of:
raw sensor data; or
a location associated with the discrepancy.
11. The system of claim 9 , wherein the additional data is obtained from one or more vehicles based at least on a prioritization of the one or more vehicles.
12. The system of claim 11 , wherein the prioritization of the one or more vehicles is based at least on one or more of:
an amount of data provided by the one or more vehicles;
a rate of the amount of data provided;
a communication bandwidth associated with the one or more vehicles;
an operating status of the one or more vehicles;
a speed of the one or more vehicles with respect to collection of the additional data; or
a time of day with respect to collection of the additional data by the one or more vehicles.
13. The system of claim 9 , wherein the second occupancy map is generated based at least on a location of a vehicle associated with the receiving of the sensor data.
14. A system comprising:
one or more processors comprising processing circuitry to perform operations comprising:
receiving a first occupancy map corresponding to a geographical region and representing objects previously detected in the geographical region;
receiving sensor data corresponding to the geographical region and representing objects currently detected in the geographical region;
generating, based at least on the first occupancy map and the sensor data, a second occupancy map;
identifying a discrepancy between the first occupancy map and the second occupancy map, wherein the discrepancy includes one or more of:
an object identifiable in the second occupancy map that is not identifiable in the first occupancy map;
an object in the first occupancy map that is not identifiable in the second occupancy map; or
a representation of an object being different between the first occupancy map and the second occupancy map; and
responsive to a significance value associated with the discrepancy being greater than a threshold, providing additional data related to the discrepancy to a map system.
15. The system of claim 14 , wherein the additional data includes one or more of:
raw sensor data; or
a location associated with the discrepancy.
16. The system of claim 15 , wherein the additional data is obtained from one or more vehicles based at least on a prioritization of the one or more vehicles.
17. The system of claim 16 , wherein the prioritization of the one or more vehicles is based at least on one or more of:
an amount of data provided by the one or more vehicles;
a rate of the amount of data provided;
a communication bandwidth associated with the one or more vehicles;
an operating status of the one or more vehicles;
a speed of the one or more vehicles with respect to collection of the additional data; or
a time of day with respect to collection of the additional data by the one or more vehicles.
18. The system of claim 14 , wherein the second occupancy map is generated based at least on a location of a vehicle associated with the receiving of the sensor data.