Systems and methods for real-time data coverage optimization
Systems and methods for real-time map data coverage optimization are disclosed. A system includes one or more processors configured to determine a real-time map data collection coverage in an interested region, wherein real-time map data are collected by one or more consumer vehicles at locations of the consumer vehicles, determine whether one or more uncovered locations in the interested region are not covered by the locations of the one or more consumer vehicles, in response to determining that the one or more uncovered locations in the interested region are not covered by the locations of the one or more consumer vehicles, generate a route comprising the one or more uncovered locations based on a map of the interested region, and send an instruction to cause operation of a data-collecting vehicle to follow the route for real-time map data collection.
1 . A system comprising one or more processors configured to:
determine a real-time map data collection coverage in an interested region, wherein real-time map data are collected by one or more consumer vehicles at locations of the consumer vehicles;
determine whether one or more uncovered locations in the interested region are not covered by the locations of the one or more consumer vehicles;
in response to determining that the one or more uncovered locations in the interested region are not covered by the locations of the one or more consumer vehicles, generate a route comprising the one or more uncovered locations based on a map of the interested region; and
send an instruction to cause operation of a data-collecting vehicle to follow the route for real-time map data collection.
2 . The system of claim 1 , wherein the one or more processors are further configured to generate, using a trained neutral network, one or more predicted uncovered locations in the interested region, and the route further comprises the one or more predicted uncovered locations.
3 . The system of claim 2 , wherein the one or more predicted uncovered locations are generated based on historical consumer vehicle distributions, weather, and hours in the interested region.
4 . The system of claim 2 , wherein the neural network is trained with training data comprising consumer vehicle distributions in one or more sample regions.
5 . The system of claim 2 , wherein the neural network is trained with training data comprising historical consumer vehicle distributions, historical map data quality, historical hour, historical weather, and historical uncovered locations in the interested region.
6 . The system of claim 1 , wherein the one or more processors are configured to:
determine, based on historical consumer vehicle distributions, whether the one or more consumer vehicles are not expected to cover one or more predicted uncovered locations within the interested region at a selected time on a specific date; and
in response to determining that the one or more predicted uncovered locations within the interested region are not expected to be covered at the selected time on the specific date, generate a predicted route comprising the one or more predicted uncovered locations at the selected time on the specific date.
7 . The system of claim 6 , wherein the one or more processors are further configured to operate the data-collecting vehicle to follow the predicted route at the selected time on the specific date.
8 . The system of claim 1 , wherein the real-time map data comprises geospatial information, traffic conditions, and road details at the locations of the consumer vehicles or the data-collecting vehicle.
9 . The system of claim 1 , wherein the one or more processors are further configured to:
determine whether a density of consumer vehicles at a saturated location is beyond a saturated threshold;
in response to determining that the density of consumer vehicles at the saturated location is beyond the saturated threshold, select one or more of the one or more consumer vehicles at the saturated location; and
refrain from receiving the real-time map data collected by vehicles other than the selected one or more of the one or more consumer vehicles at the saturated location.
10 . The system of claim 9 , wherein the saturated location is predicted based on historical consumer vehicle distributions and historical map data collection in the interested region.
11 . The system of claim 9 , wherein the one or more of the one or more consumer vehicles are selected based on map data quality of the consumer vehicles and associations between the consumer vehicles and the system.
12 . A method comprising:
determining a real-time map data collection coverage in an interested region, wherein real-time map data are collected by one or more consumer vehicles at locations of the consumer vehicles;
determining whether one or more uncovered locations in the interested region are not covered by the locations of the one or more consumer vehicles;
in response to determining that the one or more uncovered locations in the interested region are not covered by the locations of the one or more consumer vehicles, generating a route comprising the one or more uncovered locations based on a map of the interested region; and
sending an instruction to cause a data-collecting vehicle to follow the route for real-time map data collection.
13 . The method of claim 12 , wherein the method further comprises generating, using a trained neutral network, one or more predicted uncovered locations in the interested region, and the route further comprises the one or more predicted uncovered locations.
14 . The method of claim 13 , wherein the one or more predicted uncovered locations are generated based on historical consumer vehicle distributions, weather, and hours in the interested region.
15 . The method of claim 13 , wherein the neural network is trained with training data comprising consumer vehicle distributions in sample regions, the historical consumer vehicle distributions, historical map data quality, historical hour, historical weather, and historical uncovered locations in the interested region.
16 . The method of claim 12 , wherein the method further comprises:
determining, based on historical consumer vehicle distributions, whether the one or more consumer vehicles are not expected to cover one or more predicted uncovered locations within the interested region at a selected time on a specific date; and
in response to determining that the one or more predicted uncovered locations within the interested region are not expected to be covered at the selected time on the specific date, generating a predicted route comprising the one or more predicted uncovered locations at the selected time on the specific date.
17 . The method of claim 16 , wherein the method further comprises operating the data-collecting vehicle to follow the predicted route at the selected time on the specific date.
18 . The method of claim 12 , wherein the real-time map data comprises geospatial information, traffic conditions, and road details at the locations of the consumer vehicles or the data-collecting vehicle.
19 . The method of claim 12 , wherein the method further comprises:
determining whether a density of consumer vehicles at a saturated location is beyond a saturated threshold;
in response to determining that the density of consumer vehicles at the saturated location is beyond the saturated threshold, selecting one or more of the one or more consumer vehicles at the saturated location based on map data quality of the consumer vehicles and associations between the consumer vehicles and a real-time map system; and
refraining from receiving the real-time map data collected by vehicles other than the selected one or more of the one or more consumer vehicles at the saturated location.
20 . The method of claim 19 , wherein the one or more saturated locations are predicted based on historical consumer vehicle distributions and historical map data collection in the interested region.