Back to results
US 11,906,310 B2Granted
Map maintenance and verification
AssigneeGM Cruise Holdings LLC
InventorsChen Xie, Matthew Fox, Brian Joseph Donohue, Kangyuan Niu, Katherine Leung
Life of this patent
Estimating the term…
Abstract
Techniques are disclosed for evaluating digital map quality. A process includes steps for receiving change data indicating one or more feature discrepancies associated with one or more geographic regions of a digital map, analyzing the change data to determine which of the one or more feature discrepancies resulted in verified updates to the digital map, and generating a quality score for each of the geographic map regions based on the verified updates. Systems and machine-readable media are also provided.
Claims20
A method of validating a digital map comprising:
- determining, by one or more processors and using a decay model, an accuracy estimate for each of one or more features associated with one or more geographic regions of the digital map, wherein the accuracy estimate for each of the one or more features that is determined by the decay model decreases as a time period between measurements of the one or more features increases;
- receiving, by the one or more processors, change data indicating a discrepancy in a subset of the one or more features of the one or more geographic regions, wherein the change data comprises aggregated feature discrepancies received by a change detection database from one or more sources;
- updating a change rate with respect to the aggregated feature discrepancies in the subset of the one or more features;
- determining, by the one or more processors, a surveillance cadence based on an updated change rate and the accuracy estimate determined by the decay model, wherein the surveillance cadence indicates an accuracy of changes associated with the one or more features;
- and
- based on the surveillance cadence, triggering, by the one or more processors, generation of a surveillance task that causes a vehicle to navigate to the one or more geographic regions for data collection.
3 more elements
A system comprising:
- one or more sensors of an autonomous vehicle;
- and
- a processor for executing instructions stored in memory, wherein execution of the instructions by the processor executes:
- determining, by one or more processors and using a decay model, an accuracy estimate for each of one or more features associated with one or more geographic regions of a digital map, wherein the accuracy estimate for each of the one or more features that is determined by the decay model decreases as a time period between measurements of the one or more features increases;
- receiving, by the one or more processors, change data indicating a discrepancy in a subset of the one or more features of the one or more geographic regions, wherein the change data comprises aggregated feature discrepancies received by a change detection database from one or more sources;
- updating a change rate with respect to the aggregated feature discrepancies in the subset of the one or more features;
- determining, by the one or more processors, a surveillance cadence based on an updated change rate and the accuracy estimate determined by the decay model, wherein the surveillance cadence indicates an accuracy of changes associated with the one or more features;
- and
- based on the surveillance cadence, triggering, by the one or more processors, generation of a surveillance task that causes a vehicle to navigate to the one or more geographic regions for data collection.
6 more elements
A non-transitory computer readable medium comprising instructions, the instructions, when executed by a computing system, cause the computing system to:
- determine, by one or more processors and using a decay model, an accuracy estimate for each of one or more features associated with one or more geographic regions of a digital map, wherein the accuracy estimate for each of the one or more features that is determined by the decay model decreases as a time period between measurements of the one or more features increases;
- receive, by the one or more processors, change data indicating a discrepancy in a subset of the one or more features of the one or more geographic regions, wherein the change data comprises aggregated feature discrepancies received by a change detection database from one or more sources;
- update a change rate with respect to the aggregated feature discrepancies in the subset of the one or more features;
- determine, by the one or more processors, a surveillance cadence based on an updated change rate and the accuracy estimate determined by the decay model, wherein the surveillance cadence indicates an accuracy of changes associated with the one or more features;
- and
- based on the surveillance cadence, trigger, by the one or more processors, generation of a surveillance task that causes a vehicle to navigate to the one or more geographic regions for data collection.
3 more elements
Dependencies are inferred from the claim text.