Detection of Map Anomalies
To identify erroneous digital map data, a route guidance engine provides guidance from a first point to a second point along a road network using data stored in a map database. The route guidance engine determines whether a vehicle travels the recommended route or a different route. A map anomaly detection (MAD) engine compares the trace data to the recommended route data. The MAD engine identifies points along the recommended route not included in the trace and points along the trace not included in the recommended route. From this data, the MAD engine identifies section pairs and performs a filtering step. The MAD engine aggregates data for all trips from the first point to the second point within a particular period, and aggregates all trips from all starting points to ending points. The resulting set of points are points where the stored map data is likely incorrect.
1 . A computer-implemented method for identifying an error in a digital map, the method comprising:
receiving, for a first point and a second point in a road network, a recommended route provided to a vehicle traveling from the first point to the second point;
receiving a trace route describing a route traveled by the vehicle from the first point to the second point;
identifying a first set of points present in the recommended route and absent from the trace route;
identifying a second set of points present in the trace route and absent from the recommended route;
creating a plurality of section pairs, each section pair including a plurality of points from the first set and a plurality of nearby points from the second set;
for each section pair:
determining whether the section pair should be discarded;
responsive to a determination that the section pair should not be discarded:
determining that the points within the section pair represent an error in the map data; and
providing an indication of the determination.
2 . The method of claim 1 , further comprising automatically correcting the error in the map data.
3 . The method of claim 1 wherein the vehicle is an autonomous vehicle.
4 . The method of claim 1 wherein the trace route is collected using a mobile device.
5 . The method of claim 1 wherein the error in the map data is a missing road segment.
6 . The method of claim 1 wherein the error in the map data is an extraneous road segment.
7 . The method of claim 1 wherein the error in the map data is a wrongly connected road segment.
8 . The method of claim 1 wherein the error in the map data is an incorrect turn restriction.
9 . The method of claim 1 wherein the error in the map data is incorrect directionality.
10 . The method of claim 1 wherein the error in the map data is incorrect road geometry.
11 . A computer program product for identifying an error in a digital map, the computer program product stored on a non-transitory computer-readable medium and including instructions adapted to cause a processor to execute steps comprising:
receiving, for a first point and a second point in a road network, a recommended route provided to a vehicle traveling from the first point to the second point;
receiving a trace route describing a route traveled by the vehicle from the first point to the second point;
identifying a first set of points present in the recommended route and absent from the trace route;
identifying a second set of points present in the trace route and absent from the recommended route;
creating a plurality of section pairs, each section pair including a plurality of points from the first set and a plurality of nearby points from the second set;
for each section pair:
determining whether the section pair should be discarded;
responsive to a determination that the section pair should not be discarded:
determining that the points within the section pair represent an error in the map data; and
providing an indication of the determination.
12 . The computer program product of claim 11 , further comprising automatically correcting the error in the map data.
13 . The computer program product of claim 11 wherein the vehicle is an autonomous vehicle.
14 . The computer program product of claim 11 wherein the trace route is collected using a mobile device.
15 . The computer program product of claim 11 wherein the error in the map data is a missing road segment.
16 . The computer program product of claim 11 wherein the error in the map data is an extraneous road segment.
17 . The computer program product of claim 11 wherein the error in the map data is a wrongly connected road segment.
18 . The computer program product of claim 11 wherein the error in the map data is an incorrect turn restriction.
19 . The computer program product of claim 11 wherein the error in the map data is incorrect directionality.
20 . The computer program product of claim 11 wherein the error in the map data is incorrect road geometry.