LIDAR LOCALIZATION
Observed environment lidar sensor data including a plurality of spatial points is received for a mobile entity. The observed environment lidar sensor data is transformed into one or more alternative observed environment candidates. A corresponding observed environment reduced representation is calculated for the observed environment lidar sensor data and each of the one or more alternative observed environment candidates. The observed environment reduced representations is correlated with reference reduced representations for different geographical locations to determine correlation results. Based on the correlation results, a current location of the mobile entity is identified.
1 . A method, comprising:
receiving for a mobile entity, observed environment lidar sensor data including a plurality of spatial points;
transforming the observed environment lidar sensor data into one or more alternative observed environment candidates;
calculating a corresponding observed environment reduced representation for the observed environment lidar sensor data and each of the one or more alternative observed environment candidates;
correlating the observed environment reduced representations with reference reduced representations for different geographical locations to determine correlation results; and
based on the correlation results, identifying a current location of the mobile entity.
2 . The method of claim 1 , further comprising receiving a reference map associated with an initial location of the mobile entity.
3 . The method of claim 2 , wherein the initial location of the mobile entity is an estimated location based on a GPS system.
4 . The method of claim 2 , wherein the reference map associated with the initial location includes a plurality of reference localization points.
5 . The method of claim 1 , further comprising normalizing the observed environment lidar sensor data.
6 . The method of claim 5 , wherein normalizing the observed environment lidar sensor data includes upscaling the observed environment lidar sensor data to match a spatial density of a reference map associated with an initial location of the mobile entity.
7 . The method of claim 5 , wherein normalizing the observed environment lidar sensor data includes downscaling the observed environment lidar sensor data to match a spatial density of a reference map associated with an initial location of the mobile entity.
8 . The method of claim 5 , wherein normalizing the observed environment lidar sensor data includes subsampling the observed environment lidar sensor data.
9 . The method of claim 1 , wherein transforming the observed environment lidar sensor data into the one or more alternative observed environment candidates includes shifting the observed environment lidar sensor data in at least one of six degrees of freedom.
10 . The method of claim 1 , wherein transforming the observed environment lidar sensor data into the one or more alternative observed environment candidates includes shifting the observed environment lidar sensor data in at least one of four degrees of freedom.
11 . The method of claim 1 , wherein calculating the corresponding observed environment reduced representation for the observed environment lidar sensor data and each of the one or more alternative observed environment candidates includes subdividing a corresponding 3-D region associated with the observed environment lidar sensor data and each of the one or more alternative observed environment candidates into a corresponding plurality of 3-D subregions.
12 . The method of claim 11 , wherein calculating the corresponding observed environment reduced representation for the observed environment lidar sensor data and each of the one or more alternative observed environment candidates includes generating a corresponding fingerprint for each of the corresponding plurality of 3-D subregions.
13 . The method of claim 1 , wherein correlating the observed environment reduced representations with reference reduced representations for different geographical locations includes comparing fingerprints associated with the observed environment reduced representations with fingerprints associated with the reference reduced representations.
14 . The method of claim 1 , further comprising determining whether a number of matches associated with the observed environment lidar sensor data and each of the one or more alternative observed environment candidates is above a match threshold.
15 . The method of claim 14 , wherein the current location of the mobile entity is identified in response to determining that the number of matches associated with the observed environment lidar sensor data or one of the one or more alternative observed environment candidates is above the match threshold.
16 . A system, comprising:
a lidar sensor configured to detect observed environment lidar sensor data including a plurality of spatial points; and
a processor configured to:
transform the observed environment lidar sensor data into one or more alternative observed environment candidates;
calculate a corresponding observed environment reduced representation for the observed environment lidar sensor data and each of the one or more alternative observed environment candidates;
correlate the observed environment reduced representations with reference reduced representations for different geographical locations to determine correlation results; and
based on the correlation results, identifying a current location of the mobile entity.
17 . The system of claim 16 , wherein the processor is configured to receive a reference map associated with an initial location of the mobile entity.
18 . The system of claim 16 , wherein the processor is configured to normalize the observed environment lidar sensor data.
19 . The system of claim 16 , wherein to transform the observed environment lidar sensor data into the one or more alternative observed environment candidates, the processor is configured to shift the observed environment lidar sensor data in at least one of six degrees of freedom.
20 . A computer program product embodied in a non-transitory computer readable medium and comprising computer instructions for:
receiving for a mobile entity, observed environment lidar sensor data including a plurality of spatial points;
transforming the observed environment lidar sensor data into one or more alternative observed environment candidates;
calculating a corresponding observed environment reduced representation for the observed environment lidar sensor data and each of the one or more alternative observed environment candidates;
correlating the observed environment reduced representations with reference reduced representations for different geographical locations to determine correlation results; and
based on the correlation results, identifying a current location of the mobile entity.