Determining localization confidence of vehicles based on convergence ranges
According to an aspect of an embodiment, operations may comprise for each of the set of geographic X-positions, accessing an HD map of a geographical region surrounding the geographic X-position, determining a convergence range for the geographic X-position, and storing the convergence range for the geographic X-position in the HD map. The operations may also comprise accessing the HD map, predicting a next geographic X-position of a target vehicle, predicting a covariance of the predicted next geographic X-position, accessing the convergence range for the geographic X-position in the HD map closest to the predicted next geographic X-position, estimating a current geographic X-position of the target vehicle by performing a localization algorithm, and determining a confidence value for the estimated current geographic X-position of the target vehicle based on the predicted next geographic X-position, the predicted covariance, and the accessed convergence range.
1. A computer-implemented method, comprising:
accessing a set of geographic X-positions associated with one or more vehicles, wherein each geographic X-position of the set of geographic X-positions is associated with a respective vehicle of the one or more vehicles;
for each respective geographic X-position of the set of geographic X-positions:
accessing a high definition (HD) map of a geographical region surrounding the respective geographic X-position, the HD map comprising a three-dimensional (3D) representation of the geographical region, and
determining a convergence range for the respective geographic X-position;
predicting a geographic X-position of a target vehicle and a covariance of the predicted geographic X-position, the predicted geographic X-position being separate from each respective geographic X-position of the set of geographic X-positions;
estimating a geographic X-position of the target vehicle by performing a localization algorithm, the estimated geographic X-position being separate from the predicted geographic X-position and being separate from each respective geographic X-position of the set of geographic X-positions;
determining a confidence value for the estimated geographic X-position of the target vehicle based on the predicted geographic X-position, the predicted covariance, and a particular convergence range, the particular convergence range being associated with a particular geographic X-position of the set of geographic X-positions that is closest to the predicted geographic X-position relative to each respective geographic X-position of the set of geographic X-positions; and
causing performance of one or more driving operations by the target vehicle based on the confidence value.
2. The computer-implemented method of claim 1 , wherein the confidence value for the estimated geographic X-position of the target vehicle indicates a level of confidence that the target vehicle is actually located at the estimated geographic X-position.
3. The computer-implemented method of claim 1 , wherein the determining of the confidence value for the estimated geographic X-position of the target vehicle comprises calculating an integral area between minimum and maximum values of the particular convergence range of a Gaussian function of the predicted geographic X-position.
4. The computer-implemented method of claim 1 , further comprising employing the particular convergence range along with a predicted uncertainty distribution for the estimated geographic X-position to compute a new estimate of the confidence value for the estimated geographic X-position that is used to update a Kalman Filter (KF).
5. The computer-implemented method of claim 1 , wherein the particular convergence range is specified relative to a convergence error with respect to each respect geographic X-position of the set of geographic X-positions.
6. The computer-implemented method of claim 1 , wherein multiple convergence ranges are stored in the HD map for each respective geographic X-position of the set of geographic X-positions, with each of the multiple convergence ranges being relative to a specific convergence error tolerance, and with each specific convergence error tolerance configured to be used to compute confidence of a localization result relative to the specific convergence error tolerance.
7. One or more non-transitory computer readable storage media storing instructions that, in response to being executed by one or more processors, cause a computer system to perform operations, the operations comprising:
accessing a set of geographic X-positions associated with one or more vehicles wherein each geographic X-position of the set of geographic X-positions is associated with a respective vehicle of the one or more vehicles;
for each respective geographic X-position of the set of geographic X-positions:
accessing a high definition (HD) map of a geographical region surrounding the respective geographic X-position, the HD map comprising a three-dimensional (3D) representation of the geographical region, and
determining a convergence range for the respective geographic X-position;
predicting a geographic X-position of a target vehicle and a covariance of the predicted geographic X-position, the predicted geographic X-position being separate from each respective geographic X-position of the set of geographic X-positions;
estimating a geographic X-position of the target vehicle by performing a localization algorithm, the estimated geographic X-position being separate from the predicted geographic X-position and being separate from each respective geographic X-position of the set of geographic X-positions;
determining a confidence value for the estimated geographic X-position of the target vehicle based on the predicted geographic X-position, the predicted covariance, and a particular convergence range, the particular convergence range being associated with a particular geographic X-position of the set of geographic X-positions that is closest to the predicted geographic X-position relative to each respective geographic X-position of the set of geographic X-positions; and
causing performance of one or more driving operations by the target vehicle based on the confidence value.
8. The one or more non-transitory computer-readable storage media of claim 7 , wherein the confidence value for the estimated geographic X-position of the target vehicle indicates a level of confidence that the target vehicle is actually located at the estimated geographic X-position.
9. The one or more non-transitory computer-readable storage media of claim 7 , wherein the determining of the confidence value for the estimated geographic X-position of the target vehicle comprises calculating an integral area between minimum and maximum values of the particular convergence range of a Gaussian function of the predicted geographic X-position.
10. The one or more non-transitory computer-readable storage media of claim 7 , wherein the operations further comprise employing the particular convergence range along with a predicted uncertainty distribution for the estimated geographic X-position to compute a new estimate of the confidence value for the estimated geographic X-position that is used to update a Kalman Filter (KF).
11. The one or more non-transitory computer-readable storage media of claim 7 , wherein the particular convergence range is specified relative to a convergence error with respect to each respective geographic X-position of the set of geographic X-positions.
12. The one or more non-transitory computer-readable storage media of claim 7 , wherein multiple convergence ranges are stored in the HD map for each respective geographic X-position of the set of geographic X-positions, with each of the multiple convergence ranges being relative to a specific convergence error tolerance, and with each specific convergence error tolerance configured to be used to compute confidence of a localization result relative to the specific convergence error tolerance.
13. A computer system comprising:
one or more processors; and
one or more non-transitory computer readable media storing instructions that in response to being executed by the one or more processors, cause the computer system to perform operations, the operations comprising:
accessing a set of geographic X-positions associated with one or more vehicles, wherein each geographic X-position of the set of geographic X-positions is associated with a respective vehicle of the one or more vehicles;
for each respective geographic X-position of the set of geographic X-positions:
accessing a high definition (HD) map of a geographical region surrounding the respective geographic X-position, the HD map comprising a three-dimensional (3D) representation of the geographical region, and
determining a convergence range for the respective geographic X-position;
predicting a geographic X-position of a target vehicle and a covariance of the predicted geographic X-position, the predicted geographic X-position being separate from each respective geographic X-position of the set of geographic X-positions;
estimating a geographic X-position of the target vehicle by performing a localization algorithm, the estimated geographic X-position being separate from the predicted geographic X-position and being separate from each respective geographic X-position of the set of geographic X-positions;
determining a confidence value for the estimated geographic X-position of the target vehicle based on the predicted geographic X-position, the predicted covariance, and a particular convergence range, the particular convergence range being associated with a particular geographic X-position of the set of geographic X-positions that is closest to the predicted geographic X-position relative to each respective geographic X-position of the set of geographic X-positions; and
causing performance of one or more driving operations by the target vehicle based on the confidence value.
14. The computer system of claim 13 , wherein the confidence value for the estimated geographic X-position of the target vehicle indicates a level of confidence that the target vehicle is actually located at the estimated geographic X-position.
15. The computer system of claim 13 , wherein the determining of the confidence value for the estimated geographic X-position of the target vehicle comprises calculating an integral area between minimum and maximum values of the particular convergence range of a Gaussian function of the predicted geographic X-position.
16. The computer system of claim 13 , wherein the operations further comprise employing the particular convergence range along with a predicted uncertainty distribution for the estimated geographic X-position to compute a new estimate of the confidence value for the estimated geographic X-position that is used to update a Kalman Filter (KF).
17. The computer system of claim 13 , wherein the particular convergence range is specified relative to a convergence error with respect to each respective geographic X-position of the set of geographic X-positions.
18. The computer system of claim 13 , wherein multiple convergence ranges are stored in the HD map for each respective geographic X-position, with each of the multiple convergence ranges being relative to a specific convergence error tolerance, and with each specific convergence error tolerance configured to be used to compute confidence of a localization result relative to the specific convergence error tolerance.