| CPC G06N 5/04 (2013.01) [G05D 1/0214 (2013.01); G05D 1/0221 (2013.01); G06F 18/2113 (2023.01); G06F 18/217 (2023.01); G06V 20/58 (2022.01); G06V 2201/07 (2022.01)] | 20 Claims |
|
1. A method, comprising:
receiving, with at least one processor, sensor data associated with an environment that a vehicle is located in;
obtaining, with the at least one processor, a set of candidate hypotheses based on the sensor data, wherein each candidate hypothesis of the set of candidate hypotheses corresponds to one or more tracks and wherein each candidate hypothesis is representative of a candidate location of one or more targets;
evaluating, with the at least one processor, the set of candidate hypotheses against at least one criterion, wherein evaluating the set of candidate hypotheses against the at least one criterion comprises evaluating a predicted plausibility of a particular candidate hypothesis of the set of candidate hypotheses relative to a prior hypothesis with regard to a location of the one or more targets;
ranking the set of candidate hypotheses, with the at least one processor, to generate a ranked set of hypotheses based on the evaluation of the set of candidate hypotheses against the at least one criterion, wherein the ranked set of hypotheses comprises a subset of hypotheses selected from among the set of candidate hypotheses based on the at least one criterion, and wherein ranking the set of candidate hypotheses to generate a ranked set of hypotheses comprises omitting from the ranked set of hypotheses at least one candidate hypothesis from the set of candidate hypotheses; and
estimating, with the at least one processor, a location of each of the one or more targets based on the ranked set of hypotheses.
|