Classification and prioritization of objects for autonomous driving
An autonomous vehicle can classify and prioritize agent of interest (AOI) objects located around the autonomous vehicle to manage computational resources. An example method performed by an autonomous vehicle includes determining, based on a location of the autonomous vehicle and based on a map, an area in which the autonomous vehicle is operated, determining, based on sensor data received from sensors located on or in the autonomous vehicle, attributes of objects located around the autonomous vehicle, where the attributes include information that describes a status of the objects located around the autonomous vehicle, selecting, based at least on the area, a classification policy that includes a plurality of rules that are associated with a plurality of classifications to classify the objects, and for each of the objects located around the autonomous vehicle: monitoring an object according to a classification of the object based on the classification policy.
1 . A method of autonomous driving operation, comprising:
classifying, by a computer located in a first vehicle, a plurality of vehicles located in an area where the first vehicle is operating,
wherein the plurality of vehicles are classified into a plurality of ranges based on distances of the plurality of vehicles from the first vehicle,
wherein the plurality of vehicles includes a second vehicle that is classified as being in a first range in response to a first distance between the first vehicle and the second vehicle being less than a first value, and
wherein the second vehicle is located in a same lane as the first vehicle;
classifying a first set of vehicles located in the first range with a first classification indicative of a first frequency with which the first set of vehicles are tracked, wherein the first set of vehicles are classified with the first classification in response to the first set of vehicles having a number of vehicles located in front of the first vehicle being more than a pre-determined number; and
applying brakes of the first vehicle in response to determining a driving related behavior of the second vehicle;
wherein the plurality of vehicles includes a third vehicle that is classified as being in a second range in response to a second distance between the first vehicle and the third vehicle being greater than the first value and less than a second value, and
wherein the plurality of vehicles includes a fourth vehicle that is classified as being in a third range in response to a third distance between the first vehicle and the fourth vehicle being greater than the second value;
performing a first determination that an average amount of time taken to determine attributes of the first set of vehicles exceeds a pre-determined threshold value;
reducing, in response to the performing the first determination, a number of vehicles in the first set of vehicles that are tracked using the first classification.
2 . The method of claim 1 , further comprising:
classifying a second set of vehicles located in the second range and the third range with a second classification indicative of a second frequency with which the second set of vehicles are tracked, wherein the second frequency is less than the first frequency.
3 . The method of claim 1 , wherein data obtained from sensors located on the first vehicle is not analyzed to determine attributes of a second set of vehicles located in the second range and the third range.
4 . The method of claim 1 , further comprising:
classifying a third set of vehicles located in front of the first vehicle and operated in a same direction as that of the first vehicle with the first classification.
5 . The method of claim 1 , wherein attributes of one or more vehicles traveling in a direction opposite to that of the first vehicle are not determined in response to the first vehicle being driven on a highway.
6 . A system comprising:
a computer located in a first vehicle, wherein the computer includes a at least one processor and a memory comprising stored instructions that upon execution configure the at least one processor to:
classify a plurality of vehicles located in an area where the first vehicle is operating,
wherein the plurality of vehicles are classified into a plurality of ranges based on distances of the plurality of vehicles from the first vehicle,
wherein the plurality of vehicles includes a second vehicle that is classified as being in a first range in response to a first distance between the first vehicle and the second vehicle being less than a first value, and
wherein the second vehicle is located in a same lane as the first vehicle;
classify a first set of vehicles located in the first range with a first classification indicative of a first frequency with which the first set of vehicles are tracked, wherein the first set of vehicles are classified with the first classification in response to the first set of vehicles having a number of vehicles located in front of the first vehicle being more than a pre-determined number; and
applying brakes of the first vehicle in response to determining a driving related behavior of the second vehicle;
wherein the plurality of vehicles includes a third vehicle that is classified as being in a second range in response to a second distance between the first vehicle and the third vehicle being greater than the first value and less than a second value, and
wherein the plurality of vehicles includes a fourth vehicle that is classified as being in a third range in response to a third distance between the first vehicle and the fourth vehicle being greater than the second value;
wherein the processor is further configured to:
perform a first determination that an average amount of time taken to determine attributes of the first set of vehicles exceeds a pre-determined threshold value;
reduce, in response to the perform the first determination, a number of vehicles in the first set of vehicles that are tracked using the first classification.
7 . The system of claim 6 , wherein the processor is further configured to:
classify a second set of vehicles located in the second range and the third range with a second classification indicative of a second frequency with which the second set of vehicles are tracked, wherein the second frequency is less than the first frequency.
8 . The system of claim 6 , wherein data obtained from sensors located on the first vehicle is not analyzed to determine attributes of a second set of vehicles located in the second range and the third range.
9 . The system of claim 6 , wherein the processor is further configured to:
classify a third set of vehicles located in front of the first vehicle and operated in a same direction as that of the first vehicle with the first classification.
10 . The system of claim 6 , wherein attributes of one or more vehicles traveling in a direction opposite to that of the first vehicle are not determined in response to the first vehicle being driven on a highway.
11 . A non-transitory computer readable storage medium having code stored thereon, the code, when executed by a processor, causing the processor to implement a method comprising:
classifying, by a computer located in a first vehicle, a plurality of vehicles located in an area where the first vehicle is operating,
wherein the plurality of vehicles are classified into a plurality of ranges based on distances of the plurality of vehicles from the first vehicle,
wherein the plurality of vehicles includes a second vehicle that is classified as being in a first range in response to a first distance between the first vehicle and the second vehicle being less than a first value, and
wherein the second vehicle is located in a same lane as the first vehicle;
classifying a first set of vehicles located in the first range with a first classification indicative of a first frequency with which the first set of vehicles are tracked, wherein the first set of vehicles are classified with the first classification in response to the first set of vehicles having a number of vehicles located in front of the first vehicle being more than a pre-determined number; and
applying brakes of the first vehicle in response to determining a driving related behavior of the second vehicle;
wherein the plurality of vehicles includes a third vehicle that is classified as being in a second range in response to a second distance between the first vehicle and the third vehicle being greater than the first value and less than a second value, and
wherein the plurality of vehicles includes a fourth vehicle that is classified as being in a third range in response to a third distance between the first vehicle and the fourth vehicle being greater than the second value;
performing a first determination that an average amount of time taken to determine attributes of the first set of vehicles exceeds a pre-determined threshold value;
reducing, in response to the performing the first determination, a number of vehicles in the first set of vehicles that are tracked using the first classification.
12 . The non-transitory computer readable storage medium of claim 11 , wherein the method further comprises:
classifying a second set of vehicles located in the second range and the third range with a second classification indicative of a second frequency with which the second set of vehicles are tracked, wherein the second frequency is less than the first frequency.
13 . The non-transitory computer readable storage medium of claim 11 , wherein data obtained from sensors located on the first vehicle is not analyzed to determine attributes of a second set of vehicles located in the second range and the third range.
14 . The non-transitory computer readable storage medium of claim 11 , wherein the method further comprises:
classifying a third set of vehicles located in front of the first vehicle and operated in a same direction as that of the first vehicle with the first classification.
15 . The non-transitory computer readable storage medium of claim 11 , wherein attributes of one or more vehicles traveling in a direction opposite to that of the first vehicle are not determined in response to the first vehicle being driven on a highway.