SELECTIVE MODEL EXECUTION IN AN AUTONOMOUS VEHICLE

1 . A method for selective model execution in an autonomous vehicle, comprising:

identifying, based on a first state space associated with a first machine learning model, one or more second state spaces neighboring the first state space, wherein the one or more second state spaces are each associated with a corresponding second machine learning model of one or more second machine learning models; and

executing the one or more second machine learning models.

2 . The method of claim 1 , wherein the first state space comprises a current state of the autonomous vehicle.

3 . The method of claim 1 , wherein the first machine learning model and the one or more second machine learning models are configured to generate one or more control operations for the autonomous vehicle.

4 . The method of claim 1 , further comprising prohibiting execution of one or more third machine learning models each associated with a corresponding third state space of one or more third state spaces not neighboring the first state space.

5 . The method of claim 4 , further comprising:

transitioning from a first state of the first state space to a second state in a second state space in the one or more second state spaces;

identifying, from the one or more third state spaces, a third state space neighboring the second state space; and

executing a third machine learning model associated with the identified third state space.

6 . The method claim 5 , further comprising prohibiting execution of a machine learning model associated with a state space not neighboring the second state space.

7 . An apparatus for selective model execution in an autonomous vehicle, the apparatus configured to perform steps comprising:

identifying, based on a first state space associated with a first machine learning model, one or more second state spaces neighboring the first state space, wherein the one or more second state spaces are each associated with a corresponding second machine learning model of one or more second machine learning models; and

executing the one or more second machine learning models.

8 . The apparatus of claim 7 , wherein the first state space comprises a current state of the autonomous vehicle.

9 . The apparatus of claim 7 , wherein the first machine learning model and the one or more second machine learning models are configured to generate one or more control operations for the autonomous vehicle.

10 . The apparatus of claim 7 , wherein the steps further comprise prohibiting execution of one or more third machine learning models each associated with a corresponding third state space of one or more third state spaces not neighboring the first state space.

11 . The apparatus of claim 10 , wherein the steps further comprise:

transitioning from a first state of the first state space to a second state in a second state space in the one or more second state spaces;

identifying, from the one or more third state spaces, a third state space neighboring the second state space; and

executing a third machine learning model associated with the identified third state space.

12 . The apparatus of claim 11 , wherein the steps further comprise preventing execution of a machine learning model associated with a state space not neighboring the second state space.

13 . An autonomous vehicle for selective model execution in the autonomous vehicle, comprising:

an apparatus configured to perform steps comprising:

identifying, based on a first state space associated with a first machine learning model, one or more second state spaces neighboring the first state space, wherein the one or more second state spaces are each associated with a corresponding second machine learning model of one or more second machine learning models; and

executing the one or more second machine learning models.

14 . The autonomous vehicle of claim 13 , wherein the first state space comprises a current state of the autonomous vehicle.

15 . The autonomous vehicle of claim 13 , wherein the first machine learning model and the one or more second machine learning models are configured to generate one or more control operations for the autonomous vehicle.

16 . The autonomous vehicle of claim 13 , wherein the steps further comprise prohibiting execution of one or more third machine learning models each associated with a corresponding third state space of one or more third state spaces not neighboring the first state space.

17 . The autonomous vehicle of claim 16 , wherein the steps further comprise:

transitioning from a first state of the first state space to a second state in a second state space in the one or more second state spaces;

identifying, from the one or more third state spaces, a third state space neighboring the second state space; and

executing a third machine learning model associated with the identified third state space.

18 . The autonomous vehicle of claim 17 , wherein the steps further comprise preventing execution of a machine learning model associated with a state space not neighboring the second state space.

19 . A computer program product disposed upon a non-transitory computer readable medium, the computer program product comprising computer program instructions for selective model execution in an autonomous vehicle that, when executed, cause a computer system of the autonomous vehicle to carry out the steps of:

identifying, based on a first state space associated with a first machine learning model, one or more second state spaces neighboring the first state space, wherein the one or more second state spaces are each associated with a corresponding second machine learning model of one or more second machine learning models; and

executing the one or more second machine learning models.

20 . The computer program product of claim 19 , wherein the steps further comprise prohibiting execution of one or more third machine learning models each associated with a corresponding third state space of one or more third state spaces not neighboring the first state space.