Operation of a vehicle using motion planning with machine learning

1. A method comprising:

storing, using one or more processors of a vehicle located within an environment, a plurality of constraints for operating the vehicle within the environment;

receiving, using one or more sensors of the vehicle, sensor data describing the environment;

extracting, using the one or more processors, a feature vector from the stored plurality of constraints and the received sensor data, wherein the feature vector comprises a first feature describing an object located within the environment;

determining, using the one or more processors, a hierarchical ranking of the stored plurality of constraints,

wherein a rank of each constraint of the stored plurality of constraints corresponds to a level of navigational safety of the vehicle, and

wherein a rank of each constraint of the plurality of constraints is determined by a machine learning circuit of the vehicle based on the extracted feature vector;

generating, using the machine learning circuit, a first motion segment based on the feature vector, such that a weighted aggregate of a number of violations of the stored plurality of constraints is below a threshold; and

operating, using the one or more processors, the vehicle in accordance with the generated first motion segment.

2. The method of claim 1 , wherein the generated first motion segment comprises a directional orientation of the vehicle to avoid a collision with the object.

3. The method of claim 1 , wherein a second feature of the extracted feature vector comprises at least one of:

a spatiotemporal location of the object;

a speed of the object; or

a directional orientation of the object.

4. The method of claim 1 , wherein:

a third feature of the extracted feature vector comprises at least one of a maximum speed of the vehicle, a maximum acceleration of the vehicle, or a maximum jerk of the vehicle; and

the at least one of the maximum speed, the maximum acceleration, or the maximum jerk correspond to a level of passenger comfort measured by one or more passenger sensors of the vehicle.

5. The method of claim 1 , wherein a fourth feature of the extracted feature vector represents whether the operating of the vehicle in accordance with the first motion segment causes a traffic light violation.

6. The method of claim 1 , wherein the generated first motion segment comprises at least one of:

a trajectory between two spatiotemporal locations of the environment; or

a speed of the vehicle to avoid a collision of the vehicle with the object.

7. The method of claim 1 , further comprising:

aggregating, using the one or more processors, a plurality of features of the extracted feature vector into a motion planning graph, wherein:

the motion planning graph comprises a plurality of edges; and

each edge of the plurality of edges corresponds to a motion segment of the received plurality of motion segments.

8. The method of claim 7 , wherein the generating, based on the feature vector, of the first motion segment for operating the vehicle comprises:

selecting, using the one or more processors, the first motion segment corresponding to a first edge of the plurality of edges over a second motion segment corresponding to a second edge of the plurality of edges, wherein:

operating the vehicle in accordance with the first motion segment causes a violation of a first constraint having a higher rank; and

operating the vehicle in accordance with the second motion segment causes a violation of a second constraint having a lower rank.

9. The method of claim 7 , wherein:

the motion planning graph comprises a minimum-violation motion planning graph; and

each edge of the plurality of edges is associated with a value of an operational metric of a corresponding motion segment.

10. The method of claim 9 , further comprising generating, using the machine learning circuit, the value of the operational metric of each corresponding motion segment of the plurality of edges of the motion planning graph based on the feature vector.

11. The method claim 9 , wherein the generating of the first motion segment for operating the vehicle comprises identifying, using the machine learning circuit, for each edge of the plurality of edges of the motion planning graph, a likelihood that the operating of the vehicle in accordance with a corresponding motion segment causes the operational metric to be below the threshold.

12. The method of claim 9 , further comprising sampling, using the one or more processors, the stored plurality of constraints and the received sensor data to generate a third motion segment for operating the vehicle within the environment, wherein the operating of the vehicle in accordance with the third motion segment causes the operational metric associated with operating the vehicle to be below the threshold.

13. The method of claim 9 , wherein:

each violation of a constraint of the stored plurality of constraints is weighted by a rank of the constraint.

14. The method of claim 1 , wherein:

a rank of each constraint of the plurality of constraints corresponds to a level of navigational safety of the vehicle.

15. The method of claim 1 , further comprising:

receiving, using one or more additional sensors of the vehicle, additional sensor data regarding a passenger of the vehicle, wherein the additional sensor data comprises at least one of:

a heart rate of the passenger,

a temperature of the passenger,

a pupil dilation of the passenger; and

wherein the feature vector is extracted further from the received additional sensor data.

16. A vehicle comprising:

one or more computer processors; and

one or more non-transitory storage media storing instructions which, when executed by the one or more computer processors, cause the one or more computer processors to:

store a plurality of constraints for operating the vehicle within an environment;

receive, using one or more sensors of the vehicle, sensor data describing the environment;

extract a feature vector from the stored plurality of constraints and the received sensor data, wherein the feature vector comprises a first feature describing an object located within the environment;

determine a hierarchical ranking of the stored plurality of constraints,

wherein a rank of each constraint of the stored plurality of constraints corresponds to a level of navigational safety of the vehicle, and

wherein a rank of each constraint of the plurality of constraints is determined by a machine learning circuit of the vehicle based on the extracted feature vector;

generate, using the machine learning circuit, a first motion segment based on the feature vector, such that a weighted aggregate of a number of violations of the stored plurality of constraints is below a threshold; and

operate the vehicle in accordance with the generated first motion segment.

17. The vehicle of claim 16 , wherein the generated first motion segment comprises a directional orientation of the vehicle to avoid a collision with the object.

18. The vehicle of claim 16 , wherein a second feature of the extracted feature vector comprises at least one of a spatiotemporal location of the object, a speed of the object, or a directional orientation of the object.

19. A vehicle of claim 16 , wherein:

a third feature of the extracted feature vector comprises at least one of a maximum speed of the vehicle, a maximum acceleration of the vehicle, or a maximum jerk of the vehicle; and

the at least one of the maximum speed, the maximum acceleration, or the maximum jerk correspond to a level of passenger comfort measured by one or more passenger sensors of the vehicle.

20. The vehicle of claim 16 , wherein a fourth feature of the extracted feature vector represents whether the operating of the vehicle in accordance with the first motion segment causes a traffic light violation.

21. The vehicle of claim 16 , wherein the generated first motion segment comprises at least one of:

a trajectory between two spatiotemporal locations of the environment; or

a speed of the vehicle to avoid a collision of the vehicle with the object.

22. One or more non-transitory storage media storing instructions which, when executed by one or more computing devices, cause the one or more computing devices to:

store a plurality of constraints for operating a vehicle within an environment;

receive, using one or more sensors of the vehicle, sensor data describing the environment;

extract a feature vector from the stored plurality of constraints and the received sensor data, wherein the feature vector comprises a first feature describing an object located within the environment;

determine a hierarchical ranking of the stored plurality of constraints,

wherein a rank of each constraint of the stored plurality of constraints corresponds to a level of navigational safety of the vehicle, and

wherein a rank of each constraint of the plurality of constraints is determined by a machine learning circuit of the vehicle based on the extracted feature vector;

generate, using the machine learning circuit, a first motion segment based on the feature vector, such that a weighted aggregate of a number of violations of the stored plurality of constraints is below a threshold; and

operate the vehicle in accordance with the generated first motion segment.

23. The one or more non-transitory storage media of claim 22 , wherein the generated first motion segment comprises a directional orientation of the vehicle to avoid a collision with the object.

24. The one or more non-transitory storage media of claim 22 , wherein the instructions, when executed by the one or more computing devices, cause the one or more computing devices to:

aggregate a plurality of features of the extracted feature vector into a motion planning graph, wherein:

the motion planning graph comprises a plurality of edges; and

each edge of the plurality of edges corresponds to a motion segment of the received plurality of motion segments.

25. The one or more non-transitory storage media of claim 24 , wherein the generating, based on the feature vector, of the first motion segment for operating the vehicle comprises:

selecting the first motion segment corresponding to a first edge of the plurality of edges over a second motion segment corresponding to a second edge of the plurality of edges, wherein:

operating the vehicle in accordance with the first motion segment causes a violation of a first constraint having a higher rank; and

operating the vehicle in accordance with the second motion segment causes a violation of a second constraint having a lower rank.

26. The one or more non-transitory storage media of claim 24 , wherein:

the motion planning graph comprises a minimum-violation motion planning graph; and

each edge of the plurality of edges is associated with a value of an operational metric of a corresponding motion segment.

27. The one or more non-transitory storage media of claim 26 , wherein the instructions, when executed by the one or more computing devices, cause the one or more computing devices to:

generate, using the machine learning circuit, the value of the operational metric of each corresponding motion segment of the plurality of edges of the motion planning graph based on the feature vector.

28. The one or more non-transitory storage media of claim 26 , wherein the generating of the first motion segment for operating the vehicle comprises identifying, using the machine learning circuit, for each edge of the plurality of edges of the motion planning graph, a likelihood that the operating of the vehicle in accordance with a corresponding motion segment causes the operational metric to be below the threshold.

29. The one or more non-transitory storage media of claim 26 , wherein the instructions, when executed by the one or more computing devices, cause the one or more computing devices to:

sample the stored plurality of constraints and the received sensor data to generate a third motion segment for operating the vehicle within the environment, wherein the operating of the vehicle in accordance with the third motion segment causes the operational metric associated with operating the vehicle to be below the threshold.

30. The one or more non-transitory storage media of claim 26 , wherein:

each violation of a constraint of the stored plurality of constraints is weighted by a rank of the constraint.