Constraint relaxation in a navigational system
Systems and methods are provided for navigating an autonomous vehicle using reinforcement learning techniques. In one implementation, a navigation system for a host vehicle may include at least one processing device programmed to: receive, from a camera, a plurality of images representative of an environment of the host vehicle; analyze the plurality of images to identify a navigational state associated with the host vehicle; provide the navigational state to a trained navigational system; receive, from the trained navigational system, a desired navigational action for execution by the host vehicle in response to the identified navigational state; analyze the desired navigational action relative to one or more predefined navigational constraints; determine an actual navigational action for the host vehicle, wherein the actual navigational action includes at least one modification of the desired navigational action determined based on the one or more predefined navigational constraints; and cause at least one adjustment of a navigational actuator of the host vehicle in response to the determined actual navigational action for the host vehicle.
1. A navigation system for a host vehicle, the system comprising:
at least one processing device programmed to:
receive, from a camera, a plurality of images representative of an environment of the host vehicle;
analyze the plurality of images to identify a navigational state associated with the host vehicle;
determine a first predefined navigational constraint implicated by at least one aspect of the navigational state;
identify, based on analysis of the plurality of images, a presence of at least one navigational constraint augmentation factor associated with the first predefined navigational constraint;
determine a second navigational constraint based on the identification of the at least one navigational constraint augmentation factor, wherein the second navigational constraint is different from the first navigational constraint and includes at least one characteristic augmented with respect to the first navigational constraint;
determine, based on the identified navigational state, a navigational action for the host vehicle satisfying the second navigational constraint; and
cause at least one adjustment of a navigational actuator of the host vehicle in response to the determined navigational action.
2. The navigation system of claim 1 , wherein determination of the first navigational constraint occurs in a trained navigational system, and wherein the trained navigational network determines an original navigational action for the host vehicle, based on the first navigational constraint, that is different from the navigational action for the host vehicle that satisfies the second navigational constraint.
3. The navigation system of claim 1 , wherein determination of the navigational action for the host vehicle occurs in a trained navigational system.
4. The navigation system of claim 1 , wherein the first predefined navigational constraint includes a first buffer zone associated with a detected pedestrian, wherein at least a portion of the first buffer zone extends a first distance from the detected pedestrian, and wherein the second navigational constraint includes a second buffer zone associated with the detected pedestrian, wherein at least a portion of the second buffer zone extends a second distance from the detected pedestrian greater than the first distance.
5. The navigation system of claim 1 , wherein the navigational actuator includes at least one of a steering mechanism, a brake, or an accelerator.
6. The navigation system of claim 1 , wherein the relaxed characteristic includes an increased width in a buffer zone associated with at least one of a pedestrian, a target vehicle, a detected object, a roadside barrier.
7. The navigation system of claim 1 , wherein the at least one relaxed characteristic includes a decrease in speed associated with at least one predefined navigational constraint.
8. The navigation system of claim 1 , wherein the at least one relaxed characteristic includes a decrease in maximum allowable deceleration associated with at least one predefined navigational constraint.
9. The navigation system of claim 1 , wherein the at least one navigational constraint augmentation factor includes a detection of particulates on an outer surface associated with the host vehicle.
10. The navigation system of claim 1 , wherein the at least one navigational constraint augmentation factor includes a detection of the presence of at least one of ice, snow, or water on a surface of a road in the environment of the host vehicle.
11. The navigation system of claim 1 , wherein the at least one navigational constraint augmentation factor includes a detected decrease in image quality of one or more images captured by the image capture device.
12. The navigation system of claim 1 , wherein the at least one navigational constraint augmentation factor includes a detected failure or partial failure of a sensor associated with the host vehicle.
13. An autonomous vehicle, the autonomous vehicle comprising:
a frame;
a body attached to the frame;
a camera; and
at least one processing device programmed to:
receive, from a camera, a plurality of images representative of an environment of the autonomous vehicle;
analyze the plurality of images to identify a navigational state associated with the autonomous vehicle;
determine a first predefined navigational constraint implicated by at least one aspect of the navigational state;
identify, based on analysis of the plurality of images, a presence of at least one navigational constraint augmentation factor associated with the first predefined navigational constraint;
determine a second navigational constraint based on the identification of the at least one navigational constraint augmentation factor, wherein the second navigational constraint is different from the first navigational constraint and includes at least one characteristic augmented with respect to the first navigational constraint;
determine, based on the identified navigational state, a navigational action for the autonomous vehicle satisfying the second navigational constraint; and
cause at least one adjustment of a navigational actuator of the autonomous vehicle in response to the determined navigational action.
14. The autonomous vehicle of claim 13 , wherein determination of the first navigational constraint occurs in a trained navigational system, and wherein the trained navigational network determines an original navigational action for the autonomous vehicle, based on the first navigational constraint, that is different from the navigational action for the autonomous vehicle that satisfies the second navigational constraint.
15. The autonomous vehicle of claim 13 , wherein determination of the navigational action for the autonomous vehicle occurs in a trained navigational system.
16. The autonomous vehicle of claim 13 , wherein the first predefined navigational constraint includes a first buffer zone associated with a detected pedestrian, wherein at least a portion of the first buffer zone extends a first distance from the detected pedestrian, and wherein the second navigational constraint includes a second buffer zone associated with the detected pedestrian, wherein at least a portion of the second buffer zone extends a second distance from the detected pedestrian greater than the first distance.
17. The autonomous vehicle of claim 13 , wherein the navigational actuator includes at least one of a steering mechanism, a brake, or an accelerator.
18. The autonomous vehicle of claim 13 , wherein the augmented characteristic includes an increased width in a buffer zone associated with at least one of a pedestrian, a target vehicle, a detected object, a roadside barrier.
19. The autonomous vehicle of claim 13 , wherein the at least one augmented characteristic includes a decrease in speed associated with at least one predefined navigational constraint.
20. The autonomous vehicle of claim 13 , wherein the at least one augmented characteristic includes a decrease in maximum allowable deceleration associated with at least one predefined navigational constraint.
21. The autonomous vehicle of claim 13 , wherein the at least one navigational constraint augmentation factor includes a detection of particulates on an outer surface associated with the host vehicle.
22. The autonomous vehicle of claim 13 , wherein the at least one navigational constraint augmentation factor includes a detection of the presence of at least one of ice, snow, or water on a surface of a road in the environment of the host vehicle.
23. The autonomous vehicle of claim 13 , wherein the at least one navigational constraint augmentation factor includes a detected decrease in image quality of one or more images captured by the image capture device.
24. The autonomous vehicle of claim 13 , wherein the at least one navigational constraint augmentation factor includes a detected failure or partial failure of a sensor associated with the host vehicle.
25. A method for navigating an autonomous vehicle, the method comprising:
receiving, from a camera, a plurality of images representative of an environment of the autonomous vehicle;
analyzing the plurality of images to identify a navigational state associated with the autonomous vehicle;
determining a first predefined navigational constraint implicated by at least one aspect of the navigational state;
identifying, based on analysis of the plurality of images, a presence of at least one navigational constraint augmentation factor associated with the first predefined navigational constraint;
determine a second navigational constraint based on the identification of the at least one navigational constraint augmentation factor, wherein the second navigational constraint is different from the first navigational constraint and includes at least one characteristic augmented with respect to the first navigational constraint;
determining, based on the identified navigational state, a navigational action for the autonomous vehicle satisfying the second navigational constraint; and
causing at least one adjustment of a navigational actuator of the autonomous vehicle in response to the determined navigational action.