Method for influencing entities at a roadway intersection
One variation of a method for influencing entities proximal a road surface includes, at an autonomous vehicle: over a first period of time, detecting a pedestrian proximal a road surface; predicting an initial path of the pedestrian an initial confidence score for the initial path of the pedestrian based on and motion of the pedestrian during the first period of time; in response to the initial confidence score falling below a threshold confidence, replaying an audio track audible to the pedestrian and calculating a revised path of the pedestrian and a revised confidence score for the revised path based on motion of the pedestrian following replay of the audio track; and autonomously navigating across the road surface according to a planned route in response to the revised path of the pedestrian falling outside of the planned route and the revised confidence score exceeding the threshold confidence.
1. A system comprising:
at least one sensor of an autonomous vehicle, the at least one sensor configured to detect a person proximal to a travel path of the autonomous vehicle;
at least one processor configured to estimate a gaze of the person and determine whether a field of view of the gaze of the person intersects a location of the autonomous vehicle; and
one or more vehicle systems configured to execute at least one action of the autonomous vehicle autonomously, the at least one action autonomously generating based on a navigation decision corresponding to whether to navigate along the travel path, the navigation decision autonomously generated based on whether the field of view of the gaze of the person intersects the location of the autonomous vehicle.
2. The system of claim 1 , wherein the at least one processor is further configured to autonomously determine a possession of a right of way of the autonomous vehicle for navigating along the travel path, the navigation decision further generated based on the possession of the right of way.
3. The system of claim 1 , wherein a confidence score regarding whether the person observes the autonomous vehicle is generated based on the whether the field of view of the gaze of the person intersects the location of the autonomous vehicle.
4. The system of claim 3 , wherein a comparison of the confidence score to a confidence threshold is generated, the navigation decision autonomously generated based on the comparison.
5. The system of claim 1 , further comprising:
at least one output device configured to direct a movement of the person based on the navigation decision, the movement of the person directed using a prompt for presentation to the person.
6. The system of claim 5 , wherein the prompt is an audio prompt.
7. The system of claim 6 , wherein the audio prompt is output using the at least one output device along an audio vector.
8. The system of claim 7 , wherein the audio vector is determined based on a path of the person.
9. The system of claim 1 , wherein the person is a pedestrian, a bicyclist, a motorcyclist, a driver of another vehicle, or riding on a scooter.
10. A method comprising:
detecting a person proximal to a travel path of an autonomous vehicle;
estimating a gaze of the person, the gaze having a field of view;
determining whether the field of view of the gaze of the person intersects a location of the autonomous vehicle;
autonomously generating at least one action of the autonomous vehicle based on a navigation decision corresponding to whether to navigate along the travel path, the navigation decision autonomously generated based on whether the field of view of the gaze of the person intersects the location of the autonomous vehicle; and
executing the at least one action of the autonomous vehicle autonomously.
11. The method of claim 10 , further comprising:
autonomously determining a possession of a right of way of the autonomous vehicle for navigating along the travel path, the navigation decision further generated based on the possession of the right of way.
12. The method of claim 10 , further comprising:
generating a confidence score regarding whether the person observes the autonomous vehicle based on the whether the field of view of the gaze of the person intersects the location of the autonomous vehicle.
13. The method of claim 12 , further comprising:
generating a comparison of the confidence score to a confidence threshold, the navigation decision autonomously generated based on the comparison.
14. The method of claim 10 , further comprising:
directing a movement of the person based on the navigation decision, the movement of the person directed by generating a prompt for presentation to the person.
15. The method of claim 14 , wherein the prompt is an audio prompt.
16. The method of claim 15 , wherein the audio prompt is output along an audio vector.
17. The method of claim 16 , wherein the audio vector is determined based on a path of the person.
18. The method of claim 10 , wherein the person is a pedestrian, a bicyclist, a motorcyclist, a driver of another vehicle, or riding on a scooter.
19. One or more non-transitory computer-readable data storage media comprising instructions that, when executed by at least one computing unit of a computing system, cause the computing system to perform operations comprising:
detecting a person proximal to a travel path of an autonomous vehicle;
estimating a gaze of the person, the gaze having a field of view;
determining whether the field of view of the gaze of the person intersects a location of the autonomous vehicle;
generating at least one action of the autonomous vehicle based on a navigation decision corresponding to whether to navigate along the travel path, the navigation decision generated based on whether the field of view of the gaze of the person intersects the location of the autonomous vehicle; and
causing the autonomous vehicle to execute the at least one action.
20. The one or more non-transitory computer-readable data storage media of claim 19 , the operations further comprising:
directing a movement of the person based on the navigation decision, the movement of the person directed by generating a prompt for presentation to the person.