Processing a request signal regarding operation of an autonomous vehicle
Among other things, a vehicle drives autonomously on a trajectory through a road network to a goal location based on an automatic process for planning the trajectory without human intervention; and an automatic process alters the planning of the trajectory to reach a target location based on a request received from an occupant of the vehicle to engage in a speed-reducing maneuver.
1. A method comprising:
causing a vehicle to drive autonomously on a road network;
in response to a request signal representing a request for the vehicle to engage in a speed-reducing maneuver, computationally analyzing data to choose a target location for the maneuver from a plurality of target locations by:
inferring a degree of urgency and an expected stopping time interval from the request signal and the data;
computing a minimum quality threshold of the plurality of target locations based on the degree of urgency and the expected stopping time interval, wherein a shorter expected stopping time interval corresponds to a lower minimum quality threshold; and
applying the minimum quality threshold to the plurality of target locations to identify the target location; and
causing the vehicle to drive autonomously toward the target location and engage in the maneuver.
2. The method of claim 1 , in which the target location comprises a target stopping place.
3. The method of claim 1 , in which the maneuver comprises stopping the vehicle.
4. The method of claim 1 , comprising receiving the request signal from an occupant, a teleoperator, or a software or hardware process.
5. The method of claim 4 , in which the request signal comprises at least some of the data received from a user interface in the vehicle resulting from an interaction by an occupant of the vehicle.
6. The method of claim 5 , in which the user interface comprises a button, a switch, a pull-cord, a pedal, a pad, a sensor, a whistle, a display, or a voice assistant, or a combination of two or more of them.
7. The method of claim 4 , in which receiving the request signal comprises receiving a command from the teleoperator via telecommunications.
8. The method of claim 4 , in which receiving the request signal comprises receiving the request from the software or hardware process based on degradation in performance of the vehicle.
9. The method of claim 8 , in which the degradation in performance comprises degradation in performance of a sensor or a component of the vehicle.
10. The method of claim 4 , in which receiving the request signal comprises receiving the request from the software or hardware process based on detection of an event on the road network.
11. The method of claim 1 , in which the request signal or the data comprises the degree of urgency.
12. The method of claim 11 , in which the degree of urgency has been indicated by an initiator of the request signal.
13. The method of claim 11 , comprising inferring the degree of urgency by an algorithmic analysis of the request.
14. The method of claim 13 , in which the algorithmic analysis comprises analysis of a frequency, a volume, a sound, a voice, or a type, or two or more of them, of an oral request.
15. The method of claim 1 , in which the data comprises the expected stopping time interval.
16. The method of claim 15 , in which the expected stopping time interval has been indicated by an initiator of the request signal.
17. The method of claim 15 , in which the expected stopping time interval is inferred by an algorithmic analysis on the request.
18. The method of claim 17 , in which the algorithmic analysis comprises analysis of data associated with the request.
19. The method of claim 1 , in which the data comprises traffic data, sensor data, or map data, or two or more of them.
20. The method of claim 1 , further comprising evaluating numerical quality values offline relative to the vehicle.
21. The method of claim 20 , in which at least one of the numerical quality values is evaluated online when the vehicle is driving.
22. The method of claim 20 , in which the evaluating of the numerical quality values comprises computing a numerical quality value based on one or more of the following factors: an emergency condition, a location of the vehicle on the road network, a traffic speed, a traffic volume, a traffic composition, a lane choice, a blockage degree, a sightline from another vehicle, a distance from an intersection, presence of a dedicated lane, terrain, and a road slope.
23. The method of claim 22 , in which one or more of the factors are represented by numerical values.
24. The method of claim 23 , in which each of the numerical values is mapped to a pre-defined range.
25. The method of claim 22 , in which computing the numerical quality value comprises assigning weights to one or more of the factors.
26. The method of claim 25 , in which the weights are based on one or more of the following: features of the request, a type of the vehicle, a regulation, degree of urgency, and an expected stopping time interval.
27. The method of claim 22 , comprising ignoring another target location based on its numerical quality value or information specifying its exclusion.
28. The method of claim 22 , comprising classifying target locations in quality categories.
29. The method of claim 1 , further comprising computing the minimum quality threshold based on a conflicting rule.
30. The method of claim 1 , in which analyzing the data comprises identifying a region for choosing the target location.
31. The method of claim 30 , in which the region comprises a drivable area or a non-drivable area or both.
32. The method of claim 30 , in which the region comprises an area faced by a forward-facing side of the vehicle.
33. The method of claim 30 , in which the region comprises a shape or a size or both.
34. The method of claim 33 , comprising determining the shape or the size based on a traffic condition or on a degree of urgency or on both.
35. The method of claim 30 , comprising determining the region based on qualities of one or more target locations.
36. The method of claim 30 , comprising expanding the region when no target location is identified.
37. The method of claim 30 , comprising updating the region based on a new location of the vehicle.
38. The method of claim 30 , in which choosing the target location comprises discretizing the region into potential target places.
39. The method of claim 30 , in which choosing the target location comprises using availability data.
40. The method of claim 39 , comprising acquiring the availability data from one or more of the following: a crowd-sourced database, a sensor, a perception process, a historical database, a parking lot database, a parking space database, the vehicle, and another vehicle.
41. The method of claim 1 , wherein the computationally analyzing data comprises computing a numeric score for each of the plurality of target locations and comparing the numeric scores of the plurality of target locations.
42. The method of claim 41 , wherein computing the numeric score for each of the target locations comprises:
converting metrics of criteria for evaluating the target locations to numbers;
normalizing the numbers to lie within pre-defined ranges; and
using pre-defined weights to account for differences in importance of different criteria.