Providing user assistance in a vehicle based on traffic behavior models
Autonomous driving includes identifying a traffic behavior of an object in an environment surrounding a vehicle based on an evaluation of information about the environment surrounding the vehicle while the vehicle is in the midst of manual operation, and operating vehicle systems in the vehicle to perform a driving maneuver according to a driving plan for performing the driving maneuver. The autonomous driving further includes receiving a traffic behavior model that describes a predominating traffic behavior of a like population of reference objects, and operating the vehicle systems to perform the driving maneuver according to the driving plan in response to identifying that the traffic behavior of the object does not match the predominating traffic behavior of the like population of reference objects. Under the driving plan, the traffic behavior of the object is addressed.
1. A vehicle, comprising:
at least one processor; and
a memory communicably coupled to the at least one processor and storing instructions that when executed by the at least one processor cause the at least one processor to:
while the vehicle is in a midst of manual operation, evaluate information about an environment surrounding the vehicle;
quantify, based on the evaluation of the information about the environment surrounding the vehicle, an attribute of how an object in the environment surrounding the vehicle performs a traffic maneuver;
receive a traffic behavior model that describes a statistically median attribute of how a population of reference objects performs the traffic maneuver; and
in response to identifying that the attribute of how the object performs the traffic maneuver does not match the statistically median attribute of how the population of reference objects performs the traffic maneuver:
operate vehicle systems in the vehicle to perform a driving maneuver according to a driving plan for performing the driving maneuver under which the attribute of how the object performs the traffic maneuver is addressed.
2. The vehicle of claim 1 , wherein evaluating information about the environment surrounding the vehicle includes:
identifying traffic maneuvers performed by reference objects in the environment surrounding the vehicle, and quantifying attributes of how the reference objects perform the traffic maneuvers;
identifying the population of reference objects from among the reference objects;
identifying the statistically median attribute of how the population of reference objects performs the traffic maneuver; and
generating the traffic behavior model that describes the statistically median attribute of how the population of reference objects performs the traffic maneuver.
3. The vehicle of claim 1 , wherein the memory includes instructions that when executed by the at least one processor cause the at least one processor operate the vehicle systems to perform the driving maneuver according to the driving plan conditionally upon receiving a user response, at at least one interface in the vehicle, that a user accepts an offer of autonomous operation issued at the at least one interface in response to identifying that the attribute of how the object performs the traffic maneuver does not match the statistically median attribute of how the population of reference objects performs the traffic maneuver.
4. The vehicle of claim 1 , wherein:
the traffic behavior model describes a statistically outlying attribute of how the population of reference objects performs the traffic maneuver; and
the memory includes instructions that when executed by the at least one processor cause the at least one processor to operate the vehicle systems to perform the driving maneuver according to the driving plan automatically in response to identifying that the attribute of how the object performs the traffic maneuver not only does not match the statistically median attribute of how the population of reference objects performs the traffic maneuver, but also matches the statistically outlying attribute of how the population of reference objects performs the traffic maneuver.
5. The vehicle of claim 1 , wherein the population of reference objects includes reference objects maneuvering on roadways at least one of in a same location as the object, at a same time of day as the object, under a same roadway condition as the object, under a same traffic condition as the object, and under a same weather condition as the object.
6. The vehicle of claim 5 , wherein the population of reference objects includes the reference objects maneuvering on roadways in the same location as the object.
7. The vehicle of claim 5 , wherein the population of reference objects includes the reference objects maneuvering on roadways at least one of at the same time of day as the object, under the same roadway condition as the object, under the same traffic condition as the object, and under the same weather condition as the object.
8. The vehicle of claim 5 , wherein the population of reference objects includes the reference objects maneuvering on roadways in the same location as the object, and at least one of at the same time of day as the object, under the same roadway condition as the object, under the same traffic condition as the object, and under the same weather condition as the object.
9. A method of autonomous driving, comprising:
while a vehicle is in a midst of manual operation, evaluating, using at least one processor, information about an environment surrounding the vehicle;
quantifying, using the at least one processor, based on the evaluation of the information about the environment surrounding the vehicle, an attribute of how an object in the environment surrounding the vehicle performs a traffic maneuver;
receiving, using the at least one processor, a traffic behavior model that describes a statistically median attribute of how a population of reference objects performs the traffic maneuver; and
in response to identifying, using the at least one processor, that the attribute of how the object performs the traffic maneuver does not match the statistically median attribute of how the population of reference objects performs the traffic maneuver:
initiating, using the at least one processor, based on the evaluation of the information about the environment surrounding the vehicle, defensive autonomous operation under which the attribute of how the object performs the traffic maneuver is addressed.
10. The method of claim 9 , wherein evaluating information about the environment surrounding the vehicle includes:
identifying traffic maneuvers performed by reference objects in the environment surrounding the vehicle, and quantifying attributes of how the reference objects perform the traffic maneuvers;
identifying the population of reference objects from among the reference objects;
identifying the statistically median attribute of how the population of reference objects performs the traffic maneuver; and
generating the traffic behavior model that describes the statistically median attribute of how the population of reference objects performs the traffic maneuver.
11. The method of claim 9 , wherein initiating defensive autonomous operation under which the attribute of how the object performs the traffic maneuver is addressed is conditional upon receiving a user response, at at least one interface in the vehicle, that a user accepts an offer of autonomous operation issued at the at least one interface in response to identifying that the attribute of how the object performs the traffic maneuver does not match the statistically median attribute of how the population of reference objects performs the traffic maneuver.
12. The method of claim 9 , wherein:
the traffic behavior model describes a statistically outlying attribute of how the population of reference objects performs the traffic maneuver; and
initiating defensive autonomous operation under which the attribute of how the object performs the traffic maneuver is addressed is automatic in response to identifying that the attribute of how the object performs the traffic maneuver not only does not match the statistically median attribute of how the population of reference objects performs the traffic maneuver, but also matches the statistically outlying attribute of how the population of reference objects performs the traffic maneuver.
13. The method of claim 9 , wherein the population of reference objects includes reference objects maneuvering on roadways at least one of in a same location as the object, at a same time of day as the object, under a same roadway condition as the object, under a same traffic condition as the object, and under a same weather condition as the object.
14. The method of claim 13 , wherein the population of reference objects includes the reference objects maneuvering on roadways in the same location as the object.
15. The method of claim 13 , wherein the population of reference objects includes the reference objects maneuvering on roadways at least one of at the same time of day as the object, under the same roadway condition as the object, under the same traffic condition as the object, and under the same weather condition as the object.
16. The method of claim 13 , wherein the population of reference objects includes the reference objects maneuvering on roadways in the same location as the object, and at least one of at the same time of day as the object, under the same roadway condition as the object, under the same traffic condition as the object, and under the same weather condition as the object.