Detecting deviations in driving behavior for autonomous vehicles
A system to use submaps to control operation of a vehicle is disclosed. A storage system may be provided with a vehicle to store a collection of submaps that represent a geographic area where the vehicle may be driven. A programmatic interface may be provided to receive submaps and submap updates independently of other submaps.
1. A computer-implemented method comprising:
receiving, by one or more computing devices and from multiple instances of at least one autonomous vehicle utilizing one or more submaps to traverse a road segment, sensor data representing one or more scenes of the road segment;
identifying, by the one or more computing devices and based at least in part on the sensor data, a change in the road segment corresponding to a deviation in driving behavior amongst a plurality of vehicles that utilize the road segment, wherein the deviation is associated with an aggregation of a plurality of incidents where driving behavior of each of the plurality of vehicles deviates from a normal or permitted driving behavior in a same or similar manner that is associated with the change in the road segment; and
updating, by the one or more computing devices and based at least in part on the deviation, the one or more submaps to account for the change in the road segment.
2. The computer-implemented method of claim 1 , wherein the change in the road segment corresponding to the deviation comprises one or more of:
a formation of a turn lane;
a violation of a traffic law;
a violation of a traffic rule;
a reduction in speed as a result of traffic formation;
formation of an impermissible stopping space; or
inaccessibility of a permissible parking space.
3. The computer-implemented method of claim 1 , wherein identifying the change in the road segment corresponding to the deviation comprises performing variance analysis on the sensor data.
4. The computer-implemented method of claim 1 , wherein identifying the change in the road segment corresponding to the deviation comprises performing pattern analysis on the sensor data.
5. The computer-implemented method of claim 1 , wherein the method comprises determining, by the one or more computing devices, that the change in the road segment corresponding to the deviation is associated with one or more of a lighting, weather, or transient condition.
6. The computer-implemented method of claim 1 , wherein identifying the change in the road segment corresponding to the deviation comprises comparing the sensor data with one or more features of the road segment indicated by the one or more submaps.
7. The computer-implemented method of claim 1 , wherein identifying the change in the road segment corresponding to the deviation comprises comparing the sensor data with a baseline input from the one or more submaps.
8. The computer-implemented method of claim 1 , wherein the one or more computing devices comprise a combination of autonomous vehicles that form one or more of a mesh or peer network.
9. The computer-implemented method of claim 1 , wherein the sensor data comprises data representing one or more point clouds representing the one or more scenes.
10. The computer-implemented method of claim 1 , wherein the sensor data comprises data generated based at least in part on data captured by one or more of:
one or more light detection and ranging (LIDAR) sensors of the at least one autonomous vehicle; or
one or more image sensors of the at least one autonomous vehicle.
11. A system comprising:
one or more processors; and
a memory storing instructions that when executed by the one or more processors cause the system to perform operations comprising:
receiving sensor data representing one or more scenes from multiple instances of at least one autonomous vehicle utilizing one or more submaps to traverse a road segment;
identifying, based at least in part on the sensor data, a change in the road segment corresponding to a deviation in driving behavior amongst a plurality of vehicles that utilize the road segment, wherein the deviation is associated with an aggregation of a plurality of incidents where driving behavior of each of the plurality of vehicles deviates from a normal or permitted driving behavior in a same or similar manner that is associated with the change in the road segment; and
updating the one or more submaps to reflect the deviation in driving behavior amongst the vehicles that utilize the road segment.
12. The system of claim 11 , wherein identifying the change in the road segment corresponding to the deviation comprises performing one or more of variance or pattern analysis on the sensor data.
13. The system of claim 11 , wherein the operations comprise determining that the change in the road segment corresponding to the deviation is associated with one or more of a lighting, weather, or transient condition.
14. The system of claim 11 , wherein identifying the change in the road segment corresponding to the deviation comprises comparing the sensor data with one or more features of the road segment indicated by the one or more submaps.
15. The system of claim 11 , wherein identifying the change in the road segment corresponding to the deviation comprises comparing the sensor data with a baseline input from the one or more submaps.
16. One or more non-transitory computer-readable media comprising instructions that when executed by one or more computing devices cause the one or more computing devices to perform operations comprising:
identifying, based at least in part on sensor data representing one or more scenes from multiple instances of at least one autonomous vehicle utilizing one or more submaps to traverse a road segment, a change in the road segment corresponding to a deviation in driving behavior amongst a plurality of vehicles that utilize the road segment, wherein the deviation is associated with an aggregation of a plurality of incidents where driving behavior of each of the plurality of vehicles deviates from a normal or permitted driving behavior in a same or similar manner that is associated with the change in the road segment; and
updating, based at least in part on the deviation, the one or more submaps to account for the change in the road segment.
17. The one or more non-transitory computer-readable media of claim 16 , wherein identifying the change in the road segment corresponding to the deviation comprises performing one or more of variance or pattern analysis on the sensor data.
18. The one or more non-transitory computer-readable media of claim 16 , wherein the operations comprise determining that the change in the road segment corresponding to the deviation is associated with one or more of a lighting, weather, or transient condition.
19. The one or more non-transitory computer-readable media of claim 16 , wherein identifying the change in the road segment corresponding to the deviation comprises comparing the sensor data with one or more features of the road segment indicated by the one or more submaps.
20. The one or more non-transitory computer-readable media of claim 16 , wherein identifying the change in the road segment corresponding to the deviation comprises comparing the sensor data with a baseline input from the one or more submaps.