System and method for right-of-way determination based on sensor data from fleet vehicles

1 . A computing system comprising:

a communication interface communicating, over one or more networks, with human-driven vehicles operating throughout a region;

one or more processors;

a memory storing instructions that, when executed by the one or more processors, cause the computing system to automatically label a set of autonomous driving maps utilized by autonomous or semi-autonomous vehicles operating in the region, to reflect accurate and up-to-date right-of-way rules for one or more road segments of the region, by:

receiving, over the one or more networks, sensor data comprising one or more control inputs and one or more vehicle motion values from a subset of the human-driven vehicles operating through a road segment within the region, the sensor data being generated by a set of odometry sensors of each of the subset of human-driven vehicles, the set of odometry sensors comprising a positioning system, a braking input sensor, and a steering input sensor, of each of the subset of human-driven vehicles;

processing the sensor data generated by the set of odometry sensors of each of the subset of human-driven vehicles to determine a set of vehicle traces through the road segment for the subset of human-driven vehicles, each vehicle trace of the set including positional acceleration and deacceleration values determined from sensor data of the respective human-driven vehicle;

determining braking and acceleration patterns of human-driven vehicles traversing the road segment based on the positional acceleration and deacceleration values;

based at least in part on the set of vehicle traces and the determined braking and acceleration patterns, generating a set of right-of-way rules for autonomous or semi-autonomous vehicles driving through the road segment to merge onto or off of a freeway, the set of right-of-way rules indicating when an autonomous or semi-autonomous vehicle traversing the road segment is to yield to another vehicle in a competing road segment;

performing a lookup of a database that stores the set of autonomous driving maps, to identify an autonomous map of the set that includes the road segment;

determining whether the determined set of right-of-way rules for the road segment match an existing set of right-of-way rules previously determined for the road segment of the identified autonomous driving map;

modifying the identified autonomous driving map based on the generated set of right-of-way rules for the road segment when the generated set of right-of-way rules for the road segment are determined to not match the existing set of right-of-way rules; and

controlling an autonomous vehicle or a semi-autonomous vehicle using the generated set of right-of-way rules.

2 . The computing system of claim 1 , wherein the executed instructions cause the computing system to generate the set of right-of-way rules by inputting vehicle trace data corresponding to one or more vehicle traces of the set of vehicle traces into a machine learning model trained on aggregate driving behavior data, the machine learning model processing the vehicle trace data to output the set of right-of-way rules.

3 . The computing system of claim 1 wherein the executed instructions cause the computing system to superimpose the set of vehicle traces on map data to further determine the set of right-of-way rules.

4 . The computing system of claim 1 , wherein the identified autonomous driving map includes (i) map data obtained from one or more mapping vehicles operating through the road segment, and/or (ii) labeled autonomous driving rules that correspond to at least one of signage or signals along the road segment.

5 . The computing system of claim 1 , wherein the executed instructions cause the computing system to process vehicle trace data based on sensor data from the human-driven vehicles operating throughout the region to determine right-of-way rules for each road segment of a road network of the region, and wherein the executed instructions further cause the computing system to:

label a set of autonomous driving maps for autonomous or semi- autonomous vehicles driving throughout the road network based on the right-of-way rules determined for each road segment of the road network.

6 . The computing system of claim 1 , wherein modifying the identified autonomous driving map includes labelling or relabeling the identified autonomous driving map based on the generated set of right-of-way rules.

7 . The computing system of claim 1 , wherein modifying the identified autonomous driving map includes replacing a label for one or more existing right of way rules that are incorrect.

8 . A non-transitory computer readable medium storing instructions that, when executed by one or more processors of a computing system, cause the computing system to:

communicating with human-driven vehicles operating throughout a region;

automatically labeling a set of autonomous driving maps utilized by autonomous or semi-autonomous vehicles operating in the region, to reflect accurate and up-to-date right of way rules for one or more road segments of the region, by performing operations that include:

receiving, over one or more networks, sensor data comprising one or more control inputs and one or more vehicle motion values from a subset of the human-driven vehicles operating through a road segment within the region, the sensor data being generated by a set of odometry sensors of each of the subset of human-driven vehicles, the set of odometry sensors comprising a positioning system, a braking input sensor, and a steering input sensor, of each of the subset of human-driven vehicles;

processing the sensor data generated by the set of odometry sensors of each of the subset of human-driven vehicles to determine a set of vehicle traces through the road segment for the subset of human-driven vehicles, each vehicle trace of the set including positional acceleration and deacceleration values determined from sensor data of the respective human-driven vehicle;

determining braking and acceleration patterns of human-driven vehicles traversing the road segment based on the positional acceleration and deacceleration values;

based at least in part on the set of vehicle traces and the determined braking and accelerating patterns, generating a set of right-of-way rules for autonomous or semi-autonomous vehicles driving through the road segment to merge onto or off of a freeway, the set of right-of-way rules indicating when an autonomous or semi-autonomous vehicle traversing the road segment is to yield to another vehicle in a competing road segment;

performing a lookup of a database that stores the set of autonomous driving maps, to identify an autonomous map of the set that includes the road segment;

determining whether the determined set of right-of-way rules for the road segment match an existing set of right-of-way rules previously determined for the road segment of the identified autonomous driving map; and

modifying the identified autonomous driving map based on the generated set of right-of-way rules for the road segment when the generated set of right-of-way rules for the road segment are determined to not match the existing set of right-of-way rules; and

controlling an autonomous vehicle or a semi-autonomous vehicle using the generated set of right-of-way rules.

9 . The non-transitory computer readable medium of claim 8 , wherein the executed instructions cause the computing system to generate the set of right-of-way rules by inputting vehicle trace data corresponding to one or more vehicle traces of the set of vehicle traces into a machine learning model trained on aggregate driving behavior data, the machine learning model processing the vehicle trace data to output the set of right-of-way rules.

10 . The non-transitory computer readable medium of claim 8 , wherein the executed instructions cause the computing system to superimpose the set of vehicle traces on map data to further determine the set of right-of-way rules.

11 . The non-transitory computer readable medium of claim 8 , wherein the identified autonomous driving map includes (i) map data obtained from one or more mapping vehicles operating through the road segment, and (ii) labeled autonomous driving rules that correspond to at least one of signage or signals along the road segment.

12 . The non-transitory computer readable medium of claim 8 , wherein the executed instructions cause the computing system to process vehicle trace data based on sensor data from human-driven vehicles operating throughout the region to determine right-of-way rules for each road segment of a road network of the region, and wherein the executed instructions further cause the computing system to:

generate a set of autonomous driving maps for autonomous or semi-autonomous vehicles driving throughout the road network based on the right-of-way rules determined for each road segment of the road network.

13 . The non-transitory computer readable medium of claim 8 , wherein modifying the identified autonomous driving map includes labelling or relabeling the identified autonomous driving map based on the generated set of right-of-way rules.

14 . The non-transitory computer readable medium of claim 8 , wherein modifying the identified autonomous driving map includes replacing a label for one or more existing right of way rules that are incorrect.

15 . A computer-implemented method performed by one or more processors and comprising:

communicating with human-driven vehicles operating throughout a region;

automatically labeling a set of autonomous driving maps utilized by autonomous or semi-autonomous vehicles operating in the region, to reflect accurate and up-to-date right-of-way rules for one or more road segments of the region, by:

receiving, over one or more networks, sensor data comprising one or more control inputs and one or more vehicle motion values from a subset of the human-driven vehicles operating through a road segment within the region, the sensor data being generated by a set of odometry sensors of each of the subset of human-driven vehicles, the set of odometry sensors comprising a positioning system, a braking input sensor, and a steering input sensor of each of the subset of human-driven vehicles;

processing the sensor data generated by the set of odometry sensors of each of the subset of human-driven vehicles to determine a set of vehicle traces through the road segment for the subset of human-driven vehicles, each vehicle trace of the set including positional acceleration and deacceleration values determined from sensor data of the respective human-driven vehicle;

determining braking and acceleration patterns of human-driven vehicles traversing the road segment based on the positional acceleration and deacceleration values;

based at least in part on the set of vehicle traces and the determined braking and accelerating patterns, generating a set of right-of-way rules for autonomous or semi-autonomous vehicles driving through the road segment to merge onto or off of a freeway, the set of right-of-way rules indicating when an autonomous or semi-autonomous vehicle traversing the road segment is to yield to another vehicle in a competing road segment;

performing a lookup of a database that stores the set of autonomous driving maps, to identify an autonomous map of the set that includes the road segment;

determining whether the determined set of right-of-way rules for the road segment match an existing set of right-of-way rules previously determined for the road segment of the identified autonomous driving map; and

modifying the identified autonomous driving map based on the generated set of right-of-way rules for the road segment when the generated set of right-of-way rules for the road segment are determined to not match the existing set of right-of-way rules; and

controlling an autonomous vehicle or a semi-autonomous vehicle using the generated set of right-of-way rules.

16 . The computer-implemented method of claim 15 , wherein generating the set of right-of-way rules includes inputting vehicle trace data corresponding to one or more vehicle traces of the set of vehicle traces into a machine learning model trained on aggregate driving behavior data, the machine learning model processing the vehicle trace data to output the set of right-of-way rules.

17 . The computer-implemented method of claim 16 , further comprising superimposing the set of vehicle traces on map data to further determine the set of right-of-way rules.

18 . The computer-implemented method of claim 15 , wherein the identified autonomous driving map includes (i) map data obtained from one or more mapping vehicles operating through the road segment, and (ii) labeled autonomous driving rules that correspond to at least one of signage or signals along the road segment.

19 . The computer-implemented method of claim 15 , further comprising processing vehicle trace data based on sensor data from human-driven vehicles operating throughout the region to determine right-of-way rules for each road segment of a road network of the region, the method further comprising:

generating a set of autonomous driving maps for autonomous or semi-autonomous vehicles driving throughout the road network based on the right-of-way rules determined for each road segment of the road network.

20 . The computer-implemented method of claim 15 , wherein modifying the identified autonomous driving map includes labelling or relabeling the identified autonomous driving map based on the generated set of right-of-way rules, including replacing a label for one or more existing right of way rules that are incorrect.