Automated cut-in identification and classification
Example embodiments relate to a method for cut-in identification and classification. An example embodiment includes a obtaining operational data about one or more vehicles; based on the operational data, identifying the presence of one or more cut-ins within the operational data; extracting, from the operational data, cut-in data that depicts one or more of the cut-ins identified within the operational data; and, based on the extracted cut-in data, training a model for controlling an autonomous vehicle. Identifying the presence of a given cut-in includes: determining that at least one vertex of a bounding box surrounding a vehicle was located more than a threshold distance within a lane being navigated by a given vehicle; and determining that the ability of the given vehicle to maintain its course and speed was impeded by the presence of the particular additional vehicle within the lane.
1. A method comprising:
obtaining operational data about one or more vehicles;
based on the operational data, identifying the presence of one or more cut-ins within the operational data;
extracting, from the operational data, cut-in data that depicts one or more of the cut-ins identified within the operational data;
based on the extracted cut-in data, training a model for controlling an autonomous vehicle, wherein training the model for controlling the autonomous vehicle based on the extracted cut-in data comprises:
determining one or more scores for the autonomous vehicle's reaction to one or more of the cut-ins identified within the operational data, wherein the autonomous vehicle's reaction to one or more of the cut-ins identified within the operational data is determined by a first model for controlling the autonomous vehicle; and
based on the one or more scores, selecting a new model from a plurality of such models to replace the first model; and
based on the model for controlling the autonomous vehicle, generating and implementing a control output to operate the autonomous vehicle.
2. The method of claim 1 , further comprising, based on the extracted cut-in data, classifying one or more of the cut-ins identified within the operational data.
3. The method of claim 2 , wherein classifying one or more of the cut-ins identified within the operational data comprises classifying one or more of the cut-ins identified within the operational data as at least one of an aborted cut-in, a cut-through, or a zipper cut-in.
4. The method of claim 2 , wherein classifying one or more of the cut-ins identified within the operational data comprises classifying one or more of the cut-ins identified within the operational data based on at least one of: a degree to which a vehicle slowed down due to the cut-in, a timing of an action taken by a vehicle in reaction to the cut-in relative to a timing at which the cut-in occurred, or a duration of a period that a vehicle followed a cut-in agent at a distance less than a threshold safety distance following a cut-in.
5. The method of claim 1 , wherein the one or more scores comprise human-interpretable metrics for the quality of the first model with respect to efficiency or vehicle wear, wherein training the model for controlling the autonomous vehicle based on the extracted cut-in data further comprises, based on the one or more scores, updating the first model, and wherein updating the first model comprises using the one or more scores to select whether to retain the first model, replicate the first model, fold the first model, discard the first model, combine the first model with another model in the plurality of models, or set a weight of the first model relative to other models in the plurality of models.
6. The method of claim 1 , wherein determining the one or more scores comprises generating a score based on at least one of: a degree to which the autonomous vehicle slowed down due to the particular cut-in, a timing of an action taken by the autonomous vehicle in reaction to the particular cut-in relative to a timing at which the particular cut-in occurred, or a duration of a period that the autonomous vehicle followed a cut-in agent at a distance less than a threshold safety distance following the particular cut-in.
7. The method of claim 1 , wherein training the model for controlling the autonomous vehicle based on the extracted cut-in data further comprises, based on the one or more scores, updating the first model.
8. A non-transitory computer readable medium storing instructions that, when executed by one or more processors of a computing device, cause the computing device to perform operations comprising:
obtaining operational data about one or more vehicles;
based on the operational data, identifying the presence of one or more cut-ins within the operational data;
extracting, from the operational data, cut-in data that depicts one or more of the cut-ins identified within the operational data;
based on the extracted cut-in data, training a model for controlling an autonomous vehicle, wherein training the model for controlling the autonomous vehicle based on the extracted cut-in data comprises:
determining one or more scores for the autonomous vehicle's reaction to one or more of the cut-ins identified within the operational data, wherein the autonomous vehicle's reaction to one or more of the cut-ins identified within the operational data is determined by a first model for controlling the autonomous vehicle; and
based on the one or more scores, selecting a new model from a plurality of such models to replace the first model; and
based on the model for controlling the autonomous vehicle, generating and implementing a control output to operate the autonomous vehicle.
9. The non-transitory computer readable medium of claim 8 , wherein the operations further comprise, based on the extracted cut-in data, classifying one or more of the cut-ins identified within the operational data.
10. The non-transitory computer readable medium of claim 9 , wherein classifying one or more of the cut-ins identified within the operational data comprises classifying one or more of the cut-ins identified within the operational data as at least one of an aborted cut-in, a cut-through, or a zipper cut-in.
11. The non-transitory computer readable medium of claim 9 , wherein classifying one or more of the cut-ins identified within the operational data comprises classifying one or more of the cut-ins identified within the operational data based on at least one of: a degree to which a vehicle slowed down due to the cut-in, a timing of an action taken by a vehicle in reaction to the cut-in relative to a timing at which the cut-in occurred, or a duration of a period that a vehicle followed a cut-in agent at a distance less than a threshold safety distance following a cut-in.
12. The non-transitory computer readable medium of claim 8 , wherein the one or more scores comprise human-interpretable metrics for the quality of the first model with respect to efficiency or vehicle wear, wherein training the model for controlling the autonomous vehicle based on the extracted cut-in data further comprises, based on the one or more scores, updating the first model, and wherein updating the first model comprises using the one or more scores to select whether to retain the first model, replicate the first model, fold the first model, discard the first model, combine the first model with another model in the plurality of models, or set a weight of the first model relative to other models in the plurality of models.
13. The non-transitory computer readable medium of claim 8 , wherein determining the one or more scores comprises generating a score based on at least one of: a degree to which the autonomous vehicle slowed down due to the particular cut-in, a timing of an action taken by the autonomous vehicle in reaction to the particular cut-in relative to a timing at which the particular cut-in occurred, or a duration of a period that the autonomous vehicle followed a cut-in agent at a distance less than a threshold safety distance following the particular cut-in.
14. The non-transitory computer readable medium of claim 8 , wherein training the model for controlling the autonomous vehicle based on the extracted cut-in data further comprises, based on the one or more scores, updating the first model.
15. A system comprising: one or more processing units; and
a non-transitory computer-readable medium storing at least computer-executable instructions that, when executed by the one or more processing units, cause the one or more processing units to perform operations comprising:
obtaining operational data about one or more vehicles;
based on the operational data, identifying the presence of one or more cut-ins within the operational data;
extracting, from the operational data, cut-in data that depicts one or more of the cut-ins identified within the operational data;
based on the extracted cut-in data, training a model for controlling an autonomous vehicle, wherein training the model for controlling the autonomous vehicle based on the extracted cut-in data comprises:
determining one or more scores for the autonomous vehicle's reaction to one or more of the cut-ins identified within the operational data, wherein the autonomous vehicle's reaction to one or more of the cut-ins identified within the operational data is determined by a first model for controlling the autonomous vehicle; and
based on the one or more scores, selecting a new model from a plurality of such models to replace the first model; and
based on the model for controlling the autonomous vehicle, generating and implementing a control output to operate the autonomous vehicle.
16. The system of claim 15 , wherein the operations further comprise, based on the extracted cut-in data, classifying one or more of the cut-ins identified within the operational data.
17. The system of claim 16 , wherein classifying one or more of the cut-ins identified within the operational data comprises classifying one or more of the cut-ins identified within the operational data as at least one of an aborted cut-in, a cut-through, or a zipper cut-in.
18. The system of claim 16 , wherein classifying one or more of the cut-ins identified within the operational data comprises classifying one or more of the cut-ins identified within the operational data based on at least one of: a degree to which a vehicle slowed down due to the cut-in, a timing of an action taken by a vehicle in reaction to the cut-in relative to a timing at which the cut-in occurred, or a duration of a period that a vehicle followed a cut-in agent at a distance less than a threshold safety distance following a cut-in.
19. The system of claim 15 , wherein the one or more scores comprise human-interpretable metrics for the quality of the first model with respect to efficiency or vehicle wear, wherein training the model for controlling the autonomous vehicle based on the extracted cut-in data further comprises, based on the one or more scores, updating the first model, and wherein updating the first model comprises using the one or more scores to select whether to retain the first model, replicate the first model, fold the first model, discard the first model, combine the first model with another model in the plurality of models, or set a weight of the first model relative to other models in the plurality of models.
20. The system of claim 15 , wherein determining the one or more scores comprises generating a score based on at least one of: a degree to which the autonomous vehicle slowed down due to the particular cut-in, a timing of an action taken by the autonomous vehicle in reaction to the particular cut-in relative to a timing at which the particular cut-in occurred, or a duration of a period that the autonomous vehicle followed a cut-in agent at a distance less than a threshold safety distance following the particular cut-in.