Systems and methods for encoding and searching scenario information

1. A computer-implemented method comprising:

receiving, by a computing system, a query specifying at least one example scenario;

encoding, by the computing system, at least one representation of the at least one example scenario based on the query to produce at least one encoded representation;

generating, by the computing system, an embedding of the at least one representation of the at least one example scenario based on the at least one encoded representation;

identifying, by the computing system, at least one scenario that is similar to the at least one example scenario based at least in part on a determination that a threshold distance within a vector space between the embedding of the at least one representation of the at least one example scenario and an embedding representing the at least one scenario is satisfied; and

providing, by the computing system, information describing the at least one identified scenario in response to the query.

2. The computer-implemented method of claim 1 , wherein the embedding of the at least one representation of the at least one example scenario is generated within the vector space, and the embedding representing the at least one scenario is included within the vector space.

3. The computer-implemented method of claim 1 , wherein the identifying the at least one scenario further comprises:

determining, by the computing system, a distance between the embedding of the at least one representation of the at least one example scenario and the embedding representing the at least one scenario based on cosine similarity, wherein the distance satisfies the threshold distance.

4. The computer-implemented method of claim 1 , wherein the identifying the at least one scenario comprises:

determining, by the computing system, that the threshold distance between the embedding representing the at least one scenario and the embedding representing the at least one example scenario is less than a threshold distance between the embedding representing the at least one example scenario and an additional embedding representing an additional scenario.

5. The computer-implemented method of claim 1 , wherein the query identifies the at least one example scenario based on an identifier that references image data captured by one or more vehicles and a timestamp identifying particular image data that represents the at least one example scenario.

6. The computer-implemented method of claim 1 , wherein the image data is based on multiple images associated with the at least one example scenario that are captured by the one or more vehicles over a period of time.

7. The computer-implemented method of claim 6 , wherein the image data is a raster of the at least one example scenario that includes:

at least one trajectory associated with the one or more vehicles;

one or more respective trajectories associated with one or more agents; and

map data.

8. The computer-implemented method of claim 7 , wherein the one or more agents are distinguished based on pre-defined colors and the one or more respective trajectories associated with the one or more agents are represented based on different grades of the pre-defined colors.

9. The computer implemented method of claim 8 , wherein the at least one trajectory and the one or more respective trajectories are based on the period of time.

10. The computer-implemented method of claim 7 , further comprising:

training, by the computing system, a machine learning model with an anchor representation comprising a first encoded image representing a scenario, a positive representation comprising a second encoded image representing a scenario that has a threshold level of similarity to the anchor representation, and a negative representation comprising a third encoded image representation of a scenario that does not have the threshold level of similarity to the anchor representation.

11. The computer-implemented method of claim 10 , wherein, subsequent to training the machine learning model, the method further comprises:

arranging, by the computing system, the first encoded image representing the scenario within a vector space that includes the second encoded image and the third encoded image, wherein a first threshold distance between the first encoded image and the second encoded image within the vector space is less than a second threshold distance between the first encoded image and the third encoded image within the vector space.

12. A system comprising:

at least one processor; and

a memory storing instructions that, when executed by the at least one processor, cause the system to perform:

receiving a query specifying at least one example scenario;

encoding at least one representation of the at least one example scenario based on the query to produce at least one encoded representation;

generating an embedding of the at least one representation of the at least one example scenario based on the at least one encoded representation;

identifying at least one scenario that is similar to the at least one example scenario based at least in part on a determination that a threshold distance within a vector space between the embedding of the at least one representation of the at least one example scenario and an embedding representing the at least one scenario is satisfied; and

providing information describing the at least one identified scenario in response to the query.

13. The system of claim 12 , wherein the embedding of the at least one representation of the at least one example scenario is generated within the vector space, and the embedding representing the at least one scenario is included within the vector space.

14. The system of claim 12 , wherein the identifying the at least one scenario comprises:

determining a distance between the embedding of the at least one representation of the at least one example scenario and the embedding representing the at least one scenario based on cosine similarity, wherein the distance satisfies the threshold distance.

15. The system of claim 12 , wherein the identifying the at least one scenario comprises:

determining that the threshold distance between the embedding representing the at least one scenario and the embedding representing the at least one example scenario is less than a threshold distance between the embedding representing the at least one example scenario and an additional embedding representing an additional scenario.

16. The system of claim 12 , wherein the query identifies the at least one example scenario based on an identifier that references image data captured by one or more vehicles and a timestamp identifying particular image data that represents the at least one example scenario.

17. A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform a method comprising:

receiving a query specifying at least one example scenario;

encoding at least one representation of the at least one example scenario based on the query to produce at least one encoded representation;

generating an embedding of the at least one representation of the at least one example scenario based on the at least one encoded representation;

identifying at least one scenario that is similar to the at least one example scenario based at least in part on a determination that a threshold distance within a vector space between the embedding of the at least one representation of the at least one example scenario and an embedding representing the at least one scenario is satisfied; and

providing information describing the at least one identified scenario in response to the query.

18. The non-transitory computer-readable storage medium of claim 17 , wherein the embedding of the at least one representation of the at least one example scenario is generated within the vector space, and the embedding representing the at least one scenario is included within the vector space.

19. The non-transitory computer-readable storage medium of claim 17 , wherein the identifying the at least one scenario comprises:

determining a distance between the embedding of the at least one representation of the at least one example scenario and the embedding representing the at least one scenario based on cosine similarity, wherein the distance satisfies the threshold distance.

20. The non-transitory computer-readable storage medium of claim 17 , wherein the identifying the at least one scenario comprises:

determining that the threshold distance between the embedding representing the at least one scenario and the embedding representing the at least one example scenario is less than a threshold distance between the embedding representing the at least one example scenario and an additional embedding representing an additional scenario.