Approaches for encoding environmental information

1. A computer-implemented method comprising:

determining, by a computing system, sensor data captured by at least one sensor of a vehicle while navigating an environment over a period of time;

determining, by the computing system, information describing one or more agents associated with the environment during the period of time based at least in part on the captured sensor data;

generating, by the computing system, a schema-based encoding describing the environment during the period of time based at least in part on the determined information and an application of a scenario schema to the information describing the one or more agents associated with the environment, wherein the scenario schema is associated with a set of elements that include at least a first element to represent the one or more agents and a second element to represent motion information associated with the one or more agents, and wherein the schema-based encoding provides a structured representation of the environment during the period of time;

comparing, by the computing system, the schema-based encoding associated with the environment with a plurality of other schema-based encodings that provide structured representations of different environments;

determining, by the computing system, that a set of the plurality of other schema-based encodings satisfy a threshold similarity to the schema-based encoding associated with the environment;

determining, by the computing system, scenario information associated with the set of the plurality of other schema-based encodings based at least in part on the threshold similarity determined between the schema-based encoding and the set of the plurality of other schema-based encodings, wherein scenario information associated with a particular schema-based encoding of a particular environment describes one or more scenarios that may be encountered by the vehicle while navigating one or more road segments in the particular environment; and

causing, by the computing system, instructions to be provided for modifying an operation of the vehicle while navigating the environment based at least in part on the scenario information associated with the set of the plurality of other schema-based encodings.

2. The computer-implemented method of claim 1 , wherein the information includes at least one of a type of each of the one or more agents that were present within the environment during the period of time, respective motion information for each agent, information identifying the one or more agents that would potentially interact with the vehicle, and metadata associated with each of the one or more agents.

3. The computer-implemented method of claim 2 , wherein an agent corresponds to a static or dynamic object that was detected in the environment during the period of time.

4. The computer-implemented method of claim 2 , wherein motion information for an agent includes one or more of: a trajectory of the agent, a distance between the agent and the vehicle, a velocity at which the agent is traveling, a direction of travel associated with the agent, a geographic location associated with the agent, and a semantic location associated with the agent.

5. The computer-implemented method of claim 2 , wherein the metadata includes one or more of: map features associated with the environment, information indicating whether the environment is within a specific zone, contextual information, and information describing weather conditions.

6. The computer-implemented method of claim 1 , further comprising:

applying the scenario schema to the information describing the one or more agents, the scenario schema being associated with a third element to represent whether an agent that was detected by a vehicle may potentially interact with the vehicle during the period of time, and a fourth element to represent metadata describing the navigated environment.

7. The computer-implemented method of claim 1 , wherein a representation of the environment is able to be regenerated based at least in part on the schema-based encoding.

8. The computer-implemented method of claim 1 , wherein the schema-based encoding further includes information describing the vehicle that captured the sensor data, the information including motion information associated with the vehicle and information describing a perspective of the vehicle while the sensor data was captured.

9. The computer-implemented method of claim 1 , further comprising:

generating, by the computing system, a different schema-based encoding describing the environment during the period of time from a perspective of a selected one of the one or more agents that were detected in the environment, wherein the selected agent is different from the vehicle.

10. 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:

determining sensor data captured by at least one sensor of a vehicle while navigating an environment over a period of time;

determining information describing one or more agents associated with the environment during the period of time based at least in part on the captured sensor data;

generating a schema-based encoding describing the environment during the period of time based at least in part on the determined information and an application of a scenario schema to the information describing the one or more agents associated with the environment, wherein the scenario schema is associated with a set of elements that include at least a first element to represent the one or more agents and a second element to represent motion information associated with the one or more agents, and wherein the schema-based encoding provides a structured representation of the environment during the period of time;

comparing the schema-based encoding associated with the environment with a plurality of other schema-based encodings that provide structured representations of different environments;

determining that a set of the plurality of other schema-based encodings satisfy a threshold similarity to the schema-based encoding associated with the environment;

determining scenario information associated with the set of the plurality of other schema-based encodings based at least in part on the threshold similarity determined between the schema-based encoding and the set of the plurality of other schema-based encodings, wherein scenario information associated with a particular schema-based encoding of a particular environment describes one or more scenarios that may be encountered by the vehicle while navigating one or more road segments in the particular environment; and

causing instructions to be provided for modifying an operation of the vehicle while navigating the environment based at least in part on the scenario information associated with the set of the plurality of other schema-based encodings.

11. The system of claim 10 , wherein the information includes at least one of a type of each of the one or more agents that were present within the environment during the period of time, respective motion information for each agent, information identifying the one or more agents that would potentially interact with the vehicle, and metadata associated with each of the one or more agents.

12. The system of claim 11 , wherein an agent corresponds to a static or dynamic object that was detected in the environment during the period of time.

13. The system of claim 11 , wherein motion information for an agent includes one or more of: a trajectory of the agent, a distance between the agent and the vehicle, a velocity at which the agent is traveling, a direction of travel associated with the agent, a geographic location associated with the agent, and a semantic location associated with the agent.

14. 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:

determining sensor data captured by at least one sensor of a vehicle while navigating an environment over a period of time;

determining information describing one or more agents associated with the environment during the period of time based at least in part on the captured sensor data;

generating a schema-based encoding describing the environment during the period of time based at least in part on the determined information and an application of a scenario schema to the information describing the one or more agents associated with the environment, wherein the scenario schema is associated with a set of elements that include at least a first element to represent the one or more agents and a second element to represent motion information associated with the one or more agents, and wherein the schema-based encoding provides a structured representation of the environment during the period of time;

comparing the schema-based encoding associated with the environment with a plurality of other schema-based encodings that provide structured representations of different environments;

determining that a set of the plurality of other schema-based encodings satisfy a threshold similarity to the schema-based encoding associated with the environment;

determining scenario information associated with the set of the plurality of other schema-based encodings based at least in part on the threshold similarity determined between the schema-based encoding and the set of the plurality of other schema-based encodings, wherein scenario information associated with a particular schema-based encoding of a particular environment describes one or more scenarios that may be encountered by the vehicle while navigating one or more road segments in the particular environment; and

causing instructions to be provided for modifying an operation of the vehicle while navigating the environment based at least in part on the scenario information associated with the set of the plurality of other schema-based encodings.

15. The non-transitory computer-readable storage medium of claim 14 , wherein the information includes at least one of a type of each of the one or more agents that were present within the environment during the period of time, respective motion information for each agent, information identifying the one or more agents that would potentially interact with the vehicle, and metadata associated with each of the one or more agents.

16. The non-transitory computer-readable storage medium of claim 15 , wherein an agent corresponds to a static or dynamic object that was detected in the environment during the period of time.

17. The non-transitory computer-readable storage medium of claim 15 , wherein motion information for an agent includes one or more of: a trajectory of the agent, a distance between the agent and the vehicle, a velocity at which the agent is traveling, a direction of travel associated with the agent, a geographic location associated with the agent, and a semantic location associated with the agent.