Systems and methods for detecting actors with respect to an autonomous vehicle

An autonomous vehicle system, comprising:

• a memory that stores a set of instructions;
• a primary perception system configured to:
• receive sensor data comprising a plurality of sensor data points as input;
• and
• in response to receipt of the sensor data as input, generate primary perception data representing a plurality of classifiable objects and a plurality of paths representing tracked motion of the plurality of classifiable objects, wherein each classifiable object is classified by the primary perception system as a predefined class of a plurality of predefined classes of objects;
• a secondary perception system configured to receive the sensor data comprising the plurality of sensor data points as input, and, in response to receipt of the sensor data as input:
• cluster a subset of the plurality of sensor data points of the sensor data to generate one or more sensor data point clusters representing a plurality of unclassified objects;
• and
• generate secondary path data representing tracked motion of the plurality of unclassified objects;
• and
• one or more processors which use the set of instructions to perform operations comprising:
• obtaining, by the one or more processors, the sensor data comprising the plurality of sensor data points;
• generating, by the primary perception system, the primary perception data representing the plurality of classifiable objects and the plurality of paths representing the tracked motion of the plurality of classifiable objects;
• clustering, by the secondary perception system, the subset of the plurality of sensor data points of the sensor data to generate the one or more sensor data point clusters representing the plurality of unclassified objects;
• generating, by the secondary perception system, the secondary path data representing the tracked motion of the plurality of unclassified objects;
• and
• determining, by the one or more processors, fused perception data representing the tracked motion of the plurality of classifiable objects and the tracked motion of one or more unclassifiable objects, wherein the one or more unclassifiable objects are identified by deduplicating the plurality of classifiable objects with the plurality of unclassified objects.

An autonomous vehicle, comprising:

• a memory that stores a set of instructions;
• and
• an autonomous vehicle computing system comprising:
• a primary perception system configured to:
• receive sensor data comprising a plurality of sensor data points as input;
• and
• in response to receipt of the sensor data as input, generate primary perception data representing a plurality of classifiable objects and a plurality of paths representing tracked motion of the plurality of classifiable objects, wherein each classifiable object is classified by the primary perception system as a predefined class of a plurality of predefined classes of objects;
• a secondary perception system configured to receive the sensor data comprising the plurality of sensor data points as input, and, in response to receipt of the sensor data as input:
• cluster a subset of the plurality of sensor data points of the sensor data to generate one or more sensor data point clusters representing a plurality of unclassified objects;
• and
• generate secondary path data representing tracked motion of the plurality of unclassified objects;
• and
• one or more processors which use the set of instructions to perform operations comprising:
• obtaining, by the one or more processors, the sensor data comprising the plurality of sensor data points;
• generating, by the primary perception system, the primary perception data representing the plurality of classifiable objects and the plurality of paths representing the tracked motion of the plurality of classifiable objects;
• clustering, by the secondary perception system, the subset of the plurality of sensor data points of the sensor data to generate the one or more sensor data point clusters representing the plurality of unclassified objects generating, by the secondary perception system, the secondary path data representing the tracked motion of the plurality of unclassified objects;
• and
• determining, by the one or more processors, fused perception data representing the tracked motion of the plurality of classifiable objects and the tracked motion of one or more unclassifiable objects, wherein the one or more unclassifiable objects are identified by deduplicating the plurality of classifiable objects with the plurality of unclassified objects.