Identifying objects for display in a situational-awareness view of an autonomous-vehicle environment

A system, comprising:

• a sensor array of a vehicle;
• one or more non-transitory computer-readable storage media including instructions;
• and
• one or more processors coupled to the one or more non-transitory computer-readable storage media, the one or more processors configured to execute the instructions to:
• receive sensor data corresponding to an external environment of the vehicle, wherein the sensor data is captured by the sensor array of the vehicle and comprises a plurality of pre-classified point sets, wherein each pre-classified point set comprises a plurality of coordinates and is associated with a confidence score and an object classification determined by a processor of the sensor array;
• determine whether a first pre-classified point set in the plurality of point sets has a first confidence score that satisfies a predetermined condition, wherein the first pre-classified point set comprises a first plurality of coordinates and is associated with a first object classification determined by the processor of the sensor array;
• in response to a determination that the first confidence score of the first pre-classified point set fails to satisfy the predetermined condition, generate an updated object classification for the first pre-classified point set by using a machine-learning model to process at least the first plurality of coordinates, the first object classification, and secondary data;
• and
• send instructions to display a first visual representation associated with the updated object classification to represent the first pre-classified point set.

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

• receive sensor data corresponding to an external environment of a vehicle, wherein the sensor data is captured by a sensor array of the vehicle and comprises a plurality of pre-classified point sets, wherein each pre-classified point set comprises a plurality of coordinates and is associated with a confidence score and an object classification determined by a processor of the sensor array;
• determine whether a first pre-classified point set in the plurality of point sets has a first confidence score that satisfies a predetermined condition, wherein the first pre-classified point set comprises a first plurality of coordinates and is associated with a first object classification determined by the processor of the sensor array;
• in response to a determination that the first confidence score of the first pre-classified point set fails to satisfy the predetermined condition, generate an updated object classification for the first pre-classified point set by using a machine-learning model to process at least the first plurality of coordinates, the first object classification, and secondary data;
• and
• send instructions to display a first visual representation associated with the updated object classification to represent the first pre-classified point set.