Method and apparatus for self localization

A computer program product comprising at least one non-transitory computer-readable storage medium having computer-executable program code instructions stored therein, the computer-executable program code instructions comprising program code instructions to:

• receive sensor data from a vehicle traveling along a road segment, wherein the sensor data comprises first sensor data of one or more discrete objects in an environment from a first sensor and second sensor data of one or more continuous objects in the environment from a second sensor;
• determine a coarse location for the vehicle;
• identify one or more objects of the environment from the sensor data, wherein the one or more objects of the environment from the sensor data comprises at least one of one or more discrete objects from the first sensor data or one or more continuous objects from the second sensor data;
• compare the identified one or more discrete objects from the first sensor data and the identified one or more continuous objects from the second sensor data with corresponding ground truth objects;
• calculate an observation in response to the comparison of the identified one or more objects with the corresponding ground truth objects, wherein the calculated observation includes an accuracy of localization relative to the first sensor data of discrete objects in the environment and the second sensor data of continuous objects in the environment, wherein the calculated observation further includes an indication that the first sensor data has a relatively higher quality of object matching than the second sensor data;
• determine a location of the vehicle with a higher precision than the coarse location based, at least in part, on the calculated observation;
• and
• allocate resources of the apparatus based, at least in part, on the calculated observation, wherein causing the apparatus to allocate resources comprises causing the apparatus to prioritize the first sensor data from the first sensor over the second sensor data from the second sensor based, at least in part, on the calculated observation.

A method comprising:

• receiving sensor data from a vehicle traveling along a road segment, wherein the sensor data comprises first sensor data of one or more discrete objects in an environment from a first sensor and second sensor data of one or more continuous objects in the environment from a second sensor;
• identifying one or more objects of the environment from the sensor data, wherein the one or more objects of the environment from the sensor data comprises at least one of one or more discrete objects from the first sensor data or one or more continuous objects from the second sensor data;
• determining a coarse location of the vehicle;
• comparing the identified one or more discrete objects from the first sensor data and the identified one or more continuous objects from the second sensor data with corresponding ground truth objects;
• calculating an observation in response to the comparison of the identified one or more objects with the corresponding ground truth objects, wherein the calculated observation includes an accuracy of localization relative to the first sensor data of discrete objects in the environment and the second sensor data of continuous objects in the environment, wherein the calculated observation further includes an indication that the first sensor data has a relatively higher quality of object matching than the second sensor data;
• determining a location of the vehicle with a higher precision than the coarse location based, at least in part, on the calculated observation;
• and
• allocating resources of the apparatus based, at least in part, on the calculated observation, wherein causing the apparatus to allocate resources comprises causing the apparatus to prioritize the first sensor data from the first sensor over the second sensor data from the second sensor based, at least in part, on the calculated observation.