Dual-measurement data structure for autonomous vehicles

A non-transitory computer-readable storage medium for use in conjunction with an electronic device, the computer-readable storage medium storing program instructions, wherein, when executed by the computer system, the program instructions cause the computer system to perform one or more operations comprising:

• measuring, using a first sensor, first sensor information associated with a first field of view and a first timestamp and, using a second sensor, second sensor information associated with a second field of view and a second timestamp, wherein the first sensor information and the second sensor information are associated with operation of a vehicle having one or more non-retractable wheels in contact with a surface, and
• wherein the second sensor comprises a radar sensor and the second sensor uses a different sensing technique than the first sensor, and
• wherein the measuring comprises:
• determining, using a pretrained predictive model, a predefined or predetermined annotation associated with the first sensor information, wherein the first sensor information is an input of the pretrained predictive model and the predefined or predetermined annotation is an output of the pretrained predictive model, and wherein the predefined or predetermined annotation is associated with an object that is common to the first field of view and the second field of view;
• and
• storing, in memory in or associated with the electronic device, the first sensor information, the second sensor information, and the predefined or predetermined annotation, wherein the predefined or predetermined annotation is stored at a memory location associated with the second sensor information.

A method for generating a dataset, comprising:

• by an electronic device:
• measuring, using a first sensor, first sensor information associated with a first field of view and a first timestamp and, using a second sensor, second sensor information associated with a second field of view and a second timestamp, wherein the first sensor information and the second sensor information are associated with operation of a vehicle having one or more non-retractable wheels in contact with a surface, and
• wherein the second sensor comprises a radar sensor and the second sensor uses a different sensing technique than the first sensor, and
• wherein the measuring comprises:
• determining, using a pretrained predictive model, a predefined or predetermined annotation associated with the first sensor information, wherein the first sensor information is an input of the pretrained predictive model and the predefined or predetermined annotation is an output of the pretrained predictive model, and wherein the predefined or predetermined annotation is associated with an object that is common to the first field of view and the second field of view;
• and
• generating the dataset by storing, in memory in or associated with the electronic device, the first sensor information, the second sensor information, and the predefined or predetermined annotation, wherein the predefined or predetermined annotation is stored at a memory location associated with the second sensor information.