US 11,884,282 B1Granted

Machine-learned model variance compensation

AssigneeZoox, Inc.

InventorEthan Miller Pronovost

Life of this patent

Estimating the term…

Loading patent…

Abstract

Techniques for increasing performance of machine-learned models while conserving computational resources generally required by ensemble machine-learning methods are described herein. The techniques may include determining multiple views of a scene that is to be input into a machine-learned model. In some examples, a scene data input may be rotated by 90, 180, and 270 degrees to generate four scene inputs (e.g., 0-, 90-, 180-, and 270-degree rotated inputs) that can be passed through the machine-learned model and the results per scene can be aggregated to determine a final prediction/decision. Similarly, scene inputs may be shifted, reflected, translated, and/or the like before being input into the machine-learned model. The predictions may be associated with one or more objects in the environment that are represented in the scenes.

Claims20

Dependent claims

A system comprising:

one or more processors;
and
one or more non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the system to perform operations comprising:
receiving sensor data from a sensor associated with a vehicle in an environment, the sensor data representing an object in the environment;
determining, based at least in part on the sensor data, first top-down data representing the environment, wherein the first top-down data is associated with a first rotation;
determining, based at least in part on the sensor data, second top-down data representing the environment, wherein the second top-down data is associated with a second rotation that is different than the first rotation;
inputting the first top-down data and the second top-down data into a machine-learned model;
receiving, from the machine-learned model and based on the first top-down data, a first output associated with the object;
receiving, from the machine-learned model and based on the second top-down data, a second output associated with the object;
determining, based at least in part on the first output and the second output, an aggregate output;
and
controlling a trajectory of the vehicle based at least in part on the aggregate output.

9 more elements

Dependencies are inferred from the claim text.