US 12,741,655 B1Granted

Behavior modeling based on relative position data and absolute yaw data

AssigneeZoox, Inc.

InventorsNoureldin Ehab Hendy, Ethan Miller Pronovost, Peter Scott Schleede

Life of this patent

Estimating the term…

Loading patent…

Abstract

Techniques for performing prediction based on relative lateral and/or longitudinal position data are described herein. A vehicle may detect an object in an environment. The vehicle may generate an embedding associated with the object and input the embedding into a machine-learned model. The machine-learned model may generate a rotation matrix based on the lateral or longitudinal of object(s), and apply the rotation matrix to the embedding. Based on modifying the embedding (or generating a modified embedding), the attention layer of the machine-learned model may perform attention on the modified embedding and respond by outputting output data. The vehicle may rotate the output data (or generate rotated output data) which may be used by one or more machine-learned models to predict object behavior, generate vehicle actions, etc.

Claims20

Dependent claims

A system comprising:

one or more processors;
and
one or more non-transitory computer-readable media storing computer-executable instructions that, when executed, cause the system to perform operations comprising:
receiving, from a sensor device of a vehicle, sensor data of an environment;
generating, based at least in part on the sensor data, a first embedding associated with a first object;
generating, based at least in part on the sensor data, a second embedding associated with a second object;
generating, based at least in part on a position of the first object, a first matrix;
generating, based at least in part on a heading of the first object, a second matrix;
generating, based at least in part on a position of the second object, a third matrix;
determining, based at least in part on the first matrix, the second matrix, and the third matrix, a first modified embedding associated with the first embedding and a second modified embedding associated with the second embedding;
inputting the first modified embedding and the second modified embedding into an attention layer of a machine-learned model;
and
controlling the vehicle based at least in part on an output of the machine-learned model.

10 more elements

Dependencies are inferred from the claim text.

Facts

Application: 19/096,580Filed 31 Mar 2025 · continuation in part
Priority: 17 Sep 2024
Granted: 22 Sep 2026
Term ends: Not estimatedThe source records don’t support an estimate.

Classification6 codes

B60W 50/00
Details of control systems for road vehicle drive control not related to
B60W 60/001
Drive control systems specially adapted for autonomous road vehicles: planning or execution of driving tasks
B60W 2050/0028
Control system elements or transfer functions: mathematical models, e.g. for simulation
B60W 2554/80
Input parameters relating to objects: spatial relation or speed relative to objects