US 2021/0269065 A1 · PERPENDICULAR CUT-IN DETECTION

Abstract

Techniques relating to detecting that a vehicle is likely to enter a lane region in front of another vehicle is described. In an example, computing device(s) onboard a first vehicle can receive sensor data associated with an environment of the first vehicle. Based at least in part on an attribute determined from the sensor data, the computing device(s) can determine that a second vehicle proximate the first vehicle is predicted to enter a lane region in front of the first vehicle from a different direction of travel (e.g., by performing a u-turn, n-point turn, exiting a parting spot or driveway, etc.). In an example, the computing device(s) can determine an instruction for controlling the first vehicle based at least in part on the determining that the second vehicle is predicted to enter the lane region in front of the first vehicle.

Claims20

Dependent claims

A method comprising:

receiving sensor data associated with an environment of a first vehicle;
detecting, based at least in part on the sensor data, a second vehicle proximate the first vehicle, wherein the second vehicle is substantially perpendicular to the first vehicle;
determining, based at least in part on the sensor data, an attribute associated with the environment or the second vehicle that is indicative of whether the second vehicle is going to enter a lane region in front of the first vehicle;
determining, based at least in part on the attribute, an indication whether the second vehicle will enter the lane region in front of the first vehicle;
and
determining an instruction for controlling the first vehicle based at least in part on the indication.

3 more elements

One or more non-transitory computer-readable media storing instructions, that when executed by one or more processors, cause the one or more processors to perform operations comprising:

receiving sensor data associated with an environment of a first vehicle;
converting the sensor data into a top-down representation of the environment;
inputting the top-down representation into a machine-trained model;
determining, based at least in part on inputting the top-down representation into the machine-trained model, that a second vehicle proximate the first vehicle is predicted to enter a lane region in front of the first vehicle;
and
determining an instruction for controlling the first vehicle based at least in part on determining that the second vehicle proximate the first vehicle is predicted to enter the lane region in front of the first vehicle.

3 more elements

Dependencies are inferred from the claim text.

Perpendicular cut-in detection

Life of this patent

Perpendicular cut-in detection

Life of this patent

Abstract

Claims20