US 11,628,848 B2 · Systems and methods for training a neural network for estimating a trajectory of a vehicle

Abstract

Systems and methods for training a neural network for estimating a trajectory of a vehicle are disclosed. In one embodiment, a system includes one or more processors, and a non-transitory computer-readable medium storing computer-readable instructions. The computer-readable instructions cause the one or more processors to receive sensor data of a plurality of examples from a plurality of vehicle sensors, input the sensor data into a sensor data neural network to generate a sensor data intermediate space and receive structured data of the plurality of examples. The computer-readable instructions cause the one or more processors to input the structured data into a structured data neural network to generate a structured data intermediate space, calculate a first loss between the sensor data intermediate space and the structured data intermediate space using a first loss function, and provide the first loss to the sensor data neural network and the structured data neural network.

Claims16

Dependent claims

A system for training a neural network for estimating a trajectory of a vehicle, the system comprising:

one or more processors;
and
a non-transitory computer-readable medium storing computer-readable instructions that, when executed by the one or more processors, cause the one or more processors to:
receive sensor data of a plurality of vehicle maneuver examples from a plurality of vehicle sensors;
input the sensor data into a sensor data neural network to generate a sensor data intermediate space;
receive structured data of the plurality of vehicle maneuver examples;
input the structured data into a structured data neural network to generate a structured data intermediate space;
calculate a first loss between the sensor data intermediate space and the structured data intermediate space using a first loss function;
provide the first loss to the sensor data neural network and the structured data neural network;
input the structured data intermediate space data into a trajectory estimation neural network to generate one or more vehicle trajectories;
and
control the vehicle according to the one or more vehicle trajectories.

9 more elements

A method for training a neural network for estimating a trajectory of a vehicle, the method comprising:

receiving sensor data of a plurality of vehicle maneuver examples from a plurality of vehicle sensors;
inputting the sensor data into a sensor data neural network to generate a sensor data intermediate space;
receiving structured data of the plurality of vehicle maneuver examples;
inputting the structured data into a structured data neural network to generate a structured data intermediate space;
calculating a first loss between the sensor data intermediate space and the structured data intermediate space using a first loss function;
and
providing the first loss to the sensor data neural network and the structured data neural network;
inputting the structured data intermediate space data into a trajectory estimation neural network to generate one or more vehicle trajectories;
and
controlling the vehicle according to the one or more vehicle trajectories.

7 more elements

Dependencies are inferred from the claim text.

Systems and methods for training a neural network for estimating a trajectory of a vehicle

Life of this patent

Systems and methods for training a neural network for estimating a trajectory of a vehicle

Life of this patent

Abstract

Claims16