US 10,474,964 B2Granted

Training algorithm for collision avoidance

AssigneeFord Global Technologies, LLC

InventorsAshley Elizabeth Micks, Jinesh J Jain, Harpreetsingh Banvait, Kyu Jeong Han

Life of this patent

Estimating the term…

Loading patent…

Abstract

A machine learning model is trained by defining a scenario including models of vehicles and a typical driving environment. A model of a subject vehicle is added to the scenario and sensor locations are defined on the subject vehicle. A perception of the scenario by sensors at the sensor locations is simulated. The scenario further includes a model of a lane-splitting vehicle. The location of the lane-splitting vehicle and the simulated outputs of the sensors perceiving the scenario are input to a machine learning algorithm that trains a model to detect the location of a lane-splitting vehicle based on the sensor outputs. A vehicle controller then incorporates the machine learning model and estimates the presence and/or location of a lane-splitting vehicle based on actual sensor outputs input to the machine learning model.

Claims18

Dependent claims

A method comprising:

defining, by a computer system, a three dimensional (3D) model including a road, buildings, a plurality of vehicles, a lane-splitting vehicle, and a subject vehicle positioned on the road and including two or more sensor locations;
simulating, by the computer system, two or more sensor outputs from sound from the lane-splitting vehicle incident on the two or more sensor locations of the subject vehicle in the 3D model, the simulating comprising simulating movement of the subject vehicle and the lane-splitting vehicle and modeling reflection of the sound from the lane-splitting vehicle, from the road, from the buildings, and from the plurality of vehicles;
training, by the computer system, a machine-learning model to both identify and locate lane-splitting vehicles using a location of the lane-splitting vehicle in the 3D model over time and the two or more sensor outputs;
providing a vehicle including a vehicle controller and two or more microphones;
programming the vehicle controller with the machine-learning model;
receiving, by the vehicle controller, two or more audio streams from the two or more microphones;
inputting, by the vehicle controller, the two or more audio streams to the machine-learning model;
(a) determining, by the vehicle controller, that the machine-learning model indicates that the two or more audio streams currently indicate a lane-splitting vehicle is present;
and
in response to (a) at least one of outputting an alert and refraining from causing the vehicle to enter an inter-lane region.

7 more elements

A system comprising one or more processors and one or more memory devices coupled to the one or more processors, the one or more memory devices storing executable code effective to:

define a three dimensional model including a road, buildings, a plurality of vehicles, a lane-splitting vehicle, and a subject vehicle including two or more sensor locations positioned on the road;
simulate two or more sensor outputs from sound from the plurality of vehicles incident on the two or more sensor locations by simulating movement of the subject vehicle and the lane-splitting vehicle and modeling reflection of the sound from the lane-splitting vehicle from the road, buildings, and the plurality of vehicle;
and
train a machine-learning model using a location of the lane-splitting vehicle over time and the two or more sensor outputs;
further comprising a vehicle including a vehicle controller and two or more microphones;
wherein the vehicle controller is programmed with the machine-learning model;
wherein the vehicle controller is further programmed to:
receive two or more audio streams from the two or more microphones;
input the two or more audio streams to the machine-learning model;
if the machine-learning model indicates that the two or more audio streams currently indicate a lane-splitting vehicle is present, at least one of output an alert by the vehicle controller and refrain from moving, by the vehicle controller, the vehicle into an inter-lane region.

7 more elements

Dependencies are inferred from the claim text.

Facts

Application: 15/007,024Filed 26 Jan 2016
Published: US 2017/0213149 A127 Jul 2017
Granted: 12 Nov 2019
Term ends: Not estimatedThe source records don’t support an estimate.

Classification17 codes

G06N 20/00
Machine learning
B60W 30/09
Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences: taking automatic action…
G06F 30/20
Computer-aided design [CAD]: design optimisation, verification or simulation
G06N 3/088
Learning methods: non-supervised learning, e.g. competitive learning