公开(公告)号：US10266182B2

公开(公告)日：2019-04-23

申请号：US15402960

申请日：2017-01-10

Applicant: Ford Global Technologies, LLC

Inventor： Lakshmi Krishnan ,  Francois Charette

IPC: G01C22/00 ,  B60W50/10 ,  B60W40/08 ,  G10L15/22 ,  G01C21/00

Abstract: A method is disclosed for incorporating preferences of a human occupant into an autonomous driving experience. The method may include a computer system autonomously controlling speed and steering of a vehicle. While it is controlling the vehicle, the computer system may interpret a speech command received from a human occupant of the vehicle. The computer system may determine whether changing at least one of the speed and steering in accordance with the speech command would be safe and legal. If it would be safe and legal, the computer system may change the at least one of the speed and steering in accordance with the speech command. If it would not be safe and legal, the computer system may leave the at least one of the speed and steering unchanged in contravention of the speech command.

公开(公告)号：US20180194366A1

公开(公告)日：2018-07-12

申请号：US15402960

申请日：2017-01-10

Applicant: Ford Global Technologies, LLC

Inventor： Lakshmi Krishnan ,  Francois Charette

IPC: B60W50/10 ,  B60W40/08 ,  G05D1/00 ,  G10L15/22

CPC classification number: B60W50/10 ,  B60W30/10 ,  B60W50/087 ,  B60W2040/089 ,  B60W2550/22 ,  B60W2710/20 ,  B60W2720/10 ,  G01C21/3608 ,  G05D1/00 ,  G10L15/22 ,  G10L2015/223

Abstract: A method is disclosed for incorporating preferences of a human occupant into an autonomous driving experience. The method may include a computer system autonomously controlling speed and steering of a vehicle. While it is controlling the vehicle, the computer system may interpret a speech command received from a human occupant of the vehicle. The computer system may determine whether changing at least one of the speed and steering in accordance with the speech command would be safe and legal. If it would be safe and legal, the computer system may change the at least one of the speed and steering in accordance with the speech command. If it would not be safe and legal, the computer system may leave the at least one of the speed and steering unchanged in contravention of the speech command.

公开(公告)号：US11318373B2

公开(公告)日：2022-05-03

申请号：US16650160

申请日：2017-10-04

Applicant: Ford Global Technologies, LLC

Inventor： Francois Charette ,  Lakshmi Krishnan ,  Shant Tokatyan

IPC: A63F13/215 ,  A63F13/533 ,  A63F13/54 ,  A63F13/87 ,  G10L15/22

Abstract: Example natural speech data generation systems and methods are described. In one implementation, a natural speech data generator initiates a game between a first player and a second player and determines a scenario associated with the game. A first role is assigned to the first player and a second role is assigned to the second player. The natural speech data generator receives multiple natural speech utterances by the first player and the second player during the game.

公开(公告)号：US20180032902A1

公开(公告)日：2018-02-01

申请号：US15221483

申请日：2016-07-27

Applicant: Ford Global Technologies, LLC

Inventor： Lakshmi Krishnan ,  Kyu Jeong Han ,  Francois Charette ,  Gintaras Vincent Puskorius

IPC: G06N99/00 ,  G06N3/08 ,  G06F17/30

CPC classification number: G06N20/00 ,  G06F16/3344 ,  G06N3/0454 ,  G06N3/08

Abstract: Training tuples including text and a question and answer corresponding to the text are input to a machine learning algorithm, such as a deep neural network. A Q&A model is obtained that outputs questions and answers given an input text. The training tuples may be obtained from standardized test such that the text is a question prompt and the questions and answers are based on the prompt. Raw text is input to the Q&A model to obtain second training tuples including a question and an answer. An NLU model is trained according to the second training tuples. The NLU model may then be installed on a consumer device, which will then use the model to respond to conversational queries and provide an appropriate response.