IP Library › Granted Patent US 12,128,905
Granted Patent B2
US 12,128,905 · App. 17/615,749 · Granted Oct 29, 2024

Driver state estimation device, driver state estimation method, and learning method

Inventors: Kimika Ikegami (Tokyo, JP); Takuji Morimoto (Tokyo, JP); Genta Yoshimura (Tokyo, JP); Shan Gao (Tokyo, JP)
Assignee: Mitsubishi Electric Corporation
B60W40/09G07C5/04
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,128,905
App. No.
17/615,749
Granted
Oct 29, 2024
Kind
B2
Abstract

An information collection unit collects information indicating a driving operation of a vehicle by a driver and a state of the vehicle changed by the driving operation, and outputs, among the collected information, information in a period from a start point at which a driving operation contributing to stop of the vehicle is performed to a stop start point in a stop state where a stop time of the vehicle continues for a predetermined time or more, as driving operation information. A state estimation unit acquires driver state information indicating a state of the driver from a learned learner on which machine learning has been performed so as to output the driver state information when the driving operation information is input, by inputting the driving operation information output from the information collection unit to the learner and performing arithmetic processing of the learner.

Claims (16)

1. A driver state estimation device comprising:

processing circuitry to collect information indicating a driving operation of a vehicle by a driver and a state of the vehicle changed by the driving operation;

in response to a stop state of the vehicle lasting for a predetermined time or longer, to output, among the collected information, information collected in a collection period between an initiation of a driving operation leading to stop of the vehicle and a stop start point of the stop state of the vehicle, as driving operation information;

to acquire driver state information indicating a state of the driver from a learned learner on which machine learning has been performed in such a manner as to output the driver state information when the driving operation information is input, by inputting the driving operation information to the learner and performing arithmetic processing of the learner; and

to control a brake operation of the vehicle based on the driver state information.

2. The driver state estimation device according to claim 1 , wherein the driving operation information is first driving operation information that is at least one of a brake operation, a steering operation, an accelerator operation, and a vehicle speed for the vehicle, or second driving operation information that is derived from the first driving operation information.

3. A driver state estimation method comprising:

collecting information indicating a driving operation of a vehicle by a driver and a state of the vehicle changed by the driving operation;

in response to a stop state of the vehicle lasting for a predetermined time or longer, outputting, among the collected information, information collected in a collection period between an initiation of a driving operation leading to stop of the vehicle and a stop start point of the stop state of the vehicle, as driving operation information;

acquiring driver state information indicating a state of the driver from a learned learner on which machine learning has been performed in such a manner as to output the driver state information when the driving operation information is input, by inputting the driving operation information to the learner and performing arithmetic processing of the learner; and

controlling a brake operation of the vehicle based on the driver state information.

4. A learning method comprising:

collecting information indicating a driving operation of a vehicle by a driver and a state of the vehicle changed by the driving operation; and

in response to a stop state of the vehicle lasting for a predetermined time or longer, outputting, among the collected information, information collected in a collection period between an initiation of a driving operation leading to stop of the vehicle and a stop start point of the stop state of the vehicle, as driving operation information;

causing a learner to perform machine learning in such a manner as to output driver state information indicating a state of the driver when the driving operation information is input; and

causing the vehicle to control a brake operation based on the driver state information.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 3, 2021
From: IKEGAMI, KIMIKA; MORIMOTO, TAKUJI; YOSHIMURA, GENTA
To: MITSUBISHI ELECTRIC CORPORATION
Reel/Frame 058278/0184 →
Continuity (1)
Related Publication 20220315011A1 · Oct 6, 2022