Vehicle control device, vehicle control system, and vehicle control method

Patent metadata

Field	Value
Publication number	US-11248553-B2
Application number	US-202017063203-A
Country	US
Kind code	B2
Filing date	Oct 5, 2020
Priority date	Oct 18, 2019
Publication date	Feb 15, 2022
Grant date	Feb 15, 2022

Abstract

A vehicle control device includes a storage device and a processor. The storage device is configured to store relationship prescription data that prescribe a relationship between a state of a vehicle and an action variable that is a variable related to an operation of an electronic device in the vehicle. The processor is configured to calculate a reward corresponding to the operation of the electronic device. The processor is configured to update the relationship prescription data using, as inputs to updated mapping determined in advance, the state of the vehicle that is based on a detection value that is acquired, a value of the action variable that is used to operate the electronic device, and the reward corresponding to the operation of the electronic device when a computation load on the processor is equal to or less than a predetermined load.

First claim

What is claimed is:

1. A vehicle control device comprising:
a storage device configured to store relationship prescription data that prescribe a relationship between a state of a vehicle and an action variable that is a variable related to an operation of an electronic device in the vehicle; and
a processor configured to
acquire a detection value from a sensor that detects the state of the vehicle,
operate the electronic device based on a value of the action variable determined in accordance with the detection value that is acquired and the relationship prescription data that are read from the storage device,
calculate, based on the detection value that is acquired, a reward so as to be large in the case where a characteristic of the vehicle meets a predetermined criterion compared to the case where the characteristic of the vehicle does not meet the predetermined criterion, and
update the relationship prescription data using, as inputs to updated mapping determined in advance, the state of the vehicle that is based on the detection value that is acquired, the value of the action variable that is used to operate the electronic device, and the reward corresponding to the operation of the electronic device when a computation load on the processor is equal to or less than a predetermined load, wherein

the updated mapping outputs the relationship prescription data that have been updated so as to increase an expected profit for the reward for the case where the electronic device is operated in accordance with the relationship prescription data.

2. The vehicle control device according to claim 1 , wherein:
the processor is configured to acquire a detection value from a sensor that detects the state of the vehicle that includes an internal combustion engine;
the processor is configured to operate the electronic device that controls the internal combustion engine; and
the processor is configured to update the relationship prescription data by assuming that the computation load is equal to or less than the predetermined load when a rotational speed of a crankshaft of the internal combustion engine is equal to or less than a predetermined speed.

3. The vehicle control device according to claim 1 , wherein the processor is configured to update the relationship prescription data by assuming that the computation load is equal to or less than the predetermined load when the vehicle is stationary.

4. The vehicle control device according to claim 1 , wherein:
the processor is configured to acquire a detection value related to a drivability; and
the processor is configured to calculate, based on the detection value related to the drivability that is acquired, the reward so as to be large in the case where the detection value related to the drivability meets a predetermined criterion compared to the case where the detection value related to the drivability does not meet the predetermined criterion.

5. The vehicle control device according to claim 4 wherein the detection value related to the drivability includes a torque of an internal combustion engine.

6. The vehicle control device according to claim 4 wherein the detection value related to the drivability includes an acceleration of the vehicle.

7. The vehicle control device according to claim 1 , wherein:
the processor is configured to acquire a detection value related to a fuel consumption rate; and
the processor is configured calculate, based on the detection value related to the fuel consumption rate that is acquired, the reward so as to be large in the case where the detection value related to the fuel consumption rate meets a predetermined criterion compared to the case where the detection value related to the fuel consumption rate does not meet the predetermined criterion.

8. The vehicle control device according to claim 1 , wherein:
the processor is configured to acquire a detection value related to an exhaust characteristics; and
the processor is configured calculate, based on the detection value related to the exhaust characteristics that is acquired, the reward so as to be large in the case where the detection value related to the exhaust characteristics meets a predetermined criterion compared to the case where the detection value related to the exhaust characteristics does not meet the predetermined criterion.

9. A vehicle control system comprising:
a first processor and a storage device mounted on a vehicle; and
a second processor disposed outside the vehicle, wherein:
the storage device is configured to store relationship prescription data that prescribe a relationship between a state of a vehicle and an action variable that is a variable related to an operation of an electronic device in the vehicle;
the first processor is configured to
acquire a detection value from a sensor that detects the state of the vehicle,
operate the electronic device based on a value of the action variable determined in accordance with the detection value that is acquired and the relationship prescription data that are read from the storage device,
calculate, based on the detection value that is acquired, a reward so as to be large in the case where a characteristic of the vehicle meets a predetermined criterion compared to the case where the characteristic of the vehicle does not meet the predetermined criterion, and
transmit, to the second processor, the state of the vehicle that is based on the detection value that is acquired, the value of the action variable that is used to operate the electronic device, and the reward corresponding to the operation of the electronic device when a computation load on the first processor is equal to or less than a predetermined load;

the second processor is configured to
receive the state of the vehicle that is based on the detection value that is acquired, the value of the action variable that is used to operate the electronic device, and the reward corresponding to the operation of the electronic device, which are transmitted from the first processor,
update the relationship prescription data using, as inputs to updated mapping determined in advance, the state of the vehicle that is based on the detection value that is acquired, the value of the action variable that is used to operate the electronic device, and the reward corresponding to the operation of the electronic device, and
transmit the relationship prescription data that is updated to the storage device of the vehicle; wherein

the updated mapping outputs the relationship prescription data that have been updated so as to increase an expected profit for the reward for the case where the electronic device is operated in accordance with the relationship prescription data.

10. The vehicle control system according to claim 9 , wherein:
the processor is configured to acquire a detection value from a sensor that detects the state of the vehicle that includes an internal combustion engine;
the processor is configured to operate the electronic device that controls the internal combustion engine; and
the processor is configured to update the relationship prescription data by assuming that the computation load is equal to or less than the predetermined load when a rotational speed of a crankshaft of the internal combustion engine is equal to or less than a predetermined speed.

11. The vehicle control system according to claim 9 , wherein the processor is configured to update the relationship prescription data by assuming that the computation load is equal to or less than the predetermined load when the vehicle is stationary.

12. The vehicle control system according to claim 9 , wherein:
the processor is configured to acq

Assignees

• Toyota Motor Co Ltd

Inventors

• Hashimoto Yohsuke
• Katayama Akihiro
• Oshiro Yuta
• Sugie Kazuki
• Oka Naoya

Classifications

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• F02D2200/602

  Pedal position · CPC title

• F02D2250/12

  Timing of calculation, i.e. specific timing aspects when calculation or updating of engine parameter is performed · CPC title

• G06Q50/06

  Energy or water supply · CPC title

• G06N20/00

  Machine learning · CPC title