WO2021014738A1 - 快適性運転データ収集システム、運転制御装置、方法、および、プログラム - Google Patents

快適性運転データ収集システム、運転制御装置、方法、および、プログラム Download PDF

Info

Publication number
WO2021014738A1
WO2021014738A1 PCT/JP2020/020333 JP2020020333W WO2021014738A1 WO 2021014738 A1 WO2021014738 A1 WO 2021014738A1 JP 2020020333 W JP2020020333 W JP 2020020333W WO 2021014738 A1 WO2021014738 A1 WO 2021014738A1
Authority
WO
WIPO (PCT)
Prior art keywords
comfort
driving
data
comfortable
activity
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2020/020333
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
秋紗子 藤井
勇介 小板橋
卓郎 鹿嶋
雄樹 千葉
健冶 傍田
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
NEC Corp
Original Assignee
NEC Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by NEC Corp filed Critical NEC Corp
Priority to JP2021534561A priority Critical patent/JP7238994B2/ja
Priority to US17/627,969 priority patent/US12103543B2/en
Publication of WO2021014738A1 publication Critical patent/WO2021014738A1/ja
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/0098—Details of control systems ensuring comfort, safety or stability not otherwise provided for
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
    • A61B5/18—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state for vehicle drivers or machine operators
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2540/00—Input parameters relating to occupants
    • B60W2540/221—Physiology, e.g. weight, heartbeat, health or special needs

Definitions

  • the present invention relates to a comfort driving data collection system, a driving control device, a comfort driving data collection method, a driving control method, a comfort driving data collection program, and a driving control program that collect data indicating driving comfort.
  • Patent Document 1 describes a driving support device that contributes to improvement or maintenance of the situation at the time of boarding.
  • the driving support device described in Patent Document 1 monitors the driving state of the vehicle and notifies the monitoring result to a server installed outside the vehicle.
  • the server outputs a message for a proposal (or vehicle control) using the knowledge database based on the notified content.
  • the recommended information stored in the knowledge database described in Patent Document 1 is a general method, so that individual passengers do not always feel comfortable. Therefore, even if the driving support device described in Patent Document 1 is used, it is not always possible to improve the comfort of individual passengers.
  • the present invention provides a comfort driving data collection system, a comfort driving data collection method, and a comfort driving data collection program that can efficiently collect data indicating the comfort of the occupant according to the driving situation during riding. , And an operation control device, an operation control method, and an operation control program.
  • the comfort driving data collection system associates a comfort index, which is an index for measuring whether or not an individual is comfortable when an activity classified as a comfortable activity is performed, with a teacher label indicating comfort. Comfortability using the comfort activity data and the discomfort activity data in which the comfort index when the activity classified as the unpleasant activity is performed and the teacher label indicating the discomfort are associated with each other as the first learning data.
  • the comfort judgment model learning unit that learns the comfort judgment model that uses the comfort value indicating the degree of the above as the objective variable and each of the comfort indexes as the explanatory variable, and the comfort index of the subject while riding the vehicle.
  • the personal data generation unit that generates personal data including the explanatory variables used in the comfort judgment model and the driving status of the vehicle when the comfort index is acquired for each subject, and the personal data. Is applied to the comfort judgment model to calculate the comfort value, and according to the calculated comfort value, a driving data generation unit that generates driving data indicating a comfortable driving situation and driving data indicating an unpleasant driving situation. It is characterized by having.
  • the driving control device is a comfort activity in which a comfort index, which is an index for measuring whether or not an individual is comfortable when an activity classified as a comfortable activity is performed, and a teacher label indicating comfort are associated with each other.
  • Comfort learned using the data and the discomfort activity data in which the comfort index when the activity classified into the unpleasant activity is performed and the teacher label indicating the discomfort are associated with each other as the first training data.
  • the comfort value indicating the degree of is used as the objective variable and each of the comfort indexes is used as the explanatory variable, it is generated for each subject based on the comfort index of the subject who is riding the vehicle.
  • Comfortable driving generated according to the explanatory variables used in the comfort judgment model and the comfort value obtained by applying personal data including the driving status of the vehicle when the comfort index is acquired.
  • the subject was comfortable. It is characterized by including a comfortable driving determination unit for determining a feeling of driving and a comfortable driving information output unit for outputting information for controlling the driving of a vehicle based on the result of determination by the comfortable driving determination unit.
  • the comfort driving data collection method associates a comfort index, which is an index for measuring whether or not an individual is comfortable when an activity classified as a comfortable activity is performed, with a teacher label indicating comfort.
  • Comfortability using the comfort activity data and the discomfort activity data in which the comfort index when the activity classified as the unpleasant activity is performed and the teacher label indicating the discomfort are associated with each other as the first learning data.
  • a comfort judgment model is learned with the comfort value indicating the degree of the above as the objective variable and each of the comfort indexes as the explanatory variable, and the comfort is generated based on the comfort index of the subject while riding the vehicle.
  • Personal data including the explanatory variables used in the judgment model and the driving status of the vehicle when the comfort index is acquired is generated for each subject, and the personal data is applied to the comfort judgment model to obtain the comfort value. It is characterized in that it calculates and generates driving data showing a comfortable driving situation and driving data showing an unpleasant driving situation according to the calculated comfort value.
  • the driving control method is a comfort activity in which a comfort index, which is an index for measuring whether or not an individual is comfortable when an activity classified as a comfortable activity is performed, and a teacher label indicating comfort are associated with each other.
  • Comfort learned using the data and the discomfort activity data in which the comfort index when the activity classified into the unpleasant activity is performed and the teacher label indicating the discomfort are associated with each other as the first training data.
  • the comfort value indicating the degree of is used as the objective variable and each of the comfort indexes is used as the explanatory variable, it is generated for each subject based on the comfort index of the subject who is riding the vehicle.
  • Comfortable driving generated according to the explanatory variables used in the comfort judgment model and the comfort value obtained by applying personal data including the driving status of the vehicle when the comfort index is acquired. Based on the personal riding model showing the personal comfort situation according to the driving situation, which was learned by using the driving data showing the situation and the driving data showing the unpleasant driving situation as the second learning data, the subject was comfortable. It is characterized in that it determines the driving to be felt and outputs information for controlling the driving of the vehicle based on the result of the determination.
  • the comfort driving data collection program uses a computer with a comfort index, which is an index for measuring whether or not an individual is comfortable when an activity classified as a comfortable activity is performed, and a teacher label indicating comfort.
  • the comfort activity data associated with the data and the discomfort activity data associated with the comfort index when the activity classified as unpleasant activity and the teacher label indicating discomfort are used as the first learning data.
  • a comfort judgment model learning process that learns a comfort judgment model that uses a comfort value indicating the degree of comfort as an objective variable and each of the comfort indexes as an explanatory variable, and a comfort index of a subject while riding a vehicle.
  • the driving control program associates a comfort index, which is an index for measuring whether or not an individual is comfortable when an activity classified as a comfortable activity is performed, with a teacher label indicating comfort on a computer.
  • the comfort activity data and the discomfort activity data in which the comfort index when the activity classified as the unpleasant activity was performed and the teacher label indicating the discomfort were associated with each other were used as the first training data.
  • each subject is based on the comfort index of the subject while riding the vehicle.
  • the comfort determination model generated in Generated according to the explanatory variables used in the comfort determination model generated in, and the comfort value obtained by applying personal data including the driving status of the vehicle when the comfort index was acquired.
  • the subject was trained using the driving data showing the comfortable driving situation and the driving data showing the unpleasant driving situation as the second learning data. It is characterized by executing a comfortable driving judgment process that determines driving that is comfortable for the driver, and a comfortable driving information output process that outputs information that controls vehicle driving based on the result of the judgment in the comfortable driving judgment process. To do.
  • FIG. 1 is a block diagram showing a configuration example of an embodiment of a comfort situation determination system including a comfort driving data collection system and a driving control device according to the present invention.
  • the comfort situation determination system 100 of the present embodiment includes a comfort determination model generation device 10, an individual ride model generation device 20, and a comfortable driving information output device 30.
  • the comfort determination model generation device 10 is a device that generates a comfort determination model that determines the degree of comfort when riding that each individual feels.
  • the individual assumed in the present embodiment includes not only the driver who actually drives the vehicle but also the passenger of the vehicle.
  • the target individual may be simply referred to as the target person.
  • the comfort determination model generation device 10 of the present embodiment includes a sensor 11, an activity data generation unit 12, an activity data storage unit 13, a comfort determination model learning unit 14, and a comfort determination model storage unit 15. ..
  • the sensor 11 is a sensor that detects an index for measuring whether or not the subject is comfortable.
  • an index for measuring whether or not a subject is individually comfortable is referred to as a comfort index.
  • the comfort index is not limited to an index that can directly measure whether or not comfort is achieved, and may be information that can be indirectly measured.
  • Comfort indicators are, for example, human life characteristics (pulse, blood pressure, body temperature, etc.) and body maintenance status (change in center of gravity, etc.).
  • the sensor 11 includes a heart rate monitor that acquires a heartbeat, an electroencephalograph that acquires an electroencephalogram, a thermo camera that acquires body temperature and room temperature, a thermometer that acquires body temperature, a sound collecting microphone that acquires voice color and noise, and a voice color. It is an AI (Artificial Intelligence) speaker or the like to acquire.
  • a weight sensor that acquires body shaking and the center of gravity
  • an infrared sensor that acquires heartbeat and pulse, blood pressure, stress level, and oxygen saturation
  • an odor sensor that acquires odor may be used. ..
  • a smartphone or a camera capable of acquiring various information such as facial expressions, body shaking, number of blinks, complexion, number of specific movements, voice color, drowsiness, and concentration may be used as the sensor 11.
  • a plurality of comfort sensors 11 may exist, and it is preferable that the comfort sensor 11 is a sensor capable of acquiring a comfort index without restraining the subject.
  • the situation in which the sensor 11 detects the comfort index of the target person is not limited to the time of boarding.
  • the state of the activity in which the sensor 11 detects the comfort index of the subject can be identified, and whether the activity is comfortable or unpleasant for the subject is predetermined. It shall be.
  • a favorite TV program for example, a drama
  • watching a TV program that you are not interested in for example, stock price introduction
  • the situation is unpleasant activity.
  • talking to a close friend or listening to your favorite music can be said to be a comfortable activity, talking to a person you meet for the first time, or making an unpleasant sound (for example).
  • the situation of listening to the sound of scratching the blackboard can be said to be an unpleasant activity.
  • the situation of smelling a favorite odor for example, citrus
  • the situation of smelling a disliked odor for example, garbage
  • the sensor 11 detects a comfort index according to a comfortable or unpleasant situation in which the subject is active.
  • the above-mentioned activities are examples, and it is sufficient to assume the situation of any activity that the subject feels comfortable and the situation of any activity that the subject feels uncomfortable.
  • the activity data generation unit 12 generates activity data in which the comfort index detected by the sensor 11 is associated with information indicating whether or not the comfort index is comfortable when the comfort index is detected. Specifically, the activity data generation unit 12 provides comfortable activity data in which a comfort index when an activity classified as a comfortable activity is performed and a teacher label indicating comfort, and unpleasant activity. Generate one or both of the discomfort activity data in which the comfort index when the activity classified into is associated with the teacher label indicating discomfort is associated with the activity.
  • the activity data generation unit 12 may generate comfort activity data in which the comfort index in this situation and the teacher label indicating comfort are associated with each other.
  • the activity data generation unit 12 may sequentially collect the heart rate per 60 seconds and generate comfort activity data in chronological order in which the collected heart rate and the teacher label indicating comfort are associated with each other.
  • the activity data generation unit 12 may generate comfort activity data in which the comfort index at this time and the teacher label indicating discomfort are associated with each other. Similar to the above, for example, it is assumed that an uninterested TV program is watched for one hour, and the heart rate per 60 seconds at that time is sequentially collected by the sensor 11. In this case, the activity data generation unit 12 may sequentially collect the heart rate per 60 seconds and generate discomfort activity data in chronological order in which the collected heart rate and the teacher label indicating discomfort are associated with each other.
  • FIG. 2 is an explanatory diagram showing an example of activity data.
  • the activity data generation unit 12 aggregates the heart rate per 60 seconds for each comfort or discomfort, generates the comfort activity data and the discomfort activity data, and displays them in chronological order. Shown. The activity data generation unit 12 may also total the number of blinks per 60 seconds. The activity data generation unit 12 stores the generated activity data in the activity data storage unit 13.
  • the activity data storage unit 13 stores the generated activity data. Specifically, the activity data storage unit 13 may store the comfortable activity data and the unpleasant activity data in the comfortable activity DB (Database) 13a and the unpleasant activity DB 13b, respectively.
  • the activity data storage unit 13 is realized by, for example, a magnetic disk or the like.
  • the comfort determination model learning unit 14 uses the comfort activity data and the discomfort activity data as learning data, sets the degree of comfort (hereinafter, may be referred to as a comfort value) as an objective variable, and is acquired by the sensor 11. Learn a comfort judgment model with each comfort index as an explanatory variable. In order to distinguish it from the learning data described later, the comfortable activity data and the unpleasant activity data may be referred to as the first learning data.
  • the comfort determination model learning unit 14 may use the comfort index itself detected by the sensor 11 as an explanatory variable, or may use a total of the comfort indexes for a certain period as an explanatory variable. For example, as described above, the comfort determination model learning unit 14 may use the heart rate per 60 seconds or the number of blinks per 60 seconds as explanatory variables.
  • the method in which the comfort determination model learning unit 14 learns the comfort determination model is arbitrary.
  • the comfort determination model learning unit 14 may learn the comfort determination model by using, for example, multiple regression analysis.
  • the comfort determination model is used.
  • Comfort a ⁇ (heart rate per 60 seconds) + b ⁇ (number of blinks per 60 seconds) + c It can be expressed as.
  • the comfort determination model learning unit 14 stores the generated comfort determination model in the comfort determination model storage unit 15.
  • the comfort determination model storage unit 15 stores the comfort determination model for each subject. Further, the comfort determination model storage unit 15 is connected to the individual boarding model generation device 20 and is used when generating driving data described later.
  • the comfort determination model storage unit 15 is realized by, for example, a magnetic disk or the like.
  • the personal ride model generation device 20 includes a sensor 21, a personal data generation unit 22, a personal data storage unit 23, a driving data generation unit 24, a driving data storage unit 25, an individual ride model learning unit 26, and an individual ride. Includes a model storage unit 27.
  • the sensor 21 is a sensor that detects a comfort index of the subject. Specifically, the sensor 21 is mounted on a vehicle for determining comfort, for example, and detects a comfort index of the target person at the time of riding. The content of the comfort index detected by the sensor 21 is the same as the content of the comfort index detected by the sensor 11.
  • the personal data generation unit 22 generates personal data of the target person (hereinafter, simply referred to as personal data) to be applied to the comfort determination model from the comfort index of the target person while riding detected by the sensor 21.
  • the personal data generation unit 22 includes explanatory variables used in the comfort determination model, which are generated based on the detected comfort index, and the vehicle when the comfort index is detected. Generate personal data including driving status for each target person.
  • the personal data generation unit 22 associates the explanatory variables that aggregate the heart rate per 60 seconds and the number of blinks per 60 seconds acquired by the sensor 21 with the driving status of the vehicle at that time.
  • Personal data may be generated.
  • the driving situation is, for example, vehicle operation information, such as accelerator opening, brake pressure, and steering angle.
  • the personal data generation unit 22 stores the generated personal data in the personal data storage unit 23.
  • the personal data storage unit 23 stores the personal data of the target person.
  • the personal data storage unit 23 is realized by, for example, a magnetic disk or the like.
  • the driving data generation unit 24 applies the personal data to the comfort determination model of the target person, and generates driving data in which the degree of comfort (that is, the comfort value) of the target person is determined. Specifically, the driving data generation unit 24 acquires the comfort determination model of the subject from the comfort determination model storage unit 15, applies personal data to the acquired comfort determination model, and calculates the comfort value. .. Then, the driving data generation unit 24 determines driving data indicating a comfortable driving condition (hereinafter referred to as comfortable driving data) and driving data indicating an unpleasant driving condition (hereinafter referred to as unpleasant driving) according to the calculated comfort value. Data) is generated.
  • comfortable driving data a comfortable driving condition
  • unpleasant driving hereinafter referred to as unpleasant driving
  • the driving data generation unit 24 may generate comfortable driving data and unpleasant driving data by comparing a predetermined threshold value with the calculated comfort value. For example, when the comfort value exceeds the threshold value, the driving data generation unit 24 may generate driving data in which the driving situation included in the personal data and the comfortable driving flag are associated with each other as comfortable driving data. On the other hand, when the comfort value is equal to or less than the threshold value, the driving data generation unit 24 may generate driving data in which the driving situation included in the personal data and the driving flag are associated with each other as the driving data.
  • the personal data includes "heart rate per 60 seconds", "number of blinks per 60 seconds" during the ride, and data (driving status) showing the characteristics of the individual during the ride.
  • the driving data generation unit 24 applies this personal data to the comfort determination model to calculate the comfort value.
  • the comfort value is output as 0.7.
  • the threshold value for determining comfort is set to 0.5. In this case, since the comfort value exceeds the threshold value, the driving data generation unit 24 sets the comfortable driving flag in the personal data at that time, and generates data including the comfortable driving flag and the driving situation as driving data.
  • FIG. 3 is an explanatory diagram showing an example of processing for generating operation data.
  • the graph illustrated in FIG. 3 shows the transition of the comfort value in time series.
  • the threshold value is set to 0.5.
  • the driving data generation unit 24 sets a comfortable driving flag for personal data whose comfort value at the time of determination exceeds the threshold value (0.5) (or sets an unpleasant driving flag for personal data below the threshold value). Then) the operation data may be generated.
  • the operation data generation unit 24 stores the generated operation data in the operation data storage unit 25.
  • the driving data is data in which a comfortable driving flag (unpleasant driving flag) is set according to the driving situation (access acceleration, brake pressure, steering angle).
  • the operation data storage unit 25 stores operation data. Specifically, the driving data storage unit 25 may store the comfortable driving data and the unpleasant driving data in the comfortable driving DB 25a and the uncomfortable driving DB 25b, respectively.
  • the operation data storage unit 25 is realized by, for example, a magnetic disk or the like.
  • the individual riding model learning unit 26 uses the generated driving data as learning data to learn an individual riding model that indicates an individual's comfort status according to the driving situation.
  • the driving data used by the individual riding model learning unit 26 for learning may be referred to as the second learning data.
  • the method by which the individual boarding model learning unit 26 learns the individual boarding model is arbitrary.
  • the individual riding model learning unit 26 may learn the individual riding model (reward function) by using, for example, inverse reinforcement learning.
  • the individual ride model learning unit 26 stores the learned individual ride model in the individual ride model storage unit 27.
  • the personal boarding model storage unit 27 stores the generated personal boarding model storage unit 27. Further, the personal riding model storage unit 27 is connected to the comfortable driving information output device 30 and is used for determining a comfortable situation.
  • the personal boarding model storage unit 27 is realized by, for example, a magnetic disk or the like.
  • the comfortable driving information output device 30 includes a driving status acquisition unit 31, a comfortable driving determination unit 32, and a comfortable driving information output unit 33.
  • the driving status acquisition unit 31 acquires the driving status of the vehicle on which the target person is riding.
  • the driving status acquisition unit 31 is realized by, for example, an in-vehicle sensor, and acquires the accelerator opening degree, the brake pressure, the steering wheel operation angle, and the like described above.
  • the comfortable driving determination unit 32 determines driving that the subject feels comfortable with based on the individual riding model. For example, when an individual riding model (reward function) is generated by reverse reinforcement learning, the comfortable driving determination unit 32 may estimate driving that optimizes the reward as comfortable driving. Specifically, the comfortable driving determination unit 32 may generate a specific driving operation (optimal action) that approaches comfortable driving (reward) based on the information stored as comfortable driving data. ..
  • the comfortable driving information output unit 33 outputs the determination result by the comfortable driving determination unit 32.
  • the comfortable driving information output unit 33 may output a result of comparing the driving status of the vehicle on which the subject is riding with the determination result by the individual riding model. Further, the comfortable driving information output unit 33 may sequentially output the determination result, or may output the determination result when the predetermined notification standard is satisfied.
  • the comfortable driving information output unit 33 is "good driving". The judgment result of the content may be output.
  • the comfortable driving information output unit 33 specifically The judgment result of the content of the operation content (for example, the content "Please step on the accelerator gently") may be output.
  • the comfortable driving information output unit 33 may output the determination result to various output devices (voice output or output to the instrument panel) as described above. Further, the comfortable driving information output unit 33 may output information for controlling the driving of the vehicle to the vehicle control unit (not shown) based on the result of the determination by the comfortable driving determination unit 32. .. Specifically, the comfortable driving information output unit 33 may notify the control unit of the vehicle of the control method so that the comfort can be maintained in the case of automatic driving.
  • the comfort determination model learning unit 14 included in the comfort determination model generation device 10 the personal data generation unit 22 and the driving data generation unit 24 included in the individual boarding model generation device 20 are active. Data and with personal data can be used to generate driving data. Therefore, a system including at least these configurations can be called a comfortable driving data collection system 200.
  • the comfortable driving determination unit 32 and the comfortable driving information output unit 33 use the individual riding model learned from the driving data generated by applying the personal data to the comfort determination model so that the subject feels comfortable. You can control the driving of the vehicle. Therefore, the device including the comfortable driving determination unit 32 and the comfortable driving information output unit 33 can be referred to as a driving control device 300.
  • the driving control device 300 may cause, for example, the output device of the vehicle to output information indicating comfortable driving.
  • the output include displaying "Please step on the accelerator gently” on the instrument panel and outputting voice "Please step on the accelerator gently” to the speaker.
  • the driving control device 300 may notify the control unit of the autonomous driving vehicle of various signals for realizing comfortable driving. For example, when it is desired to gently control the accelerator operation, the driving control device 300 may output an operation signal to the control unit of the autonomous driving vehicle so as to loosely control the accelerator operation.
  • the activity data generation unit 12, the comfort determination model learning unit 14, the personal data generation unit 22, the driving data generation unit 24, and the individual riding model learning unit 26 operate according to a program (comfort driving data collection program). It is realized by the processor of the computer (for example, CPU (Central Processing Unit), GPU (Graphics Processing Unit)).
  • CPU Central Processing Unit
  • GPU Graphics Processing Unit
  • the program is stored in a storage unit (not shown) of the comfort determination model generation device 10 or the personal ride model generation device 20, the processor reads the program, and according to the program, the activity data generation unit 12, comfort. It may operate as a determination model learning unit 14, a personal data generation unit 22, a driving data generation unit 24, and an individual boarding model learning unit 26. Further, the function of the comfort situation determination system may be provided in the SaaS (Software as a Service) format.
  • SaaS Software as a Service
  • the activity data generation unit 12, the comfort determination model learning unit 14, the personal data generation unit 22, the driving data generation unit 24, and the individual ride model learning unit 26 are each realized by dedicated hardware. May be good. Further, a part or all of each component of each device may be realized by a general-purpose or dedicated circuit (circuitry), a processor, or a combination thereof. These may be composed of a single chip or may be composed of a plurality of chips connected via a bus. A part or all of each component of each device may be realized by a combination of the above-mentioned circuit or the like and a program.
  • the plurality of information processing devices and circuits may be centrally arranged. It may be distributed.
  • the information processing device, the circuit, and the like may be realized as a form in which each of the client-server system, the cloud computing system, and the like is connected via a communication network.
  • comfort determination model generation device 10 the individual riding model generation device 20, and the comfortable driving information output device 30 may be realized by the same device, and each configuration of each device may be realized by another device. It may be realized as a separate device in combination with the configuration of the device.
  • FIG. 4 is an explanatory diagram showing an operation example of the comfort situation determination system 100 of the present embodiment.
  • the activity data generation unit 12 generates comfortable activity data from the comfort index in the situation of performing "comfortable” activity detected by the sensor 11, and stores it in the comfort activity DB 13a of the activity data storage unit 13.
  • the activity data generation unit 12 generates unpleasant activity data from the comfort index in the situation of performing “unpleasant” activity detected by the sensor 11 and stores it in the unpleasant activity DB 13b of the activity data storage unit 13.
  • the comfort determination model learning unit 14 learns the comfort determination model from the comfort activity data and the discomfort activity data (step S101).
  • the comfort determination model learning unit 14 stores the generated comfort determination model in the comfort determination model storage unit 15.
  • the personal data generation unit 22 After that, the personal data generation unit 22 generates personal data from the comfort index of the passenger in the vehicle detected by the sensor 21, and stores it in the personal data storage unit 23.
  • the driving data generation unit 24 applies personal data to the comfort model to generate comfortable driving data and unpleasant driving data (step S102), and stores them in the comfortable driving DB 25a and the uncomfortable driving DB 25b of the driving data storage unit 25, respectively. ..
  • the individual riding model learning unit 26 learns the individual riding model from the comfortable driving data and the unpleasant driving data (step S103), and stores it in the individual riding model storage unit 27.
  • the comfortable driving determination unit 32 applies the driving status to the individual riding model (step S105), and the target person receives the driving status.
  • the comfortable driving information output unit 33 indicates a driving situation necessary for comfortable driving (step S106), and notifies the driver, the passenger, and the autonomous driving vehicle of the driving situation (step S107).
  • FIG. 5 is a flowchart showing an operation example of collecting operation data.
  • the comfort determination model learning unit 14 learns the comfort determination model using the comfort activity data and the discomfort activity data (step S11).
  • the personal data generation unit 22 generates explanatory variables generated based on the comfort index of the subject while riding the vehicle, and personal data including the driving status of the vehicle (step S12).
  • the driving data generation unit 24 applies the personal data to the comfort determination model to calculate the comfort value, and generates the comfortable driving data and the unpleasant driving data according to the calculated comfort value (step S13).
  • FIG. 6 is a flowchart showing an operation example of controlling the operation of the vehicle.
  • the comfortable driving determination unit 32 determines driving that the subject feels comfortable with based on the individual riding model (step S21).
  • the comfortable driving information output unit 33 outputs information for controlling the driving of the vehicle based on the result of the determination (step S22).
  • the comfort determination model learning unit 14 learns the comfort determination model using the comfort activity data and the discomfort activity data, and the personal data generation unit 22 is in the vehicle. It generates explanatory variables generated based on the subject's comfort index and personal data including the driving status of the vehicle. Then, the driving data generation unit 24 applies the personal data to the comfort determination model to calculate the comfort value, and generates the comfortable driving data and the unpleasant driving data according to the calculated comfort value. Therefore, it is possible to efficiently collect data indicating the comfort of the occupant according to the situation during boarding.
  • the comfortable driving determination unit 32 determines driving that the subject feels comfortable based on the individual riding model
  • the comfortable driving information output unit 33 determines the driving of the vehicle based on the determination result. Outputs information that controls. Therefore, it is possible to control the driving of the vehicle so as to be comfortable for the subject by using the data efficiently collected from the subject.
  • FIG. 7 is a block diagram showing a configuration example of the comfort situation determination system 100a including a modification of the personal riding model generation device.
  • the general-purpose riding model generation device 20a of this modified example includes a sensor 21, a personal data generation unit 22, a personal data storage unit 23, a driving data generation unit 24, a driving data storage unit 25, and a general-purpose riding model learning unit 26a. And a general-purpose boarding model storage unit 27a.
  • the comfort situation determination system 100a of the present modification includes the general-purpose riding model generation device 20a instead of the individual riding model generation device 20 of the above embodiment, and the individual riding model learning unit 26 and the personal riding model storage of the above embodiment. It differs in that it includes a general-purpose riding model learning unit 26a and a general-purpose riding model storage unit 27a instead of the unit 27.
  • Other configurations are the same as those in the above embodiment.
  • both the individual boarding model generation device 20 and the general-purpose boarding model generation device 20a can be said to be devices (boarding model generation devices) for learning the boarding model of the target person.
  • the general-purpose riding model learning unit 26a uses the generated driving data of a plurality of people as learning data to learn a general-purpose riding model that shows a general-purpose comfort situation according to the driving situation. That is, in the above embodiment, the riding model is learned for each individual, but in this modification, a general-purpose riding model for a plurality of people is generated.
  • the method of determining the target person to be used as the learning data is arbitrary. For example, the target person may be determined in units such as the gender, age, and region of the target person.
  • the general-purpose riding model learning unit 26a learns the general-purpose riding model is arbitrary.
  • the general-purpose riding model learning unit 26a may learn the general-purpose riding model (reward function) by using inverse reinforcement learning as in the above embodiment.
  • the general-purpose riding model learning unit 26a stores the learned general-purpose riding model in the general-purpose riding model storage unit 27a.
  • the general-purpose riding model learning unit 26a learns a general-purpose riding model showing a general-purpose comfort situation according to the driving situation by using the generated driving data of a plurality of people as learning data. To do.
  • a model for determining a plurality of driving operations it is possible to improve the accuracy of the riding model even when the learning data for each individual is small.
  • FIG. 8 is a block diagram showing an outline of the comfortable driving data collection system according to the present invention.
  • the comfortable driving data collection system 80 (for example, the comfortable driving data collection system 200) according to the present invention is an individual when an activity classified into a comfortable activity (for example, watching a favorite TV program, etc.) is performed.
  • Comfort activity data that associates comfort indicators (for example, heart rate, number of blinks, etc.), which are indicators for measuring comfort, with teacher labels that indicate comfort, and activities classified as unpleasant activities.
  • the degree of comfort is determined by using the discomfort activity data in which the comfort index and the teacher label indicating discomfort are associated with each other (for example, watching a TV program of no interest) as the first learning data.
  • the comfort judgment model learning unit 81 (for example, the comfort judgment model learning unit 14) that learns the comfort judgment model using the comfort value indicating the above as the objective variable and each of the comfort indexes as the explanatory variable, and the vehicle while riding.
  • Explanatory variables used in the comfort determination model (for example, heart rate per 60 seconds) generated based on the comfort index of the subject, and the vehicle when the comfort index was acquired.
  • Personal data generation unit 82 (for example, personal data generation unit 22) that generates personal data including the operating status (for example, accelerator opening, brake pressure, handle operation angle, etc.) for each target person, and personal data.
  • a driving data generation unit 83 that calculates a comfort value by applying it to a comfort determination model and generates driving data indicating a comfortable driving situation and driving data indicating an unpleasant driving situation according to the calculated comfort value. For example, it is provided with an operation data generation unit 24).
  • the comfortable driving data collection system 80 uses the driving data indicating a comfortable driving condition and the driving data indicating an unpleasant driving condition as the second learning data to indicate the comfortable condition of the subject according to the driving condition.
  • a riding model learning unit for example, an individual riding model learning unit 26, a general-purpose riding model learning unit 26a
  • a riding model for example, an individual riding model or a general-purpose riding model
  • the boarding model learning unit may learn the boarding model by reverse reinforcement learning.
  • the comfortable driving data collection system 80 is a comfortable driving information output unit (for example, a comfortable driving information output device 30) that outputs a result of comparing the driving situation of the vehicle while the subject is riding with the determination result by the riding model. ) May be provided. According to such a configuration, the subject can grasp the comfort condition of the passenger estimated by using the driving data collected efficiently.
  • a comfortable driving information output unit for example, a comfortable driving information output device 30
  • the driving data generation unit when the comfort value exceeds a threshold value (for example, a threshold value of 0.5), the driving data generation unit provides driving data in which the driving situation included in the personal data and the comfortable driving flag are associated with each other as comfortable driving data.
  • a threshold value for example, a threshold value of 0.5
  • driving data in which the driving situation included in the personal data and the unpleasant driving flag are associated with each other may be generated as the unpleasant driving data.
  • FIG. 9 is a block diagram showing an outline of the operation control device according to the present invention.
  • the driving control device 90 (for example, the driving control device 300) according to the present invention shows a comfort index and comfort which are indexes for measuring whether or not an individual is comfortable when an activity classified as a comfortable activity is performed.
  • the first learning data is the comfort activity data associated with the teacher label and the discomfort activity data associated with the comfort index when the activity classified as unpleasant activity is performed and the teacher label indicating discomfort.
  • the comfort index of the subject riding the vehicle is used for a comfort judgment model in which the comfort value indicating the degree of comfort, which is learned by using the data, is used as the objective variable and each of the comfort indexes is used as the explanatory variable.
  • a riding model that shows the comfort status of the subject according to the driving status, which was learned by using the driving data indicating the comfortable driving status and the driving data indicating the unpleasant driving status, which are generated accordingly, as the second training data.
  • Information that controls the driving of the vehicle based on the results of the determination by the comfortable driving determination unit 91 (for example, the comfortable driving determination unit 32) that determines driving that the subject feels comfortable with, and the comfortable driving determination unit 91.
  • a comfortable driving information output unit 92 (for example, a comfortable driving information output unit 33) is provided.
  • Comfort activity data in which a comfort index, which is an index for measuring whether or not an individual is comfortable when an activity classified as a comfortable activity is performed, and a teacher label indicating comfort are associated with each other, and comfort activity data.
  • a comfort value indicating the degree of comfort using the discomfort activity data in which the comfort index associated with the teacher label indicating discomfort when an activity classified as an unpleasant activity is performed is used as the first learning data.
  • a comfort judgment model learning unit that learns a comfort judgment model with each of the comfort indexes as an explanatory variable. An individual including explanatory variables used in the comfort determination model generated based on the comfort index of the subject who is riding the vehicle, and the driving status of the vehicle when the comfort index is acquired.
  • a personal data generation unit that generates data for each target person, the comfort value is calculated by applying the personal data to the comfort determination model, and a comfortable driving situation is shown according to the calculated comfort value.
  • a comfortable driving data collection system including a driving data generator that generates driving data and driving data indicating an unpleasant driving situation.
  • Appendix 2 A riding model that learns a riding model that shows the comfortable situation of the target person according to the driving situation by using the driving data that shows the comfortable driving situation and the driving data that shows the unpleasant driving situation as the second learning data.
  • the riding model learning unit is a comfort driving data collection system according to Appendix 2, which learns a riding model by reverse reinforcement learning.
  • Appendix 4 The comfort driving data collection system according to Appendix 2 or Appendix 3 provided with a comfortable driving information output unit that outputs a result of comparing the driving status of the vehicle while the subject is riding with the judgment result by the riding model. ..
  • the driving data generation unit When the comfort value exceeds the threshold value, the driving data generation unit generates driving data in which the driving situation included in the personal data and the comfortable driving flag are associated with each other as the comfortable driving data, and the comfort value is calculated. If it is below the threshold value, the comfort driving data according to any one of Appendix 1 to Appendix 4 for generating driving data in which the driving situation included in the personal data and the unpleasant driving flag are associated with each other as unpleasant driving data. Collection system.
  • Comfort activity data in which a comfort index, which is an index for measuring whether or not an individual is comfortable when an activity classified as a comfortable activity is performed, and a teacher label indicating comfort are associated with each other, and comfort activity data.
  • the degree of comfort learned using the discomfort activity data in which the comfort index associated with the teacher label indicating discomfort when the activity classified as unpleasant activity is performed is used as the first training data.
  • Comfortable driving conditions generated according to the explanatory variables used in the comfort determination model and the comfort values obtained by applying personal data including the driving conditions of the vehicle when the comfort index is acquired.
  • An operation control including a comfortable driving determination unit for determining driving and a comfortable driving information output unit for outputting information for controlling the operation of the vehicle based on the result of determination by the comfortable driving determination unit. apparatus.
  • Comfort activity data in which a comfort index, which is an index for measuring whether or not an individual is comfortable when an activity classified as a comfortable activity is performed, and a teacher label indicating comfort are associated with each other, and comfort activity data.
  • a comfort value indicating the degree of comfort using the discomfort activity data in which the comfort index associated with the teacher label indicating discomfort when an activity classified as an unpleasant activity is performed is used as the first learning data.
  • the comfort determination model generated based on the comfort index of the subject who is riding the vehicle by learning the comfort determination model with each of the comfort indexes as the explanatory variable.
  • Personal data including the explanatory variables used and the driving status of the vehicle when the comfort index is acquired is generated for each subject, and the personal data is applied to the comfort determination model to obtain the comfort value.
  • a method for collecting comfort driving data which is calculated and generates driving data indicating a comfortable driving condition and driving data indicating an unpleasant driving condition according to the calculated comfort value.
  • Appendix 7 The described comfort driving data collection method.
  • Comfort activity data in which a comfort index, which is an index for measuring whether or not an individual is comfortable when an activity classified as a comfortable activity is performed, and a teacher label indicating comfort are associated with each other, and comfort activity data.
  • the degree of comfort learned using the discomfort activity data in which the comfort index associated with the teacher label indicating discomfort when the activity classified as unpleasant activity is performed is used as the first training data.
  • Comfortable driving conditions generated according to the explanatory variables used in the comfort determination model and the comfort values obtained by applying personal data including the driving conditions of the vehicle when the comfort index is acquired.
  • a driving control method characterized in that driving is determined and information for controlling the driving of the vehicle is output based on the result of the determination.
  • Comfort activity data in which a comfort index, which is an index for measuring whether or not an individual is comfortable when an activity classified as a comfortable activity is performed, and a teacher label indicating comfort are associated with the computer.
  • the degree of comfort is determined by using the discomfort activity data in which the comfort index and the teacher label indicating discomfort are associated with each other when the activity classified into the discomfort activity is performed as the first learning data.
  • a comfort judgment model learning process that learns a comfort judgment model that uses the indicated comfort value as an objective variable and each of the comfort indexes as an explanatory variable, and is generated based on the comfort index of a subject who is riding in a vehicle.
  • the personal data generation process that generates personal data including the explanatory variables used in the comfort determination model and the driving status of the vehicle when the comfort index is acquired for each subject, and the individual.
  • the operation that applies the data to the comfort determination model to calculate the comfort value, and generates driving data indicating a comfortable driving condition and driving data indicating an unpleasant driving condition according to the calculated comfort value.
  • Comfortable driving data collection program for executing data generation processing.
  • Comfort activity data in which a comfort index, which is an index for measuring whether or not an individual is comfortable when an activity classified as a comfortable activity is performed, and a teacher label indicating comfort are associated with the computer.
  • comfort learned using the discomfort activity data in which the comfort index and the teacher label indicating the discomfort are associated with each other when the activity classified into the unpleasant activity is performed as the first learning data.
  • a comfort determination model in which a comfort value indicating the degree of is used as an objective variable and each of the comfort indexes is used as an explanatory variable, for each subject based on the comfort index of the subject riding in the vehicle.
  • the comfortable driving information output processing unit that outputs information for controlling the driving of the vehicle based on the comfortable driving determination process for determining the driving that feels comfortable and the determination result in the comfortable driving determination process. Operation control program.
  • Comfort judgment model generator 11 Sensor 12 Activity data generation unit 13 Activity data storage unit 14 Comfort judgment model learning unit 15 Comfort judgment model storage unit 20
  • Individual ride model generator 20a General-purpose ride model generator 21
  • Driving data storage unit 26 Individual riding model learning unit 26a
  • General-purpose riding model learning unit 27 Individual riding model storage unit 27a
  • General-purpose riding model storage unit 30 Comfortable driving information output device 31
  • Driving status Acquisition unit 32 Comfortable driving judgment unit 33 Comfortable driving information output unit 100 Comfortable situation judgment system 200 Comfortable driving data collection system 300 Operation control device

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • General Physics & Mathematics (AREA)
  • Medical Informatics (AREA)
  • Automation & Control Theory (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Pathology (AREA)
  • Animal Behavior & Ethology (AREA)
  • Psychology (AREA)
  • Psychiatry (AREA)
  • Hospice & Palliative Care (AREA)
  • Educational Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Developmental Disabilities (AREA)
  • Surgery (AREA)
  • Social Psychology (AREA)
  • Child & Adolescent Psychology (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Human Computer Interaction (AREA)
  • Computational Linguistics (AREA)
  • Traffic Control Systems (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
PCT/JP2020/020333 2019-07-19 2020-05-22 快適性運転データ収集システム、運転制御装置、方法、および、プログラム Ceased WO2021014738A1 (ja)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2021534561A JP7238994B2 (ja) 2019-07-19 2020-05-22 快適性運転データ収集システム、運転制御装置、方法、および、プログラム
US17/627,969 US12103543B2 (en) 2019-07-19 2020-05-22 Comfort driving data collection system, driving control device, method, and program

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2019133484 2019-07-19
JP2019-133484 2019-07-19

Publications (1)

Publication Number Publication Date
WO2021014738A1 true WO2021014738A1 (ja) 2021-01-28

Family

ID=74194127

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2020/020333 Ceased WO2021014738A1 (ja) 2019-07-19 2020-05-22 快適性運転データ収集システム、運転制御装置、方法、および、プログラム

Country Status (3)

Country Link
US (1) US12103543B2 (https=)
JP (1) JP7238994B2 (https=)
WO (1) WO2021014738A1 (https=)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114897065A (zh) * 2022-05-06 2022-08-12 西安理工大学 基于单元与多元融合预测模型的高速列车节能驾驶策略

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021014738A1 (ja) * 2019-07-19 2021-01-28 日本電気株式会社 快適性運転データ収集システム、運転制御装置、方法、および、プログラム
CN111861128B (zh) * 2020-06-20 2024-03-22 清华大学 自动驾驶车辆人机协同操纵过程的接管舒适性评价方法、系统及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006130121A (ja) * 2004-11-08 2006-05-25 Univ Nihon 生体情報に基づく感情認識方法
WO2017163538A1 (ja) * 2016-03-25 2017-09-28 ソニー株式会社 情報処理装置
WO2018109863A1 (ja) * 2016-12-14 2018-06-21 三菱電機株式会社 状態推定装置
JP2018152072A (ja) * 2017-03-14 2018-09-27 ヒュンダイ・モービス・カンパニー・リミテッド 車両安全支援装置および方法

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1961639A1 (en) 2007-02-22 2008-08-27 Nederlandse Organisatie voor toegepast- natuurwetenschappelijk onderzoek TNO Vehicle driving assistance
JP7012933B2 (ja) 2017-03-23 2022-01-31 東芝情報システム株式会社 運転支援装置および運転支援システム
WO2018211301A1 (en) * 2017-05-15 2018-11-22 Toyota Motor Europe Control device, system, and method for determining a comfort level of a driver
JP7233449B2 (ja) * 2019-02-04 2023-03-06 三菱電機株式会社 感情推定装置及び感情推定方法
US11548518B2 (en) * 2019-06-28 2023-01-10 Woven Planet North America, Inc. Subjective route comfort modeling and prediction
WO2021014738A1 (ja) * 2019-07-19 2021-01-28 日本電気株式会社 快適性運転データ収集システム、運転制御装置、方法、および、プログラム
KR102735979B1 (ko) * 2019-10-29 2024-11-28 현대자동차주식회사 뇌파 신호를 이용한 모빌리티 탑승자의 승차감 판단 장치
DE102020126676A1 (de) * 2020-10-12 2022-04-14 Bayerische Motoren Werke Aktiengesellschaft Fahrzeugführungssystem und Verfahren zum Betreiben einer Fahrfunktion in Abhängigkeit von Fahrerdaten
US20220330848A1 (en) * 2021-04-16 2022-10-20 Bayerische Motoren Werke Aktiengesellschaft Method, Computer Program, and Device for Determining Vehicle Occupant Respiration
US12311982B2 (en) * 2021-06-04 2025-05-27 Toyota Motor Engineering & Manufacturing North America, Inc. Systems and methods for displaying trajectories for autonomous vehicles
US20230256994A1 (en) * 2022-02-16 2023-08-17 Gm Cruise Holdings Llc Assessing relative autonomous vehicle performance via evaluation of other road users
JP2023129312A (ja) * 2022-03-02 2023-09-14 日本電気株式会社 分類装置、分類方法、及びプログラム

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006130121A (ja) * 2004-11-08 2006-05-25 Univ Nihon 生体情報に基づく感情認識方法
WO2017163538A1 (ja) * 2016-03-25 2017-09-28 ソニー株式会社 情報処理装置
WO2018109863A1 (ja) * 2016-12-14 2018-06-21 三菱電機株式会社 状態推定装置
JP2018152072A (ja) * 2017-03-14 2018-09-27 ヒュンダイ・モービス・カンパニー・リミテッド 車両安全支援装置および方法

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114897065A (zh) * 2022-05-06 2022-08-12 西安理工大学 基于单元与多元融合预测模型的高速列车节能驾驶策略

Also Published As

Publication number Publication date
JPWO2021014738A1 (https=) 2021-01-28
JP7238994B2 (ja) 2023-03-14
US20220274608A1 (en) 2022-09-01
US12103543B2 (en) 2024-10-01

Similar Documents

Publication Publication Date Title
US20250098999A1 (en) Method and system for monitoring and improving attention
JP7754630B2 (ja) ドライバー監視システムでメディア誘発感情から運転感情を分離するための技術
US10325066B2 (en) System for mental health clinical application
Babiker et al. Pupillary behavior in positive and negative emotions
JP7238994B2 (ja) 快適性運転データ収集システム、運転制御装置、方法、および、プログラム
WO2019086856A1 (en) Systems and methods for combining and analysing human states
JP7297342B1 (ja) 脳情報の分析によるレコメンデーション
KR20150137453A (ko) 뇌파를 이용한 제어 방법 및 휴대 장치
WO2018222589A1 (en) System and method for treating disorders with a virtual reality system
JP2021114004A (ja) 情報処理装置及び情報処理方法
Redd et al. Physiological signal monitoring for identification of emotional dysregulation in children
JP3523007B2 (ja) 満足感計測システムおよびフィードバック装置
JP7843663B2 (ja) 推定装置、推定システム、および、推定方法
Babiker et al. Non-conscious behavior in emotion recognition: gender effect
JP2020170471A (ja) 運転支援装置
WO2022259464A1 (ja) 情報処理装置、制御方法及び記憶媒体
WO2021053950A1 (ja) 情報処理装置および情報処理プログラム
WO2024204779A1 (ja) 自覚的指標の値を推定するためのシステム、方法、およびプログラム
NL1043927B1 (en) A system for emotion detection and a method for personalized patterns in emotion-related physiology thereof
WO2024252980A1 (ja) 情報処理方法及び情報処理装置
Lukosik Research on the Influence of Noise on Concentration Using Brain-Computer Interface Technology
JP2026073391A (ja) システム
JP2024169061A (ja) 推定装置、推定システム、推定方法、及び推定プログラム
JP2025162301A (ja) 感情推定装置、キャリブレーション方法、感情推定プログラムおよび感情推定システム
JP2026025323A (ja) システム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20843779

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2021534561

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20843779

Country of ref document: EP

Kind code of ref document: A1