Control support device, vehicle, control support method, recording medium, learned model for causing computer to function, and method of generating learned model

A control support device for supporting control of a vehicle using a learned model obtained by machine learning, the control support device comprising:

• a data acquisition unit configured to acquire sensor information, which is related to a state of an inside or an outside of a supplying vehicle that supplies a parameter used for the machine learning;
• a learning unit configured to generate a plurality of learned models by performing the machine learning using an input/output data set, which is the sensor information acquired by the data acquisition unit from a plurality of the supplying vehicles and is data including input parameters and an output parameter of the learned model;
• a selection unit configured to select a learned model to be transmitted to the vehicle, control of which is supported, from among the plurality of learned models;
• and
• a transmission unit configured to transmit the selected learned model to the vehicle.

A control support device for supporting control of a vehicle using a learned model obtained by machine learning, the control support device comprising:

• a data acquisition unit configured to acquire sensor information, which is related to a state of an inside or an outside of a supplying vehicle that supplies parameters to be used for the machine learning;
• a learning unit configured to generate a plurality of learned models by performing the machine learning using an input/output data set, which is the sensor information acquired by the data acquisition unit from a plurality of the supplying vehicles and is data including input parameters and an output parameter of the learned model;
• a selection unit configured to select a learned model from among the plurality of learned models;
• a prediction unit configured to calculate an output parameter, which is obtained by inputting sensor information of the vehicle, control of which is supported, to the selected learned model as input parameters;
• and
• a transmission unit configured to transmit the calculated output parameter to the vehicle.

A control support device communicating with a server storing a learned model obtained by machine learning, the control support device supporting control of a vehicle using the learned model, the control support device comprising:

• a data acquisition unit configured to acquire sensor information, which is related to a state of an inside or an outside of a supplying vehicle, the data acquisition unit being mounted on the supplying vehicle that obtains parameters to be used for the machine learning;
• a learning unit configured to generate a learned model by performing the machine learning using an input/output data set, which is the sensor information acquired by the data acquisition unit and is data including input parameters and an output parameter of the learned model;
• and
• a transmission unit configured to transmit the generated learned model to the server.

A vehicle comprising a vehicle control device communicating with a server which stores a learned model obtained by machine learning,

• wherein the server comprises:
• a server storage unit configured to store the learned model, which is generated by the machine learning, which is performed by using sensor information, which is related to a state of an inside or an outside of a supplying vehicle that supplies parameters to be used for the machine learning as an input/output data set, which is data including input parameters and an output parameter of the learned model;
• and
• a server communication unit configured to transmit at least one of the generated learned model and an output parameter, which is calculated by input of sensor information of the vehicle as an input parameter to the learned model in a case where the sensor information of the vehicle is received, and
• the vehicle control device comprises:
• a data acquisition unit configured to acquire sensor information, which is related to a state of an inside or an outside of the vehicle;
• and
• a communication unit configured to transmit a model request signal requesting transmission of the learned model or a parameter request signal requesting transmission of an output parameter calculated on a basis of the sensor information acquired by the data acquisition unit and the sensor information to the server and receive the generated learned model or the calculated output parameter in response to the model request signal or the parameter request signal, respectively.

A vehicle comprising a vehicle control device communicating with a server which stores a learned model obtained by machine learning,

• wherein the server comprises:
• a server learning unit configured to generates a learned model by performing the machine learning using an input/output data set, which is sensor information related to a state of an inside or an outside of a vehicle and is data including input parameters and an output parameter of the learned model, and
• the vehicle control device comprises:
• a data acquisition unit configured to acquire sensor information, which is related to a state of an inside or an outside of the vehicle;
• and
• a transmission unit configured to transmit the sensor information acquired by the data acquisition unit to the server.

A vehicle comprising a vehicle control device communicating with a server which stores a learned model obtained by machine learning,

• wherein the vehicle control device comprises:
• a data acquisition unit configured to acquire sensor information, which is related to a state of an inside or an outside of the vehicle;
• a learning unit configured to generate a learned model by performing the machine learning using an input/output data set, which is the sensor information acquired by the data acquisition unit and is data including input parameters and an output parameter of the learned model;
• and
• a transmission unit configured to transmit the learned model generated by the learning unit to the server.

A control support method executed by a control support device which supports control of a vehicle using a learned model obtained by machine learning, the control support method comprising:

• a data acquisition step of acquiring sensor information, which is related to a state of an inside or an outside of a supplying vehicle that supplies parameters to be used for the machine learning;
• a learning step of reading an input/output data set, which is the sensor information acquired in the data acquisition step and is data including an input parameter and an output parameter of the learned model, from a storage unit and generating a learned model by performing the machine learning using the read input/output data set;
• and
• a transmission step of transmitting at least one of the generated learned model and an output parameter obtained by inputting sensor information of the vehicle, control of which is supported, to the learned model as an input parameter.

A non-transitory computer readable recording medium storing a control support program for causing a control support device, which supports control of a vehicle using a learned model obtained by machine learning, to execute:

• a data acquisition step of acquiring sensor information, which is related to a state of an inside or an outside of a supplying vehicle that supplies parameters to be used for the machine learning;
• a learning step of reading an input/output data set, which is the sensor information acquired in the data acquisition step and is data including an input parameter and an output parameter of the learned model, from a storage unit and generating a learned model by performing the machine learning using the read input/output data set;
• and
• a transmission step of transmitting at least one of the generated learned model and an output parameter obtained by inputting sensor information of the vehicle, control of which is supported, to the learned model as an input parameter.

A learned model comprising a neural network,

• wherein the neural network comprises:
• an input layer configured to receive input of input parameters that quantify a state of an inside or an outside of a vehicle;
• an intermediate layer configured to receive input of signals output from the input layer, the intermediate layer having a multilayer structure;
• and
• an output layer configured to receive input of signals output from the intermediate layer and output an output parameter that quantifies a predetermined state of the vehicle,
• each of the layers includes one or more nodes,
• the learned model is associated with travel history information of the vehicle, and
• the learned model causes a computer to input the input parameters to the input layer, perform calculation based on a network parameter of the neural network which is a learned network parameter, and output a value that quantifies the predetermined state of the vehicle from the output layer.