Toyota Jidosha Kabushiki Kaisha

Hiroshi Oyagi

Hirokazu Ito

Tomohiro Kaneko

Yusuke Takasu

Yuki Takahashi

Akira Yamashita

Norimi Asahara

Keisuke Nagasaka

Kazuyasu Iwata

Shinya Shiratori

Daiki Yokoyama

Shigeki Nakayama

Masaki Ito

Yoshihisa Shinoda

Yoshio Yamashita

Koji Ide

Taro Aoyama

Kazuki Iwatani

Kazuhiko Seguchi

Kentaro Nishida

Akira Hojo

A machine learning device includes a processor which performs, when performing learning of a model with image data, the learning of the model while excluding the image data of an animal having a feature amount common with a feature amount of a human.

Machine learning device and recording medium

A control device includes a processor that acquires travel data of a target vehicle, determines whether the target vehicle obeys a traffic rule, and adjusts a usage form of the travel data in a case of determining that the target vehicle does not obey the traffic rule.

Control device, recording medium, and data generation method

A driving support device, in a mobile body having a plurality of seating positions, includes a processor to set a priority order for seating positions when performing improvement control with respect to emotion of an occupant, acquire a captured image and/or biometric information of the occupant, input thereof to a learning model, and output an emotion estimation result of the occupant, select, in accordance with the priority order, an occupant who is seated in a seated position in which the priority order is set to be high, determine the improvement control for the mobile body based on the emotion estimation result of the selected occupant, and control the mobile body based on the determined improvement control.

Driving support device

A driving support apparatus including a processor, where the processor acquires operation information for an own vehicle by a driver at the time of a driving assistance intervention for keeping a lane of the own vehicle, environmental information including another vehicle around the own vehicle, and biometric information of the driver, estimates emotion of the driver based on the operation information, the environmental information, and the biometric information, estimates control parameters related to an amount of intervention at the time of driving assistance intervention based on the estimation result of emotion of the driver, and controls the own vehicle based on the control parameters.

Determining emotion of a driver during driving assistance

An exhaust purifying apparatus includes an exhaust manifold, a cylindrical catalytic converter, and a cylindrical connection portion that connects the catalytic converter to the exhaust manifold. The exhaust manifold is connected to a side surface of the connection portion. The connection portion is connected to the catalytic converter so as to have the same central axis as the catalytic converter. The connection portion includes a constriction at a part connected to the catalytic converter. A part of the connection portion on an upstream side of the constriction defines a collision diffusion chamber. The cross-sectional flow area of the connection portion orthogonal to the central axis is smaller at the constriction than in the collision diffusion chamber. The constriction is not provided in a vertically lower part of the inner wall of the connection portion in a mounted state of the internal combustion engine.

Exhaust purifying apparatus for internal combustion engine

In an exhaust gas control apparatus for an internal combustion engine in which a catalytic converter is attached to an engine having a plurality of cylinders and a plurality of exhaust passages communicating with the plurality of cylinders, a diffusion portion that promotes a jet flow of a main flow of the exhaust gas flowing into the merging portion is provided at a merging portion connected to a downstream side of the exhaust passage. Further, on the inner wall of the merging portion facing the inlet of the exhaust gas provided in the exhaust passage, a dispersion face for three-dimensionally dispersing the main flow of the exhaust gas flowing linearly into the merging portion from the inlet is formed.

Exhaust gas control apparatus for internal combustion engine

A control device includes: a controller controlling a first vehicle, the controller being configured to estimate a degree of concentration of a driver in the first vehicle during traveling of the first vehicle based on a first distance between the first vehicle and a second vehicle traveling in front of the first vehicle, a second distance between the first vehicle and a third vehicle traveling behind the first vehicle, and a relationship between a vehicle speed of the first vehicle and a predetermined vehicle speed, and execute a vehicle control of recovering the concentration of the driver based on an estimation result.

Control device

A vehicle allocation device allocates a vehicle in response to a vehicle allocation request from a terminal of a user, and includes a vehicle selector configured to, when acquiring the vehicle allocation request, select a vehicle having a relatively large degree of progress in learning of a relation between input and output of a parameter depending on an area to be traveled by the user from a plurality of vehicles learning a relation between input and output of a parameter depending on a predetermined area, and output a vehicle allocation instruction to the selected vehicle.

Vehicle allocation device, vehicle, and terminal

A machine learning device training a learning model unique to a vehicle is provided with: a processor configured to use training data sets including values of state parameters detected by detectors provided at the vehicle, to train the learning model; and if an abnormality occurs in values of a state parameter detected by a detector, acquire values of the state parameter, where an abnormality has occurred, detected by another vehicle under conditions matching detection conditions when the values of the state parameter included in the training data sets were detected by the detector. If an abnormality occurs in values of the state parameter detected by the detector, the training part uses training data sets including values acquired from another vehicle by the parameter value acquiring part, instead of the values of the state parameter where an abnormality has occurred detected by the detector, to train the leaning model.

Machine learning device

A hybrid vehicle includes an internal combustion engine, electric motors, an electric supercharger, a battery, and a controller. The controller determines whether to increase a total electric power supply amount to the electric motor and the electric supercharger from the battery based on a state of charge of the battery. When so determined, electric power supply promotion control is performed to increase the total electric power supply amount from the battery. In the electric power supply promotion control, the controller controls the electric power supply amount to the electric motors and the electric supercharger so as to maximize fuel save rate, which is the percentage of decrease of the fuel consumption of an internal combustion engine relative to an increase in the total electric power supply amount from the battery.

Hybrid vehicle

A machine learning device of an amount of unburned fuel using a neural network in which the correlation functions showing correlations between parameters and an amount of unburned fuel are found for parameters relating to operation of an internal combustion engine, and the parameters with strong degrees of correlation with the amount of unburned fuel exhausted from the engine are selected from among the parameters based on the correlation functions. The amount of unburned fuel is learned by using the neural network from the selected parameters and amount of unburned fuel.

Machine learning device of amount of unburned fuel, machine learning method, learned model, electronic control unit, method of production of electronic control unit, and machine learning system

A learning use data set showing relationships among an engine speed, an engine load rate, an air-fuel ratio of the engine, an ignition timing of the engine, an HC or CO concentration of exhaust gas flowing into an exhaust purification catalyst and a temperature of the exhaust purification catalyst is acquired. The acquired engine speed, engine load rate, air-fuel ratio of the engine, ignition timing of the engine, and HC or CO concentration of the exhaust gas flowing into the exhaust purification catalyst are used as input parameters of a neural network and the acquired temperature of the exhaust purification catalyst is used as training data to learn a weight of the neural network. The learned neural network is used to estimate the temperature of the exhaust purification catalyst.

Machine learning system for estimating a temperature of an exhaust purification catalyst

A turbocharger that includes a turbine and a compressor, an electric supercharger that is arranged in an intake passage, and a control device that increases a rotational speed of the electric supercharger upon receipt of a torque increase request with respect to the internal combustion engine are provided. During a process in which the rotational speed of the electric supercharger is increasing, if the rotational speed arrives at a predetermined switching rotational speed 'Ntec', the control device decreases a rate of increase in the rotational speed from a first rate of increase 'Nteup' to a second rate of increase &#x201c;Nteup&#x201d; (&#x3c;Nteup). At such time, the control device sets each of &#x201c;Ntec&#x201d; and &#x201c;Nteup&#x201d; based on at least any one of an engine speed, a rate of increase in the engine speed, and a supercharging pressure difference between a target supercharging pressure and an actual supercharging pressure.

Control device for internal combustion engine

The invention relates to a control apparatus of an engine. The apparatus carries out a minute-injection for injecting a minute amount of a fuel so as not to generate an engine torque when a required engine load is zero. The apparatus calculates at least one coefficient for correcting a heat release gravity position calculated when the minute-injection is carried out such that it corresponds to its base position and/or for correcting a heat release rate corresponding the gravity position calculated when the minute-injection is carried out such that it corresponds to its base rate. When the required engine load is larger than zero, the apparatus controls the gravity position corrected by the coefficient to its target position.

Control apparatus of internal combustion engine

A control apparatus is provided, which controls combustion state such that the Heat Release Rate Barycentric Position (Gc) coincides with the Target Barycentric Position (Gc*), and which can prevent an increase in the combustion noise caused by an increase in an ignition lag which occurs in a case where an EGR apparatus is in execution, and, a rotational speed is low or an engine load is low. The control apparatus (ECU) prevents the increase in the ignition lag by increasing a supercharging pressure of a supercharger () which the engine () is equipped with, thus, it prevents the increase in the combustion noise.

Growing community of inventors

Susono, Japan

Hiroshi Oyagi