Nec Corporation

Jun Nakayamada

Yasunori Futatsugi

Atsushi Fukuzato

Yoshihiro Mishima

Kenji Sobata

Yuki Chiba

This invention is directed to an information processing apparatus that efficiently evaluates artificial intelligence for performing virtual automated driving of a virtual vehicle. This information processing apparatus comprises a generator that generates, from driving environment information generated by a driving environment simulator that simulates a virtual driving environment of a virtual vehicle, driving environment information representing a driving environment in which the virtual vehicle is readily put in a dangerous state and to be provided to artificial intelligence for performing automated driving of the virtual vehicle, an acquirer that acquires a virtual driving result obtained by performing the virtual automated driving of the virtual vehicle by the artificial intelligence in the virtual driving environment, and an evaluator that evaluates performance of the artificial intelligence from the virtual driving result of the virtual automated driving by the artificial intelligence.

Information processing apparatus, information processing method, and information processing program

A dangerous scene prediction devicefor predicting a dangerous scene occurring during driving of a vehicle includes a learning model selection/synthesis unitand a dangerous scene prediction unit. The learning model selection/synthesis unitselects, from two or more learning models, a learning model used for predicting the dangerous scene, depending on a scene determined based on information obtained during the driving of the vehicle. The dangerous scene prediction unitpredicts the dangerous scene occurring during the driving of the vehicle, using the selected learning model.

Dangerous scene prediction device, dangerous scene prediction method, and dangerous scene prediction program

An object recognition systemincludes: a recognition devicethat recognizes an object in an image; and a serverthat generates a learning model. The recognition deviceincludes: a first object recognition unitthat determines a type of the object in the image using the learning model; and an image transmission unitthat transmits a type-indeterminable image, which is an image in which the type has not been determined, to the serverwhen an object included in the type-indeterminable image is an object detected as a three-dimensional object. The serverincludes: a learning devicethat generates the learning model based on training data in which a teacher label is assigned to the type-indeterminable image; and a learning model transmission unitthat transmits the generated learning model to the recognition device. The first object recognition unitdetermines the type of the object in the image using the transmitted learning model.

Object recognition system, recognition device, object recognition method, and object recognition program

An object recognition deviceincludes a scene determination unit, a learning-model selection unit, and an object recognition unit. The scene determination unitdetermines, based on information obtained during driving of a vehicle, a scene of the vehicle. The learning-model selection unitselects, in accordance with the determined scene, a learning model to be used for object recognition from two or more learning models. The object recognition unitrecognizes, using the selected learning model, an object in an image to be photographed during driving of the vehicle.

Object recognition device, object recognition method, and object recognition program

The driver of a vehicle is alerted to occurrence of various pre-dangerous states. There is provided an information processing apparatus including a storage unit that stores information obtained by a traveling simulation of a vehicle in a virtual environment and indicating a pre-dangerous state before the vehicle is set in a dangerous state, a first acquirer that acquires actual information during traveling of the vehicle, and an alert controller that provides an alert of occurrence of the pre-dangerous state based on the actual information acquired by the first acquirer and the information indicating the pre-dangerous state.

Growing community of inventors

Tokyo, Japan

Jun Nakayamada