Abstract: 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.

Abstract: A dangerous scene prediction device 80 for predicting a dangerous scene occurring during driving of a vehicle includes a learning model selection/synthesis unit 81 and a dangerous scene prediction unit 82. The learning model selection/synthesis unit 81 selects, 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 unit 82 predicts the dangerous scene occurring during the driving of the vehicle, using the selected learning model.

Abstract: An object recognition system 80 includes: a recognition device 30 that recognizes an object in an image; and a server 40 that generates a learning model. The recognition device 30 includes: a first object recognition unit 310 that determines a type of the object in the image using the learning model; and an image transmission unit 320 that transmits a type-indeterminable image, which is an image in which the type has not been determined, to the server 40 when an object included in the type-indeterminable image is an object detected as a three-dimensional object. The server 40 includes: a learning device 410 that 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 unit 420 that transmits the generated learning model to the recognition device 30. The first object recognition unit 310 determines the type of the object in the image using the transmitted learning model.

Abstract: An object recognition device 80 includes a scene determination unit 81, a learning-model selection unit 82, and an object recognition unit 83. The scene determination unit 81 determines, based on information obtained during driving of a vehicle, a scene of the vehicle. The learning-model selection unit 82 selects, in accordance with the determined scene, a learning model to be used for object recognition from two or more learning models. The object recognition unit 83 recognizes, using the selected learning model, an object in an image to be photographed during driving of the vehicle.

Abstract: 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.

Abstract: A dangerous scene prediction device 80 for predicting a dangerous scene occurring during driving of a vehicle includes a learning model selection/synthesis unit 81 and a dangerous scene prediction unit 82. The learning model selection/synthesis unit 81 selects, 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 unit 82 predicts the dangerous scene occurring during the driving of the vehicle, using the selected learning model.

Abstract: An object recognition device 80 includes a scene determination unit 81, a learning-model selection unit 82, and an object recognition unit 83. The scene determination unit 81 determines, based on information obtained during driving of a vehicle, a scene of the vehicle. The learning-model selection unit 82 selects, in accordance with the determined scene, a learning model to be used for object recognition from two or more learning models. The object recognition unit 83 recognizes, using the selected learning model, an object in an image to be photographed during driving of the vehicle.

Abstract: An object recognition system 80 includes: a recognition device 30 that recognizes an object in an image; and a server 40 that generates a learning model. The recognition device 30 includes: a first object recognition unit 310 that determines a type of the object in the image using the learning model; and an image transmission unit 320 that transmits a type-indeterminable image, which is an image in which the type has not been determined, to the server 40 when an object included in the type-indeterminable image is an object detected as a three-dimensional object. The server 40 includes: a learning device 410 that 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 unit 420 that transmits the generated learning model to the recognition device 30. The first object recognition unit 310 determines the type of the object in the image using the transmitted learning model.

Abstract: 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.

Abstract: 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.

Abstract: Data in a pre-dangerous state of a vehicle that is difficult to generate in an actual environment is collected efficiently. There is provided an information processing apparatus including a traveling instructor that instructs virtual traveling while providing traveling parameters to a traveling simulator that simulates traveling of at least one virtual peripheral vehicle and a virtual self-vehicle in a virtual environment, and a detector that detects occurrence of a dangerous state for the self-vehicle in the simulation by the traveling simulator.