Abstract: An image processing device including a storage unit configured to store an object detection neural network trained using a first K-channel image generated from a first M-channel image and a first N-channel image generated from the first M-channel image, a reception unit configured to receive, from a sensor, a second M-channel image and a second N-channel image that include an identical subject, and an image analysis unit configured to generate, using the object detection neural network trained using the first K-channel image, object detection result information with respect to a second K-channel image generated from the second M-channel image and the second N-channel image, and output the object detection result information.

Abstract: A three-dimensional position and posture recognition device speeds estimation of a position posture and a gripping coordinate posture of a gripping target product. The device includes: a sensor unit configured to measure a distance between an image of an object and the object; and a processing unit configured to calculate an object type included in the image, read model data of each object from the external memory, and create structured model data having a resolution set for each object from the model data, generate measurement point cloud data of a plurality of resolutions from information on a distance between an image of the object and the object, perform a K neighborhood point search using the structured model data and the measurement point cloud data, and perform three-dimensional position recognition processing of the object by rotation and translation estimation regarding a point obtained from the K neighborhood point search.

Abstract: A system for a room with a ceiling is provided. Air supply equipment forms a laminar flow of clean air around a target by supplying the clean air downward from an outlet provided in a first area of the ceiling located directly above the target. Operating light equipment illuminates a working area on the target in a shadowless manner by multiple light sources provided in a second area around the first area. Surface light emitting equipment controls a surface light emitting member provided in a third area around the second area.

Abstract: A computing apparatus includes at least one computing device including a computation area. The computing apparatus acquires input information, generates a plurality of input feature maps from the input information, and performs DNN computation in parallel on the generated plurality of input feature maps by at least one DNN partitioning method including channel partitioning. In the channel partitioning, by grouping the feature maps into sets grouping the feature maps without partitioning the feature maps and allocating each set grouping the feature maps to each computation area, computation for layers is performed.

Abstract: An autonomous driving vehicle information presentation device includes a traffic congestion information acquisition unit that acquires information on traffic congestion ahead in a traveling direction of an own vehicle, a traveling lane identification unit that identifies a lane where the own vehicle is currently located, a stop position prediction unit that acquires a traveling state of a preceding vehicle based on an external environment information and the traffic congestion information, and to predict a stop position related to the preceding vehicle based on the acquired traveling state, an action plan generation unit that generates an action plan of the own vehicle based on the stop position and the currently located lane, and an information presentation unit that presents information including the generated action plan through using an external display device provided at a rear portion of a vehicle interior of the own vehicle.

Abstract: A vehicle control device includes a peripheral object recognition unit configured to recognize an object that is present around a vehicle to be controlled, an object state recognition unit configured to recognize, in a situation where a first object and a second object are recognized by the peripheral object recognition unit, states of the first object and the second object including distance between the vehicle to be controlled and the first object, distance between the vehicle to be controlled and the second object, moving direction of the first object, and moving direction of the second object, and a display control unit configured to cause the display device to execute external notification processing for displaying a notification to the first object or the second object based on the states of the first object and the second object recognized by the object state recognition unit.

Abstract: The time-series signal of the sensor is transformed to the spectral intensity by fast Fourier transform (FFT) or the like, and the one-dimensional data of the spectral intensity is generated. A pseudo image is generated, for example, by repeatedly arranging the one-dimensional data in the vertical direction, or by arranging the one-dimensional data for a plurality of sensors in the vertical direction. The state of the facility is identified by analyzing the pseudo image with an image analysis unit such as a convolutional neural network.

Abstract: A traffic safety support system 1 includes a recognizer configured to recognize traffic participants present near a mobile body 94 that is a support target, a notification device configured to make a risk notification to a driver of the support target, and a risk notification specifier configured to set an operation manner of the risk notification. In a case where the support target is traveling on the road and a first pedestrian 95 is present ahead of the support target, the risk notification specifier calculates a risk value of the first pedestrian 95 and the support target on the road 90 on the basis of the recognition information, and in a case where the risk value exceeds a threshold, sets ON of the risk notification. The risk notification specifier calculates the risk value on the basis of the number of pedestrians present in the vicinity of the first pedestrian 95.

Abstract: An object is to provide a wire straightening device and a wire straightening method, with which it is possible to automatically set the roller spacing in accordance with the type of the wire and to further adjust the roller spacing during operation. A wire straightening device (20) includes a preset value obtaining device that obtains a preset value of roller spacing, which is predetermined for each type of wire (2); a roller spacing automatic setting device that drives an actuator (26a) so that the roller spacing becomes equal to the preset value when the type of the wire (2) is input; and a roller spacing changing device that changes the roller spacing based on an operation by the operator while retaining the preset value during operation of a wire processing device (1).

Abstract: Provided is a training recognition device that implements training of a DNN for article recognition that does not require manual annotation for an image for training and can reduce power consumption, time, and hardware amount required for training.

Abstract: A radar distance measuring device having a BPF type ??ADC and capable of controlling a band of a BBF and modulation setting of a chirp signal in conjunction therewith is provided. A chirp signal generated by a synthesizer is distributed to a transmission antenna and each of mixers at a reception side. The chirp signal is amplified and irradiated from the transmission antenna to an object as radar. The radar reflected by the objects received by reception antennas, and is then mixed with the chirp signal from the synthesizer by the mixers to generate IF signals. These IF signals are respectively outputted to ADCs via anti-aliasing filters. Each of the ADCs is as oversampling ??ADC. The IF signals are sampled by the ??ADC, and are converted into a digital signal.

Abstract: A vehicle control device includes a peripheral object recognition unit configured to recognize an object that is present around a vehicle to be controlled, an object state recognition unit configured to recognize, in a situation where a first object and a second object are recognized by the peripheral object recognition unit, states of the first object and the second object including distance between the vehicle to be controlled and the first object, distance between the vehicle to be controlled and the second object, moving direction of the first object, and moving direction of the second object, and a display control unit configured to cause the display device to execute external notification processing for displaying a notification to the first object or the second object based on the states of the first object and the second object recognized by the object state recognition unit.

Abstract: A MASH type sigma delta AD converter includes a modulator, an analog filter filtering an extraction signal obtained by extracting a probe signal and an quantization error generated in a quantizer within a sigma delta modulator, a low speed AD converter performing an AD conversion of an output signal of the analog filter, a first adaptive filter searching for a transfer function of the sigma delta modulator, a second adaptive filter searching for a transfer function from an output of the modulator to the low speed AD converter via the analog filter, and a noise cancellation circuit cancelling the probe signal and the quantization error included in an output signal of the quantizer using the search results by the first and second adaptive filters.

Abstract: An information processing device includes a parallel deep neural network configured to input a captured image of an article to deep neural network models respectively corresponding to a plurality of articles and perform inferences about the plurality of articles in parallel using the deep neural network models, a new article determination unit configured to determine whether an article included in the image is an unlearned article based on learned model information about the articles and the image, and a new article learning unit configured to learn a deep neural network model corresponding to the article determined to be unlearned based on the image and initial model configuration information about the deep neural network model when the article included in the image is determined to be an unlearned article. The new article learning unit adds the learned deep neural network model to the deep neural network models.

Abstract: A neural network circuit having a plurality of analog-to-digital multipliers generates an analog product-sum voltage corresponding to the sum of charge signals of each of the analog-to-digital multipliers.

Abstract: A reservoir computer includes a reservoir unit including a plurality of neuron circuits and an output layer. Each of the neuron circuits includes a plurality of inputs, an analog output, and a digital output. Each of the plurality of inputs is supplied with the analog output of any one of other neuron circuits, the analog output of the neuron circuit itself, or an analog input signal from the outside. The neuron circuit includes a capacitor circuit, an amplifier, a capacitor memory circuit, a buffer circuit, and an analog-to-digital conversion circuit. The capacitor circuit includes a plurality of capacitors between the plurality of inputs and a single output, performs a product-sum calculation on analog signals supplied to the plurality of inputs together with the amplifier, and performs a non-linear calculation on a result of the product-sum calculation by using saturation characteristics of the amplifier.

Abstract: According to one embodiment, provided is an information processing system including a parent device and a plurality of child devices. The child device constitutes at least a portion of at least one device selected from a function approximator and an annealing machine, each of the parent devices and the plurality of child devices include a communication interface, and the communication interface is at least one selected from a wireless communication interface and a wired communication interface including an analog circuit. Data to be processed by the child device is transmitted from the parent device to at least one of the plurality of child devices, and an output of at least one node of the child device is transmitted to at least one of the parent device and the other child devices.

Abstract: In an autonomous driving vehicle information presentation apparatus, based on outside information, an identification unit searches for a person present around a host vehicle and identifies whether the person extracted by the search matches a user of the host vehicle. When a result of the identification by the identification unit indicates that the person extracted by the search matches the user of the host vehicle, the information presentation unit presents information by using a preset presenting state to a specific person, as a presentation target, identified to match the user of the host vehicle by the identification unit with an exterior display apparatus provided at a front portion of the host vehicle.

Abstract: An autonomous driving vehicle information presentation device includes a traffic congestion information acquisition unit that acquires information on traffic congestion ahead in a traveling direction of an own vehicle, a traveling lane identification unit that identifies a lane where the own vehicle is currently located, a stop position prediction unit that acquires a traveling state of a preceding vehicle based on an external environment information and the traffic congestion information, and to predict a stop position related to the preceding vehicle based on the acquired traveling state, an action plan generation unit that generates an action plan of the own vehicle based on the stop position and the currently located lane, and an information presentation unit that presents information including the generated action plan through using an external display device provided at a rear portion of a vehicle interior of the own vehicle.

Abstract: An information presentation device for an autonomous vehicle that automatically moves to a predetermined position where a user can get into an own vehicle in response to a request from the user includes an identification unit and an information presentation unit. The identification unit searches for a person present around the own vehicle based on external environment information including a target present around the own vehicle, and identifies whether a person extracted by the search coincides with the user of the own vehicle. When the identification indicating, as an identification result of the identification unit, that the person extracted by the search coincides with the user of the own vehicle is performed, the information presentation unit performs presentation of information to be presented to the user, and changes a presentation mode of information to be presented to the user according to a distance from the own vehicle to the user.