Nippon Telegraph and Telephone Corporation

Takahiro Hata

Yuki Yokohata

Ippei Shake

Kohei Mori

Manabu Yoshida

Atsuhiko Maeda

Kazuaki Obana

Kouhei Mori

Aki Hayashi

Nobuhiko Matsuura

Hiroshi Nakashima

Shingo Tsukada

Takayuki Ogasawara

Hisashi Kurasawa

Motonori Nakamura

Midori Kodama

Satoshi Fukada

Masumi Yamaguchi

An estimation method includes acquiring sensor information acquired by a sensor mounted on a first vehicle belonging to a vehicle line, acquiring position information on a location of the first vehicle, and estimating a cause of the vehicle line by using the sensor information and the position information. The estimating of the cause includes estimating the cause by using information on a facility or a feature present near the first vehicle, information indicating a state of the first vehicle, information on an object present ahead of the first vehicle included in the sensor information, or information on a road that affects traveling. The information on the facility or the feature is searched based on the position information, the information on the object is estimated based on the sensor information, and the information on the road is searched based on the position information.

Estimation method, estimation apparatus and estimation program of cause of line of vehicles

A position estimation unitestimates, for each movement in a predetermined section, a plurality of position candidates of a position estimation target on the basis of position information and sensor information. A position determination unitevaluates, for each movement in the predetermined section, on the basis of the plurality of position candidates of the position estimation target obtained by the movement in the predetermined section, whether the position information used to estimate the position candidates has an error caused by any of a position of a GPS satellite, a position of a mobile body in a real space, or the mobile body or does not have any error caused thereby. The position determination unitdetermines a final output value of the position of the position estimation target on the basis of a result obtained by removing, from the plurality of estimated position candidates of the position estimation target in the plurality of times of the movement in the predetermined section, a position candidate of the position estimation target estimated in the movement in the predetermined section that has been evaluated to have the error.

Position estimation method, position estimation device, and position estimation program

A technique of estimating, based on a camera image captured from a mobile object, the position coordinates of an ambient object or the mobile object itself is offered. A plurality of camera images that are captured at different geographical locations and contain at least one identical stationary object are acquired; position coordinates of the imaging locations of the corresponding camera images are acquired; and the position coordinates of the stationary object are estimated based on the position coordinates of the imaging locations and gaze vectors oriented from a camera to the stationary object in each of the camera images. Alternatively, a camera image that contains at least two stationary objects having position coordinates that are known is acquired; and the position coordinates of a location at which the camera image is captured are estimated based on the position coordinates of each of the stationary objects and a gaze vector oriented from the camera to each of the stationary objects in the camera image.

Position coordinates estimation device, position coordinates estimation method, and program

A lane pricing technique for charging a mobile body traveling on a road for use of a lane is provided. A lane pricing device according to one embodiment is configured to: acquire from a mobile body traveling on a road, at least one of position information of a mobile body measured based on a positioning signal, and/or a camera image that is acquired by capturing an image from the mobile body and includes a part of a lane in which the mobile body is moving; specify, based on at least one of the position information and/or the camera image, a lane in which the mobile body is moving; acquire lane identification information for identifying a specified lane along with time information indicative of time when the mobile body is moving; and determine and output a toll to be charged to the mobile body in units of lanes based on the lane identification information and the time information.

Lane pricing system, lane pricing device, method, and program

The traffic flow estimation apparatus acquires images and position information and speed information, the images being captured at different timings by a first moving object that is in motion in a target area and including a second moving object around the first moving object, the position information and speed information being of the first moving object at the timings; estimates a lane in which the second moving object is in motion; and estimates a traffic flow for each lane in the target area based on the speed information of the first moving object, the information indicative of a change over time of positions of the second moving object, and the lanes in which the first moving object and the second moving object are in motion.

Traffic flow estimation apparatus, traffic flow estimation method, traffic flow estimation program, and storage medium storing traffic flow estimation program

Provided is a highly reliable technology for optimizing an action for controlling an environment in a target space. An action optimization device for optimizing an action for controlling an environment: acquires environmental data related to a state of the environment; performs time/space interpolation on the acquired environmental data; trains an environment reproduction model, based on the time/space-interpolated environmental data, such that, when a state of an environment and an action for controlling the environment are input, a correct answer value for an environmental state after the action is output; trains an exploration model such that an action to be taken next is output when an environmental state output from the environment reproduction model is input; predicts a second environmental state corresponding to a first environmental state and a first action by using the trained environment reproduction model; explores for a second action to be taken for the second environmental state; and outputs a result of the exploration.

Action optimization device, method and program

A learning-type signal separation method performed using a model formulation unit, which performs learning processing based on a training-use signal including a specific component, and a training-use signal not including the specific component, the training-use signals including a common characteristic. The learning-type signal separation method includes: generating learned data by causing the model formulation unit to perform learning processing based on the training-use signal and information indicating whether or not the specific component is included in the training-use signal, to generate a data series signal in which the specific component has been separated and removed from a data series of the training-use signal; acquiring an arbitrary signal including the common characteristic; and generating, based on the acquired arbitrary signal and the generated learned data, a data series signal in which the specific component has been separated and removed from a data series of the arbitrary signal.

Growing community of inventors

Tokyo, Japan

Takahiro Hata