Abstract: A coating material composition includes an organic polyisocyanate (A) and an acrylic polyol (B), wherein the organic polyisocyanate (A) contains a modified polyisocyanate (a), the modified polyisocyanate (a) is a reaction product of a polyisocyanate component (al) and a polyol component (a2) or its modified product, the polyisocyanate component (al) contains an organic diisocyanate or its modified product, the polyol component (a2) contains at least one selected from the group consisting of polytetramethylene glycol and polycarbonate polyols which have a number average molecular weight of 200 to 750, and the acrylic polyol (B) contains an acrylic polyol (b) having a glass transition temperature of 5 to 30° C. and a hydroxyl value of more than 100 mg KOH/g and 150 mg KOH/g or less.

Abstract: The road obstacle detection device includes a semantic label estimation unit that estimates a semantic label for each pixel of an image using a classifier learned in advance and generates a semantic label image, an original image estimation unit for reconstruction of the original image from the semantic label image, a difference calculating unit for calculating a difference between the original image and the reconstructed image from the original image estimation unit as a calculation result, and a road obstacle detection unit for detecting a road obstacle based on the calculation result.

Abstract: A road obstacle detection device which uses a pre-learned first identifier to associate a semantic label with each pixel of an image, uses a pre-learned second identifier to estimate a statistical distribution of a semantic label of a predetermined region of interest of the image from a statistical distribution of a semantic label of a peripheral region that surrounds the region of interest, and uses the statistical distribution of the semantic label associated with the region of interest and the statistical distribution of the semantic label estimated for the region of interest to estimate a likelihood that an object is a road obstacle.

Abstract: In a road obstacle detection device, a first derivation unit derives, for each of a plurality of local regions, a probability that a local region is the road, such that the probability is higher as the ratio of a road region in the local region is higher; and a second derivation unit derives a probability that a target local region is not a previously decided normal physical body, and derives a probability that a road obstacle exists at the target local region, based on the derived probability that the target local region is not the normal physical body and a probability that a peripheral local region is the road, the peripheral local region being a local region at a periphery of the target local region, the probability that the peripheral local region is the road being derived by the first derivation unit.

Abstract: An image processing device includes a processor including hardware, the processor being configured to: generate a semantic label image by estimating a semantic label for each pixel of an input image by using a discriminator trained in advance; generate a restored image by estimating an original image from the semantic label image; calculate a first difference between the input image and the restored image; and update an estimation parameter for estimating the semantic label or an estimation parameter for estimating the original image based on the first difference.

Abstract: The road obstacle detection device includes a semantic label estimation unit that estimates a semantic label for each pixel of an image using a classifier learned in advance and generates a semantic label image, an original image estimation unit for reconstruction of the original image from the semantic label image, a difference calculating unit for calculating a difference between the original image and the reconstructed image from the original image estimation unit as a calculation result, and a road obstacle detection unit for detecting a road obstacle based on the calculation result.

Abstract: A road obstacle detection device which uses a pre-learned first identifier to associate a semantic label with each pixel of an image, uses a pre-learned second identifier to estimate a statistical distribution of a semantic label of a predetermined region of interest of the image from a statistical distribution of a semantic label of a peripheral region that surrounds the region of interest, and uses the statistical distribution of the semantic label associated with the region of interest and the statistical distribution of the semantic label estimated for the region of interest to estimate a likelihood that an object is a road obstacle.

Abstract: A path prediction device comprises a storage unit that generates and stores, based on information collected from a plurality of vehicles including a first vehicle, traveling path information indicating information associated with paths where the respective vehicles have traveled; a positional information acquisition unit that acquires a first position indicating the current position of the first vehicle; and a path prediction unit that predicts the traveling path of the first vehicle using at least one of first path information indicating paths of the first vehicle and second path information indicating paths of second vehicles among the traveling path information, wherein the path prediction unit determines a use ratio of the first path information, which is used to predict the traveling path, based on a past traveling record of the first vehicle at the first position.

Abstract: A route generation device configured to generate a travel route of a traveling body that travels through a network configured of a node and a link, the route generation device includes a route model storage unit configured to store a route model that is data in which a frequency of travel through each link by the traveling body in a past trip performed by the traveling body is classified by destination of the trip; a trip acquisition unit configured to acquire a route starting point and a destination of a traveling body; and a route generation unit configured to extract a set of links corresponding to the acquired destination from the route model, and generate at least a part of a route of the traveling body from the route starting point to the destination based on the travel frequency associated with the extracted link.

Abstract: An information collection apparatus collecting data sensed by a plurality of mobile sensors, the information collection apparatus comprises a condition setting unit configured to set a target area and a target time period in which data is to be collected; a position information storage unit configured to acquire and store position information of the mobile sensors; a mobile sensor selection unit configured to select, based on the history of position information of the mobile sensors and the target time period, a plurality of the mobile sensors for collecting a given amount of data sensed in the target area; and a collection unit configured to collect data from the plurality of selected mobile sensors.

Abstract: A path prediction device comprises a storage unit that generates and stores, based on information collected from a plurality of vehicles including a first vehicle, traveling path information indicating information associated with paths where the respective vehicles have traveled; a positional information acquisition unit that acquires a first position indicating the current position of the first vehicle; and a path prediction unit that predicts the traveling path of the first vehicle using at least one of first path information indicating paths of the first vehicle and second path information indicating paths of second vehicles among the traveling path information, wherein the path prediction unit determines a use ratio of the first path information, which is used to predict the traveling path, based on a past traveling record of the first vehicle at the first position.

Abstract: A route generation device configured to generate a travel route of a traveling body that travels through a network configured of a node and a link, the route generation device includes a route model storage unit configured to store a route model that is data in which a frequency of travel through each link by the traveling body in a past trip performed by the traveling body is classified by destination of the trip; a trip acquisition unit configured to acquire a route starting point and a destination of a traveling body; and a route generation unit configured to extract a set of links corresponding to the acquired destination from the route model, and generate at least a part of a route of the traveling body from the route starting point to the destination based on the travel frequency associated with the extracted link.

Abstract: A vehicle seat according to the present invention may include a seat cushion that is composed of a stationary cushion portion and a movable cushion portion, in which the movable cushion portion is capable of being tilted so as to be low in a getting in/out side while being raised with respect to the stationary cushion portion, and a cushion tilting mechanism that is disposed under the seat cushion and is configured to tilt the movable cushion portion while raising the same with respect to the stationary cushion portion.

Abstract: A bracket of a rotation device of the present invention has a guide mechanism that is configured to guide a first motor and a second motor so as to rotate the same about an axis of a cylindrical rotating body relative to each other. A first gear and a second gear can respectively be meshed with rotating body side gears corresponding thereto while the first motor or the second motor is deviated around the axis of the cylindrical rotating body from a normal attachment position with respect to the bracket. Further, the first motor or the second motor can be guided to the normal attachment position by the guide mechanism in the condition.

Abstract: An engagement fixture of a shoulder belt is connected to and supported by an engagement buckle disposed in a vehicle interior. When a platform is positioned in a getting in/out position in a vehicle exterior, the engagement fixture of the shoulder belt can be temporarily connected to a temporary fastening fixture provided to the platform. To the contrary, when the platform is positioned in a loading position in a vehicle interior, a connection condition of the engagement fixture of the shoulder belt can be changed from a temporary connection of the fastening fixture to a securely supportable connection of an engagement buckle in the vehicle interior. Thus, it is possible to simplify a belt attaching operation after a wheelchair is loaded in a vehicle while a columnar support member used in the conventional platform is abolished.

Abstract: A bracket of a rotation device of the present invention has a guide mechanism that is configured to guide a first motor and a second motor so as to rotate the same about an axis of a cylindrical rotating body relative to each other. A first gear and a second gear can respectively be meshed with rotating body side gears corresponding thereto while the first motor or the second motor is deviated around the axis of the cylindrical rotating body from a normal attachment position with respect to the bracket. Further, the first motor or the second motor can be guided to the normal attachment position by the guide mechanism in the condition.

Abstract: An engagement fixture of a shoulder belt is connected to and supported by an engagement buckle disposed in a vehicle interior. When a platform is positioned in a getting in/out position in a vehicle exterior, the engagement fixture of the shoulder belt can be temporarily connected to a temporary fastening fixture provided to the platform. To the contrary, when the platform is positioned in a loading position in a vehicle interior, a connection condition of the engagement fixture of the shoulder belt can be changed from a temporary connection of the fastening fixture to a securely supportable connection of an engagement buckle in the vehicle interior. Thus, it is possible to simplify a belt attaching operation after a wheelchair is loaded in a vehicle while a columnar support member used in the conventional platform is abolished.

Abstract: A mechanism for rotating a vehicle seat body and a mechanism for restraining rotation of the seat body are partially shared, reducing the number of parts. The seat includes a seat body, a seat rotation mechanism, a gear forming member having a rotation gear, a drive gear meshable with the rotation gear, and an actuator for rotating the drive gear. The seat further includes a moving mechanism that relatively moves the drive gear and the gear forming member in a direction of a rotation restraint position such that the drive gear is placed in such a position so as to interfere with the gear forming member when the seat body rotates to a first position and when the seat body is urged to rotate in a direction of a second position while the drive gear is in such a position so as to not mesh with the rotation gear.

Abstract: A vehicle seat according to the present invention may include a seat cushion that is composed of a stationary cushion portion and a movable cushion portion, in which the movable cushion portion is capable of being tilted so as to be low in a getting in/out side while being raised with respect to the stationary cushion portion, and a cushion tilting mechanism that is disposed under the seat cushion and is configured to tilt the movable cushion portion while raising the same with respect to the stationary cushion portion.

Abstract: A mechanism for rotating a vehicle seat body and a mechanism for restraining rotation of the seat body are partially shared, reducing the number of parts. The seat includes a seat body, a seat rotation mechanism, a gear forming member having a rotation gear, a drive gear meshable with the rotation gear, and an actuator for rotating the drive gear. The seat further includes a moving mechanism that relatively moves the drive gear and the gear forming member in a direction of a rotation restraint position such that the drive gear is placed in such a position so as to interfere with the gear forming member when the seat body rotates to a first position and when the seat body is urged to rotate in a direction of a second position while the drive gear is in such a position so as to not mesh with the rotation gear.