Abstract: Provided is a voice interaction device capable of turning lines of sight of eyes of an interactive robot to a conversation partner without inhibiting voice interaction. The voice interaction device is incorporated in the interactive robot. The voice interaction device includes a photographing unit configured to photograph an image; an environment recognition unit configured to recognize a position of a conversation partner captured in the image; a display unit disposed at positions of the eyes of the interactive robot and configured to display the eyes of the interactive robot; and an eye control unit configured to turn the lines of sight of the eyes of the interactive robot displayed on the display unit to a position where the conversation partner is recognized.

Abstract: Provided is a voice interaction device capable of reducing a sense of unfriendliness given to a conversation partner. The voice interaction device is incorporated in an interactive robot. The voice interaction device includes a display unit disposed at positions of eyes of the interactive robot and configured to display the eyes of the interactive robot; a distance measurement unit configured to measure a distance between the interactive robot and the conversation partner; and an eye control unit configured to set a size of each of pupils of the interactive robot displayed on the display unit when the distance measured by the distance measurement unit is less than a predetermined distance to be larger than a size of each of the pupils displayed on the display unit when the measured distance is equal to or more than the predetermined distance.

Abstract: A communication device includes a structure, a controller, and sensors that detect the relative position of an object around the structure. The structure has a face unit that is one of the units of the structure. The controller controls the movement of each unit of the structure, thereby causing the structure to perform a gesture expressing a communication behavior. The controller controls the movement of the units so that the structure performs different gestures depending on the angle between the direction of the face unit and the direction of the user's face as viewed from the face unit.

Abstract: According to an embodiment, there is provided a drive assist device including an index calculation unit configured to calculate an index relating to a relative relationship between a vehicle and a target object and a drive assist determination unit configured to determine whether to execute a drive assist control of the vehicle based on the index and as the vehicle width direction component of the relative speed between the vehicle and the target object decreases, the index calculation unit calculates the index with increasing a degree of influence of the relative relationship relating to the vehicle width direction component, or as the vehicle width direction component of the relative distance between the vehicle and the target object increases, the index calculation unit calculates the index with increasing the degree of influence of the relative relationship relating to the vehicle width direction component.

Abstract: A collision avoidance assistance device includes an object detection unit configured to detect the object, a planned execution timing determination unit configured to determine a planned execution timing, a motion characteristics value acquisition unit configured to acquire a motion characteristics value in a comparison target time span which is a predetermined time span later than a detection timing at which the object detection unit detects the object and prior to the planned execution timing, and a collision avoidance assistance determination unit configured to determine whether or not to execute the collision avoidance assistance at the timing prior to the planned execution timing, based on the result of comparison between the motion characteristics value and a reference motion characteristics value in the comparison target time span obtainable from a history of the past motion characteristics values.

Abstract: A collision avoidance assistance device includes an object detection unit configured to detect the object, a planned execution timing determination unit configured to determine a planned execution timing, a motion characteristics value acquisition unit configured to acquire a motion characteristics value in a comparison target time span which is a predetermined time span later than a detection timing at which the object detection unit detects the object and prior to the planned execution timing, and a collision avoidance assistance determination unit configured to determine whether or not to execute the collision avoidance assistance at the timing prior to the planned execution timing, based on the result of comparison between the motion characteristics value and a reference motion characteristics value in the comparison target time span obtainable from a history of the past motion characteristics values.

Abstract: According to an embodiment, there is provided a drive assist device including an index calculation unit configured to calculate an index relating to a relative relationship between a vehicle and a target object and a drive assist determination unit configured to determine whether to execute a drive assist control of the vehicle based on the index and as the vehicle width direction component of the relative speed between the vehicle and the target object decreases, the index calculation unit calculates the index with increasing a degree of influence of the relative relationship relating to the vehicle width direction component, or as the vehicle width direction component of the relative distance between the vehicle and the target object increases, the index calculation unit calculates the index with increasing the degree of influence of the relative relationship relating to the vehicle width direction component.

Abstract: A drive assist device includes: an approach degree calculator configured to calculate a first approach degree of a vehicle to an object in a vehicle traveling direction and to calculate a second approach degree of the vehicle to the object in a direction that intersects the vehicle traveling direction based on a relative velocity between the vehicle and the object; and a drive assist control unit configured to control execution of drive assist based on the first approach degree and the second approach degree.

Abstract: An ECU of a driving support device predicts the risk of contact between a host vehicle and obstacles around the host vehicle when the host vehicle travels by a driving action related to at least one normative action candidate, which is a normative driving action candidate of the host vehicle for the surrounding conditions of the host vehicle. Therefore, it is possible to provide the normative action candidates considering the risk of contact between the host vehicle and the obstacles around the host vehicle.

Abstract: A driving assistance apparatus includes a plurality of model candidates that define a correspondence relationship between a driving operation performed by a driver and information indicating relative positions of a moving body detected on a periphery of a host vehicle and the host vehicle. The driving assistance apparatus determines a model to be used from among the plurality of model candidates on the basis of information relating to the detected moving body, and executes driving assistance on the basis of the determined model and a driving operation performed by the driver following detection of the moving body. Preferably, the determined model can be updated on the basis of the determined model and the driving operation performed by the driver following detection of the moving body.

Abstract: An object of the present invention is to provide a sleep determination device and a sleep determination method capable of precisely determining a sleep stage based on heartbeat information of a subject.

Abstract: An object of the invention is to provide a visual recognition area estimation device that can accurately estimate an area recognized by a driver in real time. The visual recognition area estimation device of the present invention calculates the visual recognition area recognized by the driver by means of the visual recognition area calculation portion 11 based on the eyes of the driver, and estimates a time series visual recognition area as the area currently recognized by the driver by means of the visual recognition time space map creation portion 14 based on histories of a plurality of visual recognition areas calculated from the past to the present for a predetermined time. In this manner, by estimating the time series visual recognition area also including the past visual recognition area, the area currently recognized by the driver can be accurately estimated, and the eyes of the driver are not correlated with the obstacle but based on the standard area.

Abstract: Disclosed is a route creation method capable of creating a travel route which reduces the travel quantity of a robot and achieves the efficient travel of the robot. The route creation method and route creation device creates a plurality of candidate routes by using an intermediate point generated between the initial position and the final position set in advance, and thereafter evaluates the travel quantity of a traveling part of a robot with respect to each candidate route to select a candidate route, which achieves the most efficient travel, as a travel route.

Abstract: An ECU of a driving support device predicts the risk of contact between a host vehicle and obstacles around the host vehicle when the host vehicle travels by a driving action related to at least one normative action candidate, which is a normative driving action candidate of the host vehicle for the surrounding conditions of the host vehicle. Therefore, it is possible to provide the normative action candidates considering the risk of contact between the host vehicle 400-and the obstacles around the host vehicle.

Abstract: A drowsiness detector capable of detecting light drowsiness of a subject with high precision is provided. The drowsiness detector acquires the measurement data of a measurement device first, and acquires a value of the pulse rate by performing preprocessing on the measurement data and extracts a pulse fluctuation from the value of the pulse rate. Then, the drowsiness detector sets the reference section width of the pulse feature value referred to in order to acquire the standard deviation of the pulse feature value (value of the pulse rate and pulse fluctuation) and then calculates the standard deviation value of the pulse feature value in the reference section width and acquires the corrected standard deviation value of the pulse feature value by dividing the standard deviation value of the pulse feature value by the pulse feature value. Then, the drowsiness detector determines whether or not the driver is lightly drowsy using the corrected standard deviation value of the pulse feature value.

Abstract: An object of the invention is to provide a visual recognition area estimation device that can accurately estimate an area recognized by a driver in real time. The visual recognition area estimation device of the present invention calculates the visual recognition area recognized by the driver by means of the visual recognition area calculation portion 11 based on the eyes of the driver, and estimates a time series visual recognition area as the area currently recognized by the driver by means of the visual recognition time space map creation portion 14 based on histories of a plurality of visual recognition areas calculated from the past to the present for a predetermined time. In this manner, by estimating the time series visual recognition area also including the past visual recognition area, the area currently recognized by the driver can be accurately estimated, and the eyes of the driver are not correlated with the obstacle but based on the standard area.

Abstract: A path generating device 1 has a constraint mid-configuration generator 10. The constraint mid-configuration generator 10 defines a constraint surface in a joint angle space. The path generating device 1 probabilistically generates a mid-configuration in the joint angle space. The constraint mid-configuration generator 10 projects the probabilistically generated mid-configuration onto the constraint surface to generate a projected mid-configuration. Projected mid-configurations generated in this manner are joined to generate a path that does not interfere with any obstacle (environmental object) in a work space.

Abstract: An object of the present invention is to provide a sleep determination device and a sleep determination method capable of precisely determining a sleep stage based on heartbeat information of a subject.

Abstract: A drowsiness detector capable of detecting light drowsiness of a subject with high precision is provided. The drowsiness detector acquires the measurement data of a measurement device first, and acquires a value of the pulse rate by performing preprocessing on the measurement data and extracts a pulse fluctuation from the value of the pulse rate. Then, the drowsiness detector sets the reference section width of the pulse feature value referred to in order to acquire the standard deviation of the pulse feature value (value of the pulse rate and pulse fluctuation) and then calculates the standard deviation value of the pulse feature value in the reference section width and acquires the corrected standard deviation value of the pulse feature value by dividing the standard deviation value of the pulse feature value by the pulse feature value. Then, the drowsiness detector determines whether or not the driver is lightly drowsy using the corrected standard deviation value of the pulse feature value.

Abstract: A movement path generating device for a robot is provided which can generate a movement path of a jointed robot satisfying a constraint condition and accomplishing optimization of various estimation conditions.