Hitachi, Ltd.

Taiki Iimura

Kenjiro Yamamoto

Mikio Tokuyama

Azusa Amino

Alex Masuo Kaneko

The reliability of detection of the traveling lane can be improved even in a case where an image capturing environment changes. The lane detection device includes a first image capturing device which is fixed to a moving body and periodically captures a first image under a predetermined first image capturing condition, a second image capturing device which is fixed to the moving body and periodically captures a second image under a second image capturing condition different from the predetermined first image capturing condition, and an operation device, regarding a traveling lane on which the moving body travels, which detects a first boundary line of the traveling lane on the first image, detects a second boundary line of the traveling lane on the second image, and estimates the position of the first boundary line on the first image based on a position of the second boundary line on the second image under a predetermined execution condition.

Lane detection device and lane detection method

An environment information acquisition unit acquires a signal state of a traffic light. A self-position estimation unit estimates a self-position of the autonomous moving object. A traveling route decision unit calculates a first time necessary to move along a first route from the self-position to an end point of a crosswalk and a second time necessary to move along a second route from the self-point to a start point of the crosswalk in a case in which the signal state is changed from blue to red on the crosswalk after a predetermined time or in a case in which the signal state is changed from blue to red, and selects a route corresponding to a time smaller between the first time and the second time. A vehicle control unit controls autonomous movement of the autonomous moving object so that the autonomous moving object moves along the selected route.

Autonomous moving object

An autonomous moving device includes a database that stores information on which objects are necessary to avoid and which are not necessary to avoid. When the autonomous object travels, an object detection unit detects an object on the road by using a sensor; a collation unit collates the detected object on a road surface with an object stored in the database; a determination input unit receives an input of an operator regarding whether or not to avoid the object where there is no data which is the same as or similar to the object in the database as a result of collation which is performed by the collation unit; and an operation generation unit commands the next operation of the moving object, based on the result of collation which is performed by the collation unit and the determination unit.

Autonomous moving device

An object of the present invention is to provide an autonomous moving device or the like that estimates a self position based on an arrangement of landmarks in surrounding environment while suppressing the influence by external disturbances. In order to achieve the object described above, an external disturbance factor which becomes an external disturbance and a landmark used for the self position estimation when estimating a self position from an image captured by a wide angle camera are extracted, the landmark which is not affected by the external disturbance factor is selected from an image captured by the standard camera capable of controlling a posture using the extracted information, the posture of the standard camera is controlled so as to track the selected landmark, and the self position is estimated based on the arrangement of the landmarks captured by the tracking-controlled standard camera.

Autonomous moving device and self position estimation method

A self-localization device including a storage unit that associates and stores a plurality of reference images and imaging positions of the plurality of respective reference images and an operation unit that periodically estimates a self-location of a movable body based on information obtained from a sensor included in the movable body, wherein the operation unit determines, when estimation of the self-location fails, a moving distance from a latest self-location obtained from successful estimation of the self-location before the estimation fails using the information from the sensor and extracts a plurality of the reference images belonging to a range of the moving distance from the latest self-location and searches the plurality of extracted reference images for images similar to a current image captured by an imaging device included in the movable body to estimate the self-location of the movable body.

Growing community of inventors

Tokyo, Japan

Taiki Iimura