Mitsubishi Heavy Industries Limited

Mitsubishi Logisnext Co. Ltd.

Katsumasa Kitajima

Yusuke Kinouchi

Takumi Fujita

Kenji Takao

Masahiro Yamada

Hiroki Kawashima

Takuya Akashi

A position estimation system is a position estimation system for estimating a position of a forklift equipped with a camera and includes: a position estimation unit configured to estimate a position of the forklift on the basis of a feature included in an image captured by the camera; and an inclusion determination unit configured to calculate, on the basis of a position in a height direction of a mast with which the forklift is equipped, an inclusion range indicating a range in which the mast is in the image and determine to stop estimation of the position by using the position estimation unit when the inclusion range calculated exceeds an allowable range.

Position estimation system, forklift, position estimation method, and program

A control method for a mobile object that automatically moves includes: causing a sensor disposed on the mobile object to detect a target object multiple times to acquire detection results of respective detection processes performed by the sensor as a point group; estimating a position and an attitude of the target object for each detection process based on the point group; calculating reliability of accuracy in an estimation result of the position and the attitude of the target object for each detection process; selecting, from among estimation results of the respective detection processes, an estimation result used for setting an approach path to a target position at which a predetermined position and attitude with respect to the target object are achieved based on the reliability for each detection process; setting the approach path based on the selected estimation result; and causing the mobile object to move along the approach path.

Control method for mobile object, mobile object, and computer-readable storage medium

A method of controlling a movable body includes: a step of causing a sensor provided on the movable body to detect an obstacle; a step of determining the position and attitude of a front surface, of the obstacle, opposite to the travel direction of the movable body based on the detection result of the obstacle; a step of generating an avoidance path that avoids the obstacle while heading toward a side of a first direction intersecting the travel direction based on the position and attitude of the front surface; a step of causing the movable body to move along the avoidance path; a step of detecting the obstacle while the movable body is moving along the avoidance path; a step of determining the position and attitude of the side surface of the obstacle on the side of the first direction based on the detection result obtained during movement along the avoidance path; and a step of updating the avoidance path so as to return to a side of a second direction opposite to the first direction while avoiding the obstacle based on the position and attitude of the side surface.

Method of controlling movable body, movable body and program

Pallet detection device that acquires point cloud data indicating a point cloud measured by a two-dimensional distance measurement device on a depth map; detects a straight line corresponding to a front surface of a pallet based on the point cloud in a region presumed to include the front surface of the pallet in the point cloud data; detects a line segment indicating the front surface of the pallet based on the straight line; acquires position and orientation of the pallet based on the line segment. Acquires one or more straight line candidates and assigns for each of the one or more straight line candidates a score to the point cloud and selects the straight line from the one or more straight line candidates based on a score accumulated value obtained by accumulating the score for the point cloud in the region presumed to include the front surface of the pallet.

Pallet detection device, forklift, pallet detection method, and program

A device is for estimating a position of a vehicle equipped with a laser scanner capable of acquiring point cloud data by scanning a laser beam and a camera capable of acquiring an image in a predetermined direction. The device includes an acquisition unit configured to acquire the point cloud data and the image, an estimation unit configured to estimate the position based on the point cloud data or the image, and an extraction unit configured to extract, from the point cloud data, valid point cloud data that is usable for estimating the position. The estimation unit is configured to estimate the position using: (i) the valid point cloud data if a number of pieces of valid point cloud data is equal to or greater than a predetermined number; and (ii) the image if the number of pieces of valid point cloud data is less than the predetermined number.

Position estimation device, control device, industrial vehicle, logistics support system, position estimation method, and program

The self-localization device includes: an acquisition unit configured to acquire a sight image from a camera which is mounted in a mobile object; an estimation unit configured to perform a self-localization process of estimating a position and a posture of the mobile object in a world coordinate system on the basis of positions of feature points in the sight image and a map on which positions of a plurality of feature points in the world coordinate system are recorded; and a registration unit configured to register the sight image as a key frame for adding a new feature point included in the sight image to the map. The registration unit is configured to register the sight image as the key frame when movement of the mobile object satisfies a condition which is prescribed for at least one of the position and the posture of the mobile object.

Growing community of inventors

Tokyo, Japan

Katsumasa Kitajima