Forklift and stowage position detecting method for forklift

1. A forklift that stows a cargo on a loading surface, the loading surface being an upper surface of a loading platform, the forklift comprising:

an external sensor configured to detect a position of an object; and

processing circuitry, wherein

the position of the object is represented by a point cloud that is a set of points expressed by coordinates in a three-dimensional coordinate system, and

the processing circuitry is configured to

extract points that represent a horizontal plane from the point cloud,

extract, as points that represent the loading platform, points within a specified range in an up-down direction from the horizontal plane,

extract, from the points that represent the loading platform, points that represent an edge of the loading platform, the edge being in front of the forklift,

detect a straight line that represents the edge from the points representing the edge,

extract, as points that represent an object mounted on the loading platform, points that are above and separated from the horizontal plane by at least a specified distance, and

detect, as a stowage position on which the cargo will be stowed, a position that is separated from the mounted object by a prescribed distance in a direction in which the straight line extends.

2. The forklift according to claim 1 , wherein

the processing circuitry is configured to

derive normal vectors of respective points in the point cloud,

extracts points of which the normal vectors are in the up-down direction,

derive a plane equation from the extracted points, and

define a plane expressed by the plane equation as the horizontal plane.

3. The forklift according to claim 1 , wherein the processing circuitry is configured to perform clustering on the points that represent the edge, the clustering being a process that groups points into one cluster.

4. The forklift according to claim 1 , further comprising:

a self-location estimation external sensor that is different from the external sensor; and

self-location estimation processing circuitry configured to estimate a self-location of the forklift by using the self-location estimation external sensor.

5. The forklift according to claim 4 , wherein

the processing circuitry is configured to

convert orthogonal coordinates of the points that represent the loading platform into polar coordinates in a polar coordinate system,

divides the polar coordinate system into angular sections of a specified angle within a horizontal plane, and

extracts, from each angular section, a point of which the coordinate is closest to the self-location as the points that represent the edge.

6. A stowage position detecting method for a forklift, the forklift stowing a cargo on a loading surface, the loading surface being an upper surface of a loading platform, the method comprising:

detecting a position of an object using an external sensor provided in the forklift, the position of the object being represented by a point cloud that is a set of points expressed by coordinates in a three-dimensional coordinate system;

extracting points that represent a horizontal plane from the point cloud;

extracting, as points that represent the loading platform, points within a specified range in an up-down direction from the horizontal plane;

extracting, from the points that represent the loading platform, points that represent an edge of the loading platform, the edge being in front of the forklift;

detecting a straight line that represents the edge from the points that represent the edge;

extracting, as points that represent an object mounted on the loading platform, points that are above and separated from the horizontal plane by at least a specified distance: and

detecting, as a stowage position on which the cargo will be stowed, a position that is separated from the mounted object by a prescribed distance in a direction in which the straight line extends.