Method and system of simultaneous localization and mapping based on 2D LiDAR and camera
AssigneesHyundai Motor Company, Kia Corporation
InventorsDong Hwan Kwak, Sanghyeon Oh, Hyuntek Lim
Life of this patent
Estimating the term…
Abstract
A system and method of simultaneous localization and mapping can include loading a map to which 2D feature point data stored in a memory is bound, acquiring 2D LiDAR point data from a LiDAR equipped in a mobility, acquiring 3D observation feature point data by receiving a front image from a camera equipped on the mobility, reducing a dimension of the 3D observation feature point data to 2D observation feature point data, binding the 2D observation feature point data to the 2D LiDAR point data, and detecting an absolute position of the mobility based on the 2D observation feature point data bound to the 2D LiDAR point data and the map to which the 2D feature point data is bound.
Claims20
A localization and mapping method, the method comprising:
- acquiring 2D LiDAR point data from a light detection and ranging device (LiDAR) of a mobility;
- acquiring three dimension (3D) observation feature point data by receiving an image from a camera of the mobility;
- reducing a dimension of the 3D observation feature point data to 2D observation feature point data;
- before the reducing the dimension of the 3D observation feature point data to the 2D observation feature point data, deleting non-collision 3D observation feature point data for features that are not able to cause a collision with the mobility from the 3D observation feature point data;
- binding the 2D observation feature point data to the 2D LiDAR point data;
- and
- detecting an absolute position of the mobility based on the 2D observation feature point data bound to the 2D LiDAR point data and based on a map to which 2D feature point data is bound.
A localization and mapping system comprising:
- a light detection and ranging device (LiDAR) mounted on a mobility and configured to detect two dimension (2D) LiDAR point data;
- a camera mounted on the mobility and configured to acquire an image;
- and
- a controller configured to:
- receive the 2D LiDAR point data from the LiDAR;
- receive the image from the camera;
- detect three dimension (3D) observation feature point data from the image;
- reduce a dimension of the 3D observation feature point data to 2D observation feature point data;
- before reducing the dimension of the 3D observation feature point data to the 2D observation feature point data, to delete non-collision 3D observation feature point data for features that are not able to cause a collision with the mobility from the 3D observation feature point data;
- bind the 2D observation feature point data to the 2D LiDAR point data;
- and
- detect an absolute position of the mobility based on the 2D observation feature point data bound to the 2D LiDAR point data and based on a map to which two dimension (2D) feature point data is bound.
A mobility comprising:
- a driving motor;
- a wheel;
- an encoder configured to detect information on a rotation of the driving motor or the wheel;
- an inertial sensor configured to detect information on a movement situation of the mobility;
- a light detection and ranging device (LiDAR);
- a camera;
- a controller;
- and
- a memory storing instructions, that when executed by the controller cause the controller to:
- receive 2D LiDAR point data from the LiDAR,
- receive an image from the camera,
- detect three dimension (3D) observation feature point data from the image,
- reduce a dimension of the 3D observation feature point data to 2D observation feature point data,
- before reducing the dimension of the 3D observation feature point data to the 2D observation feature point data, to delete non-collision 3D observation feature point data for features that are not able to cause a collision with the mobility from the 3D observation feature point data,
- bind the 2D observation feature point data to the 2D LiDAR point data,
- select an estimated position of the mobility based on the 2D LiDAR point data, information on the rotation of the driving motor or the wheel detected by the encoder, and information on a movement of the mobility detected by the inertial sensor, and
- detect an absolute position of the mobility based on the 2D observation feature point data bound to the 2D LiDAR point data and based on a map to which two dimensional (2D) feature point data is bound.
Dependencies are inferred from the claim text.