Obstacle detection system, agricultural machine and obstacle detection method
AssigneeKubota Corporation
InventorsNagahiro Fujiwara, Shunsuke Miyashita
Life of this patent
Estimating the term…
Abstract
An obstacle detection system for an agricultural machine to perform self-driving while sensing a surrounding environment with a LiDAR sensor and a camera includes a controller configured or programmed to cause the camera, upon detecting an obstacle candidate based on data that is output from the LiDAR sensor, as a trigger, to acquire an image of the obstacle candidate, and determine whether or not to change a traveling status of the agricultural machine based on the image of the obstacle candidate acquired with the camera.
Claims7
An obstacle detection system for an agricultural machine to perform self-driving while sensing a surrounding environment with a LIDAR sensor and a camera, the obstacle detection system comprising:
- a controller configured or programmed to:
- cause the camera, upon detecting an obstacle candidate based on data that is output from the LiDAR sensor, as a trigger, to acquire an image of the obstacle candidate;
- determine whether or not to change a traveling status of the agricultural machine based on the image of the obstacle candidate acquired with the camera;
- detect an object within the surrounding environment based on data that is output from the LiDAR sensor;
- when the detected object is the obstacle candidate, cause the camera to acquire the image of the obstacle candidate and determine whether or not to change the traveling status of the agricultural machine based on the image;
- identify, based on the image acquired with the camera, a type of the object that is the obstacle candidate;
- when the obstacle candidate is a person or animal, cause the agricultural machine to stop traveling or to change a traveling path of the agricultural machine to avoid the obstacle candidate;
- when the obstacle candidate is detected, cause the camera to acquire a color image of the obstacle candidate;
- and
- exclude, from data of the color image, green pixels from a subject of identifying the type of the object.
Dependencies are inferred from the claim text.