Midea Group Co., Ltd.

Ke Huang

Yi Heng Chen

Wei Xi

The method and system disclosed herein presents a method and system for capturing, by a depth-perception device on a mobile robot moving in an environment, depth-perception information at a first location within a portion of the environment. The method includes capturing, by a camera device on the mobile robot, an image frame at the first location within the portion of the environment, generating a three-dimensional point cloud representing the portion of the environment based on the depth-perception information and the image frame, extracting semantic information by providing the frame and the point cloud to a neural network model configured to perform semantic segmentation, associating the semantic information to the three-dimensional point cloud, projecting the three-dimensional point cloud onto a two-dimensional plane to form a first two-dimensional map; and demarcating the first two-dimensional map with a plurality of different regions based on the semantic information.

Automatic robotic lawn mowing boundary detection using 3D semantic segmentation

The method and system disclosed herein presents a method and system for capturing, by a camera disposed on a device moving in an environment, a plurality of image frames recorded in a first coordinate reference frame at respective locations within a portion of the environment in a first time period; capturing, by an inertial measurement unit disposed on the device, sets of inertial odometry data recorded in a second coordinate reference frame; determining a rotational transformation matrix that corresponds to a relative rotation between the first reference frame and the second reference frame; and determining a scale factor from the matching pairs of image frames. The rotational transformation matrix defines an orientation of the device, and the scale factor and the rotational transformation matrix calibrate the plurality of image frames captured by the camera.

Method and apparatus for scale calibration and optimization of a monocular visual-inertial localization system

The method and device disclosed herein presents a method that includes capturing, by an optical sensor disposed on a device moving in an environment, a plurality of optical data at respective locations within a portion of the environment; capturing, by a wheel encoder disposed on the device, a set of encoder data corresponding to the plurality of optical data at the respective locations; determining a first relative motion based on the plurality of optical data; determining a corresponding second relative motion based on the set of encoder data. In accordance with determining that a difference between the first relative motion and the corresponding second relative motion is larger than a first threshold: increasing a counter indicating a slip event of the wheel encoder. The slip event corresponds to a wheel of the device advancing and the corresponding second relative motion being below a second threshold.

Growing community of inventors

San Jose, CA, United States of America

Ke Huang