US 2020/0005487 A1 · POSITIONING METHOD AND ROBOT USING THE SAME

Abstract

The present disclosure provides a positioning method and a robot using the same. The method includes: obtaining, through the visual sensor, a current frame image; obtaining, through the ultra-wideband tag, distance of a robot from an ultra-wideband anchor; performing a feature matching on the current frame image and an adjacent frame image to generate partial map point(s); determining whether the current frame image is a key frame image; and optimizing a pose of the visual sensor corresponding to the key frame image through a joint objective function in response to the current frame image being the key frame image, where the joint objective function at least comprises a distance cost function of the ultra-wideband anchor and a visual residual cost function. Through the above-mentioned method, the accuracy of the positioning of the robot can be improved.

Claims17

Dependent claims

A computer-implemented positioning method for a robot having a visual sensor and an ultra-wideband tag, comprising executing on a processor the steps of:

obtaining, through the visual sensor, a current frame image;
obtaining, through the ultra-wideband tag, a distance between the robot and an ultra-wideband anchor at the moment of the current frame image being obtained;
performing a feature matching on the current frame image and an adjacent frame image to generate at least a partial map point;
determining whether the current frame image is a key frame image;
and
optimizing a pose of the visual sensor corresponding to the key frame image through a joint objective function, in response to the current frame image being the key frame image, wherein the joint objective function at least comprises a distance cost function of the ultra-wideband anchor and a visual residual cost function.

3 more elements

A robot comprising:

a visual sensor;
an ultra-wideband tag;
a processor;
a memory;
and
one or more computer programs stored in the memory and executable on the processor, wherein the one or more computer programs comprise:
instructions for obtaining, through the visual sensor, a current frame image;
instructions for obtaining, through the ultra-wideband tag, a distance between the robot and an ultra-wideband anchor at the moment of the current frame image being obtained;
instructions for performing feature matching on the current frame image and an adjacent frame image to generate at least a partial map point;
instructions for determining whether the current frame image is a key frame image;
and
instructions for optimizing a pose of the visual sensor corresponding to the key frame image through a joint objective function in response to the current frame image being the key frame image, wherein the joint objective function at least comprises a distance cost function of the ultra-wideband anchor and a visual residual cost function.

9 more elements

Dependencies are inferred from the claim text.

Positioning method and robot using the same

Life of this patent

Positioning method and robot using the same

Life of this patent

Abstract

Claims17