EP-4741883-A1 - BASE STATION POSITION CHANGE DETECTION METHOD, DEVICE, AND READABLE STORAGE MEDIUM

EP4741883A1EP 4741883 A1EP4741883 A1EP 4741883A1EP-4741883-A1

Abstract

Embodiments of the present application disclose a base station position change detection method, a device, and a readable storage medium. A self-moving device travels a certain distance when switching from a non-working state to a working state, and in the traveling process, a visual image and RTK positioning are obtained, and the self-moving device is repositioned on the basis of the visual image and the RTK positioning. When the repositioning is successful, it is determined that the base station is not moved. By means of this solution, by combining the visual image and motion characteristics of the self-moving device, the self-moving device can determine whether the base station is moved or not, and there is no need to install an additional sensor, avoiding positioning anomalies of the self-moving device due to the base station being moved, achieving the objective of improving the positioning accuracy of the self-moving device.

Inventors

ZHANG, Taojing
JIANG, Daihong
FU, LEI
WANG, WEN
RU, Yichao

Assignees

Ecovacs Home Service Robotics Co., Ltd.

Dates

Publication Date: 20260513
Application Date: 20240702

Claims (20)

A detection method for reference station position changes, comprising: when a self-mobile device switches from a non-working state to a working state, controlling the self-mobile device to travel; controlling the self-mobile device to acquire visual images and real-time kinematic (RTK) positioning during a travel of the self-mobile device; performing, according to the visual images and the RTK positioning, repositioning of the self-mobile device; and when the repositioning of the self-mobile device is successful, determining that a reference station has not been moved, the reference station being configured to provide differential signals to the self-mobile device such that the self-mobile device acquires the RTK positioning according to the differential signals.
The method according to claim 1, wherein performing, according to the visual images and the RTK positioning, repositioning of the self-mobile device comprises: determining, according to current RTK positioning acquired by the self-mobile device, a predicted position of the self-mobile device, the RTK positioning comprising the current RTK positioning, and the visual images comprising current visual images; determining, according to the current RTK positioning and previous positioning, a predicted angle of the self-mobile device, the previous positioning being RTK positioning acquired by the self-mobile device before acquiring the current RTK positioning and adjacent to the current RTK positioning; and performing, according to the predicted position, the predicted angle, and the current visual images, repositioning of the self-mobile device.
The method according to claim 2, wherein performing, according to the predicted position, the predicted angle, and the current visual images, repositioning of the self-mobile device comprises: projecting, according to the predicted position and the predicted angle, feature points in an environmental map onto the current visual images to obtain a matched first point count; and when the first point count is greater than a first threshold, determining that the repositioning of the self-mobile device is successful.
The method according to claim 2, further comprising: when the repositioning of the self-mobile device fails, determining a target key frame from a plurality of key frames in an environmental map, the target key frame being a key frame with a highest similarity to the current visual images among the plurality of key frames; projecting feature points in the target key frame onto the current visual images to obtain a matched second point count; and when the second point count is greater than a second threshold, determining that the reference station has been moved, the second threshold being greater than the first threshold.
The method according to claim 4, further comprising: when the second point count is less than or equal to the second threshold, determining that it cannot be determined whether the reference station has been moved; and continuing to control the self-mobile device to travel.
The method according to claim 3, wherein projecting, according to the predicted position and the predicted angle, feature points in the environmental map onto the current visual images to obtain the matched first point count comprises: determining, according to the predicted position and the predicted angle, a pose matrix corresponding to a current pose of the self-mobile device; determining, according to the pose matrix and a transformation matrix, position coordinates of the feature points in the environmental map in a camera coordinate system, the transformation matrix being a transformation matrix from a center of the self-mobile device to a camera center; and projecting, according to the position coordinates of the feature points in the environmental map in the camera coordinate system, the feature points in the environmental map onto the current visual images to obtain the matched first point count.
The method according to any one of claims 1 to 6, wherein when the self-mobile device switches from the non-working state to the working state, controlling the self-mobile device to travel comprises: when the self-mobile device switches from the non-working state to the working state, controlling the self-mobile device to acquire environmental images; and if the environmental images indicate that a surrounding environment of the self-mobile device has changed, controlling the self-mobile device to travel.
The method according to claim 7, further comprising: after the self-mobile device switches from the non-working state to the working state, if the environmental images indicate that the surrounding environment of the self-mobile device has not changed, comparing target positioning with initial positioning, the target positioning being RTK positioning acquired by the self-mobile device before entering the non-working state, and the initial positioning being RTK positioning acquired by the self-mobile device after switching to the working state; and when a distance between the target positioning and the initial positioning is greater than a preset distance, determining that the reference station has been moved.
The method according to claim 7, further comprising: comparing a target image with an initial visual image, the target image and the initial visual image being adjacent, the target image being an image captured by the self-mobile device before entering the non-working state, and the initial visual image being an image captured by the self-mobile device after switching to the working state; and when a similarity between the target image and the initial visual image is less than a preset similarity, determining that the surrounding environment of the self-mobile device has changed.
The method according to claim 7, further comprising: comparing a target image with an initial visual image, the target image and the initial visual image being adjacent, the target image being an image captured by the self-mobile device before entering the non-working state, and the initial visual image being an image captured by the self-mobile device after switching to the working state; and when a similarity between the target image and the initial visual image is greater than or equal to a preset similarity, determining that the surrounding environment of the self-mobile device has not changed.
The method according to claim 8, before comparing the target image with the initial visual image, the method further comprising: when the self-mobile device is in the working state, acquiring the latest visual images and the latest RTK positioning in real time; and when the self-mobile device switches from the working state to the non-working state, storing the latest visual images and the latest RTK positioning, such that after the self-mobile device switches from the non-working state to the working state, the latest visual images serve as the target image, and the latest RTK positioning serves as target positioning.
The method according to any one of claims 1 to 6, wherein the RTK positioning is in a fixed solution state.
The method according to any one of claims 1 to 6, wherein the non-working state comprises any one of the following states: a pause state, a sleep state, or a power-off state.
A detection apparatus for reference station position changes, the apparatus being integrated on a self-mobile device and comprising: a traveling module, configured to, when a self-mobile device switches from a non-working state to a working state, control the self-mobile device to travel; an acquisition module, configured to control the self-mobile device to acquire visual images and real-time kinematic (RTK) positioning during a travel of the self-mobile device; a processing module, configured to perform, according to the visual images and the RTK positioning, repositioning of the self-mobile device; and a determination module, configured to, when the repositioning of the self-mobile device is successful, determine that a reference station has not been moved, the reference station being configured to provide differential signals to the self-mobile device such that the self-mobile device acquires the RTK positioning according to the differential signals.
A detection method for reference station position changes, comprising: when a self-mobile device switches from a non-working state to a working state, controlling the self-mobile device to acquire environmental images, and determining, according to the environmental images, whether a surrounding environment of the self-mobile device has changed before and after state switch; when the surrounding environment of the self-mobile device has changed before and after the state switch, controlling the self-mobile device to travel; controlling the self-mobile device to acquire visual images and real-time kinematic (RTK) positioning during a travel of the self-mobile device; determining, according to the RTK positioning, a predicted position and a predicted angle of the self-mobile device, and performing, according to the predicted position, the predicted angle, and the visual images, repositioning of the self-mobile device; and when the repositioning of the self-mobile device is successful, determining that a reference station has not been moved, the reference station being configured to provide differential signals to the self-mobile device such that the self-mobile device acquires the RTK positioning according to the differential signals.
The method according to claim 15, wherein determining, according to the RTK positioning, the predicted position and the predicted angle of the self-mobile device, and performing, according to the predicted position, the predicted angle, and the visual images, repositioning of the self-mobile device comprises: determining, according to current RTK positioning acquired by the self-mobile device, a predicted position of the self-mobile device, the RTK positioning comprising the current RTK positioning, and the visual images comprising current visual images; determining, according to the current RTK positioning and previous positioning, a predicted angle of the self-mobile device, the previous positioning being RTK positioning acquired by the self-mobile device before acquiring the current RTK positioning and adjacent to the current RTK positioning; and performing, according to the predicted position, the predicted angle, and the current visual images, repositioning of the self-mobile device.
The method according to claim 16, wherein performing, according to the predicted position, the predicted angle, and the current visual images, repositioning of the self-mobile device comprises: projecting, according to the predicted position and the predicted angle, feature points in an environmental map onto the current visual images to obtain a matched first point count; and when the first point count is greater than a first threshold, determining that the repositioning of the self-mobile device is successful.
The method according to claim 16, further comprising: when the repositioning of the self-mobile device fails, determining, according to the current visual images and an environmental map, whether the reference station has been moved.
The method according to claim 18, further comprising: when it cannot be determined, according to the current visual images and the environmental map, whether the reference station has been moved, continuing to control the self-mobile device to travel and perform repositioning.
The method according to claim 15, further comprising: when the surrounding environment of the self-mobile device has not changed before and after the state switch, determining, according to the RTK positioning, whether the reference station has been moved.

Description

TECHNICAL FIELD Embodiments of the present application relate to the technical field of lawn mowers, and in particular, to a detection method for reference station position changes, a device, and a readable storage medium. BACKGROUND Real-time kinematic (RTK) positioning technology is a high-precision positioning method on the basis of the global navigation satellite system (GNSS). Visual simultaneous localization and mapping (SLAM) technology is a method for autonomous robot positioning and environmental map construction on the basis of visual sensors. In the field of robotics, RTK technology is often combined with visual SLAM technology for robot positioning, thereby fully utilizing the advantages of both. However, once a reference station is moved, the robot's positioning becomes abnormal. Therefore, it is necessary to ensure that the reference station is not moved. In common manners, a gyroscope, an accelerometer, or the like is mounted on the reference station. If the sensors detect significant movement of the reference station, it is considered to have been moved. However, the detection method above requires additional sensors to be mounted on the reference station, resulting in high costs. SUMMARY Embodiments of the present application provide a detection method for reference station position changes, a device, and a readable storage medium. By combining visual images with motion characteristics of a self-mobile device, the self-mobile device can determine whether the reference station has been moved without mounting additional sensors, thereby enhancing the positioning accuracy of the self-mobile device. In a first aspect, the embodiments of the present application provide a detection method for reference station position changes, the method being applied to the self-mobile device and comprising: when a self-mobile device switches from a non-working state to a working state, controlling the self-mobile device to travel;controlling the self-mobile device to acquire visual images and real-time kinematic (RTK) positioning during a travel of the self-mobile device;performing, according to the visual images and the RTK positioning, repositioning of the self-mobile device; andwhen the repositioning of the self-mobile device is successful, determining that the reference station has not been moved, the reference station being configured to provide differential signals to the self-mobile device such that the self-mobile device acquires RTK positioning according to the differential signals. In a second aspect, the embodiments of the present application provide a detection apparatus for reference station position changes, the apparatus being integrated on a self-mobile device and comprising: a traveling module, configured to, when a self-mobile device switches from a non-working state to a working state, control the self-mobile device to travel;an acquisition module, configured to control the self-mobile device to acquire visual images and real-time kinematic (RTK) positioning during a travel of the self-mobile device;a processing module, configured to perform, according to the visual images and the RTK positioning, repositioning of the self-mobile device; anda determination module, configured to, when the repositioning of the self-mobile device is successful, determine that a reference station has not been moved, the reference station being configured to provide differential signals to the self-mobile device such that the self-mobile device acquires RTK positioning according to the differential signals. In a third aspect, the embodiments of the present application provide a self-mobile device comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, wherein the processor, when executing the computer program, causes the electronic device to implement the method according to the first aspect or any possible implementation of the first aspect. In a fourth aspect, the embodiments of the present application provide a computer-readable storage medium having computer instructions stored thereon, wherein the computer instructions, when executed by a processor, are configured to implement the method according to the first aspect or any possible implementation of the first aspect. In a fifth aspect, the embodiments of the present application provide a computer program product comprising a computer program, wherein the computer program, when executed by a processor, is configured to implement the method according to the first aspect or any possible implementation of the first aspect. The embodiments of the present application provide a detection method for reference station position changes, a device, and a readable storage medium. When the self-mobile device switches from a non-working state to a working state and moves a distance, visual images and RTK positioning are acquired during the travel, and repositioning of the self-mobile device is performed according to t