CN118706106A - A positioning method for a mobile robot in a dynamic channel of an electric mobile shelf - Google Patents

Abstract

The present invention relates to the technical field of electric mobile shelves, and discloses a positioning method for a mobile robot in a dynamic channel of an electric mobile shelf, the positioning method comprising: S1 laser radar scanning; S2 computer vision recognition and positioning; S3 robot positioning; the present invention uses a plurality of technologies of laser radar, computer vision and robot positioning through the coordinated use of its positioning method, and combines a SLAM algorithm and an obstacle detection algorithm at the same time, so as to realize real-time positioning and obstacle avoidance; compared with the prior art, the present invention can adapt to the positioning requirements in a dynamic environment, can obtain environmental information in different aspects, can effectively improve the accuracy and robustness of positioning, and can make intelligent adjustments according to environmental changes and robot working requirements, so as to improve the adaptability and intelligence level of the robot, and at the same time can also improve the positioning accuracy and stability of the robot, reduce errors and drifts, and ensure the safe operation and accurate navigation of the robot in the channel.

Description

A positioning method for a mobile robot in a dynamic channel of an electric mobile shelf

Technical Field

The invention relates to the technical field of electric mobile shelves, and in particular to a positioning method for a mobile robot in a dynamic channel of an electric mobile shelf.

Background Art

At present, when positioning a mobile robot in a dynamic channel of an electric mobile shelf, an inertial measurement unit (IMU) is used to measure the acceleration and angular velocity of the robot, and the robot's posture information is obtained by integration. Then, ultrasonic sensors are deployed in the environment, and the distance between the robot and a fixed marker is determined by the reflection and reception of ultrasonic waves, thereby achieving positioning. Then, a camera or a depth camera is used to capture the environment image, and then a computer vision algorithm is used to extract feature points, match the scene, and perform positioning.

Regarding the above-mentioned related technologies, the inventor believes that the inertial navigation system usually has a high update frequency and real-time performance, which is suitable for short-term positioning needs, and the ultrasonic positioning system is usually suitable for indoor environments and has a high sensitivity to obstacles. At the same time, the visual recognition positioning system can realize the recognition and positioning of objects in the environment, but is greatly affected by lighting conditions and environmental changes;

The above information disclosed in this background technology is only used to increase the understanding of the background technology of the present invention and therefore, it may include information that does not constitute the prior art known to a person of ordinary skill in the art.

Summary of the invention

In order to solve the problems that when positioning a mobile robot in a dynamic channel of an existing electric mobile shelf, the inertial navigation system is generally only suitable for short-term positioning needs, the ultrasonic positioning system is highly sensitive to obstacles, and the visual recognition positioning system is greatly affected by lighting conditions and environmental changes, the present invention provides a positioning method for a mobile robot in a dynamic channel of an electric mobile shelf.

The present invention provides a method for positioning a mobile robot in a dynamic channel of an electric mobile shelf using the following technical solutions:

A positioning method for a mobile robot in a dynamic channel of an electric mobile shelf, the positioning method comprising:

S1 LiDAR scanning: Use LiDAR to scan dynamic channels in real time to obtain channel structure and obstacle information. LiDAR can provide high-precision environmental maps, including the length and width of the channel and the location of obstacles in it;

S2 Computer vision recognition and positioning: Identify and locate landmarks or features in the channel through a computer vision system, generate a map of the channel and establish a coordinate system. This includes identifying special marks, colors, textures or other features in the channel, and then using this information to determine the robot's position and posture relative to the channel.

S3 Robot Positioning: The mobile robot receives and processes information transmitted by the LiDAR and vision system through the onboard positioning sensors and communication devices to achieve real-time positioning relative to the channel coordinate system. The robot will use this data to accurately determine its position in the channel and make dynamic adjustments based on changes in the channel environment.

Preferably, the S1 laser radar scanning includes S1.1 installing a laser radar, installing a laser radar sensor inside a dynamic channel or above a mobile robot to ensure that it can fully scan the channel space.

Preferably, the S1 laser radar scanning includes S1.2 real-time scanning, and the laser radar system scans the dynamic channel in real time to obtain the channel structure and obstacle information, including the length and width of the channel and the position and size of the obstacle.

Preferably, the S1 laser radar scanning includes S1.3 data processing, which processes and analyzes the data returned by the laser radar to generate a three-dimensional map of the channel and environmental information.

Preferably, the S2 computer vision recognition and positioning includes S2.1 visual sensor installation, where a visual sensor is mounted on the mobile robot to capture landmarks or features in the channel.

Preferably, the S2 computer vision identification and positioning includes S2.2 feature identification, which uses computer vision algorithms to identify special marks, colors, textures or other features in the channel.

Preferably, the S2 computer vision recognition and positioning includes S2.3 coordinate system establishment, based on the identified feature points, establishing a map of the interior of the channel and a coordinate system to determine the position and posture of the robot relative to the channel.

Preferably, the S3 robot positioning includes S3.1 sensor integration, and the mobile robot is equipped with a positioning sensor to receive information transmitted by the laser radar and the vision system.

Preferably, the S3 robot positioning includes S3.2 data fusion, which fuses the data obtained by the laser radar, the vision system and the robot's own sensors.

Preferably, the S3 robot positioning includes S3.3 real-time positioning, which realizes real-time positioning relative to the channel coordinate system through fused data, so that the robot can accurately determine its position in the channel and make dynamic adjustments according to changes in the channel environment.

In summary, the present invention includes the following beneficial technical effects:

1. Through the coordinated use of its positioning methods, it uses a variety of technologies such as laser radar, computer vision and robot positioning, and combines SLAM algorithm and obstacle detection algorithm to achieve real-time positioning and obstacle avoidance; compared with existing technologies, it can adapt to the positioning needs in dynamic environments, can obtain environmental information in different aspects, and can effectively improve the accuracy and robustness of positioning through data fusion;

2. The algorithms and technologies involved use adaptive positioning algorithms and deep learning technologies, which can make intelligent adjustments based on environmental changes and robot work requirements, improve the robot's adaptability and intelligence, and through data fusion and sensor integration, the above methods can improve the robot's positioning accuracy and stability, reduce errors and drifts, and ensure the robot's safe operation and accurate navigation in the channel.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a schematic diagram of a method for positioning a mobile robot in a dynamic channel of an electric mobile shelf according to an embodiment of the invention.

DETAILED DESCRIPTION

The present invention is further described in detail below in conjunction with FIG1 .

The embodiment of the present invention discloses a method for positioning a mobile robot in a dynamic channel of an electric mobile shelf. Referring to Figure 1, a method for positioning a mobile robot in a dynamic channel of an electric mobile shelf, the positioning method includes: S1 laser radar scanning: using laser radar to scan the dynamic channel in real time to obtain channel structure and obstacle information, the laser radar can provide a high-precision environmental map, including the length and width of the channel and the position of obstacles therein, the S1 laser radar scanning includes S1.1 installing the laser radar, installing the laser radar sensor inside the dynamic channel or above the mobile robot to ensure that it can fully scan the channel space, the S1 laser radar scanning includes S1.2 real-time scanning, the laser radar system scans the dynamic channel in real time to obtain channel structure and obstacle information, including the length and width of the channel and the position and size of the obstacles, the S1 laser radar scanning includes S1.3 data processing, processing and analyzing the data returned by the laser radar to generate a three-dimensional map of the channel and environmental information;

By adopting the above technical solution, firstly, by selecting a suitable lidar sensor and ensuring that it is installed inside the dynamic channel or above the mobile robot, the channel space can be fully scanned. The lidar acquires three-dimensional information of the environment by emitting a laser beam and measuring its return time and angle, thereby building a map of the environment. Then, the lidar system scans the dynamic channel in real time to acquire channel structure and obstacle information. The lidar scans the surrounding environment at a certain frequency, and acquires information such as the length and width of the channel and the location and size of obstacles by measuring the reflection time and position of the laser beam. The data returned by the lidar is then processed and analyzed to generate a three-dimensional map of the channel and environmental information. By processing and analyzing the lidar data, a three-dimensional map of the channel can be constructed, and the location and shape of obstacles can be identified, providing basic information for subsequent robot navigation.

Referring to Figure 1, S2 computer vision recognition and positioning: using a computer vision system to identify and locate landmarks or features in the channel, generate a map of the interior of the channel and establish a coordinate system, which includes identifying special marks, colors, textures or other features in the channel, and then using this information to determine the position and posture of the robot relative to the channel. S2 computer vision recognition and positioning includes S2.1 visual sensor installation, carrying a visual sensor on the mobile robot to capture landmarks or features in the channel, S2 computer vision recognition and positioning includes S2.2 feature recognition, using a computer vision algorithm to identify special marks, colors, textures or other features in the channel, S2 computer vision recognition and positioning includes S2.3 coordinate system establishment, based on the identified feature points, establish a map of the interior of the channel and establish a coordinate system to determine the position and posture of the robot relative to the channel;

By adopting the above technical solution, by selecting a suitable visual sensor and installing it on a mobile robot to capture the landmarks or features in the channel, a suitable visual sensor is selected and installed on a mobile robot to capture the landmarks or features in the channel, and then a computer vision algorithm is used to identify the special marks, colors, textures or other features in the channel. Image processing technology is used to extract and match feature points to identify the landmarks or features in the channel, so as to determine the position and posture of the robot relative to the channel, and then a map of the inside of the channel and a coordinate system are established based on the identified feature points to determine the position and posture of the robot relative to the channel. A map of the inside of the channel is established based on the identified feature points, and the landmark points therein are used to determine the position and posture of the robot relative to the channel.

Referring to Figure 1, S3 robot positioning: the mobile robot receives and processes the information transmitted by the laser radar and vision system through the onboard positioning sensors and communication devices to achieve real-time positioning relative to the channel coordinate system. The robot will use these data to accurately determine its own position in the channel and dynamically adjust according to changes in the channel environment. S3 robot positioning includes S3.1 sensor integration. The mobile robot is equipped with positioning sensors to receive information transmitted by the laser radar and vision system. S3 robot positioning includes S3.2 data fusion, which fuses the data obtained by the laser radar, vision system and the robot's own sensors. S3 robot positioning includes S3.3 real-time positioning. The fused data can achieve real-time positioning relative to the channel coordinate system, allowing the robot to accurately determine its own position in the channel and dynamically adjust according to changes in the channel environment.

By adopting the above technical solution, the mobile robot is equipped with positioning sensors, such as inertial measurement units (IMUs), encoders, etc., to receive information transmitted by lidar and vision systems. The positioning sensors integrate different types of sensors to obtain information such as the robot's own position, speed, and posture to assist in positioning. The data obtained by the lidar, vision system, and the robot's own sensors are fused to improve positioning accuracy and robustness. The information obtained by different sensors is fused using a sensor fusion algorithm to improve the accuracy and robustness of the robot's positioning. The fused data is used to achieve real-time positioning relative to the channel coordinate system, so that the robot can accurately determine its position in the channel and dynamically adjust it according to changes in the channel environment. The fused data is used to achieve real-time positioning of the robot relative to the channel through a positioning algorithm so that the robot can accurately sense and adjust its own position.

The implementation principle of a positioning method for a mobile robot in a dynamic channel of an electric mobile shelf in an embodiment of the present invention is as follows: first, by selecting a suitable laser radar sensor and ensuring that it is installed inside the dynamic channel or above the mobile robot, the channel space can be fully scanned. The laser radar obtains three-dimensional information of the environment by emitting a laser beam and measuring its return time and angle, thereby building a map of the environment. Then, the laser radar system scans the dynamic channel in real time to obtain channel structure and obstacle information. The laser radar scans the surrounding environment at a certain frequency, and obtains information such as the length, width of the channel and the position and size of the obstacle by measuring the reflection time and position of the laser beam. Then, the data returned by the laser radar is processed and analyzed to generate a three-dimensional map of the channel and environmental information. By processing and analyzing the laser radar data, a three-dimensional map of the channel can be constructed, and the position and shape of the obstacle can be identified, providing basic information for subsequent robot navigation. It selects a suitable visual sensor and installs it on the mobile robot to capture the landmarks or features in the channel. Then, a computer vision algorithm is used to identify special marks, colors, textures or other features in the channel. Image processing technology is used to extract and Matching, identifying the landmarks or features in the channel, so as to determine the position and posture of the robot relative to the channel, and then based on the identified feature points, establish a map inside the channel and establish a coordinate system to determine the position and posture of the robot relative to the channel. According to the identified feature points, establish a map inside the channel, and use the landmarks therein to determine the position and posture of the robot relative to the channel. Finally, the mobile robot is equipped with positioning sensors, such as inertial measurement units (IMUs), encoders, etc., to receive information transmitted by the laser radar and vision system. The positioning sensor integrates different types of sensors to obtain information such as the robot's own position, speed and posture to assist in positioning. The data obtained by the laser radar, vision system and the robot's own sensors are fused to improve the positioning accuracy and robustness. The information obtained by different sensors is fused using the sensor fusion algorithm to improve the accuracy and robustness of the robot's positioning. The real-time positioning relative to the channel coordinate system is realized through the fused data, so that the robot can accurately determine its position in the channel and dynamically adjust according to changes in the channel environment. The real-time positioning of the robot relative to the channel is realized through the positioning algorithm using the fused data, so that the robot can accurately perceive and adjust its own position. The above-mentioned laser radar can be selected from Hokuyo High-performance LiDAR sensors such as UST-10LX are installed on the mobile robot to provide high-precision environmental map data. The above-mentioned visual sensor can be selected as Basler acA1300-60gm high-resolution industrial camera, which is mounted on the mobile robot to capture feature points or markers in the channel. The inertial measurement unit (IMU) chooses to integrate high-precision MEMS inertial sensors, such as ADIS16470, to obtain the robot's acceleration, angular velocity and other posture information. The encoder can use a high-resolution optical encoder, such as HEDL-5540, which is used to measure the robot's movement and displacement with the robot's drive wheel. The LiDAR scanning algorithm uses SLAM (Simultaneous Localization and Mapping) algorithm, such as Hector SLAM or Cartographer, to process and analyze the data returned by the LiDAR to generate a three-dimensional map of the channel and environmental information. The SLAM algorithm calculates the robot's movement trajectory and map construction simultaneously to achieve the robot's positioning and navigation in an unknown environment. The computer vision algorithm can use feature point extraction and matching algorithms, such as SIFT (Scale-Invariant Feature Transform) or SURF (Speeded-Up Robust Features), to identify and match special markers or features in the channel to determine the robot's position and posture relative to the channel. Sensor fusion algorithm: Use the extended Kalman filter (EKF) or unscented Kalman filter (UKF) algorithm to fuse the data obtained by the lidar, vision system and the robot's own sensors to improve positioning accuracy and robustness. These algorithms fuse information from different sensors and take into account their error characteristics to achieve a more accurate estimate of the robot's position and posture. LiDAR scanning data processing can filter, transform coordinates and build maps for the data returned by the lidar. Data processing and mapping are performed using tools such as the Point Cloud Library (PCL), and visual sensor data processing uses computer vision libraries such as OpenCV to perform visual The images acquired by the sensor are used for feature extraction, matching and posture estimation to establish a map and coordinate system inside the channel. The sensor fusion calculation uses the EKF or UKF algorithm to fuse the data obtained by the lidar, vision system and the robot's own sensors to achieve real-time positioning of the robot relative to the channel. Finally, real-time adjustment and navigation can be based on the real-time positioning results. Through navigation algorithms such as the A* algorithm or the RRT* algorithm, the robot's path planning and adjustment in the dynamic channel can be achieved to ensure that the robot can move and carry out operations safely and efficiently. Through the above specific sensor selection, algorithm application and calculation process, combined with advanced sensor technology and positioning algorithms, accurate positioning and navigation of mobile robots in dynamic channels of electric mobile shelves can be achieved, thereby improving the efficiency and accuracy of material handling and management.

Finally, a few points should be explained: First, in the description of the present invention, it should be noted that, unless otherwise specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, which may refer to mechanical connection or electrical connection, or internal communication between two components, or direct connection. "upper", "lower", "left", "right", etc. are only used to indicate relative positional relationships. When the absolute position of the object being described changes, the relative positional relationship may change;

Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. A positioning method of a mobile robot in a dynamic channel of an electric mobile goods shelf is characterized in that: the positioning method comprises the following steps:

s1 laser radar scanning: the laser radar is utilized to scan the dynamic channel in real time to acquire the channel structure and the barrier information, and the laser radar can provide a high-precision environment map which comprises the length and the width of the channel and the barrier position in the channel;

S2, computer vision recognition and positioning: identifying and locating the mark points or features in the channel through a computer vision system, generating a map of the interior of the channel and establishing a coordinate system, wherein the map comprises identifying special marks, colors, textures or other features in the channel, and then utilizing the information to determine the position and the gesture of the robot relative to the channel;

s3, robot positioning: the mobile robot receives and processes information transmitted by the laser radar and the vision system through the carried positioning sensor and the communication device, so that real-time positioning relative to a channel coordinate system is realized, the robot can accurately determine the position of the robot in the channel by using the data, and the robot can dynamically adjust according to the change of the channel environment.

2. The method for positioning a mobile robot in a dynamic aisle of an electrically mobile shelving as defined in claim 1, wherein: the S1 laser radar scanning comprises S1.1 laser radar installation, and a laser radar sensor is installed in a dynamic channel or above a mobile robot, so that the space of the channel can be comprehensively scanned.

3. The method for positioning a mobile robot in a dynamic aisle of an electrically mobile shelving as defined in claim 1, wherein: the S1 laser radar scanning comprises S1.2 real-time scanning, and the laser radar system scans a dynamic channel in real time to acquire channel structure and barrier information, wherein the channel structure and barrier information comprises the length and width of the channel and the position and the size of the barrier.

4. The method for positioning a mobile robot in a dynamic aisle of an electrically mobile shelving as defined in claim 1, wherein: the S1 laser radar scanning comprises S1.3 data processing, and data returned by the laser radar are processed and analyzed to generate a three-dimensional map and environment information of the channel.

5. The method for positioning a mobile robot in a dynamic aisle of an electrically mobile shelving as defined in claim 1, wherein: the S2 computer vision recognition and positioning comprises the step of installing an S2.1 vision sensor, carrying the vision sensor on a mobile robot, and capturing mark points or characteristics in a channel.

6. The method for positioning a mobile robot in a dynamic aisle of an electrically mobile shelving as defined in claim 1, wherein: the S2 computer vision recognition and positioning comprises S2.2 feature recognition, and a computer vision algorithm is utilized to recognize special marks, colors, textures or other features in the channel.

7. The method for positioning a mobile robot in a dynamic aisle of an electrically mobile shelving as defined in claim 1, wherein: the S2 computer vision identification and positioning comprises the step of establishing an S2.3 coordinate system, establishing a map of the interior of the channel based on the identified characteristic points, establishing the coordinate system, and determining the position and the gesture of the robot relative to the channel.

8. The method for positioning a mobile robot in a dynamic aisle of an electrically mobile shelving as defined in claim 1, wherein: the S3 robot positioning comprises S3.1 sensor integration, and the mobile robot is provided with a positioning sensor to receive information transmitted by the laser radar and the vision system.

9. The method for positioning a mobile robot in a dynamic aisle of an electrically mobile shelving as defined in claim 1, wherein: the S3 robot positioning comprises S3.2 data fusion, and data acquired by a laser radar, a vision system and a sensor of the robot are fused.

10. The method for positioning a mobile robot in a dynamic aisle of an electrically mobile shelving as defined in claim 1, wherein: the S3 robot positioning comprises S3.3 real-time positioning, and real-time positioning relative to a channel coordinate system is realized through fused data, so that the robot can accurately determine the position of the robot in the channel and dynamically adjust the robot according to the change of the channel environment.