WO2022134680A1

WO2022134680A1 - Method and device for robot positioning, storage medium, and electronic device

Info

Publication number: WO2022134680A1
Application number: PCT/CN2021/119172
Authority: WO
Inventors: 黄晓庆; 张站朝
Original assignee: 达闼机器人股份有限公司
Priority date: 2020-12-25
Filing date: 2021-09-17
Publication date: 2022-06-30
Also published as: CN112581535B; CN112581535A

Abstract

The present disclosure relates to a method and device for robot positioning, a storage medium, and an electronic device, for acquiring more environment feature points for feature matching in a robot positioning process, thus achieving robot positioning. The method for robot positioning comprises: controlling a robot to move in a target environment on the basis of a positioning navigation path corresponding to a constructed map; acquiring an actual environment feature of the position at where the robot is located during the moving process, and determining a sample environment feature corresponding to the position at where the robot is located; if the degree of match between the actual environment feature and the sample environment feature is less than a preset threshold, controlling the robot to make left and right swaying movements while traveling along the centerline of the positioning navigation path, thus adjusting the scanning range of a sensor used for collecting environment feature information; and determining, on the basis of an environment feature of the position at where the robot is located and collected by the sensor having the adjusted scanning range, the position at where the robot is located.

Description

Robot positioning method, device, storage medium and electronic device

CROSS-REFERENCE TO RELATED APPLICATIONS

This disclosure claims the priority of a Chinese patent application with application number 202011565214.5 and entitled "Robot Positioning Method, Device, Storage Medium and Electronic Equipment" filed with the Chinese Patent Office on December 25, 2020, the entire contents of which are incorporated by reference in in this disclosure.

technical field

The present disclosure relates to the field of robot technology, and in particular, to a robot positioning method, device, storage medium and electronic device.

Background technique

The indoor robot needs to scan and map the environment, and then match the environmental characteristics currently collected by the sensor with the environmental characteristics collected by the sensor when the map is built to determine the position and posture of the robot in space, that is, Realize the positioning of the robot. In practical application scenarios, there may be situations in which the currently collected environmental features cannot match the environmental features collected during mapping, or the matching degree is lower than the matching threshold, resulting in the problem that the robot cannot be accurately positioned.

In order to solve the above-mentioned problem that the robot cannot be positioned accurately, the related art usually optimizes the environmental features collected by the sensors, for example, the environmental features collected by the sensors can be denoised, etc., to improve the feature matching degree. However, in a scenario with a simple environment, such as a hotel corridor with a simple environment for delivering items, due to repeated and sparse environmental features, even if the environmental features are optimized, a better feature matching result may not be obtained, thus affecting the robot. accurate positioning.

SUMMARY OF THE INVENTION

The purpose of the present disclosure is to provide a robot positioning method, device, storage medium and electronic equipment, so as to provide a new robot positioning method.

In order to achieve the above object, in a first aspect, the present disclosure provides a method for positioning a robot, including:

Control the robot to move in the target environment based on the positioning and navigation path corresponding to the built map, and the built map is based on the sample environment features collected by the robot in the target environment by swinging left and right to perform map reconstruction. obtained;

Acquire the actual environmental characteristics of the position of the robot during the movement process, and determine the sample environmental characteristics corresponding to the position of the robot;

If the matching degree between the actual environment feature and the sample environment feature is less than a preset threshold, the robot is controlled to swing left and right along the centerline of the positioning and navigation path during the traveling process, so as to adjust the environment for collecting the environment. The scanning range of the sensor of the characteristic information;

The position of the robot is determined according to the environmental characteristics collected by the sensor at the position of the robot after the adjustment of the scanning range.

Optionally, the controlling the robot to perform a left-right rocking movement along the centerline of the positioning and navigation path during the traveling process includes:

The robot is controlled to move in an S-shape along the centerline of the positioning and navigation path.

When the density of the sample environment features corresponding to the position of the robot is greater than or equal to a preset density, control the robot to perform a left-right swinging motion with a first movement range along the centerline of the positioning and navigation path during traveling. move;

When the density of the sample environment features corresponding to the position of the robot is less than the preset density, the robot is controlled to perform a left-right rocking movement along the centerline of the positioning and navigation path with a second movement amplitude during the traveling process, Wherein, the second movement range is greater than the first movement range, and the movement range is used to represent the distance that the robot deviates from the center line.

Optionally, the controlling the robot to perform rocking movement from side to side with a first movement range along the centerline of the positioning and navigation path during the traveling process, including:

Controlling the robot to oscillate left and right along the centerline of the positioning and navigation path with the same first movement amplitude during travel; or

The first movement range is determined according to the density of the sample environmental features at the location of the robot and the first preset correspondence between the density of the environmental features and the movement range, and the robot is controlled to navigate along the positioning The center line of the path performs rocking side-to-side rocking movement at the first movement amplitude during the travel.

Optionally, the controlling the robot to perform a left-right rocking movement along the centerline of the positioning and navigation path with a second movement amplitude during the traveling process, including:

Controlling the robot to perform a left-right rocking movement along the centerline of the positioning and navigation path with the same second movement amplitude during travel; or

The second movement range is determined according to the density of the sample environment features at the location of the robot and the second preset correspondence between the density of the environment features and the movement range, and the robot is controlled to navigate along the positioning The centerline of the path performs a side-to-side rocking movement during travel with a second movement amplitude.

Optionally, determining the position of the robot according to the environmental characteristics collected by the sensor at the position of the robot after adjusting the scanning range includes:

If the degree of matching between the environmental characteristics collected by the sensor at the position of the robot after adjusting the scanning range and the sample environmental characteristics is less than the preset threshold, the robot is controlled to repeatedly execute the rotation positioning instruction, Until the degree of matching between the environmental characteristics collected by the sensor and the sample environmental characteristics of the corresponding position is greater than or equal to the preset threshold, the rotation and positioning instruction is used to control the robot to rotate at the position, and when all When the degree of matching between the environmental characteristics collected by the sensor and the sample environmental characteristics of the corresponding position after the robot rotates is less than the preset threshold, the robot is controlled to move forward along the positioning and navigation path to a new position;

The position of the robot is determined according to the environmental characteristics collected by the sensor after the robot stops executing the rotation positioning instruction.

Optionally, also include:

During the swinging movement of the robot left and right along the centerline of the positioning and navigation path, determining an obstacle-free area in which the robot can travel, and determining an obstacle-avoiding movement path of the robot in the obstacle-free area;

The robot is controlled to move according to the obstacle avoidance movement path.

In a second aspect, the present disclosure also provides a robot positioning device, comprising:

The first control module is used to control the robot to move based on the positioning and navigation path corresponding to the built map, and the built map is based on the sample environment features collected by the robot in the target environment by swinging left and right. rebuilt;

an acquisition module, configured to acquire the actual environmental characteristics of the location of the robot during the movement process, and to determine the sample environmental characteristics corresponding to the location of the robot;

The second control module is configured to control the robot to swing left and right along the centerline of the positioning and navigation path during traveling when the matching degree between the actual environment feature and the sample environment feature is less than a preset threshold , to adjust the scanning range of the sensor used to collect environmental feature information;

The positioning module is configured to determine the position of the robot according to the environmental characteristics collected by the sensor at the position of the robot after adjusting the scanning range.

In a third aspect, the present disclosure also provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, implements the steps of any one of the methods in the first aspect.

In a fourth aspect, the present disclosure also provides an electronic device, comprising:

a memory on which a computer program is stored;

A processor for executing the computer program in the memory to implement the steps of any one of the methods in the first aspect.

In a fifth aspect, the present disclosure also provides a computer program product comprising a computer program executable by a programmable apparatus, the computer program having, when executed by the programmable apparatus, for performing the first aspect The code portion of any one of the methods.

Through the above technical solution, during the mapping process, the robot can obtain more sample environment features by swinging left and right, and in the actual positioning process, if the matching degree between the actual environment features and the sample environment features is less than the preset threshold , then the robot can be controlled to swing left and right along the center line of the positioning and navigation path during the traveling process, so as to adjust the scanning range of the sensor used to collect environmental feature information, so as to obtain more actual environmental features. As a result, both the sample environment features and the actual environment features used for environment feature matching are increased, so the matching degree of the environment features can be improved, so as to achieve more stable robot positioning, and to a certain extent, the accuracy of the robot positioning can be improved.

Other features and advantages of the present disclosure will be described in detail in the detailed description that follows.

Description of drawings

The accompanying drawings are used to provide a further understanding of the present disclosure, and constitute a part of the specification, and together with the following detailed description, are used to explain the present disclosure, but not to limit the present disclosure. In the attached image:

Figure 1 is a dense point cloud image of the environment obtained by the robot scanning and mapping the environment;

Figure 2 is a sparse point cloud image of the environment obtained by the robot scanning and mapping the environment;

3 is a schematic diagram of a positioning and navigation path obtained by a robot scanning and mapping the environment;

4 is a flowchart of a method for positioning a robot according to an exemplary embodiment of the present disclosure;

5 is a schematic diagram of a built map in a robot positioning method according to an exemplary embodiment of the present disclosure;

6 is a schematic diagram of an obstacle avoidance process in a robot positioning method according to an exemplary embodiment of the present disclosure;

7 is a schematic diagram of interaction between a robot body and a server in a method for positioning a robot according to an exemplary embodiment of the present disclosure;

FIG. 8 is a block diagram of a robot positioning device according to an exemplary embodiment of the present disclosure;

FIG. 9 is a block diagram of an electronic device according to an exemplary embodiment of the present disclosure;

Fig. 10 is a block diagram of an electronic device according to another exemplary embodiment of the present disclosure.

Detailed ways

The specific embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the present disclosure, but not to limit the present disclosure.

SLAM (Simultaneous Iocalization and Mapping), real-time positioning and map construction, or concurrent mapping and positioning. The problem can be described as: put a robot into an unknown position in an unknown environment, is there a way for the robot to gradually draw a complete map of the environment while moving, the so-called complete map (a consistent map) means that the robot travels without obstacles to every corner of the room accessible. During this process, position estimation of the robot is required. Specifically, after obtaining the robot position estimate using the robot motion equation, the position of the robot can be corrected using the surrounding environment information obtained by the ranging unit. The above correction process is generally realized by extracting environmental features, and then re-observing the position of the features after the robot moves. EKF (Extended Kalman Filter, Extended Kalman Filter) is used to estimate the exact position of the robot in combination with the above information. Among them, the features selected in the above process are generally called landmarks, that is, the EKF will continuously estimate the position of the robot and the landmark positions in the surrounding environment.

As the robot moves, its position will change. At this time, according to the observation of the robot position sensor, the feature points in the observation information are extracted, and then the robot combines the position of the currently observed feature point, the robot motion distance and the position of the feature point before the robot motion through the EKF. Current location and current environment information are estimated.

Therefore, the robot needs to first scan and map the environment through single-line or multi-line lidar 3D scanning, visual sensors (including but not limited to binocular vision, TOF and infrared active light cameras, etc.) Environment dense point cloud map, environment sparse point cloud map shown in Figure 2, and navigation path map shown in Figure 3). Then the robot can determine its position and posture in space by matching the environmental features collected by sensors in the environment where the map has been built, that is, to realize the positioning of the robot.

Therefore, in the actual navigation process of the robot, it is necessary to follow the trajectory route of the built map as much as possible on the basis of the built map (for example, according to the navigation path shown in Figure 3) Travel and move, which ensures that the features of the current environment scanned by the lidar and vision sensors get the most and most credible search matches to the features that have been mapped to get the best feature matching locations, in other words, the maximum The guaranteed matching probability is the largest.

However, in practical application scenarios, there may be situations in which the currently collected environmental features cannot match the environmental features collected during mapping, or the matching degree is lower than the matching threshold, resulting in the problem that the robot cannot be accurately positioned. In order to solve the above-mentioned problem that the robot cannot be positioned accurately, the related art usually optimizes the environmental features collected by the sensors, for example, the environmental features collected by the sensors can be denoised, etc., to improve the feature matching degree.

The inventor's research found that in a scenario with a simple environment, such as a hotel corridor with a simple environment for delivering items, due to repeated and sparse environmental features, even if the environmental features are optimized, a better feature matching result may not be obtained. , thus affecting the accurate positioning of the robot. Or, in a scene with a complex environment and rich visual features, such as parks and communities where robots need to patrol, due to the complex and rich environmental features, optimizing the environmental features may lose some important environmental features, thereby affecting the accurate positioning of the robot. . That is to say, the related technology optimizes the environmental features without changing the number of collected environmental features to improve the matching degree of the environmental features, which may lead to the inability to obtain a better environment in a scene with a simple or complex environment. The result of feature matching, and then the accurate positioning of the robot cannot be achieved.

In view of this, the present disclosure proposes a robot positioning method, device, storage medium and electronic device, so as to obtain more environmental feature points for feature matching during the robot positioning process, thereby improving the accuracy of robot positioning and better application Robot positioning requirements in different scenarios.

Fig. 4 is a flowchart of a method for positioning a robot according to an exemplary embodiment of the present disclosure. 4, the robot positioning method includes:

Step 401 , controlling the robot to move in the target environment based on the positioning and navigation path corresponding to the built map. The built map is obtained by reconstructing the map based on the sample environment features collected by the robot in the target environment by swinging left and right.

Step 402: Acquire the actual environmental characteristics of the location where the robot is located during the moving process, and determine the sample environmental characteristics corresponding to the location where the robot is located.

Step 403, if the matching degree between the actual environment feature and the sample environment feature is less than the preset threshold, then control the robot to swing left and right along the center line of the positioning and navigation path during the traveling process, so as to adjust the sensor used for collecting the environment feature information. Scan range.

Step 404: Determine the position of the robot according to the environmental characteristics collected by the sensor at the position of the robot after adjusting the scanning range.

Through the above method, during the mapping process, the robot can obtain more sample environment features by swinging left and right, and in the actual positioning process, if the matching degree between the actual environment feature and the sample environment feature is less than the preset threshold, Then, the robot can be controlled to swing left and right along the center line of the positioning and navigation path during the traveling process, so as to adjust the scanning range of the sensor used for collecting environmental feature information, so as to obtain more actual environmental features. As a result, both the sample environment features and the actual environment features used for environment feature matching are increased, so the matching degree of the environment features can be improved, so as to achieve more stable robot positioning, and to a certain extent, the accuracy of the robot positioning can be improved.

In order to make those skilled in the art better understand the robot positioning method provided by the embodiments of the present disclosure, the above steps are described in detail below.

Illustratively, prior to step 401, the robot may move in the target environment. And in order to obtain more environmental features for mapping (such as environment dense point cloud image and environment sparse point cloud image), the robot can swing left and right in the target environment. For example, the head or body part of the robot provided with sensors for collecting environmental features can be controlled to swing left and right, or the whole robot can be controlled to swing left and right in an S-shape, and so on. Wherein, the sensors used to collect environmental features include but are not limited to lidar, depth camera, and millimeter-wave radar, and can be selected according to requirements when the present disclosure is specifically implemented.

By performing map reconstruction through the sample environment features pre-collected by the robot, a built map corresponding to the target environment can be obtained, such as the built map shown in FIG. 5 . After that, the robot can be controlled to move in the target environment based on the positioning and navigation path corresponding to the built map, and during the movement process, the actual environmental characteristics of the robot's location can be obtained, and the sample environmental characteristics corresponding to the robot's location can be determined at the same time. , so that the subsequent process can realize the positioning of the robot according to the matching of environmental characteristics.

For example, if the matching degree between the actual environment feature and the sample environment feature is less than the preset threshold, the robot is controlled to swing left and right along the centerline of the positioning and navigation path during the traveling process, so as to adjust the sensor used for collecting the environment feature information. Scan range. The preset threshold may be set according to an actual scene, which is not limited in this embodiment of the present disclosure. The matching degree between the actual environment feature and the sample environment feature is less than the preset threshold, which may be that the matching degree between the actual environment feature and the sample environment feature is less than the preset threshold at a certain moment, or it may be the matching between the actual environment feature and the sample environment feature for a continuous period of time. The degree is smaller than the preset threshold, etc., which is not limited in this embodiment of the present disclosure.

For example, both the actual environment feature and the sample environment feature may include multiple environment feature points, and accordingly, the matching degree between the actual environment feature and the sample environment feature may be determined by the number of matched environment feature points in the actual environment feature and the sample environment feature. express. Of course, the matching degree between the actual environment feature and the sample environment feature may also be determined by other methods in the related art, which is not limited in this embodiment of the present disclosure.

For example, the positioning navigation path may be shown in FIG. 3 , which is used to represent the movement path of the robot in the target environment. The positioning navigation path may correspond to a road with a width in the actual environment, so the center line of the positioning navigation path may be the road center line corresponding to the positioning navigation path. In specific implementation, the centerline of the positioning navigation path can be determined according to the trajectory during visual SLAM mapping, or the navigation path planned by laser SLAM.

For example, controlling the robot to perform a left-right rocking movement along the centerline of the positioning and navigation path during the traveling process may be controlling the robot as a whole to perform a left-right rocking movement along the centerline of the positioning and navigation path during the traveling process, or it may also be to control the The provided sensor for collecting environmental feature information performs a swinging movement from side to side, and so on, which is not limited in this embodiment of the present disclosure. For example, if the depth camera used to collect environmental feature information is set on the head of the robot, when the matching degree between the actual environmental features and the sample environmental features is less than the preset threshold, the head of the robot can be controlled to rotate left and right by several angles to increase the The scanning range of the depth camera is used to obtain more actual environmental features for environmental feature matching to achieve robot positioning.

In a possible manner, controlling the robot to perform a left-right rocking movement along the centerline of the positioning and navigation path during the traveling process may be to control the robot to move in an S-shape along the centerline of the positioning and navigation path. That is to say, the whole robot can be controlled to perform left-right S-shaped movement, or the sensor provided on the robot for collecting environmental features can be controlled to perform left-right S-shaped movement, etc., which are not limited in the embodiments of the present disclosure. In this way, during the mapping process, the robot can acquire more sample environment features through S-shaped movement. In the actual positioning process, the robot can also obtain more actual environment features through S-shaped movement, which can further improve the matching degree of the sample environment features and the actual environment features, thereby improving the positioning accuracy of the robot.

In a possible manner, controlling the robot to perform a left-right rocking movement along the centerline of the positioning and navigation path during the traveling process may also be: when the density of the sample environment features corresponding to the position of the robot is greater than or equal to the preset density, controlling the robot Along the centerline of the positioning and navigation path, the first movement amplitude is used to move left and right during the travel process. When the density of the sample environment features corresponding to the position of the robot is less than the preset density, the robot is controlled along the centerline of the positioning and navigation path to move to the left and right. The second movement range performs a left-right rocking movement during traveling, the second movement range is greater than the first movement range, and the movement range is used to represent the distance that the robot deviates from the center line. The preset density may be set according to actual conditions, which is not limited in this embodiment of the present disclosure.

In the actual positioning process, the environment complexity in the target environment can be determined according to the sample environment characteristics collected during map construction. Therefore, in this embodiment of the present disclosure, the complexity of the current environment (that is, the density and sparseness of environmental characteristics) can be determined. Adapt to the magnitude of the robot's left and right rocking movement. Specifically, in the case of complex environment (such as dense, obvious and unobstructed environment features), the robot can move slowly or not at a small amplitude to save energy consumption of the robot. On the other hand, when the environment is simple (such as sparse and inconspicuous environmental features), the amplitude of the robot's left and right swaying movement can be increased to obtain more actual environmental features that match the sample environmental features, so as to achieve more effective position.

It should be understood that the movement range is used to represent the distance that the robot moves away from the centerline of the navigation path. to more environmental features. This embodiment of the present disclosure does not limit the setting of the first movement range and the second movement range, as long as the first movement range is smaller than the second movement range, and in a possible manner, the first movement range may be set to 0.

In a possible manner, the robot is controlled to move left and right with a first movement amplitude along the centerline of the positioning and navigation path during the traveling process, which may be to control the robot to travel along the centerline of the positioning and navigation path with the same first movement amplitude During the process, the swinging movement is performed left and right; or, according to the density of the sample environment features at the location of the robot, and the first preset correspondence between the density of the environment features and the movement range, determine the first movement range, and control the robot to move along the The center line of the positioning navigation path performs a left-right oscillating movement with a first movement range during traveling.

That is to say, the embodiments of the present disclosure provide two ways of controlling the robot to swing left and right along the center line of the positioning and navigation path with the first movement range during the traveling process, so as to better meet the positioning requirements of the robot in different scenarios. . Among them, the first way is to control the robot to swing left and right during the traveling process with the same first movement range, which simplifies the control of the robot. The second method is to determine the first movement range of the robot according to the density of environmental characteristics, so that when the density of sample environmental characteristics is greater than or equal to the preset density, the robot can also determine different first movement ranges according to the density of environmental characteristics, Increased flexibility for robot control.

For the second method, during the mapping process, for each position in the target environment where the density of environmental characteristics is greater than or equal to the preset density, the robot can be controlled to perform left and right movements of different amplitudes during the travel process according to the density of environmental characteristics of the position. Rocking movement to maximize the sample environment characteristics corresponding to the location. Then, for each position in the target environment where the environmental characteristic density is greater than or equal to the preset density, the environmental characteristic density of the position and the corresponding robot movement range can be recorded, thereby obtaining the first preset correspondence. In the subsequent actual positioning process, during the movement of the robot, after determining the characteristic density of the sample environment where the robot is located, if the characteristic density of the sample environment is greater than or equal to the preset density, the Set the corresponding relationship, determine the first movement range, and control the robot to move left and right along the center line of the positioning and navigation path with the first movement range, so as to collect more actual environment features for feature matching.

Similarly, controlling the robot to perform rocking movement along the centerline of the positioning and navigation path with the second movement amplitude during the traveling process may be: controlling the robot to perform the same second moving amplitude during the traveling process along the centerline of the positioning and navigation path swinging left and right; or, according to the density of the sample environment features at the location where the robot is located, and the second preset correspondence between the density of the environment features and the movement range, determine the second movement range, and control the robot along the positioning and navigation path The center line of , with a second movement amplitude, moves side-to-side oscillatingly during travel.

That is to say, the embodiments of the present disclosure can provide two ways of controlling the robot to swing left and right along the center line of the positioning navigation path with the second movement amplitude during the traveling process, so as to better satisfy the robot positioning in different scenarios. need. Among them, the first method is to control the robot to swing left and right during the traveling process with the same second movement range, which simplifies the control of the robot. The second method is to determine the second moving range of the robot according to the density of environmental features, so that when the density of sample environmental features is less than the preset density, the robot can also determine different second moving ranges according to the density of environmental features, increasing the Flexibility for robot control.

For the second method, during the mapping process, for each position in the target environment where the density of environmental characteristics is less than the preset density, the robot can be controlled to swing left and right with different amplitudes in the process of traveling according to the density of environmental characteristics of the position. Move to maximize the collection of sample environmental characteristics corresponding to that location. Then, for each position in the target environment where the environmental characteristic density is less than the preset density, the environmental characteristic density of the position and the corresponding robot movement range can be recorded, so as to obtain a second preset corresponding relationship. In the subsequent actual positioning process, during the movement of the robot, after determining the sample environment characteristic density of the location where the robot is located, if the sample environment characteristic density is less than the preset density, then the sample environment characteristic density can correspond to the second preset according to the sample environment characteristic density. relationship, and determine the second movement range, so as to control the robot to perform the left and right range along the center line of the positioning and navigation path with the second movement range, so as to collect more actual environment features for feature matching.

In the above manner, the robot can be controlled to swing left and right along the center line of the positioning and navigation path through a fixed movement range, which simplifies the positioning control of the robot. Alternatively, the corresponding movement range can be determined according to the density of the environmental features, so that the robot can be controlled to swing left and right with different amplitudes during the traveling process along the positioning and navigation path, which increases the control flexibility and can better adapt to different positioning scenarios.

In practical applications, it may be possible to adjust the scanning range of the sensor used to collect environmental feature information by controlling the robot to swing left and right along the centerline of the positioning and navigation path during travel, that is, after increasing the scanning range of the sensor, If the matching degree between the collected actual environmental characteristics and the sample environmental characteristics is still less than the preset threshold, it can be considered that the matching degree between the actual environmental characteristics and the sample environmental characteristics is smaller than the preset threshold continuously.

In this case, step 404 may be: if the matching degree between the environmental characteristics collected by the sensor at the position of the robot after adjusting the scanning range and the sample environmental characteristics is less than the preset threshold, the robot is controlled to repeatedly execute the rotation and positioning instructions until The matching degree of the environmental features collected by the sensor and the sample environmental features of the corresponding position is greater than or equal to the preset threshold. The rotation positioning instruction is used to control the robot to rotate at the position, and when the degree of matching between the environmental characteristics collected by the sensor after the robot rotates and the sample environmental characteristics of the corresponding position is less than a preset threshold, the robot is controlled to move along the positioning and navigation path. before moving to a new location. Finally, the position of the robot is determined according to the environmental characteristics collected by the sensor after the robot stops executing the rotation positioning instruction.

For example, when the matching degree between the actual environment feature and the sample environment feature is less than a preset threshold value, the robot can be controlled to suspend the movement, and the robot can be controlled to repeatedly execute the rotation positioning instruction. Specifically, the robot can be controlled to rotate 360 degrees on the spot to obtain the maximum feature matching probability at the current position. If the probability of the maximum feature matching is less than the preset probability, it means that the degree of matching between the environmental features collected by the sensor and the sample environmental features of the corresponding position after the rotation is still less than the preset threshold, that is, the robot still cannot achieve positioning through feature matching. The robot can then be controlled to move forward along the positioning and navigation path to a new position, and this process is an execution process of the rotation positioning instruction. If, after moving to a new position, the matching degree between the actual environmental features collected by the robot at the new position and the sample environmental features corresponding to the new position is greater than or equal to the preset threshold, it means that the robot can achieve positioning through the matching of environmental features. This stops the execution of the rotation positioning command. And according to the environmental characteristics collected by the sensor after the robot stops executing the rotation positioning instruction, the position of the robot is determined, that is, the positioning of the robot is realized. The preset probability may be set according to an actual situation, which is not limited in this embodiment of the present disclosure.

On the other hand, if after moving to a new position, the matching degree between the actual environmental features collected by the robot at the new position and the sample environmental features corresponding to the new position is still less than the preset threshold, it means that the robot has moved to the new position. After that, it is still impossible to achieve positioning through environmental feature matching, so that the rotation positioning command can be executed again, that is, the robot can be controlled to rotate 360 degrees in a new position, and when the robot rotates, the environmental characteristics collected by the sensor and the sample environmental characteristics of the corresponding position When the matching degree is less than the preset threshold, control the robot to move forward along the positioning and navigation path to another new position, so as to repeatedly find the position where the robot can be positioned by the environmental features, so as to realize the positioning of the robot.

In a possible way, taking into account the accidental error, it is also possible to control the robot to continue to move based on inertial motion when the actual environmental characteristics currently collected and the sample environmental characteristics collected during mapping cannot be matched or the matching degree is lower than the preset threshold. At the same time, it continues to match subsequent environmental features. When the matching degree between the actual environment features and the sample environment features collected during mapping is less than the preset threshold for several consecutive moments, the robot is controlled to swing left and right along the center line of the positioning and navigation path during the traveling process to adjust the data used for the collection. The scanning range of the sensor for environmental feature information. When the matching degree between the actual environment features and the sample environment features collected during mapping is smaller than the preset minimum threshold for several consecutive moments, the robot will be controlled along the positioning method by automatically gradually increasing the left and right swaying movement amplitude and reducing the moving speed at the same time. The center line of the navigation path is swayed left and right during the traveling process to search for more matching feature points to achieve a higher degree of environmental feature matching, thereby achieving accurate positioning. Wherein, the preset minimum threshold is smaller than the preset threshold, and the preset minimum threshold may be set according to the actual situation, which is not limited in this embodiment of the present disclosure.

If the degree of matching between the environmental features collected by the sensor at the location of the robot and the sample environmental features is still less than the preset threshold after the amplitude of the left-right swinging movement is increased, the robot can also be controlled to repeatedly execute the rotation and positioning instructions until the sensor collects The degree of matching between the environmental feature and the sample environmental feature of the corresponding position is greater than or equal to a preset threshold.

In practical application scenarios, the most common situation is that when the robot is surrounded by crowds or a large obstacle appears temporarily, the environmental features used for positioning will be lost in a large area due to artificial occlusion, resulting in the loss of the robot's positioning. In order to solve this problem, the embodiments of the present disclosure can determine the obstacle-free area where the robot can travel during the swinging movement of the robot along the center line of the positioning and navigation path, and determine the obstacle-avoiding movement path of the robot in the obstacle-free area, and then Control the robot to move according to the obstacle avoidance movement path.

That is to say, when facing an obstacle, the robot can first find an area where it can continue to travel by swinging left and right to walk the S-shaped route, and plan an obstacle avoidance movement path around the obstacle to return to On the normal positioning navigation path. As shown in Figure 6, the robot can find a feasible obstacle avoidance area by swinging left and right to walk an S-shaped path, and plan a local path to obtain an obstacle avoidance path. The robot can then be controlled to move along the obstacle avoidance path. Referring to FIG. 6 , after the obstacle avoidance path, the robot can move to the normal planned path (that is, the positioning and navigation path determined during mapping) and continue to move, so that the obstacle avoidance function can be realized while improving the positioning accuracy.

It should be understood that any of the above-mentioned robot positioning methods can be applied to a robot, that is, to a controller of the robot. In this case, a built map corresponding to the target environment can be stored in the memory of the robot. Correspondingly, during the moving process, the robot can obtain the actual environmental characteristics of its own location, and determine the sample environmental characteristics corresponding to its own location through the stored built map. If the matching degree between the actual environment feature and the sample environment feature is less than the preset threshold, the robot can be controlled to swing left and right along the center line of the positioning and navigation path during the traveling process, so as to adjust the scanning range of the sensor used to collect the environment feature information. , and finally determine its own position according to the environmental characteristics collected by the sensor at the position of the robot after adjusting the scanning range.

In another possible manner, any one of the above robot positioning methods can be applied to the server. In this case, referring to FIG. 7 , the server may store a built map, the robot may obtain environmental information of its own location through sensors, and extract environmental features from the environmental information through a feature extraction module. Correspondingly, the server can acquire the actual environmental characteristics corresponding to the position of the robot by receiving the environmental characteristics. At the same time, the server can determine the sample environment characteristics corresponding to the location of the robot through the stored map. Then the server can determine the matching degree between the actual environment feature and the sample environment feature. If the matching degree between the actual environment feature and the sample environment feature is less than the preset threshold, the server can send a control instruction to the robot to control the robot along the positioning and navigation path. The center line swings left and right during the traveling process to adjust the scanning range of the sensor used to collect environmental feature information. Finally, the position of the robot is determined according to the environmental features collected by the sensor at the location of the robot after adjusting the scanning range. , the robot body can send the environmental characteristics collected by the sensor after adjusting the scanning range to the server, so that the server can locate the robot according to the matching degree between the environmental characteristics and the corresponding sample environmental characteristics.

Based on the same inventive concept, the present disclosure also provides a robot positioning device, which can become part or all of a robot or a server through software, hardware, or a combination of the two. 8, the robot positioning device 800 may include:

The first control module 801 is used to control the robot to move based on the positioning and navigation path corresponding to the built map. The built map is based on the sample environment characteristics collected by the robot in the target environment by swinging left and right. obtained from map reconstruction;

an acquisition module 802, configured to acquire the actual environmental characteristics of the location where the robot is located during the movement process, and determine the sample environmental characteristics corresponding to the location of the robot;

The second control module 803 is configured to control the robot to sway from side to side along the centerline of the positioning and navigation path during the traveling process when the matching degree between the actual environment feature and the sample environment feature is less than a preset threshold Move to adjust the scanning range of the sensor used to collect environmental feature information;

The positioning module 804 is configured to determine the position of the robot according to the environmental characteristics collected by the sensor at the position of the robot after adjusting the scanning range.

Optionally, the second control module 803 is used for:

The first movement range is determined according to the density of the sample environmental features at the location of the robot and the first preset correspondence between the density of the environmental features and the movement range, and the robot is controlled to navigate along the positioning The center line of the path performs a side-to-side rocking movement with a first movement amplitude during the travel.

Optionally, the second control module 803 is used for:

Optionally, the positioning module is used for:

When the degree of matching between the environmental characteristics collected by the sensor at the location of the robot after adjusting the scanning range and the sample environmental characteristics is less than the preset threshold, the robot is controlled to repeatedly execute the rotation positioning instruction, Until the degree of matching between the environmental characteristics collected by the sensor and the sample environmental characteristics of the corresponding position is greater than or equal to the preset threshold, the rotation and positioning instruction is used to control the robot to rotate at the position, and when all When the degree of matching between the environmental characteristics collected by the sensor and the sample environmental characteristics of the corresponding position after the robot rotates is less than the preset threshold, the robot is controlled to move forward along the positioning and navigation path to a new position;

Optionally, the apparatus 800 further includes:

The determining module is used to determine the obstacle-free area in which the robot can travel during the swinging movement of the robot along the centerline of the positioning and navigation path, and determine the avoidance of the robot in the obstacle-free area. obstacle movement path;

The third control module is configured to control the robot to move according to the obstacle avoidance movement path.

Regarding the apparatus in the above-mentioned embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be described in detail here.

Based on the same inventive concept, the present disclosure also provides an electronic device, including:

a memory on which a computer program is stored;

The processor is configured to execute the computer program in the memory, so as to implement the steps of any one of the above robot positioning methods.

In a possible manner, the block diagram of the electronic device is shown in FIG. 9 . Referring to FIG. 9 , the electronic device 900 may include: a processor 901 and a memory 902 . The electronic device 900 may also include one or more of a multimedia component 903 , an input/output (I/O) interface 904 , and a communication component 905 .

Wherein, the processor 901 is used to control the overall operation of the electronic device 900 to complete all or part of the steps in the above-mentioned robot positioning method. The memory 902 is used to store various types of data to support operations on the electronic device 900, such data may include, for example, instructions for any application or method operating on the electronic device 900, and application-related data, Such as sent and received messages, pictures, audio, video and so on. The memory 902 can be implemented by any type of volatile or nonvolatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, SRAM for short), electrically erasable programmable read-only memory ( Electrically Erasable Programmable Read-Only Memory (EEPROM for short), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (Read-Only Memory, ROM for short), magnetic memory, flash memory, magnetic disk or optical disk. Multimedia components 903 may include screen and audio components. Wherein the screen can be, for example, a touch screen, and the audio component is used for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in memory 902 or transmitted through communication component 905 . The audio assembly also includes at least one speaker for outputting audio signals. The I/O interface 904 provides an interface between the processor 901 and other interface modules, and the above-mentioned other interface modules may be a keyboard, a mouse, a button, and the like. These buttons can be virtual buttons or physical buttons. The communication component 905 is used for wired or wireless communication between the electronic device 900 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or one or more of them The combination is not limited here. Therefore, the corresponding communication component 905 may include: Wi-Fi module, Bluetooth module, NFC module and so on.

In an exemplary embodiment, the electronic device 900 may be implemented by one or more application-specific integrated circuits (Application Specific Integrated Circuit, ASIC for short), digital signal processors (Digital Signal Processor, DSP for short), digital signal processing devices (Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), controller, microcontroller, microprocessor or other electronic components Implementation is used to execute the above-mentioned robot positioning method.

In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, the program instructions implement the steps of the above-mentioned robot positioning method when executed by a processor. For example, the computer-readable storage medium can be the above-mentioned memory 902 including program instructions, and the above-mentioned program instructions can be executed by the processor 901 of the electronic device 900 to complete the above-mentioned robot positioning method.

In another possible way, the electronic device may be provided as a server. 10 , the electronic device 1000 includes a processor 1022 , which may be one or more in number, and a memory 1032 for storing a computer program executable by the processor 1022 . A computer program stored in memory 1032 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processor 1022 may be configured to execute the computer program to perform the robot positioning method described above.

In addition, the electronic device 1000 may also include a power supply component 1026, which may be configured to perform power management of the electronic device 1000, and a communication component 1050, which may be configured to enable communication of the electronic device 1000, eg, wired or wireless communication. Additionally, the electronic device 1000 may also include an input/output (I/O) interface 1058 . Electronic device 1000 may operate based on an operating system stored in memory 1032, such as Windows Server™, Mac OS X™, Unix™, Linux™, and the like.

In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, the program instructions implement the steps of the above-mentioned robot positioning method when executed by a processor. For example, the computer-readable storage medium can be the above-mentioned memory 1032 including program instructions, and the above-mentioned program instructions can be executed by the processor 1022 of the electronic device 1000 to complete the above-mentioned robot positioning method.

In another exemplary embodiment, there is also provided a computer program product comprising a computer program executable by a programmable apparatus, the computer program having, when executed by the programmable apparatus, for performing the above The code section of the robot positioning method.

The preferred embodiments of the present disclosure have been described above in detail with reference to the accompanying drawings. However, the present disclosure is not limited to the specific details of the above-mentioned embodiments. Various simple modifications can be made to the technical solutions of the present disclosure within the scope of the technical concept of the present disclosure. These simple modifications all fall within the protection scope of the present disclosure.

In addition, it should be noted that the various specific technical features described in the above-mentioned specific embodiments can be combined in any suitable manner unless they are inconsistent. In order to avoid unnecessary repetition, the present disclosure provides The combination method will not be specified otherwise.

In addition, the various embodiments of the present disclosure can also be arbitrarily combined, as long as they do not violate the spirit of the present disclosure, they should also be regarded as the contents disclosed in the present disclosure.

Claims

A method for positioning a robot, comprising:

Control the robot to move in the target environment based on the positioning and navigation path corresponding to the built map, and the built map is based on the sample environment features collected by the robot in the target environment by swinging left and right to perform map reconstruction. obtained;

Acquire the actual environmental characteristics of the location where the robot is located during the moving process, and determine the sample environment characteristics corresponding to the location where the robot is located;

If the matching degree between the actual environment feature and the sample environment feature is less than a preset threshold, the robot is controlled to swing left and right along the centerline of the positioning and navigation path during the traveling process, so as to adjust the environment for collecting the environment. The scanning range of the sensor of the characteristic information;

The position of the robot is determined according to the environmental characteristics collected by the sensor at the position of the robot after the adjustment of the scanning range.
The method according to claim 1, wherein the controlling the robot to perform rocking movement from side to side along the centerline of the positioning and navigation path during the traveling process comprises:

The robot is controlled to move in an S-shape along the centerline of the positioning and navigation path.
The method according to claim 1 or 2, wherein the controlling the robot to perform rocking movement from side to side along the center line of the positioning and navigation path during the traveling process comprises:

When the density of the sample environment features corresponding to the position of the robot is greater than or equal to a preset density, control the robot to perform a left-right swinging motion with a first movement range along the centerline of the positioning and navigation path during traveling. move;

When the density of the sample environment features corresponding to the position of the robot is less than the preset density, the robot is controlled to perform a left-right rocking movement along the centerline of the positioning and navigation path with a second movement amplitude during the traveling process, Wherein, the second movement range is greater than the first movement range, and the movement range is used to represent the distance that the robot deviates from the center line.
The method according to claim 3, wherein the controlling the robot to perform rocking movement from side to side with a first movement range along the center line of the positioning and navigation path during the traveling process, comprising:

Controlling the robot to oscillate left and right along the centerline of the positioning and navigation path with the same first movement amplitude during travel; or

The first movement range is determined according to the density of the sample environmental features at the location of the robot and the first preset correspondence between the density of the environmental features and the movement range, and the robot is controlled to navigate along the positioning The center line of the path performs a rocking side-to-side rocking movement with a first movement amplitude during the traveling process.
The method according to claim 3, wherein the controlling the robot to perform rocking movement from side to side with a second movement range along the center line of the positioning and navigation path during traveling, comprising:

Controlling the robot to perform a left-right rocking movement along the centerline of the positioning and navigation path with the same second movement amplitude during travel; or

The second movement range is determined according to the density of the sample environment features at the location of the robot and the second preset correspondence between the density of the environment features and the movement range, and the robot is controlled to navigate along the positioning The centerline of the path moves side-to-side oscillatingly during travel by the second movement amplitude.
The method according to claim 1 or 2, wherein the position of the robot is determined according to the environmental characteristics collected by the sensor after the adjustment of the scanning range at the position of the robot, include:

If the matching degree between the environmental characteristics collected by the sensor at the position of the robot after adjusting the scanning range and the sample environmental characteristics is less than the preset threshold, the robot is controlled to repeatedly execute the rotation positioning instruction, Until the degree of matching between the environmental characteristics collected by the sensor and the sample environmental characteristics of the corresponding position is greater than or equal to the preset threshold, the rotation and positioning instruction is used to control the robot to rotate at the position, and when all When the degree of matching between the environmental characteristics collected by the sensor and the sample environmental characteristics of the corresponding position after the robot rotates is less than the preset threshold, the robot is controlled to move forward along the positioning and navigation path to a new position;

The position of the robot is determined according to the environmental characteristics collected by the sensor after the robot stops executing the rotation positioning instruction.
The method according to claim 1 or 2, further comprising:

During the swinging movement of the robot left and right along the centerline of the positioning and navigation path, determining an obstacle-free area in which the robot can travel, and determining an obstacle-avoiding movement path of the robot in the obstacle-free area;

The robot is controlled to move according to the obstacle avoidance movement path.
A robot positioning device, comprising:

The first control module is used to control the robot to move based on the positioning and navigation path corresponding to the built map, and the built map is based on the sample environment features collected by the robot in the target environment by swinging left and right. rebuilt;

an acquisition module, configured to acquire the actual environmental characteristics of the location of the robot during the movement process, and to determine the sample environmental characteristics corresponding to the location of the robot;

The second control module is configured to control the robot to swing left and right along the centerline of the positioning and navigation path during traveling when the matching degree between the actual environment feature and the sample environment feature is less than a preset threshold , to adjust the scanning range of the sensor used to collect environmental feature information;

The positioning module is configured to determine the position of the robot according to the environmental characteristics collected by the sensor at the position of the robot after adjusting the scanning range.
A computer-readable storage medium on which a computer program is stored, characterized in that, when the program is executed by a processor, the steps of the method according to any one of claims 1-7 are implemented.
An electronic device, comprising:

a memory on which a computer program is stored;

A processor for executing the computer program in the memory to implement the steps of the method of any one of claims 1-7.
A computer program product, characterized in that the computer program product comprises a computer program executable by a programmable device, the computer program having, when executed by the programmable device, for performing any one of claims 1-7 The code part of the method described in item.