Self-adaptive repositioning method and system of mobile robot, robot and medium

Abstract

The invention provides a self-adaptive repositioning method and system of a mobile robot, the robot and a medium, and relates to the technical field of repositioning. The method comprises the steps that after it is detected that positioning of the mobile robot fails, repositioning is carried out according to current multi-source sensor data; if the relocation fails, determining a relocation failure type according to the multi-source sensor data; and according to the relocation failure type and the relocation times, determining whether to continue relocation and parameters during relocation. According to the method provided by the invention, invalid retry can be avoided, so that the real-time performance is ensured, and the success rate of relocation is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of repositioning, and particularly relates to a self-adaptive repositioning method and system for a mobile robot, the robot and a medium. BACKGROUND

[0002] Mobile robots such as intelligent forklifts generally use technologies such as simultaneous localization and mapping (SLAM) to achieve autonomous operation. However, in a complex dynamic environment (such as cargo occlusion, light changes, ground reflections, etc.), positioning drift or loss often occurs, and the system needs to trigger a repositioning process to restore the pose estimation.

[0003] In related technologies, when a mobile robot detects a positioning anomaly, an unlimited number of or fixed long-time repositioning attempts are usually started, and the vehicle is stalled during the waiting period. If the environment features are not good (such as an empty corridor or a repeated structure area), invalid retries are easily caused, which leads to a long-term failure of repositioning, causes task blocking and scheduling delay, and even causes subsequent path conflicts.

[0004] Therefore, a self-adaptive repositioning scheme for a mobile robot is needed, which can avoid invalid retries to ensure real-time performance and improve the success rate of repositioning. SUMMARY

[0005] Embodiments of the present application provide a self-adaptive repositioning method and system for a mobile robot, which can avoid invalid retries to ensure real-time performance and improve the success rate of repositioning.

[0006] In a first aspect, embodiments of the present application provide a self-adaptive repositioning method for a mobile robot, comprising:

[0007] After detecting that the mobile robot fails to position, repositioning is performed according to current multi-source sensor data;

[0008] If the repositioning fails, a repositioning failure type is determined according to the multi-source sensor data.

[0009] According to the repositioning failure type and the number of repositioning, it is determined whether to continue repositioning and parameters during repositioning.

[0010] In a possible implementation, the repositioning according to the current multi-source sensor data comprises:

[0011] According to the data collected by the sensors of the mobile robot, multi-source sensor data is determined, and the sensors include one or more of a laser radar, a camera, an inertial measurement unit (IMU), and a wheel speed encoder.

[0012] relocalization is performed according to the multi-source sensor data and a particle filter algorithm, a relocalization confidence is obtained, and a relocalization number is recorded.

[0013] In a possible implementation, the determining of the relocalization failure type according to the multi-source sensor data comprises:

[0014] The environment quality indicator is determined according to the multi-source sensor data, and the environment quality indicator comprises at least one of a laser point cloud density, a visual ORB feature point quantity, and a motion blur index.

[0015] The motion parameter indicator is determined according to the multi-source sensor data, and the motion parameter indicator comprises at least one of an IMU data quality and a wheel speed encoder data quality.

[0016] The relocalization failure type is determined according to the environment quality indicator and the motion parameter indicator.

[0017] In a possible implementation, the determining of the relocalization failure type according to the environment quality indicator and the motion parameter indicator comprises:

[0018] It is determined whether the motion parameter indicator is normal data quality.

[0019] If the motion parameter indicator is abnormal data, it is determined that the relocalization failure type is structural mismatch.

[0020] If the motion parameter indicator is normal data, it is determined whether the environment quality indicator is low. When the environment quality indicator is high, it is determined that the relocalization failure type is temporary interference. When the environment quality indicator is low, a new environment quality indicator is determined according to new multi-source sensor data, and it is determined whether the new environment quality indicator is low. If the new environment quality indicator is low, it is determined that the relocalization failure type is structural mismatch. If the new environment quality indicator is high, it is determined that the relocalization failure type is temporary interference.

[0021] In a possible implementation, the determining of whether the environment quality indicator is low comprises:

[0022] It is determined whether the environment quality indicator satisfies the following A-C:

[0023] A: The laser point cloud density is less than a point cloud density threshold value, and a difference between the laser point cloud density and the point cloud density threshold value is greater than a preset density difference threshold value.

[0024] B: The visual ORB feature point quantity is less than a feature point quantity threshold value, and a difference between the visual ORB feature point quantity and the feature point quantity threshold value is greater than a preset quantity difference threshold value.

[0025] C: The motion blur index is less than the blur index threshold, and the difference between the motion blur index and the blur index threshold is greater than a preset index difference threshold;

[0026] If the environmental quality indicator meets any one or more of the above AC criteria, then the environmental quality indicator is determined to be low.

[0027] If none of the environmental quality indicators meet the above AC requirements, then the environmental quality indicators are determined to be high.

[0028] In one possible implementation, when the relocation failure type is structural mismatch, the step of determining whether to continue relocation based on the relocation failure type and the number of relocation attempts, and the parameters during relocation, includes:

[0029] End the relocation process and output a prompt for manual intervention;

[0030] or,

[0031] When the number of relocations is less than a preset threshold, a map update request is output. If an updated map is received within a preset time period, the relocation step based on the current multi-source sensor data is re-executed according to the updated map, and the number of relocations is updated. If an updated map is not received within the preset time period or the number of relocations is equal to the threshold, the relocation process ends, and a manual intervention prompt is output.

[0032] In one possible implementation, when the relocation failure type is temporary interference, determining whether to continue relocation based on the relocation failure type and the number of relocations, and the parameters during relocation, includes:

[0033] If the number of relocations is less than the preset threshold, the parameters of the particle filter algorithm are adjusted, and the relocation step based on the current multi-source sensor data is re-executed according to the adjusted parameters, and the number of relocations is updated.

[0034] If the number of relocations equals the threshold number, the relocation process ends and a manual intervention prompt is output.

[0035] Secondly, embodiments of this application provide a relocation system, including:

[0036] The detection module is used to reposition the mobile robot based on the current multi-source sensor data after detecting that the robot has failed to locate.

[0037] The processing module is used to determine the relocation failure type based on the multi-source sensor data if relocation fails; and to determine whether to continue relocation and the parameters for relocation based on the relocation failure type and the number of relocation attempts.

[0038] Thirdly, embodiments of this application provide another relocation system, including:

[0039] The processor, and the memory that is in communication with the processor;

[0040] Memory is used to store instructions that the computer executes;

[0041] The processor is configured to execute computer execution instructions stored in memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0042] Fourthly, embodiments of this application provide a mobile robot, including: a sensor, and a relocation system as described in the third aspect, wherein the sensor is connected to the relocation system;

[0043] The sensors include one or more of the following: lidar, camera, inertial measurement unit (IMU), and wheel speed encoder.

[0044] Fifthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect described above.

[0045] In a sixth aspect, embodiments of this application provide a computer program product, including a computer program, which, when executed by a processor, is used to implement the first aspect and / or various possible implementations of the first aspect as described above.

[0046] This application provides an adaptive relocation method, system, robot, and medium for a mobile robot. After detecting a localization failure, the system first performs relocation based on multi-source sensor data collected by the robot's various sensors, thereby improving the success rate of relocation. If the first round of relocation fails, the system can intelligently identify the failure type based on the multi-source sensor data and adjust the relocation process and parameters differently according to different failure types and the number of relocation attempts, achieving "retry on demand and intelligent termination." For types destined to fail, relocation can be terminated early to avoid invalid retries, thus ensuring real-time performance and improving system response efficiency and resource utilization. For types temporarily affected by interference, relocation parameters can be adjusted to further improve the success rate, and limiting the number of relocation attempts further ensures real-time performance, ensuring rapid system response in complex scenarios and avoiding task blocking. Attached Figure Description

[0047] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0048] Figure 1 This is a system architecture diagram of an embodiment of this application;

[0049] Figure 2 This is a flowchart of an adaptive relocalization method for a mobile robot according to an embodiment of this application;

[0050] Figure 3 This is a schematic diagram of the structure of a relocation system according to an embodiment of this application;

[0051] Figure 4 This is a schematic diagram of the relocation system according to another embodiment of this application.

[0052] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0053] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0054] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0055] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0056] It should also be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with relevant laws, regulations and standards, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0057] The adaptive relocation method, system, robot, and medium for mobile robots of this application can be used in the field of relocation, or in any field other than the field of relocation, such as the field of robotics. The application fields of the adaptive relocation method, system, robot, and medium for mobile robots of this application are not limited.

[0058] The adaptive relocation method, system, robot, and medium for mobile robots of this application can be applied to scenarios where mobile robots such as intelligent forklifts and food delivery robots operate autonomously, such as intelligent forklifts operating autonomously in intelligent warehousing systems. As long as the mobile robot is equipped with a relocation system, the adaptive relocation method, system, robot, and medium for mobile robots of this application can be applied.

[0059] Intelligent forklifts and other mobile robots commonly employ technologies such as Simultaneous Localization and Mapping (SLAM) to achieve autonomous operation. However, in complex and dynamic environments (such as cargo obstruction, changes in lighting, and ground reflections), positioning drift or loss often occurs. In such cases, the system needs to trigger a relocalization process to restore pose estimation.

[0060] In related technologies, when a mobile device detects a positioning anomaly, it typically initiates an unlimited number of relocation attempts or a fixed-duration relocation attempt, during which the vehicle remains stationary and waits. If the environmental characteristics remain unfavorable (such as an empty corridor or a repetitive structure area), it can easily lead to invalid retries, causing relocation to fail for an extended period, resulting in task blocking, scheduling delays, and even subsequent path conflicts.

[0061] Based on the above-mentioned technical problems, the inventive concept of this application is to provide an adaptive relocation scheme for mobile robots that can avoid invalid retries to ensure real-time performance and improve the relocation success rate.

[0062] This application provides an adaptive relocation method, system, robot, and medium for a mobile robot. After detecting a localization failure, the system first performs relocation based on multi-source sensor data collected by the robot's various sensors, thereby improving the success rate of relocation. If the first round of relocation fails, the system can intelligently identify the failure type based on the multi-source sensor data and adjust the relocation process and parameters differently according to different failure types and the number of relocation attempts, achieving "retry on demand and intelligent termination." For types destined to fail, relocation can be terminated early to avoid invalid retries, thus ensuring real-time performance and improving system response efficiency and resource utilization. For types temporarily affected by interference, relocation parameters can be adjusted to further improve the success rate, and limiting the number of relocation attempts further ensures real-time performance, ensuring rapid system response in complex scenarios and avoiding task blocking.

[0063] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0064] Figure 1 This is a system architecture diagram of an embodiment of this application, such as... Figure 1 As shown, the mobile robot may include a LiDAR, camera, IMU, and wheel speed encoder. The LiDAR, camera, IMU, and wheel speed encoder are all connected to the relocation system, sending the collected data to the relocation system. The relocation system is also connected to the positioning system, continuously monitoring the confidence level output by the positioning system. After detecting a positioning failure, it performs relocation based on the current multi-source sensor data. If relocation fails, it determines the type of relocation failure based on the multi-source sensor data. Based on the relocation failure type and the number of relocation attempts, it determines whether to continue relocation and the parameters to be used during relocation.

[0065] Figure 2 This is a flowchart of an adaptive relocalization method for a mobile robot according to an embodiment of this application. This embodiment describes the adaptive relocalization method for the mobile robot using the relocalization system as the executing entity. Figure 2 As shown, the adaptive relocalization method for this mobile robot may include the following steps:

[0066] S201: After detecting a failure in the mobile robot's localization, relocalize it based on the current multi-source sensor data.

[0067] In this embodiment, the mobile robot can be a smart forklift, a delivery robot, a food delivery robot, or other machinery capable of autonomous movement.

[0068] In this embodiment, the relocalization system can continuously monitor the confidence level output by the localization system during the operation of the mobile robot, which is the proportion of effective particles in the particle set output by Adaptive Monte Carlo Localization (AMCL). When the confidence level is less than a preset localization confidence threshold, localization is considered to have failed, and the relocalization process is triggered.

[0069] In this embodiment, the mobile robot can be equipped with sensors such as lidar, camera, inertial measurement unit (IMU), and wheel speed encoder. These sensors can be connected to a repositioning system, which can acquire data collected by the sensors to obtain multi-source sensor data.

[0070] S202: Determine whether the relocation was successful.

[0071] In this embodiment, the success of relocation can be determined based on whether the relocation confidence level is greater than a preset relocation confidence threshold. If the relocation confidence level is less than the preset relocation confidence threshold, the relocation is determined to have failed; if the relocation confidence level is greater than or equal to the relocation confidence threshold, the relocation is determined to have succeeded.

[0072] In this embodiment, the preset relocation confidence threshold can be flexibly set by those skilled in the art according to actual conditions; for example, it can be 0.4, without any limitation. Preferably, in order to improve the accuracy and reliability of relocation, the relocation confidence threshold can be greater than the localization confidence threshold.

[0073] S203: If repositioning fails, determine the type of repositioning failure based on multi-source sensor data.

[0074] In this embodiment, multi-source sensor data may include point cloud data collected by lidar, image data collected by camera, IMU data, wheel speed encoder, etc., without any limitations.

[0075] In this embodiment, relocation failure types may include temporary interference and structural mismatch.

[0076] In this embodiment, temporary interference can be caused by dynamic changes in the environment, resulting in temporary relocation failure. Reacquiring sensor data again will likely lead to successful relocation. Structural mismatch can be caused by motion malfunctions of the mobile robot itself or map changes, in which case relocation is unlikely to succeed even if sensor data is reacquired again.

[0077] S204: Based on the relocation failure type and the number of relocation attempts, determine whether to continue relocation, and the parameters to be used during relocation.

[0078] In this embodiment, if the relocation failure type is temporary interference, to avoid invalid retries, the parameters during relocation can be adjusted and relocation can be performed again to improve the success rate of relocation. If the relocation failure type is structural mismatch, to avoid invalid retries and ensure real-time performance, the relocation mileage can be terminated and manual intervention requested.

[0079] In this embodiment, if the relocation failure type is temporary interference, when relocating again after adjusting the parameters, it is not an unlimited number of relocations, but a maximum number of relocations is set. If the maximum number of relocations is reached, the relocation process ends and manual intervention is requested to avoid invalid retries, thereby further improving the system response efficiency and resource utilization.

[0080] S205: If relocalization is successful, update the global pose of the mobile robot and end the relocalization process.

[0081] In this embodiment, if the relocation is successful, the global pose of the mobile robot can be updated, enabling the positioning system to continuously locate and track the robot based on the updated global pose, thus driving the mobile robot to continue to operate autonomously.

[0082] In this embodiment, after a mobile robot localization failure is detected, relocalization is first performed based on multi-source sensor data collected by the various sensors of the mobile robot, thereby improving the success rate of relocalization. If the first round of relocalization fails, the failure type can be intelligently identified based on the multi-source sensor data, and the relocalization process and parameters can be adjusted differently according to different failure types and the number of relocalization attempts, achieving "retry on demand and intelligent termination". For types destined to fail, relocalization can be terminated in advance to avoid invalid retries, thus ensuring real-time performance and improving system response efficiency and resource utilization. For types temporarily affected by interference, relocalization parameters can be adjusted to further improve the success rate of relocalization, and limiting the number of relocalization attempts further ensures real-time performance, ensuring that the system responds quickly in complex scenarios and avoiding task blocking.

[0083] In one possible implementation, the relocation based on the current multi-source sensor data in step S201 above may include:

[0084] S11: Based on the data collected by the mobile robot's sensors, determine the multi-source sensor data, including one or more of the following sensors: LiDAR, camera, inertial measurement unit (IMU), and wheel speed encoder.

[0085] S12: Relocation is performed based on multi-source sensor data and particle filter algorithm to obtain relocation confidence and record the number of relocations.

[0086] In this embodiment, if the relocation confidence is less than the preset relocation confidence threshold, the relocation is determined to have failed; if the relocation confidence is greater than or equal to the relocation confidence threshold, the relocation is determined to have succeeded.

[0087] In this embodiment, after detecting a mobile robot positioning failure, the repositioning system can initialize the repositioning count to 0. After performing a repositioning based on multi-source sensor data and a particle filter algorithm, the repositioning count is updated to 1, and so on.

[0088] For example, when relocalizing based on multi-source sensor data and particle filter algorithm, a standard particle filter can be used with 500 particles and an initial distribution centered on the last known pose with a radius of 1.5m.

[0089] In this embodiment, the relocation system can acquire data collected by sensors to obtain multi-source sensor data, and perform relocation based on the multi-source sensor data and particle filtering algorithm, thereby improving the success rate of relocation.

[0090] In one possible implementation, determining the relocation failure type based on multi-source sensor data in step S203 above may include:

[0091] S21: Determine environmental quality indicators based on multi-source sensor data. Environmental quality indicators include at least one of laser point cloud density, number of visual ORB feature points, and motion blur index.

[0092] S22: Determine motion parameter indicators based on multi-source sensor data, including at least one of IMU data quality and wheel speed encoder data quality.

[0093] S23: Determine the relocation failure type based on environmental quality indicators and motion parameter indicators.

[0094] In this embodiment, the laser point cloud density can be determined by analyzing the laser point cloud data collected by the lidar.

[0095] In this embodiment, the number of visual ORB feature points and the motion blur index can be determined by analyzing the image data acquired by the camera.

[0096] In this embodiment, IMU data quality can include normal IMU data and abnormal IMU data, and wheel speed encoder data quality can include normal wheel speed encoder data and abnormal wheel speed encoder data.

[0097] In this embodiment, if repositioning fails, environmental quality indicators and motion parameter indicators can be determined based on multi-source sensor data. The cause of repositioning failure can be determined based on the environmental quality indicators and motion parameter indicators, thereby accurately determining the type of repositioning failure.

[0098] In one possible implementation, step S23 above, which determines the relocation failure type based on environmental quality indicators and motion parameter indicators, may include:

[0099] S31: Determine whether the motion parameter indicators are of normal data quality.

[0100] S32: If the motion parameter index shows abnormal data, then the relocation failure type is determined to be structural mismatch.

[0101] S33: If the motion parameter indicators are normal, then determine whether the environmental quality indicators are low.

[0102] S34: When the environmental quality index is high, the relocation failure type is determined to be temporary interference.

[0103] S35: When the environmental quality index is low, determine the new environmental quality index based on the new multi-source sensor data, and determine whether the new environmental quality index is low.

[0104] S36: If the new environmental quality index is low, then the relocation failure type is determined to be structural mismatch.

[0105] S37: If the new environmental quality index is high, then the relocation failure type is determined to be a temporary disturbance.

[0106] In this embodiment, temporary interference can be caused by dynamic changes in the environment, resulting in temporary relocation failure. Reacquiring sensor data again will likely lead to successful relocation. Structural mismatch can be caused by motion malfunctions of the mobile robot itself or map changes, in which case relocation is unlikely to succeed even if sensor data is reacquired again.

[0107] In this embodiment, determining whether the motion parameter indicators (IMU data and / or wheel speed encoder data) are of normal data quality can be done by referring to relevant existing technologies, which will not be elaborated here.

[0108] In this embodiment, if the IMU data and / or wheel speed encoder data are abnormal, it indicates that the mobile robot's own movement is malfunctioning and is unrelated to dynamic changes in the environment. Even if the sensor data is reacquired, repositioning will basically not be successful. Therefore, the repositioning failure type can be determined to be structural mismatch.

[0109] In this embodiment, if the motion parameters are normal and the environmental quality is high, it indicates that the relocation failure may be caused by accidental factors and the success rate of relocation is high. Therefore, the relocation failure type can be determined to be temporary interference.

[0110] In this embodiment, if the motion parameter index is normal and the environmental quality index is low, it indicates that the relocation failure may be caused by accidental dynamic changes in the environment or by a mismatch between the map and the environment. A new environmental quality index can be determined based on the new multi-source sensor data. If the new environmental quality index is high, it indicates that the relocation failure was caused by accidental dynamic changes in the environment, and the relocation failure type can be determined as temporary interference. If the new environmental quality index is low, it indicates that the relocation failure was caused by a mismatch between the map and the environment, and the relocation failure type can be determined as structural mismatch.

[0111] In this embodiment, the new multi-source sensor data can be collected by the mobile robot using the sensors in place, or it can be collected by the mobile robot using the sensors after moving a certain distance.

[0112] In this implementation, the motion parameters can be used to determine whether the mobile robot's motion is malfunctioning. If the motion parameters are normal, the relocation failure is due to environmental factors. By analyzing two consecutive environmental quality indices, it can be determined whether the failure is caused by accidental environmental changes or by a mismatch between the map and the environment, thus accurately identifying the type of relocation failure.

[0113] In one possible implementation, determining whether an environmental quality indicator is low includes:

[0114] S41: Determine whether the environmental quality indicators meet the following AC:

[0115] A: The laser point cloud density is less than the point cloud density threshold, and the difference between the laser point cloud density and the point cloud density threshold is greater than the preset density difference threshold.

[0116] B: The number of visual ORB feature points is less than the feature point number threshold, and the difference between the number of visual ORB feature points and the feature point number threshold is greater than the preset number difference threshold.

[0117] C: The motion blur index is less than the blur index threshold, and the difference between the motion blur index and the blur index threshold is greater than the preset index difference threshold.

[0118] S42: If an environmental quality indicator meets any one or more of the above AC criteria, then the environmental quality indicator is determined to be low.

[0119] S43: If none of the environmental quality indicators meet the above AC requirements, then the environmental quality indicators are determined to be high.

[0120] In this embodiment, the point cloud density threshold, feature point quantity threshold, and fuzziness index threshold can be flexibly set by those skilled in the art according to actual conditions, and no restrictions are imposed here.

[0121] In this embodiment, the density difference threshold, quantity difference threshold, and exponential difference threshold can be flexibly set by those skilled in the art according to actual conditions, and no restrictions are imposed here.

[0122] In this embodiment, if the laser point cloud density is less than the point cloud density threshold and the difference between the laser point cloud density and the point cloud density threshold is greater than the preset density difference threshold, it indicates that the environment causes abnormal data acquisition by the lidar. Regardless of whether other indicators are normal, this will result in a low environmental quality index.

[0123] In this embodiment, if the number of visual ORB feature points is less than the feature point number threshold, and the difference between the number of visual ORB feature points and the feature point number threshold is greater than the preset difference threshold, it indicates that the environment causes abnormal data acquisition by the camera. Regardless of whether other indicators are normal, this will result in a low environmental quality index.

[0124] In this embodiment, if the motion blur index is less than the blur index threshold and the difference between the motion blur index and the blur index threshold is greater than the preset index difference threshold, it indicates that the environment causes abnormal data acquisition by the camera. Regardless of whether other indicators are normal, this will result in a low environmental quality index.

[0125] In this embodiment, the environmental quality index can be determined to be high only if the laser point cloud density, the number of visual ORB feature points, and the motion blur index are all greater than the corresponding thresholds, or are not significantly different from the corresponding thresholds. If any one of the three is less than the corresponding threshold and is significantly different from the corresponding threshold, the environmental quality index is low.

[0126] In one possible implementation, when the relocation failure type is structural mismatch, step S204 above determines whether to continue relocation based on the relocation failure type and the number of relocation attempts, and the parameters during relocation may include:

[0127] The relocation process ends, and a prompt for manual intervention is displayed.

[0128] In this embodiment, the manual intervention prompt information can be one or more of the following: text information, image information, sound information, and light information.

[0129] In this embodiment, when the relocation failure type is structural mismatch, it may be caused by a malfunction in the movement of the mobile robot itself (such as abnormal IMU data or wheel speed encoder data). Even if the sensor data is reacquired, relocation will basically not be successful. In order to avoid invalid retries and ensure real-time performance, the relocation process can be terminated directly and manual intervention can be requested, which improves the system response efficiency and resource utilization.

[0130] In one possible implementation, when the relocation failure type is structural mismatch, step S204 above determines whether to continue relocation based on the relocation failure type and the number of relocation attempts, and the parameters during relocation may include:

[0131] S51: When the number of relocations is less than the preset threshold, output a map update request.

[0132] S52: If an updated map is received within a preset time period, the relocation step based on the current multi-source sensor data is re-executed according to the updated map, and the relocation count is updated.

[0133] S53: If an updated map is not received within the preset time period or the number of relocations equals the threshold, the relocation process ends and a manual intervention prompt is output.

[0134] In this embodiment, the number of times threshold can be flexibly set by those skilled in the art according to actual needs. For example, it can be 3 times, and no restrictions are imposed here.

[0135] In this embodiment, the preset duration can be flexibly set by those skilled in the art according to actual needs; for example, it can be 200ms, and no restrictions are imposed here.

[0136] In this implementation, when the relocation failure type is structural mismatch, it may be caused by a map incompatibility with the environment. A map update request can be output. If an updated map is received within a preset time period, relocation can be performed again based on the updated map to improve the success rate of relocation. If an updated map is not received within the preset time period, the relocation process can be terminated directly and manual intervention requested to avoid invalid retries and ensure real-time performance. Furthermore, the number of relocations is guaranteed not to exceed a threshold during the relocation process, further improving system response efficiency and resource utilization.

[0137] In one possible implementation, when the relocation failure type is temporary interference, step S203 above determines whether to continue relocation based on the relocation failure type and the number of relocation attempts, and the parameters during relocation may include:

[0138] S61: If the number of repositioning attempts is less than the preset threshold, adjust the parameters of the particle filter algorithm, re-execute the repositioning step based on the current multi-source sensor data according to the adjusted parameters, and update the number of repositioning attempts.

[0139] S62: If the number of relocations equals the threshold, the relocation process ends and a manual intervention prompt is output.

[0140] In this embodiment, adjusting the parameters of the particle filter algorithm can increase the particle radius and increase the weight of IMU data and / or wheel speed encoder data.

[0141] In this embodiment, the parameters of the particle filter algorithm can also be adjusted according to the number of relocations. For example, the particle radius in the third relocation is greater than the particle radius in the second relocation, or the weight of the IMU data and / or wheel speed encoder data in the third relocation is greater than the weight of the IMU data and / or wheel speed encoder data in the second relocation.

[0142] In this implementation, when the relocation failure type is temporary interference, it may be caused by accidental dynamic changes in the environment. The parameters of the particle filter algorithm can be adjusted to improve environmental robustness and further improve the success rate of relocation. In addition, the number of relocations is ensured not to exceed a threshold during the relocation process to avoid invalid retries and ensure real-time performance.

[0143] The adaptive relocation method for mobile robots of this application is illustrated below with a specific embodiment.

[0144] In one specific embodiment, in a certain warehousing and logistics system, an intelligent forklift is performing autonomous handling. During this process, the adaptive relocation process of the intelligent forklift is as follows:

[0145] The first step is that the relocation system continuously monitors the proportion of effective particles in the particle set output by AMCL (i.e., the positioning confidence) during the operation of the intelligent forklift. At time A, if the positioning confidence is detected to be 0.2 < 0.3, the relocation process is triggered.

[0146] The second step involves the repositioning system acquiring multi-source sensor data using LiDAR, camera, IMU, and wheel speed encoder. Repositioning is then performed based on the multi-source sensor data and a particle filter algorithm (standard particle filter is used in this process, with 500 particles and an initial distribution centered on the last known pose with a radius of 1.5m). The repositioning confidence score is 0.25, and the number of repositionings is recorded as 1.

[0147] The third step involves the relocation system determining that if the relocation confidence level is 0.25 < 0.4, then the relocation is considered a failure.

[0148] The fourth step is that the repositioning system determines that the IMU data and wheel speed encoder data are normal based on the multi-source sensor data, and then the motion parameter indicators are considered normal.

[0149] In the fifth step, the relocation system determines the laser point cloud density to be 42 points / m² (threshold 50), the ORB feature point count to be 80 (threshold 100), and the motion blur index to be 0.6 (threshold 0.5) based on multi-source sensor data, and judges the overall environmental quality index to be low.

[0150] The sixth step is for the relocation system to acquire new multi-source sensor data, determine new environmental quality indicators based on the new multi-source sensor data, and determine that the new environmental quality indicators are high. If the new environmental quality indicators are high, then the relocation failure type is determined to be temporary interference.

[0151] Step 7: The relocation system expands the particle radius and increases the weight of the IMU data and / or wheel speed encoder data, repeats step 2 above for relocation, and updates the number of relocations to 2.

[0152] Step 8: If the relocation confidence level is determined to be 0.7 > 0.4, the relocation is considered successful. The global pose of the mobile robot is then updated, and the relocation process ends.

[0153] Figure 3 This is a schematic diagram of the structure of a relocation system according to an embodiment of this application, as shown below. Figure 3 As shown, the relocation system includes: a detection module 31, used to perform relocation based on current multi-source sensor data after detecting that the mobile robot has failed to locate; and a processing module 32, used to determine the relocation failure type based on the multi-source sensor data if relocation fails; and to determine whether to continue relocation and the parameters during relocation based on the relocation failure type and the number of relocation attempts.

[0154] The relocation system provided in this application embodiment can execute the technical solution shown in the above method embodiment. Its implementation principle and beneficial effects are similar, and will not be described again here.

[0155] Figure 4 This is a schematic diagram of the relocation system according to another embodiment of this application, as shown below. Figure 4 As shown, the relocation system includes: a processor 401 and a memory 402 communicatively connected to the processor 401; the memory 402 stores computer execution instructions; the processor 401 executes the computer execution instructions stored in the memory 402 to implement the steps of the adaptive relocation method for the mobile robot in the above method embodiments.

[0156] In the aforementioned relocation system, the memory 402 and the processor 401 are electrically connected directly or indirectly to enable data transmission or interaction. For example, these components can be electrically connected to each other via one or more communication buses or signal lines, such as a bus connection. The memory 402 stores computer-executable instructions that implement data access control methods, including at least one software functional module that can be stored in the memory 402 in the form of software or firmware. The processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 402.

[0157] The memory 402 may be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc. The memory 402 stores programs, which are executed by the processor 401 upon receiving execution instructions. Furthermore, the software programs and modules within the memory 402 may also include an operating system, which may include various software components and / or drivers for managing system tasks (e.g., memory management, storage device control, power management, etc.) and can communicate with various hardware or software components to provide an operating environment for other software components.

[0158] Processor 401 can be an integrated circuit chip with signal processing capabilities. The aforementioned processor 401 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor.

[0159] One embodiment of this application also provides a mobile robot, such as Figure 1 As shown, the mobile robot may include: sensors, and such as Figure 4 The repositioning system shown is connected to the sensor.

[0160] The sensors include one or more of the following: lidar, camera, inertial measurement unit (IMU), and wheel speed encoder.

[0161] An embodiment of this application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the steps of the various method embodiments of this application.

[0162] An embodiment of this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the various method embodiments of this application.

[0163] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0164] It should be further noted that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0165] It should be understood that the above-described device embodiments are merely illustrative, and the device of this application can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units, modules, or components may be combined, or integrated into another system, or some features may be ignored or not executed.

[0166] Furthermore, unless otherwise specified, the functional units / modules in the various embodiments of this application can be integrated into one unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated together. The integrated units / modules described above can be implemented in hardware or as software program modules.

[0167] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0168] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the appended claims.

[0169] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. An adaptive relocalization method for a mobile robot, characterized in that, include: After detecting that the mobile robot has failed to locate, it performs relocation based on the current multi-source sensor data; If relocation fails, the type of relocation failure is determined based on the multi-source sensor data. Based on the relocation failure type and the number of relocation attempts, determine whether to continue relocation, and the parameters to be used during relocation.

2. The adaptive relocalization method for a mobile robot according to claim 1, characterized in that, The relocation based on current multi-source sensor data includes: Based on the data collected by the sensors of the mobile robot, multi-source sensor data is determined, wherein the sensors include one or more of LiDAR, camera, inertial measurement unit (IMU), and wheel speed encoder; Relocation is performed based on the multi-source sensor data and particle filter algorithm to obtain the relocation confidence and record the number of relocations. If the relocation confidence is less than a preset confidence threshold, then the relocation is determined to have failed. If the relocation confidence is greater than or equal to the confidence threshold, then the relocation is considered successful.

3. The adaptive relocalization method for a mobile robot according to claim 2, characterized in that, The step of determining the relocation failure type based on the multi-source sensor data includes: The environmental quality indicators are determined based on the multi-source sensor data, and the environmental quality indicators include at least one of laser point cloud density, number of visual ORB feature points, and motion blur index. Motion parameter indicators are determined based on the multi-source sensor data, and the motion parameter indicators include at least one of IMU data quality and wheel speed encoder data quality; The relocation failure type is determined based on the environmental quality indicators and the motion parameter indicators.

4. The adaptive relocalization method for a mobile robot according to claim 3, characterized in that, The step of determining the relocation failure type based on the environmental quality indicators and the motion parameter indicators includes: Determine whether the motion parameter indicators are of normal data quality; If the motion parameter index shows abnormal data, the relocation failure type is determined to be structural mismatch; If the motion parameter index is normal, then determine whether the environmental quality index is low; when the environmental quality index is high, determine the relocation failure type as temporary interference; when the environmental quality index is low, determine a new environmental quality index based on new multi-source sensor data, and determine whether the new environmental quality index is low. If the new environmental quality index is low, determine the relocation failure type as structural mismatch; if the new environmental quality index is high, determine the relocation failure type as temporary interference.

5. The adaptive relocalization method for a mobile robot according to claim 4, characterized in that, Determining whether the environmental quality indicator is low includes: Determine whether the environmental quality indicators meet the following AC: A: The laser point cloud density is less than the point cloud density threshold, and the difference between the laser point cloud density and the point cloud density threshold is greater than a preset density difference threshold. B: The number of visual ORB feature points is less than the feature point number threshold, and the difference between the number of visual ORB feature points and the feature point number threshold is greater than the preset number difference threshold. C: The motion blur index is less than the blur index threshold, and the difference between the motion blur index and the blur index threshold is greater than a preset index difference threshold; If the environmental quality indicator meets any one or more of the above AC criteria, then the environmental quality indicator is determined to be low. If none of the environmental quality indicators meet the above AC requirements, then the environmental quality indicators are determined to be high.

6. The adaptive relocalization method for a mobile robot according to claim 4, characterized in that, When the relocation failure type is structural mismatch, the determination of whether to continue relocation based on the relocation failure type and the number of relocation attempts, and the parameters during relocation, includes: End the relocation process and output a prompt for manual intervention; or, When the number of relocations is less than a preset threshold, a map update request is output. If an updated map is received within a preset time period, the relocation step based on the current multi-source sensor data is re-executed according to the updated map, and the number of relocations is updated. If an updated map is not received within the preset time period or the number of relocations is equal to the threshold, the relocation process ends, and a manual intervention prompt is output.

7. The adaptive relocalization method for a mobile robot according to claim 4, characterized in that, When the relocation failure type is temporary interference, the determination of whether to continue relocation based on the relocation failure type and the number of relocations, and the parameters during relocation, includes: If the number of relocations is less than the preset threshold, the parameters of the particle filter algorithm are adjusted, and the relocation step based on the current multi-source sensor data is re-executed according to the adjusted parameters, and the number of relocations is updated. If the number of relocations equals the threshold number, the relocation process ends and a manual intervention prompt is output.

8. A repositioning system, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory is used to store computer-executed instructions; The processor is configured to execute computer execution instructions stored in the memory, causing the processor to perform the adaptive relocation method for the mobile robot as described in any one of claims 1-7.

9. A mobile robot, characterized in that, include: The sensor, and the repositioning system as described in claim 8, wherein the sensor is connected to the repositioning system; The sensors include one or more of the following: lidar, camera, inertial measurement unit (IMU), and wheel speed encoder.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the adaptive relocation method of the mobile robot according to any one of claims 1-7.

Images