Mobile robot navigation positioning method based on multi-sensor data and related assembly

Abstract

The invention relates to a mobile robot navigation and positioning method based on multi-sensor data and related components, which are applied to the technical field of robot navigation and positioning, and the method comprises the following steps: acquiring environmental data and a mode conversion instruction; acquiring sensor monitoring data based on the environment data; determining a motion mode based on the sensor monitoring data, the mode conversion instruction and a preset rule; determining a positioning mode based on the environment data and the motion mode; and determining robot positioning based on the environment data, the positioning mode and the sensor monitoring data. The method has the effect of improving the navigation positioning accuracy of the mobile robot.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of robot navigation positioning, and in particular to a mobile robot navigation positioning method based on multi-sensor data and related components. BACKGROUND

[0002] With the continuous development of technology, mobile robots have been widely applied in various fields such as industry, logistics, and service. For example, in industrial production, mobile robots can undertake tasks such as material handling and component assembly, greatly improving production efficiency and automation level; in the logistics industry, mobile robots can realize fast sorting and transportation of goods, optimizing warehouse management processes; in the service field, such as hotels, restaurants and other places, mobile robots can provide meal delivery, guidance and other services, bringing convenience to people's lives. The various applications of mobile robots cannot be separated from navigation positioning, and the accuracy of navigation positioning is related to the reliability of mobile robot applications.

[0003] In the field of mobile robot navigation positioning, currently a single type of sensor data is usually used for positioning, for example, some robots use laser radar sensors to construct an environment map by emitting laser beams and measuring the time of reflected light, thereby determining their own position. Some robots use visual sensors to capture images of the surrounding environment using cameras, and use image recognition and processing techniques for positioning. In addition, there are also methods that use wheel speed meters to record wheel rotation information to calculate the position of the robot.

[0004] However, these positioning methods based on single sensor data have obvious defects. Single sensor data is greatly affected by the environment, for example, in an environment with a lot of dust or smoke, the reflection of laser beams will be disturbed, resulting in inaccurate positioning; in poor lighting conditions, the image recognition effect of visual sensors will be poor, thereby affecting the positioning accuracy; when the ground is uneven or the wheels slip, the calculated position information will have a large error. And the information provided by single sensor data is limited, it is difficult to accurately reflect the environment and the state of the robot, and it cannot meet the needs of mobile robot navigation positioning in complex and variable environments. SUMMARY

[0005] In order to improve the accuracy of mobile robot navigation positioning, the present application provides a mobile robot navigation positioning method based on multi-sensor data and related components.

[0006] In a first aspect, the present application provides a mobile robot navigation positioning method based on multi-sensor data, which adopts the following technical solution: A mobile robot navigation positioning method based on multi-sensor data, comprising: obtaining environment data and modal conversion instructions; acquire sensor monitoring data based on the environment data; determine a motion mode based on the sensor monitoring data, the mode conversion instruction and a preset rule; determine a positioning mode based on the environment data and the motion mode; determine robot positioning based on the environment data, the positioning mode and the sensor monitoring data.

[0007] By adopting the above technical solutions, the sensor monitoring data is adapted to the environment according to the current environment data, the reliability of the sensor monitoring data is improved, the motion mode of the mobile robot is determined by analyzing the sensor monitoring data and the mode conversion instruction according to the preset rule, the positioning mode is determined in combination with the environment data and the motion mode, the rationality of the positioning mode is improved, the robot positioning is determined by comprehensively considering the environment data, the positioning mode and the sensor monitoring data, and the accuracy of the navigation and positioning of the mobile robot is improved.

[0008] Optionally, the acquiring of the sensor monitoring data based on the environment data comprises: acquiring historical monitoring information, the historical monitoring information comprising historical environment data, historical monitoring parameters of sensors and historical monitoring reliability; dividing the historical monitoring information based on the historical environment data and sensor types to obtain a plurality of historical information combinations, each historical information combination corresponding to one historical environment data and one sensor type; analyzing each historical information combination to obtain target monitoring parameters corresponding to each sensor type under each environment data; acquiring the sensor monitoring data based on the target monitoring parameters.

[0009] By adopting the above technical solutions, the historical monitoring information is acquired and divided according to the historical environment data and the sensor types, the target monitoring parameters corresponding to each sensor type under each environment data are obtained, and then the sensor monitoring data is acquired based on the target monitoring parameters, so that the acquired sensor monitoring data is more suitable for the actual environment, the accuracy and reliability of the data are improved, and more accurate data basis is provided for subsequent determination of the motion mode, the positioning mode and the robot positioning.

[0010] Optionally, the determination of the motion mode based on the sensor monitoring data, the mode conversion instruction and the preset rule comprises: determining monitoring data thresholds of various modes based on the preset rule; if the sensor monitoring data all meet the monitoring data thresholds, determining the motion mode based on the monitoring data thresholds; If the sensor monitoring data does not meet the monitoring data threshold, the motion mode is determined based on the modal conversion instruction.

[0011] By adopting the above technical solutions, the monitoring data thresholds of various modes are determined according to the preset rules, when the sensor monitoring data all meet the monitoring data thresholds, the motion mode is determined according to the mode corresponding to the monitoring data threshold, and when there is a case of not meeting the monitoring data threshold, the motion mode is determined according to the modal conversion instruction, that is, the motion mode can be flexibly determined by combining the sensor monitoring data and the modal conversion instruction, which provides an accurate basis for subsequent determination of the positioning mode and the robot positioning, so that the mobile robot navigation positioning is more reasonable and accurate.

[0012] Optionally, the positioning mode is determined based on the environment data and the motion mode, including: a positioning dimension is determined based on the motion mode; an environment interference value corresponding to each positioning dimension is determined based on the environment data and a preset interference weight; a dimension weight of each positioning dimension is determined based on the environment interference value; the positioning mode is determined based on the dimension weight and the positioning dimension.

[0013] By adopting the above technical solutions, the determination of the positioning mode comprehensively considers the motion mode and the environment interference, improves the accuracy and adaptability of the positioning mode, and further improves the precision and reliability of the robot positioning.

[0014] Optionally, the positioning dimension is determined based on the motion mode, including: if the motion mode is a rolling mode, the positioning dimension includes wheel speed meter data and laser radar point cloud data; if the motion mode is a rotor mode, the positioning dimension includes IMU data and GPS data; if the motion mode is a walking mode, the positioning dimension includes visual SLAM data and laser SLAM data; if the motion mode is a transition mode, the positioning dimension is determined based on the modal conversion instruction.

[0015] By adopting the above technical solutions, the wheel speed meter data and the laser radar point cloud data are used for positioning in the rolling mode, which can be suitable for the rolling motion scene; the IMU data and the GPS data are used for positioning in the rotor mode, which can meet the positioning requirements of the rotor flight motion; the visual SLAM data and the laser SLAM data are used for positioning in the walking mode, which can better perform the positioning in the walking motion; the positioning dimension is determined based on the mode conversion instruction in the transition mode, which can flexibly cope with the positioning situation in the motion mode conversion, and the accuracy and adaptability of the mobile robot navigation positioning are improved.

[0016] Optionally, the robot positioning is determined based on the environment data, the positioning mode and the sensor monitoring data, including: a preprocessing threshold is determined based on the environment data; the sensor monitoring data is preprocessed based on the preprocessing threshold and a preset denoising algorithm; the preprocessed sensor monitoring data is fused according to the positioning mode and a preset fusion algorithm to determine the robot positioning.

[0017] By adopting the above technical solutions, the preprocessing threshold is determined according to the environment data, which can make the preprocessing threshold more suitable for the actual environment. The sensor monitoring data is preprocessed using the preprocessing threshold and the preset denoising algorithm, which can effectively remove the noise interference in the data and improve the data quality. The preprocessed sensor monitoring data is fused according to the positioning mode and the preset fusion algorithm to determine the robot positioning, which can more accurately integrate the data in combination with the positioning mode, and improve the accuracy and reliability of the robot positioning.

[0018] Optionally, the method further includes: obtaining monitoring system resources; determining the task priority of each real-time task based on the positioning mode; determining a resource scheduling strategy based on the task priority and the monitoring system resources.

[0019] By adopting the above technical solutions, the task priority of each real-time task is determined according to the positioning mode, and the resource scheduling strategy is determined in combination with the task priority and the monitoring system resources. The resources can be reasonably allocated according to the system resources and the task importance, the system operation efficiency and the resource utilization rate are improved, and the high-priority task is successfully executed.

[0020] In a second aspect, the application provides a mobile robot navigation positioning device based on multi-sensor data, which adopts the following technical solutions: A mobile robot navigation positioning device based on multi-sensor data, comprising: a first data acquisition module for acquiring environment data and mode conversion instructions; a second data acquisition module, configured to acquire sensor monitoring data based on the environment data; a motion mode determination module, configured to determine a motion mode based on the sensor monitoring data, the mode conversion instruction and a preset rule; a positioning mode determination module, configured to determine a positioning mode based on the environment data and the motion mode; a robot positioning module, configured to determine robot positioning based on the environment data, the positioning mode and the sensor monitoring data.

[0021] By using the above technical solution, the sensor monitoring data is adapted to the environment according to the current environment data, the reliability of the sensor monitoring data is improved, the motion mode of the mobile robot is determined according to the preset rule by analyzing the sensor monitoring data and the mode conversion instruction, the positioning mode is determined in combination with the environment data and the motion mode, the rationality of the positioning mode is improved, the robot positioning is determined by comprehensively considering the environment data, the positioning mode and the sensor monitoring data, and the accuracy of the navigation and positioning of the mobile robot is improved.

[0022] In a third aspect, the present application provides an electronic device, which adopts the following technical solution: An electronic device includes a processor coupled with a memory; The memory stores a computer program capable of being loaded and executed by the processor to implement the method for navigation and positioning of a mobile robot based on multi-sensor data according to any one of the first aspect.

[0023] In a fourth aspect, the present application provides a computer readable storage medium, which adopts the following technical solution: A computer readable storage medium stores a computer program capable of being loaded and executed by the processor to implement the method for navigation and positioning of a mobile robot based on multi-sensor data according to any one of the first aspect. BRIEF DESCRIPTION OF DRAWINGS

[0024] Figure 1 is a flowchart of a method for navigation and positioning of a mobile robot based on multi-sensor data provided by an embodiment of the present application.

[0025] Figure 2 is a structural block diagram of a device for navigation and positioning of a mobile robot based on multi-sensor data provided by an embodiment of the present application.

[0026] Figure 3 is a structural block diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0027] The present application will be further described in detail below with reference to the accompanying drawings.

[0028] This application provides a mobile robot navigation and positioning method based on multi-sensor data. This method can be executed by an electronic device, which can be a server or a terminal device. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, tablet computer, desktop computer, etc., but is not limited to these.

[0029] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0030] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0031] like Figure 1 As shown, a mobile robot navigation and localization method based on multi-sensor data is described in the following main process (steps S101 to S105): Step S101: Obtain environmental data and mode conversion instructions.

[0032] Environmental data includes parameters such as light intensity, wind speed, dust concentration, smoke concentration, and ground friction coefficient. Various environmental monitoring devices, such as light sensors and ground roughness sensors, are installed on or within the mobile robot's movement range to acquire environmental data.

[0033] The robot's motion modes include rolling mode, rotor mode, and walking mode. Mode conversion commands can be issued by the operator through the control terminal or automatically generated according to a preset program. Examples of mode conversion commands include: switching from rolling mode to walking mode, and switching from rotor mode to walking mode.

[0034] Step S102: Obtain sensor monitoring data based on environmental data.

[0035] The mobile robot is installed with various sensors, including sensors for monitoring the robot's own form (e.g., joint encoders), sensors for monitoring the robot's motion state (e.g., inertial measurement units, torque sensors, etc.), and sensors for positioning (e.g., vision sensors, laser radar sensors, GPS positioning devices, barometers, wheel speed meters, etc.). These sensors need to adjust monitoring parameters (e.g., resolution, frame rate, etc.) in different environments to improve monitoring accuracy. The optimal monitoring parameters of the sensors are determined based on environmental data, so that the sensors acquire sensor monitoring data according to the optimal monitoring parameters.

[0036] Specifically, the sensor monitoring data is acquired based on environmental data, including: acquiring historical monitoring information, the historical monitoring information including historical environmental data, historical monitoring parameters of the sensors, and historical monitoring reliability; dividing the historical monitoring information based on the historical environmental data and the sensor types to obtain a plurality of historical information combinations, each historical information combination corresponding to a kind of historical environmental data and a kind of sensor type; analyzing each historical information combination to obtain target monitoring parameters corresponding to each sensor type under various environmental data; and acquiring the sensor monitoring data based on the target monitoring parameters.

[0037] In this embodiment, the historical monitoring information is acquired from a database; the historical monitoring information is divided according to the historical environmental data and the sensor types to obtain a plurality of historical information combinations, all historical monitoring information in a historical information combination corresponding to the same kind of historical environmental data and the same kind of sensor type; each historical information combination is analyzed by a data analysis tool (e.g., Python, EXCEL, etc.), for a historical information combination, the historical monitoring parameter with the highest monitoring reliability is determined as the target monitoring parameter of the sensor type and the environmental data corresponding to the historical information combination; the target monitoring parameters of various sensors are matched according to the current environmental data, and the sensors are parameter-adjusted according to the target monitoring parameters to acquire sensor monitoring data.

[0038] Step S103, determining the motion mode based on the sensor monitoring data, the modal conversion instruction, and the preset rule.

[0039] Specifically, the motion mode is determined based on the sensor monitoring data, the modal conversion instruction, and the preset rule, including: determining monitoring data thresholds of various modes based on the preset rule; if the sensor monitoring data all meet the monitoring data thresholds, determining the motion mode based on the monitoring data thresholds; and if there is sensor monitoring data that does not meet the monitoring data thresholds, determining the motion mode based on the modal conversion instruction.

[0040] In the embodiment, the preset rule includes a threshold range of each sensor monitoring data of the mobile robot in various motion modalities, i.e., monitoring data thresholds, the current sensor monitoring data of the mobile robot is compared with the monitoring data thresholds corresponding to each motion modality in turn, if all the sensor monitoring data simultaneously meets the monitoring data thresholds corresponding to one motion modality, the motion modality is determined as the current motion modality of the mobile robot; if all the sensor monitoring data cannot simultaneously meet the monitoring data thresholds corresponding to one motion modality, it indicates that the mobile robot is currently in a modal transition, and a transition process corresponding to a modal transition instruction is determined as the current motion modality of the mobile robot, for example: a transition modality from a rolling mode to a walking mode.

[0041] In step S104, the positioning manner is determined based on the environment data and the motion modality.

[0042] The reliabilities of various sensors for positioning are different under different environments and different motion modalities, and by analyzing the environment data and the motion modality, the positioning manner of the mobile robot is determined.

[0043] Specifically, the positioning manner is determined based on the environment data and the motion modality, including: determining a positioning dimension based on the motion modality; determining an environment interference value corresponding to each positioning dimension based on the environment data and a preset interference weight; determining a dimension weight of each positioning dimension based on the environment interference value; and determining the positioning manner based on the dimension weight and the positioning dimension.

[0044] In the embodiment, each motion modality is previously set with a corresponding positioning dimension (one positioning dimension corresponds to one sensor type): if the motion modality is a rolling mode, the positioning dimension includes wheel speed meter data and laser radar point cloud data; if the motion modality is a rotor mode, the positioning dimension includes IMU data and GPS data; if the motion modality is a walking mode, the positioning dimension includes visual SLAM data and laser SLAM data; if the motion modality is a transition modality, the positioning dimension includes the positioning dimensions of two motion modalities in the modal transition instruction, for example: if the modal transition instruction is to convert from a rolling mode to a walking mode, the positioning dimension includes wheel speed meter data, laser radar point cloud data, visual SLAM data, and laser SLAM data.

[0045] Since the environment can affect the accuracy of different sensor positioning, it is necessary to determine the current environmental data of the environment interference of different sensor positioning, the database stores the influence values of various environmental data on various sensor positioning, and the same environment has different influence on different sensor positioning monitoring, so the preset interference weights of different positioning dimensions (sensor types) are different, for example: for sensor type A, the preset interference weight of light intensity is 0.3, the preset interference weight of wind speed is 0.5, and the preset interference weight of smoke concentration is 0.2; for sensor type B, the preset interference weight of light intensity is 0.5, the preset interference weight of wind speed is 0.1, and the preset interference weight of smoke concentration is 0.4.

[0046] When determining the environmental interference value of the environment on a sensor positioning monitoring, the influence values of the current various environmental data on the sensor type are matched from the database, and the environmental interference value is the sum of the products of each influence value and the corresponding preset interference weight.

[0047] For a motion mode, the dimension weight of a positioning dimension = the environmental interference value of the positioning dimension / (the sum of the environmental interference values of all positioning dimensions of the motion mode); the positioning mode of a motion mode is determined according to the positioning dimensions corresponding to the motion mode and the dimension weights of each positioning dimension.

[0048] Step S105, determining the robot positioning based on the environmental data, the positioning mode and the sensor monitoring data.

[0049] Specifically, determining the robot positioning based on the environmental data, the positioning mode and the sensor monitoring data comprises: determining a preprocessing threshold based on the environmental data; preprocessing the sensor monitoring data based on the preprocessing threshold and a preset denoising algorithm; and fusing the preprocessed sensor monitoring data according to the positioning mode and a preset fusion algorithm to determine the robot positioning.

[0050] In this embodiment, before positioning by sensor monitoring data of each positioning dimension, the obtained sensor monitoring data needs to be preprocessed to remove noise in the sensor monitoring data. Different environmental data have different judgment standards for noise, i.e., different preprocessing thresholds. The preprocessing threshold of various sensor monitoring data is obtained from the database according to the current environmental data. For example, when the ground friction coefficient is less than 0.3 (high interference), the wheel speed mutation threshold is 1 m / s, and the contact force judgment threshold is 8 N. The sensor monitoring data is preprocessed according to the preprocessing threshold and a preset denoising algorithm (for example, statistical filtering algorithm, voxel filtering algorithm, etc.). The preprocessed sensor monitoring data corresponding to the positioning mode is fused according to a preset fusion algorithm to determine the robot positioning. The preset fusion algorithm is, for example, EKF, visual-laser tight coupling SLAM, FGO, etc. When data fusion positioning is performed, the parameters of the preset fusion algorithm are adjusted according to the dimension weight of each positioning dimension and a preset adjustment rule. For example, the noise covariance matrix of EKF is adjusted according to the dimension weight and the preset adjustment rule. The preset adjustment rule is not specifically limited here.

[0051] Specifically, the method further includes: obtaining monitoring system resources; determining task priorities of each real-time task based on the positioning mode; and determining a resource scheduling strategy based on the task priorities and the monitoring system resources.

[0052] In this embodiment, the monitoring system resources are obtained from the monitoring system. Different positioning modes correspond to different task priorities of various real-time tasks. The relationship between the positioning mode and the task priority of the real-time task is preset, which is not specifically limited here. The resource scheduling strategy is to allocate the monitoring system resources to the real-time tasks in turn from high to low according to the task priorities, so that the tasks with higher priorities can be processed in time.

[0053] Figure 2 A structural block diagram of a mobile robot navigation positioning device 200 based on multi-sensor data provided by an embodiment of the present application.

[0054] As shown in Figure 2 The mobile robot navigation positioning device 200 based on multi-sensor data mainly includes: A first data acquisition module 201 for acquiring environmental data and modal conversion instructions; A second data acquisition module 202 for acquiring sensor monitoring data based on the environmental data; A motion modal determination module 203 for determining a motion modal based on the sensor monitoring data, the modal conversion instructions, and a preset rule; A positioning mode determination module 204 for determining a positioning mode based on the environmental data and the motion modal; The robot positioning module 205 is configured to determine the robot positioning based on the environment data, the positioning mode, and the sensor monitoring data.

[0055] As an optional implementation of the present embodiment, the second data acquisition module 202 is further configured to acquire the sensor monitoring data based on the environment data, including: acquiring historical monitoring information, the historical monitoring information including historical environment data, historical monitoring parameters of the sensor, and historical monitoring reliability; dividing the historical monitoring information based on the historical environment data and the sensor type to obtain a plurality of historical information combinations, each historical information combination corresponding to one historical environment data and one sensor type; analyzing each historical information combination to obtain a target monitoring parameter corresponding to each sensor type under various environment data; and acquiring the sensor monitoring data based on the target monitoring parameter.

[0056] As an optional implementation of the present embodiment, the motion mode determination module 203 is further configured to determine the motion mode based on the sensor monitoring data, the mode conversion instruction, and a preset rule, including: determining monitoring data thresholds of various modes based on the preset rule; determining the motion mode based on the monitoring data thresholds if all the sensor monitoring data meet the monitoring data thresholds; and determining the motion mode based on the mode conversion instruction if there is sensor monitoring data that does not meet the monitoring data thresholds.

[0057] As an optional implementation of the present embodiment, the positioning mode determination module 204 is further configured to determine the positioning mode based on the environment data and the motion mode, including: determining a positioning dimension based on the motion mode; determining environment interference values corresponding to various positioning dimensions based on the environment data and a preset interference weight; determining dimension weights of each positioning dimension based on the environment interference values; and determining the positioning mode based on the dimension weights and the positioning dimension.

[0058] As an optional implementation of the present embodiment, the positioning mode determination module 204 is further configured to determine the positioning dimension based on the motion mode, including: if the motion mode is a rolling mode, the positioning dimension includes wheel speed meter data and laser radar point cloud data; if the motion mode is a rotor mode, the positioning dimension includes IMU data and GPS data; if the motion mode is a walking mode, the positioning dimension includes visual SLAM data and laser SLAM data; and if the motion mode is a transition mode, the positioning dimension is determined based on the mode conversion instruction.

[0059] As an optional implementation of the embodiment, the robot positioning module 205 is further specifically configured to determine the robot positioning based on the environment data, the positioning mode and the sensor monitoring data, including: determining a preprocessing threshold based on the environment data; preprocessing the sensor monitoring data based on the preprocessing threshold and a preset denoising algorithm; and fusing the preprocessed sensor monitoring data according to the positioning mode and a preset fusion algorithm to determine the robot positioning.

[0060] As an optional implementation of the embodiment, the mobile robot navigation positioning device 200 based on multi-sensor data is further specifically configured to: acquire monitoring system resources; determine task priorities of each real-time task based on the positioning mode; and determine a resource scheduling strategy based on the task priorities and the monitoring system resources.

[0061] In one example, the modules in any of the above apparatuses can be one or more integrated circuits configured to implement one or more of the above methods, for example, one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0062] For another example, when the modules in the apparatus can be implemented in the form of a processing element scheduler, the processing element can be a general purpose processor, such as a central processing unit (CPU) or other processor that can invoke a program. For another example, these modules can be integrated together to be implemented in the form of a system-on-a-chip (SOC).

[0063] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the apparatus and modules described above can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0064] Figure 3 A structural block diagram of an electronic device 300 is provided for the embodiment of the present application.

[0065] As shown in Figure 3 The electronic device 300 includes a processor 301 and a memory 302, and can further include one or more of an information input / output (I / O) interface 303, a communication component 304 and a communication bus 305.

[0066] The processor 301 is configured to control overall operations of the electronic device 300 to complete all or part of the steps of the above-mentioned method for navigation and positioning of a mobile robot based on multi-sensor data. The memory 302 is configured to store various types of data to support operations of the electronic device 300, which can include, for example, instructions for any application or method operating on the electronic device 300, and application-related data. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as one or more of a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk, or an optical disk.

[0067] The I / O interface 303 provides an interface between the processor 301 and other interface modules, which can be a keyboard, a mouse, a button, and the like. These buttons can be virtual buttons or physical buttons. The communication component 304 is configured to perform wired or wireless communication between the electronic device 300 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G, or 4G, or a combination of one or more of them, so the corresponding communication component 304 can include a Wi-Fi component, a Bluetooth component, and an NFC component.

[0068] The electronic device 300 can be implemented with one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for performing the method of navigation and positioning of a mobile robot based on multi-sensor data according to the embodiments described above.

[0069] The communication bus 305 can include a path for transmitting information between the above-described components. The communication bus 305 can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, or the like. The communication bus 305 can be divided into an address bus, a data bus, a control bus, and the like.

[0070] The electronic device 300 can include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (Personal Digital Assistant), a PAD (Tablet PC), a PMP (Portable Multimedia Player), a car terminal (e.g., a car navigation terminal), and the like, and a stationary terminal such as a digital TV, a desktop computer, and the like, and can also be a server or the like.

[0071] The present application also provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the steps of the method of navigation and positioning of a mobile robot based on multi-sensor data described above.

[0072] The computer-readable storage medium can include a U disk, a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and the like, various media that can store program codes.

[0073] The terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0074] The description above only concerns preferred embodiments of the application and the explanation of the principles of the technology used. The person skilled in the art should understand that the scope of the application involved in the application is not limited to the technical solutions formed by the specific combinations of the technical features described above, and should also cover other technical solutions formed by any combinations of the technical features described above or their equivalent features without departing from the above-mentioned application concept. For example, the technical solutions formed by the mutual replacement of the above-mentioned features and the technical features applied in the application (but not limited to) having similar functions.

Claims

1. A method for navigation and localization of a mobile robot based on multi-sensor data, characterized in that, The method comprises the following steps: acquiring environmental data and modal conversion instructions; acquiring sensor monitoring data based on the environmental data; determining a motion mode based on the sensor monitoring data, the modal conversion instructions, and preset rules; determining a positioning mode based on the environmental data and the motion mode; determining a robot position based on the environmental data, the positioning mode, and the sensor monitoring data.

2. The method of claim 1, wherein, The step of acquiring sensor monitoring data based on the environmental data comprises the following steps: acquiring historical monitoring information, wherein the historical monitoring information comprises historical environmental data, historical monitoring parameters of sensors, and historical monitoring reliability; dividing the historical monitoring information based on the historical environmental data and sensor types to obtain a plurality of historical information combinations, wherein each historical information combination corresponds to one type of the historical environmental data and one type of the sensors; analyzing each historical information combination to obtain target monitoring parameters corresponding to each type of the sensors under each type of the environmental data; acquiring the sensor monitoring data based on the target monitoring parameters.

3. The method of claim 1, wherein, The step of determining a motion mode based on the sensor monitoring data, the modal conversion instructions, and preset rules comprises the following steps: determining monitoring data thresholds of various modes based on the preset rules; if all the sensor monitoring data meet the monitoring data thresholds, determining the motion mode based on the monitoring data thresholds; if there is sensor monitoring data that does not meet the monitoring data thresholds, determining the motion mode based on the modal conversion instructions.

4. The method of claim 1, wherein, The step of determining a positioning mode based on the environmental data and the motion mode comprises the following steps: determining positioning dimensions based on the motion mode; determining environmental interference values corresponding to each positioning dimension based on the environmental data and preset interference weights; determining dimension weights of each positioning dimension based on the environmental interference values; determining the positioning mode based on the dimension weights and the positioning dimensions.

5. The method of claim 4, wherein, The step of determining positioning dimensions based on the motion mode comprises the following steps: if the motion mode is a rolling mode, the positioning dimensions comprise wheel speed meter data and laser radar point cloud data; if the motion mode is a rotor mode, the positioning dimensions comprise IMU data and GPS data; if the motion mode is a walking mode, the positioning dimensions comprise visual SLAM data and laser SLAM data; if the motion mode is a transition mode, determining the positioning dimensions based on the modal conversion instructions.

6. The method of claim 1, wherein, The step of determining a robot position based on the environmental data, the positioning mode, and the sensor monitoring data comprises the following steps: determining a preprocessing threshold based on the environmental data; preprocessing the sensor monitoring data based on the preprocessing threshold and a preset denoising algorithm; fusing the preprocessed sensor monitoring data according to the positioning mode and a preset fusion algorithm to determine the robot position.

7. The method of claim 1, wherein, The method further comprises the following steps: acquiring monitoring system resources; determining task priorities of each real-time task based on the positioning mode; determining a resource scheduling strategy based on the task priorities and the monitoring system resources.

8. A mobile robot navigation and localization apparatus based on multi-sensor data, characterized by, The method comprises the following steps: a first data obtaining module, configured to obtain environment data and a modal conversion instruction; a second data obtaining module, configured to obtain sensor monitoring data based on the environment data; a motion modal determining module, configured to determine a motion modal based on the sensor monitoring data, the modal conversion instruction, and a preset rule; a positioning mode determining module, configured to determine a positioning mode based on the environment data and the motion modal; a robot positioning module, configured to determine robot positioning based on the environment data, the positioning mode, and the sensor monitoring data.

9. An electronic device, comprising: comprising a processor coupled to a memory; the processor is configured to execute a computer program stored in the memory, so that the electronic device executes the method of any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, comprising computer programs or instructions, which, when run on a computer, cause the computer to execute the method of any one of claims 1-7.

Images