Positioning method, device, robot positioning method, and robot

Abstract

Embodiments of the present disclosure disclose a positioning method, a device, a robot positioning method, and a robot. The positioning method includes: obtaining a plurality of positioning information of a target object; using a first part of the plurality of positioning information to perform positioning on the target object to obtain a first pose estimation result of the target object. Since positioning can be performed using a part of the plurality of positioning information, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in certain cases can be overcome.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technologies, and particularly to a positioning method, an apparatus, a robot positioning method, and a robot. Background Art

[0002] With the development of computer technologies and positioning technologies, devices with autonomous movement capabilities are increasingly applied in various services. During the movement of a device, it may be necessary to handle various complex scenarios such as indoor, outdoor, and semi-occluded outdoor scenarios, which pose great challenges to the precise positioning of the device. For example, when a device can obtain multiple positioning information, the failure of some positioning information or the inability to obtain some positioning information in some scenarios may lead to the inability to perform positioning. Summary of the Invention

[0003] To solve the problems in the related technologies, embodiments of the present disclosure provide a positioning method, an apparatus, a robot positioning method, and a robot.

[0004] In a first aspect, an embodiment of the present disclosure provides a positioning method, including:

[0005] Obtain an image of the delivery process of a target object;

[0006] Obtain multiple positioning information of the target object;

[0007] Use a first part of the multiple positioning information to perform positioning on the target object to obtain a first pose estimation result of the target object.

[0008] In combination with the first aspect, in a first implementation manner of the first aspect of the present disclosure, the using a first part of the multiple positioning information to perform positioning on the target object to obtain a first pose estimation result of the target object includes:

[0009] Use a second part of the multiple positioning information including the first part of the positioning information to perform positioning on the target object to obtain a second pose estimation result of the target object;

[0010] Use the first part of the multiple positioning information to perform pose estimation based on the second pose estimation result to obtain a first pose estimation result of the target object.

[0011] In combination with the first aspect, in a second implementation manner of the first aspect of the present disclosure, before the using a first part of the multiple positioning information to perform positioning on the target object to obtain a first pose estimation result of the target object, it includes:

[0012] Synchronize the time of the multiple positioning information.

[0013] Combined with the first implementation of the first aspect, in the third implementation of the first aspect of the present disclosure, the positioning of the target object by using the second part of the positioning information including the first part of the positioning information among the multiple positioning information to obtain the second pose estimation result of the target object includes:

[0014] Positioning the target object by using the second part of the positioning information to obtain multiple positioning results;

[0015] Calculating the second pose estimation result based on the obtained multiple positioning results.

[0016] Combined with the third implementation of the first aspect, in the fourth implementation of the first aspect of the present disclosure, the positioning of the target object by using the second part of the positioning information including the first part of the positioning information among the multiple positioning information to obtain the second pose estimation result of the target object further includes:

[0017] Establishing a map by using the data of the same type as the second part of the positioning information obtained in advance for obtaining the second pose estimation result of the target object.

[0018] Combined with the fourth implementation of the first aspect, in the fifth implementation of the first aspect of the present disclosure, the second part of the positioning information includes visual positioning information.

[0019] Combined with the fifth implementation of the first aspect, in the sixth implementation of the first aspect of the present disclosure, the positioning of the target object by using the second part of the positioning information to obtain multiple positioning results includes:

[0020] Estimating the relative position of the target object in the map by using the positioning information other than the visual positioning information in the second part of the positioning information;

[0021] Based on the estimated relative position of the target object in the map, positioning the target object by using the visual positioning information in the second part of the positioning information to obtain a visual positioning result.

[0022] Combined with the third implementation of the first aspect, in the seventh implementation of the first aspect of the present disclosure, the positioning of the target object by using the second part of the positioning information to obtain multiple positioning results includes:

[0023] Establishing a first coordinate system;

[0024] Obtaining a satellite positioning result by converting the second coordinate system to which the satellite positioning information in the second part of the positioning information belongs to the first coordinate system.

[0025] Combined with the seventh implementation manner of the first aspect, in the eighth implementation manner of the first aspect of the present disclosure, obtaining the satellite positioning result by converting the second coordinate system to which the satellite positioning information in the second part of positioning information belongs into the first coordinate system includes:

[0026] Obtaining the satellite positioning result by converting the second coordinate system to which the satellite positioning information in the second part of positioning information belongs and the third coordinate system to which the visual tracking information in the second part of positioning information belongs into the first coordinate system.

[0027] Combined with the third implementation manner of the first aspect, in the ninth implementation manner of the first aspect of the present disclosure, positioning the target object by using the second part of positioning information to obtain multiple positioning results includes:

[0028] Obtaining the wheel speed meter and inertial navigation fusion positioning result by combining the wheel speed meter information and the inertial navigation information in the second part of positioning information.

[0029] Combined with the ninth implementation manner of the first aspect, in the tenth implementation manner of the first aspect of the present disclosure, when the first part of positioning information includes wheel speed meter information and inertial navigation information, using the first part of positioning information in the multiple positioning information to perform pose estimation based on the second pose estimation result to obtain the first pose estimation result of the target object includes:

[0030] Using the wheel speed meter and inertial navigation fusion positioning result to perform pose estimation based on the second pose estimation result to obtain the first pose estimation result of the target object.

[0031] Combined with the third implementation manner of the first aspect, in the eleventh implementation manner of the first aspect of the present disclosure, calculating the second pose estimation result based on the obtained multiple positioning results includes:

[0032] Calculating the second pose estimation result by optimizing the obtained multiple positioning results.

[0033] Combined with the first aspect or the second implementation manner of the first aspect, in the twelfth implementation manner of the first aspect of the present disclosure, positioning the target object by using the first part of positioning information in the multiple positioning information to obtain the first pose estimation result of the target object includes:

[0034] Obtaining the wheel speed meter and inertial navigation fusion positioning result by combining the wheel speed meter information and the inertial navigation information in the first part of positioning information as the first pose estimation result of the target object.

[0035] Combined with the first aspect and any one of the first to eleventh implementation manners of the first aspect, in the thirteenth implementation manner of the first aspect of the present disclosure, the first pose estimation result is a real-time pose estimation result, and the second pose estimation result is a pose estimation result with a time delay.

[0036] Combined with the first aspect and any one of the first to eleventh implementation manners of the first aspect, in the fourteenth implementation manner of the first aspect of the present disclosure, the plurality of positioning information includes at least a part of wheel speed meter information, inertial navigation information, satellite positioning information, and visual positioning information.

[0037] In a second aspect, an embodiment of the present disclosure provides a positioning device, including:

[0038] An acquisition module, configured to acquire a plurality of positioning information of a target object;

[0039] A positioning module, configured to perform positioning on the target object by using a first part of the plurality of positioning information to obtain a first pose estimation result of the target object.

[0040] In a third aspect, an embodiment of the present disclosure provides a positioning method, including:

[0041] Acquiring a plurality of positioning information of a robot;

[0042] Performing positioning on the robot by using at least a part of the plurality of positioning information to obtain a first pose estimation result of the robot.

[0043] In a fourth aspect, an embodiment of the present disclosure provides a robot, including:

[0044] A plurality of sensors, configured to acquire a plurality of positioning information of the robot;

[0045] A positioning device, configured to perform positioning on the robot by using at least a part of the plurality of positioning information to obtain a first pose estimation result of the robot.

[0046] Combined with the fourth aspect, in the first implementation manner of the fourth aspect of the present disclosure, the positioning device includes:

[0047] A first positioning module, configured to perform positioning on the target object by using a second part of the plurality of positioning information including the first part of the positioning information to obtain a second pose estimation result of the target object;

[0048] The second positioning module is configured to perform pose estimation based on the second pose estimation result by using the first part of the plurality of positioning information to obtain the first pose estimation result of the target object.

[0049] Combined with the second implementation manner of the fourth aspect, the present disclosure further includes, in the third implementation manner of the fourth aspect:

[0050] A sensor synchronization module configured to perform time synchronization on the plurality of positioning information.

[0051] Combined with the first implementation manner of the fourth aspect, in the third implementation manner of the fourth aspect, the first positioning module includes:

[0052] A first positioning sub-module configured to perform positioning on the target object by using the second part of the positioning information to obtain a plurality of positioning results;

[0053] A calculation sub-module configured to calculate a second pose estimation result based on the obtained plurality of positioning results.

[0054] Combined with the third implementation manner of the fourth aspect, in the fourth implementation manner of the fourth aspect, the first positioning module further includes:

[0055] A mapping sub-module configured to establish a map by using pre-acquired data of the same type as the second part of the positioning information for obtaining the second pose estimation result of the target object.

[0056] Combined with the fourth implementation manner of the fourth aspect, in the fifth implementation manner of the fourth aspect, the second part of the positioning information includes visual positioning information.

[0057] Combined with the fifth implementation manner of the fourth aspect, in the sixth implementation manner of the fourth aspect, the first positioning sub-module includes:

[0058] A second positioning sub-module configured to estimate the relative position of the target object in the map by using the positioning information other than the visual positioning information in the second part of the positioning information;

[0059] A third positioning sub-module configured to perform positioning on the target object by using the visual positioning information in the second part of the positioning information based on the estimated relative position of the target object in the map to obtain a visual positioning result.

[0060] Combined with the third implementation manner of the fourth aspect, in the seventh implementation manner of the fourth aspect, the first positioning sub-module includes:

[0061] A coordinate system establishment sub-module configured to establish a first coordinate system;

[0062] A coordinate system conversion sub-module, configured to obtain a satellite positioning result by converting a second coordinate system to which satellite positioning information in the second part of positioning information belongs into a first coordinate system.

[0063] Combined with the seventh implementation manner of the fourth aspect, in the eighth implementation manner of the fourth aspect of the present disclosure, the coordinate system conversion sub-module is further configured to:

[0064] Obtain a satellite positioning result by converting a second coordinate system to which satellite positioning information in the second part of positioning information belongs and a third coordinate system to which visual tracking information in the second part of positioning information belongs into a first coordinate system.

[0065] Combined with the third implementation manner of the fourth aspect, in the ninth implementation manner of the fourth aspect of the present disclosure, the first positioning sub-module is further configured to:

[0066] Obtain a wheel speed meter and inertial navigation fusion positioning result by combining wheel speed meter information and inertial navigation information in the second part of positioning information.

[0067] Combined with the ninth implementation manner of the fourth aspect, in the tenth implementation manner of the fourth aspect of the present disclosure, when the first part of positioning information includes wheel speed meter information and inertial navigation information, the second positioning module is further configured to:

[0068] Use the wheel speed meter and inertial navigation fusion positioning result to perform pose estimation based on the second pose estimation result to obtain a first pose estimation result of the target object.

[0069] Combined with the third implementation manner of the fourth aspect, in the eleventh implementation manner of the fourth aspect of the present disclosure, the calculation sub-module is further configured to:

[0070] Calculate a second pose estimation result by optimizing the obtained multiple positioning results.

[0071] Combined with the fourth aspect or the second implementation manner of the fourth aspect, in the twelfth implementation manner of the fourth aspect of the present disclosure, the positioning device is further configured to:

[0072] Obtain a wheel speed meter and inertial navigation fusion positioning result by combining wheel speed meter information and inertial navigation information in the first part of positioning information as a first pose estimation result of the target object.

[0073] Combined with the fourth aspect and any one of the first to eleventh implementation manners of the fourth aspect, in the thirteenth implementation manner of the fourth aspect of the present disclosure, the first pose estimation result is a real-time pose estimation result, and the second pose estimation result is a pose estimation result with a time delay.

[0074] Combined with the fourth aspect and any one of the first to eleventh implementation manners of the fourth aspect, in the fourteenth implementation manner of the fourth aspect of the present disclosure, the plurality of positioning information includes at least a part of wheel speedometer information, inertial navigation information, satellite positioning information, and visual positioning information.

[0075] Fifth aspect, an embodiment of the present disclosure provides a positioning method, including:

[0076] Obtaining a plurality of positioning information of a target object;

[0077] Based on a first part of the plurality of positioning information, obtaining a first positioning result, where the first positioning result is a real-time positioning result;

[0078] Based on a second part of the plurality of positioning information, obtaining a second positioning result, where the second positioning result is a positioning result with a time delay;

[0079] Based on the first positioning result and the second positioning result, providing target positioning information of the target object.

[0080] Sixth aspect, an embodiment of the present disclosure provides an electronic device, including a memory and a processor; wherein,

[0081] The memory is used to store one or more computer instructions, where the one or more computer instructions are executed by the processor to implement the method described in any one of the first aspect, the first to fourteenth implementation manners of the first aspect, the third aspect, and the fifth aspect.

[0082] Seventh aspect, an embodiment of the present disclosure provides a readable storage medium, on which computer instructions are stored, and when the computer instructions are executed by a processor, the method described in any one of the first aspect, the first to fourteenth implementation manners of the first aspect, the third aspect, and the fifth aspect is implemented.

[0083] The technical solution provided by the embodiment of the present disclosure may include the following beneficial effects:

[0084] According to the technical solution provided by the embodiments of the present disclosure, by obtaining multiple positioning information of a target object; using a first part of the multiple positioning information to position the target object to obtain a first pose estimation result of the target object, it is possible to perform positioning using a part of the multiple positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0085] According to the technical solution provided by the embodiments of the present disclosure, the step of using a first part of the multiple positioning information to position the target object to obtain a first pose estimation result of the target object includes: using a second part of the multiple positioning information including the first part of the positioning information to position the target object to obtain a second pose estimation result of the target object; using the first part of the multiple positioning information, based on the second pose estimation result, to perform pose estimation to obtain the first pose estimation result of the target object. It is possible to perform positioning using a part of the multiple positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0086] According to the technical solution provided by the embodiments of the present disclosure, before using a first part of the multiple positioning information to position the target object to obtain a first pose estimation result of the target object, it includes: performing time synchronization on the multiple positioning information, which is beneficial to fusing the multiple positioning information, so as to perform positioning using a part of the multiple positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome. Moreover, through the time synchronization between multi-sensor information, the error caused by timestamp errors in the multi-sensor fusion solution can be reduced.

[0087] According to the technical solution provided by the embodiments of the present disclosure, positioning the target object by using the second part of the positioning information including the first part of the positioning information among the multiple positioning information to obtain the second pose estimation result of the target object includes: positioning the target object by using the second part of the positioning information to obtain multiple positioning results; calculating the second pose estimation result based on the obtained multiple positioning results. Multiple positioning results can be obtained through different positioning information, and at least one of the positioning results is used for positioning. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0088] According to the technical solution provided by the embodiments of the present disclosure, positioning the target object by using the second part of the positioning information including the first part of the positioning information among the multiple positioning information to obtain the second pose estimation result of the target object further includes: establishing a map by using the data of the same type as the second part of the positioning information obtained in advance for obtaining the second pose estimation result of the target object. A map can be established, and multiple positioning results are obtained through different positioning information on the map, and at least one of the positioning results is used for positioning. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0089] According to the technical solution provided by the embodiments of the present disclosure, since the second part of the positioning information includes visual positioning information, positioning can be performed on the map by using the visual positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0090] According to the technical solution provided by the embodiments of the present disclosure, positioning the target object by using the second part of the positioning information to obtain multiple positioning results includes: estimating the relative position of the target object in the map by using the positioning information other than the visual positioning information in the second part of the positioning information; based on the estimated relative position of the target object in the map, positioning the target object by using the visual positioning information in the second part of the positioning information to obtain a visual positioning result. Multiple positioning results can be obtained through different positioning information on the map, and at least one of the positioning results is used for positioning. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0091] According to the technical solution provided by the embodiments of the present disclosure, by using the second part of the positioning information to position the target object to obtain multiple positioning results, including: establishing a first coordinate system; obtaining a satellite positioning result by converting the second coordinate system to which the satellite positioning information in the second part of the positioning information belongs into the first coordinate system, the satellite positioning result can be obtained through the conversion between different coordinate systems, and using at least one of the positioning results including the satellite positioning result for positioning. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0092] According to the technical solution provided by the embodiments of the present disclosure, by obtaining the satellite positioning result by converting the second coordinate system to which the satellite positioning information in the second part of the positioning information belongs into the first coordinate system, including: obtaining the satellite positioning result by converting the second coordinate system to which the satellite positioning information in the second part of the positioning information belongs and the third coordinate system to which the visual tracking information in the second part of the positioning information belongs into the first coordinate system, the satellite positioning result can be obtained through the conversion between different coordinate systems, and using at least one of the positioning results including the satellite positioning result for positioning. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0093] According to the technical solution provided by the embodiments of the present disclosure, by using the second part of the positioning information to position the target object to obtain multiple positioning results, including: obtaining a wheel speed meter and inertial navigation fusion positioning result by combining the wheel speed meter information and inertial navigation information in the second part of the positioning information, positioning can be performed through a part of the positioning information among multiple positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0094] According to the technical solution provided by the embodiments of the present disclosure, when the first part of the positioning information includes wheel speed meter information and inertial navigation information, by using the first part of the positioning information among the multiple positioning information to perform pose estimation based on the second pose estimation result to obtain the first pose estimation result of the target object, including: using the wheel speed meter and inertial navigation fusion positioning result to perform pose estimation based on the second pose estimation result to obtain the first pose estimation result of the target object. Even in various complex scenarios such as indoors, outdoors, and semi-occluded outdoors, the positioning of the target object can be completed. Moreover, by using the wheel speed meter and inertial navigation fusion positioning result, real-time positioning can be completed.

[0095] According to the technical solution provided by the embodiments of the present disclosure, calculating the second pose estimation result based on the obtained multiple positioning results includes: calculating the second pose estimation result by optimizing the obtained multiple positioning results, and positioning can be performed using a part of the positioning information among the multiple positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0096] According to the technical solution provided by the embodiments of the present disclosure, positioning the target object using the first part of the positioning information among the multiple positioning information to obtain the first pose estimation result of the target object includes: obtaining the wheel speed meter and inertial navigation fusion positioning result by combining the wheel speed meter information and inertial navigation information in the first part of the positioning information as the first pose estimation result of the target object. Even in various complex scenarios such as indoor, outdoor, and semi-occluded outdoor, the positioning of the target object can be completed. Moreover, using the wheel speed meter and inertial navigation fusion positioning result, real-time positioning can be completed.

[0097] According to the technical solution provided by the embodiments of the present disclosure, the first pose estimation result is a real-time pose estimation result, and the second pose estimation result is a pose estimation result with a time delay. Positioning can be performed using a part of the positioning information among the multiple positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome. Moreover, real-time positioning can be completed.

[0098] According to the technical solution provided by the embodiments of the present disclosure, the multiple positioning information includes at least a part of wheel speed meter information, inertial navigation information, satellite positioning information, and visual positioning information. Positioning can be performed using a part of the positioning information among the multiple positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0099] According to the technical solution provided by the embodiments of the present disclosure, through an acquisition module configured to acquire multiple positioning information of a target object; a positioning module configured to position the target object using the first part of the positioning information among the multiple positioning information to obtain the first pose estimation result of the target object. Positioning can be performed using a part of the positioning information among the multiple positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0100] According to the technical solution provided by the embodiments of the present disclosure, by obtaining multiple positioning information of a robot; using at least a part of the multiple positioning information to position the robot to obtain a first pose estimation result of the robot, it is possible to perform positioning through a part of the positioning information among the multiple positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0101] According to the technical solution provided by the embodiments of the present disclosure, through multiple sensors for obtaining multiple positioning information of a robot; a positioning device for using at least a part of the multiple positioning information to position the robot to obtain a first pose estimation result of the robot, it is possible to perform positioning through a part of the positioning information among the multiple positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0102] According to the technical solution provided by the embodiments of the present disclosure, by obtaining multiple positioning information of a target object; obtaining a first positioning result based on a first part of the multiple positioning information, where the first positioning result is a real-time positioning result; obtaining a second positioning result based on a second part of the multiple positioning information, where the second positioning result is a delayed positioning result; providing target positioning information of the target object based on the first positioning result and the second positioning result, it is possible to perform positioning through a part of the positioning information among the multiple positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome. Moreover, real-time positioning can be completed.

[0103] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. Brief Description of the Drawings

[0104] In combination with the drawings, through the following detailed description of non-limiting embodiments, other labels, objectives, and advantages of the present disclosure will become more obvious. In the drawings:

[0105] Figure 1 A flowchart showing a positioning method according to an embodiment of the present disclosure is shown;

[0106] Figure 2 Shown according to Figure 1 A flowchart showing an example of step S120 in the positioning method in the shown embodiment is shown;

[0107] Figure 3 A flowchart showing a positioning method according to another embodiment of the present disclosure;

[0108] Figure 4 Showing according to Figure 2 A flowchart showing an example of step S210 in the positioning method in the embodiment shown;

[0109] Figure 5 Showing according to Figure 4 A flowchart showing an example of step S410 in the positioning method in the embodiment shown;

[0110] Figure 6 Showing according to Figure 4 A flowchart showing another example of step S410 in the positioning method in the embodiment shown;

[0111] Figure 7 A structural block diagram showing a positioning device according to an embodiment of the present disclosure;

[0112] Figure 8 A schematic structural block diagram showing an example of a positioning device according to an embodiment of the present disclosure;

[0113] Figure 9 A flowchart showing a robot positioning method according to an embodiment of the present disclosure;

[0114] Figure 10 A structural block diagram showing a robot according to an embodiment of the present disclosure;

[0115] Figure 11 Showing according to Figure 10 A structural block diagram showing an example of the positioning device 1020 in the robot according to the embodiment shown;

[0116] Figure 12 A structural block diagram showing a robot according to another embodiment of the present disclosure;

[0117] Figure 13 Showing according to Figure 11 A structural block diagram showing an example of the first positioning module 1110 in the positioning device 1020 according to the embodiment shown;

[0118] Figure 14 Showing according to Figure 13 A structural block diagram showing an example of the first positioning sub-module 1310 in the positioning device 1020 according to the embodiment shown;

[0119] Figure 15 Showing according to Figure 13 A structural block diagram showing another example of the first positioning sub-module 1310 in the positioning device 1020 according to the embodiment shown;

[0120] Figure 16 Shows a structural block diagram of an electronic device according to an embodiment of the present disclosure;

[0121] Figure 17 Is a schematic structural diagram of a computer system suitable for implementing a positioning method and a robot positioning method according to an embodiment of the present disclosure. Specific embodiments

[0122] Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. In addition, for clarity, parts irrelevant to the description of the exemplary embodiments are omitted in the drawings.

[0123] In the present disclosure, it should be understood that terms such as "including" or "having" are intended to indicate the presence of the labels, numbers, steps, actions, components, parts, or combinations thereof disclosed in this specification, and do not intend to exclude the possibility of the presence or addition of one or more other labels, numbers, steps, actions, components, parts, or combinations thereof.

[0124] It should also be noted that, without conflict, the embodiments in the present disclosure and the labels in the embodiments can be combined with each other. The present disclosure will be described in detail below with reference to the drawings and in combination with the embodiments.

[0125] According to the technical solution provided by the embodiments of the present disclosure, by obtaining multiple positioning information of a target object; using the first part of the positioning information among the multiple positioning information to position the target object to obtain a first pose estimation result of the target object, it is possible to perform positioning through a part of the positioning information among the multiple positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, it can overcome the problem of insufficient positioning information in certain cases.

[0126] Figure 1 Shows a flowchart of a positioning method according to an embodiment of the present disclosure. As Figure 1 shown, the positioning method includes the following steps S110 and S120:

[0127] In step S110, multiple positioning information of a target object is obtained.

[0128] In step S120, the target object is positioned using the first part of the positioning information among the multiple positioning information to obtain a first pose estimation result of the target object.

[0129] In the embodiments of the present disclosure, the target object can be a device with autonomous movement ability, such as various devices like self-driving vehicles and robots.

[0130] In one embodiment of the present disclosure, the multiple positioning information includes at least a part of wheel speedometer information, inertial navigation information, satellite positioning information, and visual positioning information.

[0131] According to the technical solution provided by the embodiment of the present disclosure, by including at least a part of wheel speedometer information, inertial navigation information, satellite positioning information, and visual positioning information in the multiple positioning information, positioning can be performed using a part of the positioning information among the multiple positioning information. Therefore, even if some information fails or certain positioning information cannot be obtained in certain scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in certain cases can be overcome.

[0132] In one embodiment of the present disclosure, the wheel speedometer is also called a wheel speed encoder, and the wheel speed can be calculated by accumulating the number of photoelectric encoder pulses. The wheel speedometer in the embodiment of the present disclosure can be a wheel speedometer known in the related art.

[0133] In one embodiment of the present disclosure, the inertial navigation information is provided by an inertial navigation element or an inertial measurement unit (IMU). For example, the inertial navigation information can be information such as the acceleration and angular acceleration of the target object. The inertial navigation element or inertial measurement unit in the embodiment of the present disclosure can be an inertial navigation element or an inertial measurement unit known in the related art.

[0134] In one embodiment of the present disclosure, the satellite positioning information can be provided by a satellite system such as the Global Navigation Satellite System (GNSS). For example, the global navigation satellite system can include various satellite navigation systems known in the related art such as the GPS system, the GLONASS system, and the Beidou satellite navigation system.

[0135] In one embodiment of the present disclosure, the visual positioning information can be positioning information obtained by a computer based on visual feature tracking or matching, where the visual feature is a feature point extracted from an image by an algorithm. The means for obtaining the visual positioning information in the embodiment of the present disclosure can be a technique known in the related art.

[0136] In one embodiment of the present disclosure, the above-mentioned wheel speedometer information, inertial navigation information, satellite positioning information, and visual positioning information are merely examples of positioning information. According to the difference in the device for obtaining the positioning information or the source of the positioning information, various positioning information known in the related art can be obtained for the target object, or the positioning information of the target object can be obtained by using future technical means.

[0137] In an embodiment of the present disclosure, since the target object may be in various complex scenarios such as indoor, outdoor, and semi-occluded outdoor, some of the multiple positioning information cannot be obtained in a specific scenario. In the case where some positioning information of the target object cannot be obtained, the technical solution of the embodiment of the present disclosure can use the first part of the positioning information among the multiple positioning information to locate the target object to obtain the first pose estimation result of the target object. For example, in an embodiment of the present disclosure, the first part of the positioning information may be one kind of positioning information, a part of the positioning information, or all of the positioning information among the aforementioned wheel speedometer information, inertial navigation information, satellite positioning information, and visual positioning information.

[0138] The following refers to Figure 2 description Figure 1 An example of step S120 in the positioning method in the illustrated embodiment.

[0139] Figure 2 Illustrates according to Figure 1 An example of step S120 in the positioning method in the illustrated embodiment is shown in the flowchart. As Figure 2 shown, step S120 includes steps S210 and S220.

[0140] In step S210, the target object is located using the second part of the positioning information including the first part of the positioning information among the multiple positioning information to obtain the second pose estimation result of the target object.

[0141] In step S220, the first part of the positioning information among the multiple positioning information is used to perform pose estimation based on the second pose estimation result to obtain the first pose estimation result of the target object.

[0142] According to the technical solution provided by the embodiment of the present disclosure, when the first part of the positioning information includes wheel speedometer information and inertial navigation information, the first part of the positioning information among the multiple positioning information is used to perform pose estimation based on the second pose estimation result to obtain the first pose estimation result of the target object, including: using the fusion positioning result of the wheel speedometer and inertial navigation to perform pose estimation based on the second pose estimation result to obtain the first pose estimation result of the target object. Even in various complex scenarios such as indoor, outdoor, and semi-occluded outdoor, the positioning of the target object can be completed. Moreover, using the fusion positioning result of the wheel speedometer and inertial navigation, real-time positioning can be completed.

[0143] In one embodiment of the present disclosure, the positioning of the target object using the first part of the multiple positioning information to obtain the first pose estimation result of the target object can be achieved in two steps. First, the target object is positioned using the second part of the multiple positioning information including the first part of the positioning information to obtain the second pose estimation result of the target object. Next, pose estimation is performed based on the second pose estimation result using the first part of the positioning information to obtain the first pose estimation result of the target object.

[0144] In one embodiment of the present disclosure, the first part of the positioning information can be considered as the positioning information that can be obtained in various scenarios when positioning the target object, that is, the positioning information of the target object that is not affected by the scenario. For example, the first part of the positioning information may include wheel speedometer information, inertial navigation information, or both wheel speedometer information and inertial navigation information. Those skilled in the art can understand that the wheel speedometer information and inertial navigation information can be the information provided by the wheel speedometer and inertial navigation elements installed on the target object itself and are not affected by the external environment. For example, even if the target object is located in an indoor environment or a dark environment, the wheel speedometer and inertial navigation elements installed on the target object can still provide the wheel speedometer information and inertial navigation information. Moreover, the real-time performance of the wheel speedometer information and inertial navigation information is better than that of satellite positioning information and visual positioning information.

[0145] In one embodiment of the present disclosure, step S120 includes: obtaining a wheel speedometer and inertial navigation fusion positioning result by combining the wheel speedometer information and inertial navigation information in the first part of the positioning information as the first pose estimation result of the target object.

[0146] According to the technical solution provided by the embodiments of the present disclosure, by using the first part of the multiple positioning information to position the target object to obtain the first pose estimation result of the target object, it includes: obtaining a wheel speedometer and inertial navigation fusion positioning result by combining the wheel speedometer information and inertial navigation information in the first part of the positioning information as the first pose estimation result of the target object. Even in various complex scenarios such as indoor, outdoor, and semi-occluded outdoor, the positioning of the target object can be completed. Moreover, using the wheel speedometer and inertial navigation fusion positioning result, real-time positioning can be completed.

[0147] In one embodiment of the present disclosure, the wheel speedometer information and inertial navigation information are collected within a certain time period [t0, t1]. By integrating the wheel speedometer information, the six-degree-of-freedom relative pose P1 and its confidence level C1 at time t1 relative to time t0 can be obtained. At the same time, by integrating the inertial navigation information, the six-degree-of-freedom relative pose P2 and its confidence level C2 at time t1 relative to time t0 can be obtained. By solving the optimization problem min P (P1 - P)T C1 -1 (P1 - P)+(P2 - P) T C2 -1 (P2 - P), the optimal estimated pose P’ (and its confidence C’) can be obtained, that is, the relative pose of the target object after fusing the odometer information and the inertial navigation information, which is also the positioning result of the odometer and inertial navigation fusion.

[0148] In an embodiment of the present disclosure, when the obtained positioning information of the target object includes not only the first positioning information but also other positioning information, all the obtained positioning information can be referred to as the second part of the positioning information. For example, in the embodiments of the present disclosure, the second part of the positioning information may be a part or all of the foregoing odometer information, inertial navigation information, satellite positioning information, and visual positioning information.

[0149] Those skilled in the art can understand that generally, by using the second part of the positioning information for positioning, a more accurate positioning result can be obtained than by only using the first part of the positioning information. However, after obtaining the second pose estimation result of the target object according to the second part of the positioning information, further positioning using the first positioning information based on the second pose estimation result can ensure the real-time performance of the first pose estimation result. For example, when the first part of the positioning information includes odometer information and inertial navigation information, the odometer and inertial navigation fusion positioning result can be used to perform pose estimation based on the second pose estimation result to obtain the first pose estimation result of the target object. In this way, the first pose estimation result can be ensured to be a real-time pose estimation result.

[0150] The following refers to Figure 3 Describe a positioning method according to another embodiment of the present disclosure.

[0151] Figure 3 Show a flowchart of a positioning method according to another embodiment of the present disclosure. Figure 3 The shown embodiment is different from Figure 1 The shown embodiment in that before step S120, there is also step S310.

[0152] In step S310, time synchronization is performed on multiple positioning information.

[0153] According to the technical solution provided by the embodiments of the present disclosure, before obtaining the first pose estimation result of the target object by positioning the target object using the first part of the multiple positioning information, it includes: performing time synchronization on the multiple positioning information, which can facilitate the fusion of the multiple positioning information, so as to perform positioning through a part of the multiple positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome. Moreover, through the time synchronization between multi-sensor information, the error caused by timestamp errors in the multi-sensor fusion solution can be reduced.

[0154] In an embodiment of the present disclosure, the time synchronization between the information of multiple sensors can be achieved, that is, the timestamps of the observation data of multiple sensors all correspond to the same time. Those skilled in the art can understand that technical means for performing time synchronization on multiple positioning information have been provided in the related art, and the present disclosure will not elaborate on this.

[0155] The following refers to Figure 4 to describe an example of step S210 in the positioning method according to the Figure 2 embodiment shown.

[0156] Figure 4 Illustrates Figure 2 a flowchart of an example of step S210 in the positioning method according to the embodiment shown. As Figure 4 shown, step S210 includes step S410 and step S420.

[0157] In step S410, the target object is positioned using the second part of the positioning information to obtain multiple positioning results.

[0158] In step S420, the second pose estimation result is calculated based on the multiple positioning results obtained.

[0159] According to the technical solution provided by the embodiments of the present disclosure, by positioning the target object using the second part of the multiple positioning information including the first part of the positioning information to obtain the second pose estimation result of the target object, it includes: positioning the target object using the second part of the positioning information to obtain multiple positioning results; calculating the second pose estimation result based on the multiple positioning results obtained. Multiple positioning results can be obtained through different positioning information, and at least one of the positioning results is used for positioning. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0160] In one embodiment of the present disclosure, since the second part of the positioning information includes the first part of the positioning information, therefore, multiple positioning results can be obtained according to the second part of the positioning information, that is, at least one positioning result obtained by using the first part of the positioning information and at least one positioning result obtained by using information other than the first part of the positioning information. The second pose estimation result can be calculated based on the multiple obtained positioning results.

[0161] In one embodiment of the present disclosure, step S210 further includes: establishing a map by using the data of the same type as the second part of the positioning information obtained in advance for obtaining the second pose estimation result of the target object.

[0162] According to the technical solution provided by the embodiment of the present disclosure, by using the second part of the positioning information including the first part of the positioning information in the multiple positioning information to position the target object to obtain the second pose estimation result of the target object, it further includes: establishing a map by using the data of the same type as the second part of the positioning information obtained in advance for obtaining the second pose estimation result of the target object, a map can be established, and multiple positioning results are obtained through different positioning information on the map, and at least one of the positioning results is used for positioning. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0163] In one embodiment of the present disclosure, environmental data (multiple positioning information) can be collected in advance to establish a map (or called a priori map). The device or module for establishing the map can be the target object itself, other objects, online devices or modules such as local or remote computers, or offline devices or modules. After the map is established, it can be transmitted to the target object for use during online positioning.

[0164] In one embodiment of the present disclosure, in order to be able to position the target object on the map by using the multiple obtained positioning information, a map can be established in advance based on the types of the multiple positioning information to be obtained, that is, a map is established by using the data of the same type as all the multiple positioning information obtained in advance. In the case where the second part of the positioning information obtained is only a part of the multiple positioning information, a map can be established by using the data of the same type as the second part of the positioning information. Therefore, as long as the target object can be positioned by using the second part of the positioning information, the types of the positioning information included in the map can be changed.

[0165] In one embodiment of the present disclosure, the second part of the positioning information includes visual positioning information.

[0166] According to the technical solution provided by the embodiments of the present disclosure, by including visual positioning information in the second part of the positioning information, positioning can be performed on the map using the visual positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0167] In an embodiment of the present disclosure, the established map can be referred to as a "multi-sensor fusion map" or a "map of multi-sensor fusion". For example, a "multi-sensor fusion map" can refer to a three-dimensional visual feature map established by fusing images provided by a camera (data of the same type as the visual positioning information) and at least one other type of sensor information (data of the same type as the positioning information other than the visual positioning information in the second part of the positioning information). The specific implementation method is to use a multi-sensor system with time synchronization to collect data in the three-dimensional space where the multi-sensor fusion map needs to be established, and then according to the known sensor observation model, use the collected multi-sensor data to construct an optimization problem. By minimizing this optimization problem, the positions of the landmarks extracted from the images in the three-dimensional coordinate system can be obtained. The descriptions and three-dimensional positions of all the landmarks constitute a map of this three-dimensional space, which can be used for positioning. Since multiple sensors including a visual sensor (camera) are used to assist in improving the quality of map construction during the map construction process, the map can be referred to as a multi-sensor fusion map.

[0168] In an embodiment of the present disclosure, by fusing multi-sensor information in advance to establish a map, the accuracy and robustness of target object positioning can be improved. For example, in cases where positioning information such as satellite positioning information cannot be obtained, high-quality target object positioning results can still be provided.

[0169] The following refers to Figure 5 Describe an example of step S410 in the positioning method according to Figure 4 the embodiment shown.

[0170] Figure 5 Show a flowchart of an example of step S410 in the positioning method according to Figure 4 the embodiment shown. In the case where a map has been established and the second part of the positioning information includes visual positioning information, step S410 includes steps S510 and S520.

[0171] In step S510, the relative position of the target object in the map is estimated using the positioning information other than the visual positioning information in the second part of the positioning information.

[0172] In step S520, based on the estimated relative position of the target object in the map, the target object is located using the visual positioning information in the second part of the positioning information, and a visual positioning result is obtained.

[0173] According to the technical solution provided by the embodiments of the present disclosure, by using the second part of the positioning information to locate the target object to obtain multiple positioning results, including: estimating the relative position of the target object in the map using the positioning information other than the visual positioning information in the second part of the positioning information; based on the estimated relative position of the target object in the map, using the visual positioning information in the second part of the positioning information to locate the target object, and obtaining a visual positioning result, multiple positioning results can be obtained in the map through different positioning information, and at least one of the positioning results is used for positioning. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0174] In an embodiment of the present disclosure, at least a part of positioning information such as satellite positioning information, wheel speed meter information, and inertial navigation information (for example, the fusion positioning result of the wheel speed meter and inertial navigation) can be relied on to assist the use of visual positioning information, find a matching landmark in the map, and then estimate the relative position of the target object in the map. The information of sensors other than the time sensor (camera) is used to predict the position of the target object in the map, thereby accelerating visual relocalization.

[0175] The following refers to Figure 6 Describe another example of step S410 in the positioning method according to Figure 4 the embodiment shown.

[0176] Figure 6 Show a flowchart of another example of step S410 in the positioning method according to Figure 4 the embodiment shown. In Figure 6 the embodiment shown, step S410 includes steps S610 and S620.

[0177] In step S610, a first coordinate system is established.

[0178] In step S620, the satellite positioning result is obtained by converting the second coordinate system to which the satellite positioning information in the second part of the positioning information belongs into the first coordinate system.

[0179] According to the technical solution provided by an embodiment of the present disclosure, obtaining a satellite positioning result by converting the second coordinate system to which the satellite positioning information in the second part of positioning information belongs into the first coordinate system includes: obtaining a satellite positioning result by converting the second coordinate system to which the satellite positioning information in the second part of positioning information belongs and the third coordinate system to which the visual tracking information in the second part of positioning information belongs into the first coordinate system. The satellite positioning result can be obtained through the conversion between different coordinate systems, and positioning is performed using at least one of the positioning results including the satellite positioning result. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0180] In an embodiment of the present disclosure, step S620 includes: obtaining a satellite positioning result by converting the second coordinate system to which the satellite positioning information in the second part of positioning information belongs and the third coordinate system to which the visual tracking information in the second part of positioning information belongs into the first coordinate system.

[0181] According to the technical solution provided by an embodiment of the present disclosure, obtaining a satellite positioning result by converting the second coordinate system to which the satellite positioning information in the second part of positioning information belongs into the first coordinate system includes: obtaining a satellite positioning result by converting the second coordinate system to which the satellite positioning information in the second part of positioning information belongs and the third coordinate system to which the visual tracking information in the second part of positioning information belongs into the first coordinate system. The satellite positioning result can be obtained through the conversion between different coordinate systems, and positioning is performed using at least one of the positioning results including the satellite positioning result. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0182] The following describes an example of the coordinate system conversion process.

[0183] In this example, an earth tangent plane coordinate system, such as an east-north-up or north-east-down coordinate system, can be initialized, and the calibration between the earth tangent plane coordinate system and the visual tracking local coordinate system can be initialized through the calibration of the satellite positioning antenna at the target object position.

[0184] In this embodiment, satellite positioning observations (i.e., three-dimensional positioning results) are in the Earth coordinate system (i.e., longitude-latitude-altitude coordinate system), providing only the position without orientation. When fusing satellite positioning observations with other sensors, it is necessary to unify the coordinate systems. In the positioning system of the present disclosure embodiment, it is possible to select to establish, for example, an east-north-up coordinate system in the operating area of the target object. Both the satellite positioning observations and the pose estimation of the local visual tracking are converted to the east-north-up coordinate system. Here, a six-degree-of-freedom transformation between the local coordinate system g of the visual tracking and the east-north-up coordinate system n is required. The specific implementation process is as follows:

[0185] 1. Ensure the normal operation of the local visual tracking and continuously output the displacement estimation p_ga(t) of the satellite positioning antenna center in the local coordinate system of the visual tracking, where t represents time.

[0186] 2. At time t0, after receiving the first satellite positioning information, an east-north-up coordinate system n is established with the observed longitude and latitude as the origin. All subsequent satellite positioning information received during operation will first be converted to this east-north-up coordinate system n before being used. At the same time, record p_ga(t0).

[0187] 3. Next, continuously collect satellite positioning information and convert it to the east-north-up coordinate system n to obtain the displacement estimation p_na = [p_na_x, p_na_y, p_na_z] of the satellite positioning antenna center in the east-north-up coordinate system n. Continuously check the norm of [p_na_x, p_na_y] (i.e., the distance on the plane). When the norm is greater than a threshold thres_1, record the current p_ga(t1) (assumed to be time t1) and proceed to the next step. If the norm is less than thres_1, repeat this step.

[0188] 4. This step initializes the six-degree-of-freedom calibration (R_gn, p_gn) between the east-north-up coordinate system n and the local coordinate system g of the visual tracking. First, decompose R_gn into Euler angle form R_gn = R_roll * R_pitch * R_yaw. Among them, R_roll and R_pitch are the rotation matrices corresponding to the roll angle and pitch angle,

[0189]

[0190] Roll and pitch can be obtained by aligning the gravity vector estimate G_g in the visual tracking local coordinate system g with the gravity vector in the east-north-up coordinate system n, that is, [0,0,-9.8]. Regarding the acquisition method of the gravity vector estimate G_g, G_g is continuously estimated online together with p_ga. Let the vector g_v_a_t1_t2 = p_ga(t1)-p_ga(t0), and then the yaw angle can be obtained by aligning the vectors [p_na_x,p_na_y] and [g_v_a_t1_t2_x,g_v_a_t1_t2_y], and

[0191]

[0192] So we can get R_gn. Next, calculate p_gn=p_ga-R_gn*p_na.

[0193] 5. At this point, (R_gn, p_gn) initialization is completed.

[0194] In this example, (R_gn, p_gn) will always be optimized together in the optimization module, and the estimate will be continuously updated.

[0195] Through the calculation coordinate system conversion process given above, a satellite positioning result can be obtained according to the satellite positioning information. That is, a satellite positioning result applicable to the visual tracking local coordinate system can be obtained. This satellite positioning result can be used as one of the multiple positioning results obtained by positioning the target object using the second part of the positioning information.

[0196] Those skilled in the art can understand that the coordinate system conversion process exemplified above is only an example, and the present disclosure is not limited thereto. According to the above teachings of the present disclosure, those skilled in the art can use other methods to complete the coordinate system conversion and obtain the satellite positioning result.

[0197] In one embodiment of the present disclosure, step S410 includes: obtaining a fusion positioning result of the wheel speed meter and the inertial navigation by combining the wheel speed meter information and the inertial navigation information in the second part of the positioning information.

[0198] According to the technical solution provided by the embodiment of the present disclosure, the target object of the computing submodule is positioned by the computing submodule using the second part of the positioning information of the computing submodule to obtain multiple positioning results, including: the wheel speed meter information and the inertial navigation information in the second part of the positioning information are combined to obtain the wheel speed meter and inertial navigation fusion positioning result, and the positioning can be performed by a part of the positioning information in the multiple positioning information, so even if some information fails or some positioning information cannot be obtained in some scenes, the position and posture of the target object can still be estimated. That is, the problem of insufficient positioning information in some cases can be overcome.

[0199] In one embodiment of the present disclosure, the process of obtaining the fused positioning result of the wheel speedometer and inertial navigation by combining the wheel speedometer information and inertial navigation information in the second part of the positioning information is the same as the process of obtaining the fused positioning result of the wheel speedometer and inertial navigation by combining the wheel speedometer information and inertial navigation information in the first part of the positioning information.

[0200] In one embodiment of the present disclosure, when the first part of the positioning information includes wheel speedometer information and inertial navigation information, step S220 includes: using the fused positioning result of the wheel speedometer and inertial navigation, performing pose estimation based on the second pose estimation result to obtain the first pose estimation result of the target object.

[0201] According to the technical solution provided by the embodiments of the present disclosure, when the first part of the positioning information includes wheel speedometer information and inertial navigation information, using the first part of the positioning information in the multiple positioning information, performing pose estimation based on the second pose estimation result to obtain the first pose estimation result of the target object, includes: using the fused positioning result of the wheel speedometer and inertial navigation, performing pose estimation based on the second pose estimation result to obtain the first pose estimation result of the target object. Even in various complex scenarios such as indoor, outdoor, and outdoor semi-occluded, the positioning of the target object can be completed. Moreover, using the fused positioning result of the wheel speedometer and inertial navigation, real-time positioning can be completed.

[0202] In one embodiment of the present disclosure, using the fused positioning result of the wheel speedometer and inertial navigation, performing pose estimation based on the second pose estimation result to obtain the first pose estimation result of the target object can ensure the real-time performance of the first pose estimation result.

[0203] In one embodiment of the present disclosure, step S420 includes: calculating the second pose estimation result by optimizing the obtained multiple positioning results.

[0204] According to the technical solution provided by the embodiments of the present disclosure, calculating the second pose estimation result based on the obtained multiple positioning results, includes: calculating the second pose estimation result by optimizing the obtained multiple positioning results. Positioning can be performed through a part of the positioning information in the multiple positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0205] In one embodiment of the present disclosure, the operation of optimizing the obtained multiple positioning results may refer to performing non-linear optimization on the obtained multiple positioning results.

[0206] The following describes an example of performing non-linear optimization on the obtained multiple positioning results.

[0207] In this example, various data such as camera images (visual positioning information and / or visual tracking information), satellite positioning information, wheel speedometer information, inertial navigation information, extrinsic calibration from camera to wheel speedometer, translation calibration of the satellite positioning antenna center in the wheel speedometer coordinate system, camera intrinsic calibration, and wheel speedometer intrinsic calibration can be used to perform non-linear optimization on multiple positioning results. When processing the data, a sliding window strategy can be adopted. That is, for each newly obtained frame of image (or key frame image), all multi-sensor data from the current frame to the previous N frames are processed to obtain the positioning result corresponding to the current frame. For example, these processes may include:

[0208] 1. Extract visual features in the current image and match them with the visual features extracted from the previous N frames of images. Combining the intrinsic and extrinsic calibrations of the camera, a cost function Cost1 related to the feature coordinates and the pose of the target object can be obtained. Specifically, let be the camera pose corresponding to the i-th frame of image, and f j be the j-th visual feature, z ij be the pixel coordinate of the j-th visual feature on the i-th frame of image, and h is the projection model of the calibrated camera.

[0209]

[0210] 2. By fusing the wheel speedometer and inertial navigation, a cost function Cost2 related to the poses of two consecutive target objects can be obtained. The cost function Cost2 refers to the description related to step S120 above.

[0211] Cost2 = min P (P1 - P) T C1 -1 (P1 - P) + (P2 - P) T C2 -1 (P2 - P)

[0212] 3. The satellite positioning information at each t_i moment can be processed through the above-mentioned processing related to step S620 and the coordinate system conversion process to obtain the corresponding information.

[0213]

[0214] Thus, a cost function Cost3 related to the pose of the target object and (R_gn, p_gn) can be obtained.

[0215] In this example, by optimizing the total non-linear cost function Cost = Cost1 + Cost2 + Cost3, the estimation of the pose of the target object can be obtained to achieve the purpose of positioning.

[0216] Calculating the second pose estimation result by optimizing the obtained multiple positioning results can ensure the positioning accuracy and robustness of the target object.

[0217] The above description of the process of calculating the second pose estimation result by non-linearly optimizing the obtained multiple positioning results is merely an example. According to the teachings of the present disclosure, those skilled in the art can adopt various methods to optimize the multiple positioning results.

[0218] In an embodiment of the present disclosure, the first pose estimation result is a real-time pose estimation result, and the second pose estimation result is a pose estimation result with a time delay.

[0219] According to the technical solution provided by the embodiment of the present disclosure, since the first pose estimation result is a real-time pose estimation result and the second pose estimation result is a pose estimation result with a time delay, the target object can be positioned by using a part of the positioning information among the multiple positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome. Moreover, real-time positioning can be completed.

[0220] In an embodiment of the present disclosure, since the accuracy and robustness can be ensured by non-linear optimization when calculating the second pose estimation result by optimizing the obtained multiple positioning results. For example, when performing non-linear optimization, the multi-sensor data within a sliding window is used to perform multiple iterations of non-linear optimization to ensure the accuracy and robustness. Moreover, since the image processing part and other parts also need to be added during the positioning process, the calculation amount is relatively large, resulting in a time delay. That is, the second pose estimation result is a pose estimation result with a time delay.

[0221] In an embodiment of the present disclosure, since the calculation amount of the wheel speed sensor and inertial navigation fusion positioning is significantly smaller than that of calculating the second pose estimation result and has almost no impact on real-time performance. Therefore, the wheel speed sensor and inertial navigation fusion positioning result can be utilized, and pose estimation is performed based on the second pose estimation result to obtain the first pose estimation result of the target object. That is, the real-time performance of the first pose estimation result is ensured.

[0222] In an embodiment of the present disclosure, at regular intervals, the wheel speed sensor and inertial navigation fusion positioning need to obtain a reference pose with relatively high accuracy given by a module (such as a non-linear optimization module) that calculates the second pose estimation result by optimizing the obtained multiple positioning results. In this way, the current pose can be quickly estimated based on this without accumulating errors.

[0223] In an embodiment of the present disclosure, in the case where only the wheel speedometer information and the inertial navigation information are obtained, there is no need to calculate the second pose estimation result because, in this case, even if the second pose estimation result is obtained, the second pose estimation result is the same wheel speedometer and inertial navigation fusion positioning result as the first pose estimation result.

[0224] In an embodiment of the present disclosure, in the case where a combination of a wheel speedometer and inertial navigation is introduced, through the observation of the vehicle's own speed, pose estimation can still be performed when satellite positioning information or visual positioning information cannot be obtained due to sensor failure, and problems such as insufficient information for positioning in cases such as uniform linear motion in inertial navigation can be overcome. Moreover, by using the wheel speedometer information and inertial navigation fusion positioning, when a pose estimation result with a time delay is received, a real-time pose estimation result can also be output to ensure real-time performance. Moreover, the embodiments of the present disclosure can achieve longitude and latitude positioning output of the target object in indoor, outdoor, and outdoor areas with satellite positioning signal occlusion, and have high precision and robustness.

[0225] The following refers to Figure 7 Describe a positioning device according to an embodiment of the present disclosure.

[0226] Figure 7 The structural block diagram of a positioning device 700 according to an embodiment of the present disclosure is shown. In Figure 7 In the shown embodiment, the positioning device 700 includes an acquisition module 710 and a positioning module 720.

[0227] The acquisition module 710 is configured to acquire multiple positioning information of the target object.

[0228] The positioning module 720 is configured to use the first part of the positioning information among the multiple positioning information to position the target object to obtain the first pose estimation result of the target object.

[0229] According to the technical solution provided by the embodiment of the present disclosure, through the acquisition module, which is configured to acquire multiple positioning information of the target object; and the positioning module, which is configured to use the first part of the positioning information among the multiple positioning information to position the target object to obtain the first pose estimation result of the target object, positioning can be performed through a part of the positioning information among the multiple positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0230] Those skilled in the art can understand that the technical solutions described with reference to Figure 7 can be combined with the embodiments described with reference to Figures 1 to 6 so as to have the reference to Figures 1 to 6The technical effects achieved by the described embodiments. For specific details, reference may be made to the above description based on Figures 1 to 6 which will not be elaborated herein.

[0231] The following describes an example of a positioning device according to an embodiment of the present disclosure with reference to Figure 8 Figure [to be filled with the corresponding figure number].

[0232] Figure 8 FIG. [to be filled with the corresponding figure number] shows a schematic structural block diagram of an example of a positioning device according to an embodiment of the present disclosure. Figure 8 The shown positioning device may be a part of the aforementioned target object.

[0233] Figure 8 The shown positioning device includes a plurality of sensor modules. For example, a wheel speedometer module, an IMU (inertial navigation element) module, a GNSS (global navigation satellite system) module, and a vision module.

[0234] Figure 8 The shown positioning device further includes a sensor hub module for time synchronization of the information provided by the plurality of sensors, that is, the timestamps of the multi-sensor observation data all correspond to the same time. The sensor hub module can be implemented in a hardware, software, or a combination of hardware and software manner, which will not be elaborated in this disclosure.

[0235] In Figure 8 the shown positioning device, after being synchronized by the sensor hub module, the plurality of time-synchronized positioning information can be sent to an offline mapping module to establish a map. For example, the offline mapping module can be used to establish a map (prior map) by collecting environmental data in advance. This offline mapping module can be the target object itself, other objects, a local or remote computer. After the map is established, it will be transmitted to the positioning device for use during online positioning. It should be noted that the offline mapping module can be a part of the positioning device or not, and this disclosure does not limit this. It should be noted that a map can be established using the plurality of positioning information obtained by the positioning device or data of the same type as the plurality of positioning information obtained by the positioning device from other data sources, and this disclosure does not limit this.

[0236] Figure 8 The shown positioning device further includes a first pose estimation module. In Figure 8 the shown positioning device, after being synchronized by the sensor hub module, the plurality of time-synchronized positioning information can be sent to the first pose estimation module. The first pose estimation module includes an assisted visual relocalization module, a visual tracking module, a wheel speedometer-IMU fusion module, a GNSS observation processing module, and a non-linear optimization-based positioning module.

[0237] It should be noted that in the above translation, for tags like Figures 1 to 6 etc., since their specific meaning is not clear from the context, they are directly retained as they are. Also, for the parts like "Figure [to be filled with the corresponding figure number]. " and "FIG. [to be filled with the corresponding figure number] shows... ", the figure number placeholders need to be filled according to the actual figures in the original patent content.The assisted visual relocalization module relies on GNSS positioning information and the fused positioning information of the wheel speedometer and IMU to assist in the use of visual information, find matching landmarks in the map transmitted by the offline mapping module, and then estimate the relative position of the target object in the map. That is, the information of sensors other than the visual sensor is used to predict the position of the target object in the prior map, thereby accelerating visual relocalization. The assisted visual relocalization module is used for absolute positioning with respect to the map. The visual tracking module has nothing to do with the map and only provides the relative pose estimation between frames.

[0238] The wheel speedometer IMU fusion module fuses the IMU module and the wheel speedometer module to improve the accuracy of the wheel speedometer. The specific working method can refer to the relevant description of the foregoing embodiment for obtaining the fused positioning result of the wheel speedometer and inertial navigation.

[0239] The GNSS observation processing module initializes an earth tangent plane coordinate system, such as the east-north-up coordinate system or the north-east-down coordinate system, etc., and initializes the calibration between the earth tangent plane coordinate system and the visual tracking local coordinate system through the calibration of the GNSS antenna at the target object position.

[0240] The positioning module based on nonlinear optimization can perform positioning using data such as camera images, GNSS observations, wheel speedometer observations, IMU observations, external parameter calibration from the camera to the wheel speedometer, translation calibration of the GNSS antenna center in the wheel speedometer coordinate system, camera internal parameter calibration, and wheel speedometer internal parameter calibration. The data processing of this module adopts a sliding window strategy, that is, for each new frame of image (or key frame image) obtained, all multi-sensor data from the current frame to the previous N frames will be processed to obtain the positioning result corresponding to the current frame. The positioning module based on nonlinear optimization can achieve higher robustness and accuracy compared with the related technology. The working method of the positioning module based on nonlinear optimization can refer to the relevant description in the foregoing embodiment for calculating the second pose estimation result by optimizing the obtained multiple positioning results.

[0241] Figure 8 The shown positioning device further includes a real-time pose generation module. The real-time pose generation module uses the wheel speedometer IMU fusion module, receives the sometimes-delayed pose estimation result of the positioning module based on nonlinear optimization, and outputs a real-time pose estimation to ensure real-time performance. The working method of the real-time pose generation module can refer to the relevant description in the foregoing embodiment for using the fused positioning result of the wheel speedometer and inertial navigation and performing pose estimation based on the second pose estimation result to obtain the first pose estimation result of the target object.

[0242] Those skilled in the art can understand that the technical solutions described with reference to Figure 8 can be combined with the embodiments described with reference to Figures 1 to 7 so as to have the reference to Figures 1 to 7Technical effects achieved by the described embodiments. For specific details, reference may be made to the above description based on Figures 1 to 7 which will not be elaborated herein.

[0243] The following refers to Figure 9 to describe the flowchart of a robot positioning method according to an embodiment of the present disclosure.

[0244] Figure 9 Shows the flowchart of a robot positioning method according to an embodiment of the present disclosure. Figure 9 The shown embodiment includes steps S910 and S920.

[0245] In step S910, multiple positioning information of the robot is obtained.

[0246] In step S920, at least a part of the multiple positioning information is used to position the robot to obtain the first pose estimation result of the robot.

[0247] According to the technical solution provided by the embodiments of the present disclosure, by obtaining multiple positioning information of the robot; using at least a part of the multiple positioning information to position the robot to obtain the first pose estimation result of the robot, positioning can be performed through a part of the positioning information among the multiple positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0248] In an embodiment of the present disclosure, the target object may be a robot.

[0249] Those skilled in the art can understand that the technical solution described with reference to Figure 9 can be combined with the embodiment described with reference to Figures 1 to 8 so as to have the technical effects achieved by the embodiment described with reference to Figures 1 to 8 For specific details, reference may be made to the above description based on Figures 1 to 8 which will not be elaborated herein.

[0250] The following refers to Figure 10 to describe a robot according to an embodiment of the present disclosure.

[0251] Figure 10 Shows the block diagram of a robot 1000 according to an embodiment of the present disclosure. As Figure 10 shown, the robot 1000 includes multiple sensors 1010 and a positioning device 1020.

[0252] The multiple sensors 1010 are used to obtain multiple positioning information of the robot.

[0253] The positioning device 1020 is used to position the robot by using at least a part of the plurality of positioning information to obtain a first pose estimation result of the robot.

[0254] According to the technical solution provided by the embodiments of the present disclosure, through a plurality of sensors, a plurality of positioning information of the robot is obtained; a positioning device, which is used to position the robot by using at least a part of the plurality of positioning information to obtain a first pose estimation result of the robot, can perform positioning by using a part of the positioning information among the plurality of positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0255] The following refers to Figure 11 Describe Figure 10 An example of the positioning device 1020 in the robot according to the shown embodiment.

[0256] Figure 11 Show Figure 10 A structural block diagram of an example of the positioning device 1020 in the robot according to the shown embodiment. As Figure 11 shown, the positioning device 1020 includes a first positioning module 1110 and a second positioning module 1120.

[0257] The first positioning module 1110 is configured to position the target object by using a second part of the positioning information including the first part of the positioning information among the plurality of positioning information to obtain a second pose estimation result of the target object.

[0258] The second positioning module 1120 is configured to use the first part of the positioning information among the plurality of positioning information and perform pose estimation based on the second pose estimation result to obtain a first pose estimation result of the target object.

[0259] According to the technical solution provided by the embodiments of the present disclosure, the positioning device includes: a first positioning module, which is configured to position the target object by using a second part of the positioning information including the first part of the positioning information among the plurality of positioning information to obtain a second pose estimation result of the target object; a second positioning module, which is configured to use the first part of the positioning information among the plurality of positioning information and perform pose estimation based on the second pose estimation result to obtain a first pose estimation result of the target object. It can perform positioning by using a part of the positioning information among the plurality of positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0260] Refer to the following Figure 12 to describe a robot according to another embodiment of the present disclosure.

[0261] Figure 12 A structural block diagram of a robot 1200 according to another embodiment of the present disclosure is shown. As Figure 12 shown, the difference between the robot 1200 and the Figure 10 robot 1000 shown is that, in addition to including the Figure 10 multiple sensors 1010 and the positioning device 1020 shown, it further includes a sensor synchronization module 1210.

[0262] The sensor synchronization module 1210 is configured to perform time synchronization on the multiple positioning information.

[0263] According to the technical solution provided by the embodiments of the present disclosure, by including: a sensor synchronization module configured to perform time synchronization on the multiple positioning information, it is beneficial to fuse the multiple positioning information, so as to perform positioning through a part of the positioning information among the multiple positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome. Moreover, through the time synchronization between multi-sensor information, the error caused by timestamp errors in the multi-sensor fusion solution can be reduced.

[0264] Refer to the following Figure 13 to describe an example of a first positioning module 1110 in the positioning device 1020 according to the Figure 11 embodiment shown.

[0265] Figure 13 An example of a first positioning module 1110 in the positioning device 1020 according to the Figure 11 embodiment shown is shown. As Figure 13 shown, the first positioning module 1110 includes a first positioning sub-module 1310 and a calculation sub-module 1320.

[0266] The first positioning sub-module 1310 is configured to use the second part of the positioning information to position the target object to obtain multiple positioning results.

[0267] The calculation sub-module 1320 is configured to calculate a second pose estimation result based on the obtained multiple positioning results.

[0268] According to the technical solution provided by the embodiments of the present disclosure, the first positioning module includes: a first positioning sub-module configured to use the second part of positioning information to position the target object to obtain multiple positioning results; a calculation sub-module configured to calculate a second pose estimation result based on the multiple positioning results obtained. Multiple positioning results can be obtained through different positioning information, and at least one of the positioning results is used for positioning. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0269] In an embodiment of the present disclosure, the first positioning module 1110 further includes: a mapping sub-module (not shown in the figure) configured to establish a map using pre-acquired data of the same type as the second part of positioning information for obtaining the second pose estimation result of the target object.

[0270] According to the technical solution provided by the embodiments of the present disclosure, the first positioning module further includes: a mapping sub-module configured to establish a map using pre-acquired data of the same type as the second part of positioning information for obtaining the second pose estimation result of the target object. A map can be established, and multiple positioning results can be obtained through different positioning information on the map, and at least one of the positioning results is used for positioning. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0271] In an embodiment of the present disclosure, the second part of positioning information includes visual positioning information.

[0272] According to the technical solution provided by the embodiments of the present disclosure, by including visual positioning information in the second part of positioning information, positioning can be performed on the map using visual positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0273] The following refers to Figure 14 Describe an example of the first positioning sub-module 1310 in the positioning device 1020 according to the Figure 13 shown embodiment.

[0274] Figure 14 Show Figure 13 a structural block diagram of an example of the first positioning sub-module 1310 in the positioning device 1020 according to the shown embodiment. As Figure 14 shown, the first positioning sub-module 1310 includes a second positioning sub-module 1410 and a third positioning sub-module 1420.

[0275] The second positioning sub-module 1410 is configured to estimate the relative position of the target object in the map by using the positioning information other than the visual positioning information in the second part of the positioning information.

[0276] The third positioning sub-module 1420 is configured to perform positioning on the target object by using the visual positioning information in the second part of the positioning information based on the estimated relative position of the target object in the map, and obtain a visual positioning result.

[0277] According to the technical solution provided by the embodiment of the present disclosure, the first positioning sub-module includes: a second positioning sub-module, configured to estimate the relative position of the target object in the map by using the positioning information other than the visual positioning information in the second part of the positioning information; a third positioning sub-module, configured to perform positioning on the target object by using the visual positioning information in the second part of the positioning information based on the estimated relative position of the target object in the map, and obtain a visual positioning result. Multiple positioning results can be obtained for the map through different positioning information, and at least one of the positioning results is used for positioning. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0278] The following refers to Figure 15 Describe another example of the first positioning sub-module 1310 in the positioning device 1020 according to Figure 13 the embodiment shown.

[0279] Figure 15 Show a structural block diagram of another example of the first positioning sub-module 1310 in the positioning device 1020 according to Figure 13 the embodiment shown. As Figure 15 shown, the first positioning sub-module 1310 includes a coordinate system establishment sub-module 1510 and a coordinate system conversion sub-module 1520.

[0280] The coordinate system establishment sub-module 1510 is configured to establish a first coordinate system.

[0281] The coordinate system conversion sub-module 1520 is configured to obtain a satellite positioning result by converting the second coordinate system to which the satellite positioning information in the second part of the positioning information belongs into the first coordinate system.

[0282] According to the technical solution provided by the embodiments of the present disclosure, the first positioning sub-module includes: a coordinate system establishment sub-module configured to establish a first coordinate system; a coordinate system conversion sub-module configured to obtain a satellite positioning result by converting the second coordinate system to which the satellite positioning information in the second part of the positioning information belongs into the first coordinate system. The satellite positioning result can be obtained through the conversion between different coordinate systems, and positioning is performed using at least one of the positioning results including the satellite positioning result. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0283] In an embodiment of the present disclosure, the coordinate system conversion sub-module 1520 is further configured to: obtain a satellite positioning result by converting the second coordinate system to which the satellite positioning information in the second part of the positioning information belongs and the third coordinate system to which the visual tracking information in the second part of the positioning information belongs into the first coordinate system.

[0284] According to the technical solution provided by the embodiments of the present disclosure, the coordinate system conversion sub-module is further configured to: obtain a satellite positioning result by converting the second coordinate system to which the satellite positioning information in the second part of the positioning information belongs and the third coordinate system to which the visual tracking information in the second part of the positioning information belongs into the first coordinate system. The satellite positioning result can be obtained through the conversion between different coordinate systems, and positioning is performed using at least one of the positioning results including the satellite positioning result. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0285] In an embodiment of the present disclosure, the first positioning sub-module 1310 is further configured to: obtain a wheel speedometer and inertial navigation fusion positioning result by combining the wheel speedometer information and the inertial navigation information in the second part of the positioning information.

[0286] According to the technical solution provided by the embodiments of the present disclosure, the first positioning sub-module is further configured to: obtain a wheel speedometer and inertial navigation fusion positioning result by combining the wheel speedometer information and the inertial navigation information in the second part of the positioning information. Positioning can be performed using a part of the positioning information among multiple positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0287] In one embodiment of the present disclosure, when the first part of the positioning information includes tachometer information and inertial navigation information, the second positioning module 1120 is further configured to: use the tachometer and inertial navigation fusion positioning result to perform pose estimation based on the second pose estimation result to obtain the first pose estimation result of the target object.

[0288] According to the technical solution provided by the embodiment of the present disclosure, the second positioning module is further configured to: use the tachometer and inertial navigation fusion positioning result to perform pose estimation based on the second pose estimation result to obtain the first pose estimation result of the target object. Even in various complex scenarios such as indoor, outdoor, and outdoor semi-occlusion, the positioning of the target object can be completed. Moreover, using the tachometer and inertial navigation fusion positioning result, real-time positioning can be completed.

[0289] In one embodiment of the present disclosure, the calculation sub-module 1320 is further configured to: calculate the second pose estimation result by optimizing the obtained multiple positioning results.

[0290] According to the technical solution provided by the embodiment of the present disclosure, the calculation sub-module is further configured to: calculate the second pose estimation result by optimizing the obtained multiple positioning results. It is possible to perform positioning through a part of the positioning information in multiple positioning information. Therefore, even if some information fails or certain positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in certain cases can be overcome.

[0291] In one embodiment of the present disclosure, the positioning device 1020 is further configured to: combine the tachometer information and inertial navigation information in the first part of the positioning information to obtain the tachometer and inertial navigation fusion positioning result as the first pose estimation result of the target object.

[0292] According to the technical solution provided by the embodiment of the present disclosure, the positioning device is further configured to: combine the tachometer information and inertial navigation information in the first part of the positioning information to obtain the tachometer and inertial navigation fusion positioning result as the first pose estimation result of the target object. Even in various complex scenarios such as indoor, outdoor, and outdoor semi-occlusion, the positioning of the target object can be completed. Moreover, using the tachometer and inertial navigation fusion positioning result, real-time positioning can be completed.

[0293] In one embodiment of the present disclosure, the first pose estimation result is a real-time pose estimation result, and the second pose estimation result is a pose estimation result with a time delay.

[0294] According to the technical solution provided by the embodiments of the present disclosure, since the first pose estimation result is a real-time pose estimation result and the second pose estimation result is a pose estimation result with a time delay, positioning can be performed using a part of the multiple positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome. Moreover, real-time positioning can be completed.

[0295] In an embodiment of the present disclosure, the multiple positioning information includes at least a part of wheel speed meter information, inertial navigation information, satellite positioning information, and visual positioning information.

[0296] According to the technical solution provided by the embodiments of the present disclosure, since the multiple positioning information includes at least a part of wheel speed meter information, inertial navigation information, satellite positioning information, and visual positioning information, positioning can be performed using a part of the multiple positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome.

[0297] Those skilled in the art can understand that the technical solutions described with reference to Figures 10 - 15 can be combined with the embodiments described with reference to Figures 1 to 9 so as to have the technical effects achieved by the embodiments described with reference to Figures 1 to 9 The specific content can be referred to the description above according to Figures 1 to 9 and will not be elaborated herein.

[0298] In an embodiment of the present disclosure, a positioning method is provided, including:

[0299] Obtaining multiple positioning information of a target object;

[0300] Based on a first part of the multiple positioning information, obtaining a first positioning result, where the first positioning result is a real-time positioning result;

[0301] Based on a second part of the multiple positioning information, obtaining a second positioning result, where the second positioning result is a positioning result with a time delay;

[0302] Based on the first positioning result and the second positioning result, providing target positioning information of the target object.

[0303] According to the technical solution provided by the embodiments of the present disclosure, by obtaining multiple positioning information of a target object; based on the first part of the multiple positioning information, a first positioning result is obtained, where the first positioning result is a real-time positioning result; based on the second part of the multiple positioning information, a second positioning result is obtained, where the second positioning result is a positioning result with a time delay; based on the first positioning result and the second positioning result, the target positioning information of the target object is provided. Positioning can be performed through a part of the positioning information in the multiple positioning information. Therefore, even if some information fails or some positioning information cannot be obtained in some scenarios, the pose estimation of the target object can still be performed. That is, the problem of insufficient positioning information in some cases can be overcome. Moreover, real-time positioning can be completed.

[0304] In this embodiment, the first part of the multiple positioning information may include at least a part of wheel speed meter information, inertial navigation information, satellite positioning information, and visual positioning information. For example, wheel speed meter information and inertial navigation information. For example, based on the wheel speed meter information and inertial navigation information, a real-time positioning result can be obtained.

[0305] In this embodiment, the second part of the multiple positioning information may include at least a part of wheel speed meter information, inertial navigation information, satellite positioning information, and visual positioning information. For example, satellite positioning information and / or visual positioning information. For example, based on the satellite positioning information and / or visual positioning information, a positioning result with a time delay can be obtained.

[0306] In this embodiment, the first positioning result and the second positioning result can be used to provide the target positioning information of the target object, which can overcome the problem of insufficient positioning information in some cases, and real-time positioning can be completed.

[0307] Those skilled in the art can understand that the technical solution of this embodiment can be combined with the embodiments described with reference to Figures 1 to 15 so as to have the technical effects achieved by the embodiments described with reference to Figures 1 to 15 The specific content can refer to the above description according to Figures 1 to 15 which will not be elaborated herein.

[0308] The foregoing embodiments describe the internal functions and structures of the positioning device and the robot. In a possible design, the structures of the positioning device and the robot can be implemented as an electronic device, such as Figure 16 shown in, the electronic device 1600 may include a processor 1601 and a memory 1602.

[0309] The memory 1602 is used to store a program for supporting the positioning device to execute the positioning method in any of the above embodiments, and the processor 1601 is configured to execute the program stored in the memory 1602.

[0310] The memory 1602 is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor 1601 to implement the following steps:

[0311] Obtain multiple positioning information of the target object;

[0312] Use the first part of the multiple positioning information to position the target object to obtain a first pose estimation result of the target object.

[0313] In an embodiment of the present disclosure, the using the first part of the multiple positioning information to position the target object to obtain a first pose estimation result of the target object includes:

[0314] Use the second part of the multiple positioning information including the first part of the positioning information to position the target object to obtain a second pose estimation result of the target object;

[0315] Use the first part of the multiple positioning information to perform pose estimation based on the second pose estimation result to obtain a first pose estimation result of the target object.

[0316] In an embodiment of the present disclosure, before the using the first part of the multiple positioning information to position the target object to obtain a first pose estimation result of the target object, the one or more computer instructions are executed by the processor 1601 to implement the following steps:

[0317] Perform time synchronization on the multiple positioning information.

[0318] In an embodiment of the present disclosure, the using the second part of the multiple positioning information including the first part of the positioning information to position the target object to obtain a second pose estimation result of the target object includes:

[0319] Use the second part of the positioning information to position the target object to obtain multiple positioning results;

[0320] Calculate the second pose estimation result based on the obtained multiple positioning results.

[0321] In an embodiment of the present disclosure, using second - part positioning information including the first - part positioning information among the multiple positioning information to position the target object to obtain a second pose estimation result of the target object further includes:

[0322] Establishing a map using data of the same type as the second - part positioning information obtained in advance for obtaining the second pose estimation result of the target object.

[0323] In an embodiment of the present disclosure, the second - part positioning information includes visual positioning information.

[0324] In an embodiment of the present disclosure, using the second - part positioning information to position the target object to obtain multiple positioning results includes:

[0325] Estimating the relative position of the target object in the map using positioning information other than the visual positioning information in the second - part positioning information;

[0326] Based on the estimated relative position of the target object in the map, using the visual positioning information in the second - part positioning information to position the target object to obtain a visual positioning result.

[0327] In an embodiment of the present disclosure, using the second - part positioning information to position the target object to obtain multiple positioning results includes:

[0328] Establishing a first coordinate system;

[0329] Obtaining a satellite positioning result by converting a second coordinate system to which the satellite positioning information in the second - part positioning information belongs to the first coordinate system.

[0330] In an embodiment of the present disclosure, obtaining a satellite positioning result by converting a second coordinate system to which the satellite positioning information in the second - part positioning information belongs to the first coordinate system includes:

[0331] Obtaining a satellite positioning result by converting a second coordinate system to which the satellite positioning information in the second - part positioning information belongs and a third coordinate system to which the visual tracking information in the second - part positioning information belongs to the first coordinate system.

[0332] In an embodiment of the present disclosure, using the second - part positioning information to position the target object to obtain multiple positioning results includes:

[0333] Obtaining a wheel speed meter and inertial navigation fusion positioning result by combining the wheel speed meter information and inertial navigation information in the second - part positioning information.

[0334] In one embodiment of the present disclosure, when the first part of the positioning information includes tachometer information and inertial navigation information, the using of the first part of the positioning information among the multiple positioning information to perform pose estimation based on the second pose estimation result to obtain the first pose estimation result of the target object includes:

[0335] Using the positioning result of the integrated tachometer and inertial navigation, and performing pose estimation based on the second pose estimation result to obtain the first pose estimation result of the target object.

[0336] In one embodiment of the present disclosure, the calculating of the second pose estimation result based on the obtained multiple positioning results includes:

[0337] Calculating the second pose estimation result by optimizing the obtained multiple positioning results.

[0338] In one embodiment of the present disclosure, the using of the first part of the positioning information among the multiple positioning information to position the target object to obtain the first pose estimation result of the target object includes:

[0339] Combining the tachometer information and the inertial navigation information in the first part of the positioning information to obtain the positioning result of the integrated tachometer and inertial navigation as the first pose estimation result of the target object.

[0340] In one embodiment of the present disclosure, the first pose estimation result is a real-time pose estimation result, and the second pose estimation result is a pose estimation result with a time delay.

[0341] In one embodiment of the present disclosure, the multiple positioning information includes at least a part of tachometer information, inertial navigation information, satellite positioning information, and visual positioning information.

[0342] The exemplary embodiment of the present disclosure further provides a computer storage medium for storing computer software instructions used by the positioning device, which includes a program for executing any of the above embodiments, so as to have the technical effects brought by the method.

[0343] Figure 17 It is a schematic structural diagram of a computer system suitable for implementing the positioning method and the robot positioning method according to an embodiment of the present disclosure.

[0344] As Figure 17As shown, computer system 1700 includes a central processing unit (CPU) 1701, which can perform various processes in the embodiments shown in the above-mentioned drawings according to the programs stored in the read-only memory (ROM) 1702 or the programs loaded from the storage section 1708 into the random access memory (RAM) 1703. In the RAM 1703, various programs and data required for the operation of the system 1700 are also stored. The CPU 1701, ROM 1702, and RAM 1703 are connected to each other via a bus 1704. An input / output (I / O) interface 1705 is also connected to the bus 1704.

[0345] The following components are connected to the I / O interface 1705: an input section 1706 including a keyboard, a mouse, etc.; an output section 1707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 1708 including a hard disk, etc.; and a communication section 1709 including a network interface card such as a LAN card, a modem, etc. The communication section 1709 performs communication processing via a network such as the Internet. A drive 1710 is also connected to the I / O interface 1705 as needed. A removable medium 1711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1710 as needed so that a computer program read from it can be installed into the storage section 1708 as needed.

[0346] Specifically, according to the embodiments of the present disclosure, the methods described above with reference to the accompanying drawings can be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product, which includes a computer program tangibly embodied on a machine-readable medium, the computer program including program code for performing the methods in the drawings. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 1709, and / or installed from the removable medium 1711.

[0347] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0348] The units or modules involved in the embodiments described in the present disclosure can be implemented in software or in hardware. The units or modules described can also be provided in a processor, and the names of these units or modules do not, in some cases, constitute a limitation on the units or modules themselves.

[0349] As another aspect, the present disclosure also provides a computer-readable storage medium, which can be the computer-readable storage medium included in the device described in the above embodiments; or it can exist separately and be a computer-readable storage medium not assembled into the device. The computer-readable storage medium stores one or more programs, and the one or more programs are used by one or more processors to execute the methods described in the present disclosure, thereby achieving the technical effects brought by the methods.

[0350] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles applied. Those skilled in the art should understand that the scope of the invention involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, but also covers other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, technical solutions formed by mutually replacing the above features with (but not limited to) technical features having similar functions disclosed in the present disclosure.

Claims

1. A positioning method, characterized in that, Including: Obtaining multiple positioning information of a target object; Positioning the target object using a first part of the multiple positioning information to obtain a first pose estimation result of the target object; The positioning the target object using a first part of the multiple positioning information to obtain a first pose estimation result of the target object includes: Positioning the target object using a second part of the multiple positioning information including the first part of the positioning information to obtain a second pose estimation result of the target object, where the first part of the positioning information includes wheel speed meter information and inertial navigation information, and in addition to the first part of the positioning information, the second part of the positioning information further includes partial positioning information or all positioning information of satellite positioning information and visual positioning information; Based on the second pose estimation result, performing pose estimation using the first part of the multiple positioning information to obtain a first pose estimation result of the target object; The positioning the target object using a second part of the multiple positioning information including the first part of the positioning information to obtain a second pose estimation result of the target object includes: Positioning the target object using the second part of the positioning information to obtain multiple positioning results; Calculating a second pose estimation result based on the obtained multiple positioning results; Wherein, the calculating a second pose estimation result based on the obtained multiple positioning results includes: Calculating a second pose estimation result by optimizing the obtained multiple positioning results; Wherein, the optimization specifically is: Obtaining a current image and the previous N frames of images according to visual positioning information and / or visual tracking information; Extracting visual features in the current image, matching them with the visual features extracted in the previous N frames of images, and combining the internal and external parameter calibration of the camera to obtain a first cost function related to the feature coordinates and the pose of the target object; Determining a second cost function related to the poses of two consecutive target objects through the fusion of the wheel speed meter and inertial navigation; Obtaining a satellite positioning result according to the satellite positioning information; Determining a third cost function related to the pose of the target object and six-degree-of-freedom calibration according to the satellite positioning result; Optimizing the sum of the first cost function, the second cost function, and the third cost function.

2. The method according to claim 1, characterized in that Before the positioning the target object using a first part of the multiple positioning information to obtain a first pose estimation result of the target object, it includes: Performing time synchronization on the multiple positioning information.

3. The method according to claim 1, wherein The positioning the target object using a second part of the multiple positioning information including the first part of the positioning information to obtain a second pose estimation result of the target object further includes: Establishing a map using pre-acquired data of the same type as the second part of the positioning information for obtaining a second pose estimation result of the target object.

4. The method according to claim 3, characterized in that, The second part of the positioning information includes visual positioning information.

5. The method according to claim 4, characterized in that, The positioning the target object using the second part of the positioning information to obtain multiple positioning results includes: Estimate the relative position of the target object in the map using the positioning information other than the visual positioning information in the second part of the positioning information; Based on the estimated relative position of the target object in the map, use the visual positioning information in the second part of the positioning information to position the target object and obtain a visual positioning result.

6. The method according to claim 1, wherein The positioning of the target object using the second part of the positioning information to obtain multiple positioning results includes: Establish a first coordinate system; Obtain a satellite positioning result by converting the second coordinate system to which the satellite positioning information in the second part of the positioning information belongs to the first coordinate system.

7. The method according to claim 6, characterized in that, The obtaining of the satellite positioning result by converting the second coordinate system to which the satellite positioning information in the second part of the positioning information belongs to the first coordinate system includes: Obtain a satellite positioning result by converting the second coordinate system to which the satellite positioning information in the second part of the positioning information belongs and the third coordinate system to which the visual tracking information in the second part of the positioning information belongs to the first coordinate system.

8. The method according to claim 1, characterized in that The positioning of the target object using the second part of the positioning information to obtain multiple positioning results includes: Obtain a wheel speed meter and inertial navigation fusion positioning result by combining the wheel speed meter information and inertial navigation information in the second part of the positioning information.

9. The method according to claim 8, characterized in that, When the first part of the positioning information includes wheel speed meter information and inertial navigation information, the using of the first part of the positioning information in the multiple positioning information to perform pose estimation based on the second pose estimation result to obtain the first pose estimation result of the target object includes: Use the wheel speed meter and inertial navigation fusion positioning result to perform pose estimation based on the second pose estimation result to obtain the first pose estimation result of the target object.

10. The method according to claim 1 or 2, characterized in that, The positioning of the target object using the first part of the positioning information in the multiple positioning information to obtain the first pose estimation result of the target object includes: Obtain a wheel speed meter and inertial navigation fusion positioning result by combining the wheel speed meter information and inertial navigation information in the first part of the positioning information as the first pose estimation result of the target object.

11. The method according to any one of claims 1-9, characterized in that, The first pose estimation result is a real-time pose estimation result, and the second pose estimation result is a pose estimation result with a time delay.

12. The method according to any one of claims 1-9, characterized in that, The multiple positioning information includes at least a part of wheel speed meter information, inertial navigation information, satellite positioning information, and visual positioning information.

13. A positioning device, characterized in that, Including: An acquisition module configured to acquire multiple positioning information of a target object; A positioning module configured to position the target object using the first part of the positioning information in the multiple positioning information to obtain the first pose estimation result of the target object; The positioning of the target object using the first part of the positioning information in the multiple positioning information to obtain the first pose estimation result of the target object includes: Using the second part of the multiple positioning information that includes the first part of the positioning information to position the target object, so as to obtain a second pose estimation result of the target object, where the first part of the positioning information includes wheel speed meter information and inertial navigation information, and in addition to the first part of the positioning information, the second part of the positioning information further includes partial positioning information or all positioning information of satellite positioning information and visual positioning information; Using the first part of the multiple positioning information, performing pose estimation based on the second pose estimation result to obtain a first pose estimation result of the target object; The using the second part of the multiple positioning information that includes the first part of the positioning information to position the target object, so as to obtain a second pose estimation result of the target object, includes: Using the second part of the positioning information to position the target object to obtain multiple positioning results; Calculating a second pose estimation result based on the obtained multiple positioning results; Wherein, the calculating the second pose estimation result based on the obtained multiple positioning results includes: Calculating the second pose estimation result by optimizing the obtained multiple positioning results; Wherein, the optimization specifically is: Obtaining the current image and the previous N frames of images according to the visual positioning information and / or visual tracking information; Extracting visual features in the current image, matching the visual features extracted from the previous N frames of images, and combining the internal and external parameter calibration of the camera to obtain a first cost function related to the feature coordinates and the pose of the target object; Determining a second cost function related to the poses of the front and rear target objects through the fusion of the wheel speed meter and inertial navigation; Obtaining a satellite positioning result according to the satellite positioning information; Determining a third cost function related to the pose of the target object and the six-degree-of-freedom calibration according to the satellite positioning result; Optimizing the sum of the first cost function, the second cost function, and the third cost function.

14. A robot positioning method, characterized in that, Including: Obtaining multiple positioning information of the robot; Using the first part of the multiple positioning information to position the robot to obtain a first pose estimation result of the robot; The using the first part of the multiple positioning information to position the robot to obtain a first pose estimation result of the robot, includes: Using the second part of the multiple positioning information that includes the first part of the positioning information to position the robot to obtain a second pose estimation result of the robot, where the first part of the positioning information includes wheel speed meter information and inertial navigation information, and in addition to the first part of the positioning information, the second part of the positioning information further includes partial positioning information or all positioning information of satellite positioning information and visual positioning information; Using the first part of the multiple positioning information, performing pose estimation based on the second pose estimation result to obtain a first pose estimation result of the robot; Using the second part of the positioning information including the first part of the positioning information among the multiple positioning information to position the target object to obtain the second pose estimation result of the target object, including: Using the second part of the positioning information to position the target object to obtain multiple positioning results; Calculating the second pose estimation result based on the obtained multiple positioning results; Wherein, the calculating the second pose estimation result based on the obtained multiple positioning results includes: Calculating the second pose estimation result by optimizing the obtained multiple positioning results; Wherein, the optimization specifically is: Obtaining the current image and the previous N frames of images according to the visual positioning information and / or visual tracking information; Extracting visual features in the current image, matching the visual features extracted in the previous N frames of images, and combining the internal and external parameter calibration of the camera to obtain a first cost function related to the feature coordinates and the pose of the target object; Determining a second cost function related to the poses of the front and rear target objects through the fusion of the wheel speedometer and inertial navigation; Obtaining the satellite positioning result according to the satellite positioning information; Determining a third cost function related to the pose of the target object and the six-degree-of-freedom calibration according to the satellite positioning result; Optimizing the sum of the first cost function, the second cost function, and the third cost function.

15. A robot, characterized in that, Including: Multiple sensors for obtaining multiple positioning information of the robot; A positioning device for positioning the robot using the first part of the positioning information among the multiple positioning information to obtain the first pose estimation result of the robot; The positioning device includes: A first positioning module configured to position the robot using the second part of the positioning information including the first part of the positioning information among the multiple positioning information to obtain the second pose estimation result of the robot, wherein the first part of the positioning information includes wheel speedometer information and inertial navigation information, and in addition to the first part of the positioning information, the second part of the positioning information further includes partial positioning information or all positioning information of satellite positioning information and visual positioning information; A second positioning module configured to perform pose estimation based on the second pose estimation result using the first part of the positioning information among the multiple positioning information to obtain the first pose estimation result of the robot; Using the second part of the positioning information including the first part of the positioning information among the multiple positioning information to position the target object to obtain the second pose estimation result of the target object, including: Using the second part of the positioning information to position the target object to obtain multiple positioning results; Calculating the second pose estimation result based on the obtained multiple positioning results; Wherein, the calculating the second pose estimation result based on the obtained multiple positioning results includes: Calculating the second pose estimation result by optimizing the obtained multiple positioning results; Wherein, the optimization specifically is: Obtaining the current image and the previous N frames of images according to the visual positioning information and / or visual tracking information; Extract visual features from the current image and match them with the visual features extracted from the previous N frames of images. Combine the internal and external parameter calibrations of the camera to obtain a first cost function related to the feature coordinates and the pose of the target object. Determine a second cost function related to the poses of the front and rear target objects through the fusion of the wheel speed sensor and inertial navigation. Obtain the satellite positioning result according to the satellite positioning information. Determine a third cost function related to the pose of the target object and the six-degree-of-freedom calibration according to the satellite positioning result. Optimize the sum of the first cost function, the second cost function, and the third cost function.

16. The robot according to claim 15, wherein, Further includes: A sensor synchronization module configured to perform time synchronization on the multiple positioning information.

17. The robot according to claim 15, characterized in that, The first positioning module further includes: A mapping sub-module configured to establish a map using pre-acquired data of the same type as the second part of the positioning information for obtaining the second pose estimation result of the robot.

18. The robot according to claim 17, characterized in that, The second part of the positioning information includes visual positioning information.

19. The robot according to claim 18, characterized in that, The first positioning sub-module includes: A second positioning sub-module configured to estimate the relative position of the robot in the map using the positioning information other than the visual positioning information in the second part of the positioning information. A third positioning sub-module configured to position the robot using the visual positioning information in the second part of the positioning information based on the estimated relative position of the robot in the map to obtain a visual positioning result.

20. The robot according to claim 15, characterized in that, The first positioning sub-module includes: A coordinate system establishment sub-module configured to establish a first coordinate system. A coordinate system conversion sub-module configured to obtain the satellite positioning result by converting the second coordinate system to which the satellite positioning information in the second part of the positioning information belongs to the first coordinate system.

21. The robot according to claim 20, wherein The coordinate system conversion sub-module is further configured to: Obtain the satellite positioning result by converting the second coordinate system to which the satellite positioning information in the second part of the positioning information belongs and the third coordinate system to which the visual tracking information in the second part of the positioning information belongs to the first coordinate system.

22. The robot according to claim 15, characterized in that, The first positioning sub-module is further configured to: Obtain the wheel speed sensor and inertial navigation fusion positioning result by combining the wheel speed sensor information and inertial navigation information in the second part of the positioning information.

23. The robot according to claim 22, wherein, When the first part of the positioning information includes wheel speed sensor information and inertial navigation information, the second positioning module is further configured to: Use the wheel speed sensor and inertial navigation fusion positioning result to perform pose estimation based on the second pose estimation result to obtain the first pose estimation result of the robot.

24. The robot according to claim 15 or 16, characterized in that, The positioning device is further configured to: Obtain the wheel speed sensor and inertial navigation fusion positioning result by combining the wheel speed sensor information and inertial navigation information in the first part of the positioning information as the first pose estimation result of the robot.

25. The robot according to any one of claims 15-23, characterized in that, The first pose estimation result is a real-time pose estimation result, and the second pose estimation result is a pose estimation result with a time delay.

26. The robot according to any one of claims 15 - 23, characterized in that, The multiple positioning information includes at least a part of wheel speed sensor information, inertial navigation information, satellite positioning information, and visual positioning information.

27. A positioning method, characterized in that, Includes: Obtain multiple positioning information of the target object; Obtain a first positioning result based on a first part of the multiple positioning information, where the first positioning result is a real-time positioning result, and the first part of the multiple positioning information includes wheel speed meter information and inertial navigation information; Obtain a second positioning result based on a second part of the multiple positioning information, where the second positioning result is a positioning result with a time delay, and in addition to the first part of the multiple positioning information, the second part of the multiple positioning information further includes partial positioning information or all positioning information in satellite positioning information and visual positioning information; Provide target positioning information of the target object based on the first positioning result and the second positioning result; Use a second part of the positioning information including the first part of the positioning information in the multiple positioning information to position the target object to obtain a second pose estimation result of the target object, including: Use the second part of the positioning information to position the target object to obtain multiple positioning results; Calculate a second pose estimation result based on the obtained multiple positioning results; Wherein, the calculating the second pose estimation result based on the obtained multiple positioning results includes: Calculate the second pose estimation result by optimizing the obtained multiple positioning results; Wherein, the optimization is specifically: Obtain the current image and the previous N frames of images according to visual positioning information and / or visual tracking information; Extract visual features in the current image, match them with the visual features extracted in the previous N frames of images, and combine the internal and external parameter calibrations of the camera to obtain a first cost function related to the feature coordinates and the pose of the target object; Determine a second cost function related to the poses of the front and rear target objects through the fusion of the wheel speed meter and inertial navigation; Obtain a satellite positioning result according to the satellite positioning information; Determine a third cost function related to the pose of the target object and the six-degree-of-freedom calibration according to the satellite positioning result; Optimize the sum of the first cost function, the second cost function, and the third cost function.

28. An electronic device, characterized in that, Include a memory and a processor; wherein, The memory is used to store one or more computer instructions, and the one or more computer instructions are executed by the processor to implement the method according to any one of claims 1-12, 14, 27.

29. A readable storage medium storing computer instructions thereon, characterized in that, When the computer instruction is executed by the processor, it implements the method according to any one of claims 1-12, 14, 27.

Images