Robot positioning, devices, scheduling equipment, storage media and program products

Abstract

The disclosed embodiments provide a robot positioning, device, scheduling equipment, storage medium and program product. For the situation of robot team combination, the method includes: determining a first target image matching a first image collected by a first robot at a teaming point from an environmental image library; acquiring a second image collected by a second robot at a teaming point; the first robot arrives at the teaming point earlier than the second robot, and the second robot is the head robot in the original team, and the first robot and the second robot are combined into a new team at the teaming point; judging whether the posture of the second robot is consistent with that of the first robot at the teaming point based on the first image and the second image; if consistent, positioning the second robot based on the first target image, thereby realizing positioning of the second robot based on the positioning result of the first robot, reducing the data processing amount of the scheduling equipment and improving the positioning efficiency.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent warehousing technology, and in particular to a robot positioning, device, scheduling equipment, storage medium and program product. Background Art

[0002] Warehousing is an important part of the logistics process. Robots can replace manual labor in handling goods and play an important role in smart warehousing logistics.

[0003] In order to build a map of the warehouse system or navigate the robot, the robot needs to be positioned. The commonly used visual positioning technology is SLAM (Simultaneous Localization and Mapping) technology. For SLAM, closed-loop detection is an indispensable step in building maps and robot navigation.

[0004] When robots move in a warehouse in a fleet, the server or scheduling device needs to locate the robot based on the images collected by each robot in the fleet, which results in a large number of repeated calculation steps in the server or scheduling device, resulting in large server computing overhead, which in turn leads to high robot positioning cost and low efficiency. Summary of the invention

[0005] The present disclosure provides a robot positioning, device, scheduling equipment, storage medium and program product. For the situation of robot fleet combination, the scheduling equipment omits the step of performing closed-loop detection or image matching on the image collected by the second robot at the combination fixed point through image inheritance, thereby reducing the computational overhead of the scheduling equipment, thereby reducing the cost of robot positioning and improving the efficiency of robot positioning.

[0006] In a first aspect, an embodiment of the present disclosure provides a robot positioning method, which is applied to a scheduling device, and the method includes:

[0007] According to a first image collected by the first robot at the teaming fixed point, a first target image matching the first image is determined from the environmental image library; a second image collected by the second robot at the teaming fixed point is obtained; according to the first image and the second image, whether a first posture of the second robot at the teaming fixed point is consistent with a second posture of the first robot at the teaming fixed point is determined; if the first posture is consistent with the second posture, the second robot is positioned according to the first target image to update the environmental image library or navigate the second robot; wherein, at the teaming fixed point, the first robot and the second robot form a combined vehicle team, and the first robot reaches the teaming fixed point earlier than the second robot, the first robot walks in the form of a first sub-vehicle team before reaching the teaming fixed point, the first robot is any one of the first sub-vehicle team, the second robot walks in the form of a second sub-vehicle team before reaching the teaming fixed point, the second robot is the head robot of the second sub-vehicle team, and the number of robots included in the first sub-vehicle team and the second sub-vehicle team is at least 1.

[0008] Optionally, determining a first target image matching the first image from an environment image library according to a first image collected by the first robot at a team-forming fixed point includes:

[0009] Based on the closed-loop detection algorithm, according to the first image, it is determined whether there is an environmental image matching the first image in the environmental image library; if so, the closed-loop detection is successful, and the matched environmental image is determined as the first target image of the first image.

[0010] Optionally, if the first posture is inconsistent with the second posture, the method further includes:

[0011] Adjust the posture of the second robot according to the first posture and the second posture; obtain at least one frame of the third image captured by the second robot during the position adjustment of the second robot; determine whether there is at least one frame of the third image corresponding to the third posture of the second robot that is consistent with the first posture; if so, locate the second robot according to the first target image to update the environmental image library or navigate the second robot.

[0012] Optionally, if the first posture is inconsistent with the second posture, the method further includes:

[0013] According to the second image, a second target image matching the second image is determined from the environment image library; according to the second target image, the environment image library is updated or navigation of the second robot is performed.

[0014] Optionally, the method further includes:

[0015] When determining the team formation point, the sensors turned on by the second robot are determined according to the role of the second robot in the combined team, wherein the roles in the team include the head robot, the tail robot and the middle robot.

[0016] In a second aspect, the present disclosure also provides another robot positioning method, which is applied to a scheduling device and includes:

[0017] According to a first image collected by a first robot at a team fixed point, a first target image matching the first image is determined from an environmental image library; state parameters of the first robot when collecting the first image are obtained, and the first image and the state parameters are sent to a second robot to control the second robot to adjust the state of the second robot based on the state parameters; wherein the state parameters include the first posture of the first robot when collecting the first image; when a posture consistency message is received from the second robot, the second robot is positioned according to the first target image to update the environmental image library or navigate the second robot, wherein the posture consistency message is generated by the second robot when it determines that the second posture of the second robot at the team fixed point is consistent with the first posture.

[0018] Optionally, the state parameters also include a first state parameter, which is used to describe a position parameter of a sensor that is turned on when the first robot collects the first image; when the team fixed point is a team fixed point, the first state parameter is used to control the second robot to turn on the sensor at the corresponding position in the first state parameter, so as to perform image collection based on each turned on sensor.

[0019] In a third aspect, an embodiment of the present disclosure further provides a robot positioning device, which is applied to a scheduling device, and includes:

[0020] a first determination module, for determining a first target image matching the first image from the environment image library according to a first image collected by the first robot at the teaming fixed point; a second image acquisition module, for acquiring a second image collected by the second robot at the teaming fixed point; a posture determination module, for judging whether the first posture of the second robot at the teaming fixed point is consistent with the second posture of the first robot at the teaming fixed point according to the first image and the second image; an image inheritance first module, for locating the second robot according to the first target image if the first posture is consistent with the second posture, so as to update the environment image library or navigate the second robot; wherein the first robot and the second robot form a combined vehicle team at the teaming fixed point, and the first robot reaches the teaming fixed point earlier than the second robot, the first robot walks in the form of a first sub-vehicle team before reaching the teaming fixed point, the first robot is any one of the first sub-vehicle team, the second robot walks in the form of a second sub-vehicle team before reaching the teaming fixed point, the second robot is the head robot of the second sub-vehicle team, and the number of robots included in the first sub-vehicle team and the second sub-vehicle team is at least 1 respectively.

[0021] In a fourth aspect, an embodiment of the present disclosure further provides a robot positioning device, which is applied to a scheduling device, and includes:

[0022] A second determination module is used to determine a first target image matching the first image collected by the first robot at the team fixed point from the environmental image library; a state parameter sending module is used to obtain the state parameters of the first robot when collecting the first image, and send the first image and the state parameters to the second robot, so as to control the second robot to adjust the state of the second robot based on the state parameters; wherein the state parameters include the first posture of the first robot when collecting the first image; an image inheritance second module is used to position the second robot according to the first target image when receiving a posture consistency message fed back by the second robot, so as to update the environmental image library or navigate the second robot, wherein the posture consistency message is generated by the second robot when determining that the second posture of the second robot at the team fixed point is consistent with the first posture.

[0023] In a fifth aspect, an embodiment of the present disclosure further provides a scheduling device, comprising: a memory and at least one processor; the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the robot positioning method provided by any embodiment of the present disclosure.

[0024] In a sixth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, a robot positioning method as provided in any embodiment of the present disclosure is implemented.

[0025] In a seventh aspect, an embodiment of the present disclosure further provides a computer program product, including a computer program, which, when executed by a processor, implements a robot positioning method as provided in any embodiment of the present disclosure.

[0026] The robot positioning, device, scheduling equipment, storage medium and program product provided by the embodiments of the present disclosure are aimed at the scenario of robots or robot fleets forming a team. The first robot or the fleet to which the first robot belongs reaches the teaming point earlier than the second robot or the fleet to which the second robot belongs. Through feature matching, a first target image matching the first image is determined from the environmental image library. Based on the first image and the second image successively captured by the first robot and the second robot at the teaming point, it is judged whether the positions and postures of the first robot and the second robot at the teaming point, that is, the first posture and the second posture are consistent. If they are consistent, the second robot inherits the positioning result of the first robot, that is, the second robot is positioned based on the first target image corresponding to the first robot, thereby omitting the step of matching the second image from the environmental image library, reducing the computational overhead of the scheduling equipment, and improving the efficiency of robot positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0028] Figure 1 A diagram of an application scenario of the robot positioning method provided by an embodiment of the present disclosure;

[0029] Figure 2 A flowchart of a robot positioning method provided by one embodiment of the present disclosure;

[0030] Figure 3A For this disclosure Figure 2 A schematic diagram of the positions of the robots before forming a team in the illustrated embodiment;

[0031] Figure 3B For this disclosure Figure 3A A schematic diagram of the positions of the robots after forming a team in the embodiment shown;

[0032] Figure 4 A flowchart of a robot positioning method provided by another embodiment of the present disclosure;

[0033] Figure 5A flowchart of a robot positioning method provided by another embodiment of the present disclosure;

[0034] Figure 6 A schematic diagram of the structure of a robot positioning device provided by an embodiment of the present disclosure;

[0035] Figure 7 A schematic structural diagram of a robot positioning device provided by another embodiment of the present disclosure;

[0036] Figure 8 A schematic diagram of the structure of a scheduling device provided for one embodiment of the present disclosure.

[0037] The above drawings show clear embodiments of the present disclosure, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the present disclosure in any way, but to illustrate the concepts of the present disclosure to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0038] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0039] The technical solution of the present invention and how the technical solution of the present invention solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0040] The application scenarios of the embodiments of the present disclosure are explained below:

[0041] Figure 1 An application scenario diagram of the robot positioning method provided by the embodiment of the present disclosure, such as Figure 1 As shown, Figure 1As shown, when constructing a warehouse system map, the robot 110 needs to be positioned. The main process of the positioning technology based on visual SLAM is as follows: the robot 110 walks in the warehouse system, such as walking in the aisles between shelves. The robot 110 perceives the environment through sensors arranged thereon, such as image sensors, inertial sensors, etc., and uploads the detection images collected by the sensors to the scheduling device 120. The scheduling device 120 determines the camera pose corresponding to each frame of the detection image based on the detection images received at each moment, and performs loop detection or closed-loop detection on each frame of the detection image based on the image library to determine whether the robot has reached the position when the frame of image was collected before, and locates the robot 110. Then, based on the loop detection results and the camera pose corresponding to each frame of the detection image, the image in the image library is optimized to obtain a globally consistent trajectory and map, thereby realizing the construction or optimization of the warehouse system map.

[0042] Loop detection is a key step in robot positioning based on SLAM technology. It mainly compares the image currently collected by the robot 110 with each frame of image in the pre-stored environmental image library or map to determine whether the robot 110 has reached the location before, so as to locate the robot 110 or adjust the constructed map.

[0043] In some embodiments, in order to improve the efficiency of picking up and placing goods or the efficiency of building maps, the robot 110 will move in the form of a convoy, that is, a convoy composed of multiple robots 110 will move in the form of a robot convoy.

[0044] In the robot fleet, the roles of robot 110 include the head robot, the tail robot and the middle robot. The head robot is the first robot in the robot fleet along the walking direction, the tail robot is the last robot in the robot fleet along the walking direction, and the middle robots are the robots located between the tail robot and the head robot.

[0045] When performing tasks in the form of a robot fleet, such as building maps, patrolling, picking up and placing goods, etc., each robot 110 in the robot fleet needs to perform environmental detection based on sensors, and then the scheduling device 120 or the server performs positioning, obstacle avoidance and other operations based on the data collected by the robot's sensors. When the robots 110 move in the form of a fleet, the amount of data that the scheduling device 120 or the server needs to process increases exponentially compared to a single robot 110.

[0046] In order to reduce the data processing amount of the scheduling device 120, the present disclosure targets the situation where robots or robot teams are formed into teams. By inheriting the positioning result or the first target image of the robot (the first robot) of the team that arrives at the teaming point first, the positioning of the head robot (the second robot) of the team that arrives later is performed, thereby omitting the step of performing target image matching or loop detection on the image (the second image) collected by the second robot at the teaming point, thereby reducing the data processing amount of the scheduling device and improving the positioning efficiency of the robot.

[0047] Figure 2 A flowchart of a robot positioning method provided by an embodiment of the present disclosure is shown in FIG. Figure 2 As shown, the robot positioning method is applicable to a warehousing system and can be executed by a scheduling device. The robot positioning method provided in this embodiment includes the following steps:

[0048] Step S201: According to a first image collected by a first robot at a team-forming fixed point, a first target image matching the first image is determined from an environment image library.

[0049] The teaming point is a location where the robots are teamed, and can be a location where two or more robots are teamed. The environment image library includes each frame image corresponding to the map of the established storage system.

[0050] In some embodiments, the first robot and the second robot form a team at a teaming point to form a robot fleet.

[0051] In some embodiments, the team of the first robot is teamed with the second robot at a teaming point to form a new robot team.

[0052] In some embodiments, the fleet of vehicles that the first robot and the second robot are in is teamed up at a teaming point to form a new robot fleet.

[0053] In some embodiments, the team of vehicles in which the first robot is located is teamed up with the team of vehicles in which the second robot is located at a teaming point to form a new robot team.

[0054] Among them, the first robot arrives at the team point earlier than the second robot.

[0055] Specifically, when the first robot walks to the teaming point as a single robot or in a convoy, the first robot collects a first image at the teaming point based on the turned-on sensor, and uploads the first image to the scheduling device. The scheduling device traverses each frame image in the environmental image library to determine a first target image that matches the first image.

[0056] Specifically, the scheduling device can extract image features of the first image, and determine, by feature matching, from the environmental image library an image that has the most features matching the first image or has the highest similarity to the first image as the first target image of the first image.

[0057] Furthermore, the scheduling device may calculate the similarity between each frame image in the environment image library and the first image, and determine, from each frame image whose similarity is greater than a preset value, an image with the greatest similarity to the first image as the first target image of the first image.

[0058] Specifically, a first target image matching the first image can be determined from the environment image library according to the first image and the odometer corresponding to the first image. The odometer corresponding to the first image can be determined according to data collected by sensors such as an inertial sensor and a wheel speed meter of the first robot that collects the first image.

[0059] Optionally, determining a first target image matching the first image from an environment image library according to a first image collected by the first robot at a team-forming fixed point includes:

[0060] Based on the closed-loop detection algorithm, according to the first image, it is determined whether there is an environmental image matching the first image in the environmental image library; if so, the closed-loop detection is successful, and the matched environmental image is determined as the first target image of the first image.

[0061] Among them, the closed-loop detection algorithm can be any closed-loop detection algorithm, such as BA (Bundle Adjustment, bundle adjustment method), bag-of-words model, similarity calculation, deep learning and other algorithms.

[0062] Specifically, after obtaining the first image, the scheduling device can extract features of the first image, and then determine whether there is an image matching the first image in the environmental image library based on the closed-loop detection algorithm and the features of the first image. If there is an image matching the first image, the closed-loop detection is successful, and an image matching the first image, i.e., the first target image, is output.

[0063] Specifically, each frame image in the environment image library can be updated based on the first image and the first target image, that is, the result of closed-loop detection of the first image, so as to reduce the inter-frame error of the environment image library, thereby reducing the navigation or positioning error of the robot.

[0064] Step S202, obtaining a second image captured by the second robot at the team fixed point.

[0065] Wherein, at the team formation point, the first robot and the second robot form a combined vehicle team, and the first robot reaches the team formation point earlier than the second robot, the first robot walks in the form of a first sub-vehicle team before reaching the team formation point, the first robot is any robot in the first sub-vehicle team, the second robot walks in the form of a second sub-vehicle team before reaching the team formation point, the second robot is the head robot of the second sub-vehicle team, and the number of robots included in the first sub-vehicle team and the second sub-vehicle team respectively is at least 1.

[0066] The combined vehicle fleet is composed of a first sub-vehicle fleet and a second sub-vehicle fleet, and in the combined vehicle fleet, the first robot is located in front of the second robot along the walking direction.

[0067] When the number of robots included in the first sub-team is 1, before walking to the team-forming point, the first robot walks as a single robot, that is, it does not team up with other robots; when the number of robots included in the second sub-team is 1, before walking to the team-forming point, the second robot walks as a single robot, that is, it does not team up with other robots.

[0068] In some embodiments, the robots mentioned in the present disclosure, including the first robot and the second robot, are the same robots, the type, size and other parameters of the robots are the same, and the positions and quantities of the visual sensors on the robots are the same.

[0069] Specifically, the teaming point is the position point where the first sub-carriage where the first robot is located and the second sub-carriage where the second robot is located are combined into a combined car team. The first sub-carriage and the second sub-carriage can reach the teaming point along the same or different paths, and the first sub-carriage reaches the teaming point earlier than the second sub-carriage.

[0070] For example, Figure 3A For this disclosure Figure 2 A schematic diagram of the positions of the robots before forming a team in the embodiment shown, Figure 3B For this disclosure Figure 3A The schematic diagram of the positions of the robots after forming a team in the embodiment shown in the figure is combined with Figure 3A and Figure 3B It can be seen that since the walking path and walking direction of the first sub-carriage and the robot 303 are the same after the team formation point C1, the first sub-carriage and the robot 303 can be combined at the team formation point to form a combined car. Figure 3AAs shown, before reaching the team formation point, the first sub-team includes robot 301 and robot 302. In the first sub-team, robot 301 is the head robot and robot 302 is the tail robot. The first sub-team goes straight along road r2 to road r3, and its walking direction is shown by the dotted arrow d1; robot 303 needs to turn left along road r1 to road r3 and go straight on road r3, and its walking direction is shown by the dotted arrow d2. The first sub-team arrives at the team formation point C1 earlier than robot 303. After robot 303 arrives at the team formation point C1, it forms a new team with the first sub-team that arrived previously, that is, a combined team, which includes robots 301, robot 302 and robot 303 in the walking direction. Among them, the first robot can be robot 301 or robot 302, and the second robot is robot 303.

[0071] In some embodiments, if the second sub-team includes multiple robots, the second robot is the head robot of the second sub-team.

[0072] In some embodiments, the first robot and the second robot have the same role in the combined vehicle team, such as both are robots in the team.

[0073] In some embodiments, the first robot is the leading robot of the combined vehicle fleet, and the second robot is the tail robot or the middle robot of the combined vehicle fleet.

[0074] In some embodiments, at least one visual sensor, such as a laser sensor, an image sensor, etc., may be provided on each side of the robot to collect images of the robot's external environment. For example, at least one visual sensor may be provided on each side of the robot chassis, and the visual sensor may also be provided on the temporary storage shelf or the pick-up and release device of the robot. The visual sensor may be divided into a forward-looking sensor, a rear-looking sensor, and a side-looking sensor, wherein the forward-looking sensor is used to collect images of the environment in front of the robot in the walking direction, the rear-looking sensor is used to collect images of the environment behind the robot in the walking direction, and the side-looking sensor is used to collect images of the environment on the left or right side of the robot in the walking direction.

[0075] In some embodiments, when the robot is walking in the form of a robot convoy or alone, the robot can turn on various visual sensors provided on it, such as the above-mentioned forward-looking sensor, rear-looking sensor and side-looking sensor.

[0076] Specifically, when the robot is walking in the form of a robot team, or when the role of the robot in the robot team is updated, the sensor that the robot needs to turn on can be determined according to the role of the robot in the robot team. The role of the robot in the team includes the team leader robot, the team middle robot and the team tail robot, or can only include the team leader robot and the team middle robot.

[0077] In some embodiments, the sensors turned on by the head robot in the robot fleet can be a forward-looking sensor and various side-looking sensors, the sensors turned on by the robots in the middle can be various side-looking sensors, and the sensors turned on by the tail robot can be a rear-looking sensor and various side-looking sensors.

[0078] In some embodiments, the sensors turned on by the head robot of the robot fleet may be a front-view sensor and various side-view sensors, and the sensors turned on by the robots in the middle and the rear of the team may be a rear-view sensor and various side-view sensors.

[0079] Specifically, for robots traveling in a convoy or a robot fleet, the sensors turned on by the robots can collect images of the robot's external environment at a set period. The dispatching device performs steps such as feature extraction, image matching, and odometer calculation for the images of the external environment uploaded by each robot to locate the robot or reconstruct the map.

[0080] When the first robot arrives at the team fixed point, the first robot collects a first image at the team fixed point based on the sensor turned on by the first robot, and the first image is uploaded to the scheduling device; the scheduling device locates the first robot based on the first image; and when the second robot arrives at the team fixed point, the second robot collects a second image at the team fixed point based on the sensor turned on by the second robot, and the second image is uploaded to the scheduling device.

[0081] Specifically, the position corresponding to the image uploaded by the robot can be determined by using inertial sensors, gyroscopes, tachometers and other devices provided on the robot (the first robot or the second robot), thereby obtaining the images collected by the first robot and the second robot at a fixed point in the team, that is, obtaining the first image or the second image.

[0082] Step S203: Determine, based on the first image and the second image, whether the first posture of the second robot at the team-forming fixed point is consistent with the second posture of the first robot at the team-forming fixed point.

[0083] Among them, the first posture is the posture of the first robot when the team is fixed at a fixed point to collect the first image, and the second posture is the posture of the second robot when the team is fixed at a fixed point to collect the second image.

[0084] Specifically, it is possible to extract image features of the first image and the second image, and determine whether the first posture of the second robot at the team-forming fixed point is consistent with the second posture of the first robot at the team-forming fixed point based on image feature matching. If the image features of the first image and the second image match or the image similarity is greater than a preset value, it is determined that the first posture is consistent with the second posture.

[0085] Specifically, whether the first posture is consistent with the second posture may be determined based on image features of the same key area in the first image and the second image.

[0086] Step S204: if the first posture is consistent with the second posture, positioning the second robot is performed according to the first target image to update the environment image library or to navigate the second robot.

[0087] Specifically, if the first posture and the second posture are consistent, it can be determined that the first robot and the second robot have the same orientation when they arrive at the team's fixed point. The second robot can be positioned directly based on the positioning result of the first robot or the result of the loop detection, that is, the first target image, thereby omitting the process of the scheduling device searching for the second target image that matches the second image in the environmental image library, thereby reducing the computational overhead of the scheduling device.

[0088] The robot positioning method provided by the disclosed embodiment aims at a scenario in which robots or robot fleets are formed. A first robot or a fleet to which the first robot belongs reaches a teaming point earlier than a second robot or a fleet to which the second robot belongs. A first target image matching the first image is determined from an environmental image library through feature matching. Based on the first image and the second image successively captured by the first robot and the second robot at the teaming point, it is determined whether the positions and postures of the first robot and the second robot at the teaming point, that is, the first position and the second position, are consistent. If they are consistent, the second robot inherits the positioning result of the first robot, that is, the second robot is positioned based on the first target image corresponding to the first robot, thereby omitting the step of matching the second image from the environmental image library, reducing the computational overhead of the scheduling equipment, and improving the efficiency of robot positioning.

[0089] Optionally, if the first posture is inconsistent with the second posture, the method further includes:

[0090] According to the second image, a second target image matching the second image is determined from the environment image library; according to the second target image, the environment image library is updated or navigation of the second robot is performed.

[0091] Specifically, if the first posture is inconsistent with the second posture, it means that the posture of the second robot when it reaches the teaming point is different from the posture of the first robot when it reaches the teaming point. Then, according to the second image collected by the second robot at the teaming point, a second target image matching the second image can be determined from the environmental image library. The specific method is similar to step S201, and only the first image is replaced by the second image. Then, the second robot is positioned according to the second target image to navigate the second robot, and each frame image in the environmental image library is updated based on the second image and the second target image, or based on the result of the closed-loop detection of the second image, so as to reduce the inter-frame error of the environmental image library, thereby reducing the navigation or positioning error of the robot.

[0092] In some embodiments, when the first sub-convoy walks to the team formation point, it can stop or slow down after passing the team formation point for a certain distance along the walking direction, and wait for the second sub-convoy or the second robot to walk to the team formation point. After the second robot completes its positioning, the first sub-convoy and the second sub-convoy continue to walk as a combined convoy.

[0093] Specifically, the second sub-carriage may also decelerate or briefly stop when walking to the team-forming fixed point, so that the dispatching device controls the second robot to adjust its posture at the team-forming fixed point.

[0094] Specifically, when the first posture is inconsistent with the second posture, the posture of the second robot at the team fixed point can also be adjusted, and one or more third images collected by the second robot when adjusting the posture at the team fixed point can be obtained. If the third posture of the second robot corresponding to at least one frame of the third image is consistent with the first posture, the second robot is positioned based on the first target image, thereby completing the positioning of the second robot.

[0095] Figure 4 This is a flowchart of a robot positioning method provided by another embodiment of the present disclosure. The robot positioning method provided by this embodiment is Figure 2 On the basis of the embodiment shown, after step S203, a step of adjusting the posture when the first posture and the second posture are inconsistent is added, and a step of determining the sensor turned on by the second robot is added before acquiring the second image. Figure 4 As shown, the robot positioning method provided in this embodiment may include the following steps:

[0096] Step S401, obtaining a first image captured by a first robot at a team-forming fixed point.

[0097] Specifically, the first image can be obtained based on sensors turned on by the first robot when walking to the team formation point, such as a front view sensor and various side view sensors.

[0098] Step S402: determining, according to the first image, from an environment image library a first target image that matches the first image.

[0099] Step S403, when determining the team formation point, determine the sensors turned on by the second robot according to the role of the second robot in the combined team.

[0100] Among them, the roles of robots in the team include the head robot, the tail robot and the middle robot.

[0101] Since at the team formation point, the role of the second robot in the team is changed from the head robot in the original second sub-team to the tail robot or the middle robot in the combined team, it is necessary to redetermine the sensors turned on by the second robot. Specifically, the sensors turned on by the second robot can be determined based on the role of the second robot in the combined team, the tail robot or the middle robot.

[0102] Specifically, if the second sub-team where the second robot is located includes multiple robots, the role of the second robot in the combined team is a team robot, and the sensor turned on at the team fixed point can be a side view sensor.

[0103] Specifically, if the second sub-team where the second robot is located includes one robot, that is, the second robot walks as a single robot before walking to the team formation point, then the role of the second robot in the combined team is the tail robot, and the sensors turned on at the team formation point can be side view sensors and rear view sensors.

[0104] Specifically, when the role of each robot in the fleet changes, the sensors turned on by the robot can be determined based on the new role of the robot.

[0105] For example, the sensors turned on by the first robot in the robot fleet may be the front view sensor and each side view sensor, the sensors turned on by the robots in the team may be each side view sensor, and the sensors turned on by the last robot may be the rear view sensor and each side view sensor. Alternatively, the sensors turned on by the first robot in the robot fleet may be the front view sensor and each side view sensor, and the sensors turned on by the robots in the team and the last robot may be each side view sensor.

[0106] Step S404: Based on the sensor turned on by the second robot, a second image collected by the second robot at the team fixed point is obtained.

[0107] Specifically, when the second robot walks to the teaming fixed point, a second image of the second robot at the teaming fixed point can be acquired based on sensors turned on by the second robot, such as the rear view sensor and each side view sensor, or each side view sensor.

[0108] Step S405: Determine, based on the first image and the second image, whether the first posture of the second robot at the team-forming fixed point is consistent with the second posture of the first robot at the team-forming fixed point.

[0109] Specifically, by comparing the features of the first image and the second image captured by sensors at the same installation position of the first robot and the second robot, it can be determined whether the postures of the first robot and the second robot at the teaming fixed point, that is, the first posture and the second posture, are consistent.

[0110] Specifically, the images collected by the sensors at the same installation positions on the first robot and the second robot at the team fixed point can be determined in sequence according to the installation positions of the sensors corresponding to the images, that is, the first image and the second image, that is, the images are compared in sequence. 1i and I 2i ,According to the comparison results, determine whether the first pose and the second pose are consistent.

[0111] Where i = 1, 2, ..., n, n is the total number of sensors turned on by the first robot, I 1i is the first image collected by the i-th enabled sensor of the first robot, I 2i The second image captured by the i-th enabled sensor of the second robot.

[0112] Specifically, if I 1i and I 2i , i = 1, 2, ..., n, all match, then it is determined that the first pose is consistent with the second pose. Alternatively, if the first image and the second image captured by at least m sensors all match, then it is determined that the first pose is consistent with the second pose. Wherein, m is a positive integer less than n.

[0113] Specifically, the first posture of the first robot at the teaming point can be determined based on each first image corresponding to the first robot, and the second posture of the second robot at the teaming point can be determined based on each second image corresponding to the second robot. Then, it is determined whether the first posture and the second posture are consistent, such as whether the posture difference between the first posture and the second posture is less than a preset difference. If so, it is determined that the first posture and the second posture are consistent. Among them, the posture difference can be represented by two parameters: the difference in the orientation angle and the difference in the distance from the teaming point.

[0114] Step S406: If the first posture is consistent with the second posture, the second robot is positioned according to the first target image to update the environment image library or to navigate the second robot.

[0115] Furthermore, if the posture difference between the first posture and the second posture is too large, such as the difference in distance to the team fixed point is greater than the first difference, or the difference in orientation angle is greater than the second difference, a second target image matching the second image is determined from the environmental image library based on the second image; and the second robot is positioned based on the second target image.

[0116] Step S407: If the first posture is inconsistent with the second posture, adjusting the posture of the second robot according to the first posture and the second posture.

[0117] Specifically, when the first posture and the second posture are inconsistent, a posture adjustment instruction for the second robot can be generated based on the posture difference between the first posture and the second posture, so as to adjust the position and orientation of the second robot based on the posture adjustment instruction to change the posture of the second robot at the team fixed point.

[0118] Specifically, a posture adjustment instruction of the second robot may be generated according to the difference in image coordinates of points corresponding to the first image and the second image, so as to adjust the posture of the second robot based on the posture adjustment instruction.

[0119] Furthermore, when the second posture is inconsistent with the first posture, the type of task and the task priority of the second robot or each robot in the combined fleet are obtained. When the type of task and the task priority of each robot in the combined fleet meet the preset conditions, the posture adjustment instruction of the second robot is generated according to the first posture and the second posture. If the type of task and the task priority of each robot in the combined fleet do not meet the preset conditions, a second target image matching the second image is determined from the environmental image library according to the second image, and the second robot is positioned according to the second target image.

[0120] Exemplarily, the preset condition may be that the type of the task is a set type, and the task priority is lower than the preset priority.

[0121] Step S408: acquiring at least one frame of a third image captured by the second robot while the second robot is adjusting its posture.

[0122] Specifically, the specific method of acquiring the third image is similar to that of the second image, and only the acquisition time is different, which will not be repeated here.

[0123] Step S409: determine whether there is at least one frame of the third image corresponding to the second robot whose third posture is consistent with the first posture.

[0124] Specifically, feature extraction may be performed on the third image, and based on features corresponding to the third image, the third posture of the second robot corresponding to each frame of the third image may be determined, and then it may be determined whether any of the third postures is consistent with the first posture.

[0125] Step S410: if it exists, positioning the second robot is performed according to the first target image to update the environment image library or perform navigation of the second robot.

[0126] Specifically, if there is at least one third image whose corresponding third posture is consistent with the first posture, the second robot can be positioned based on the first target image of the first robot, that is, the second robot inherits the loop detection or positioning result of the first robot, so there is no need to search for a target image matching the second image from an environmental image library including more frame images, thereby saving the computing resources of the scheduling equipment and improving the positioning efficiency of the second robot in team positioning.

[0127] Furthermore, if there is no third posture corresponding to the third image that is consistent with the first posture, a second target image matching the second image or the third image is determined from the environmental image library based on the second image or the third image; and the second robot is positioned based on the second target image.

[0128] In this embodiment, for the case where two robot fleets are combined into a combined fleet, based on the role of the second robot in the combined team, the sensor of the second robot is automatically controlled to be turned on, and then based on the second image collected by the turned-on sensor at the team fixed point, based on the images collected by the second robot and the first robot at the team fixed point, it is judged whether the postures of the second robot and the first robot at the team fixed point are consistent. If they are consistent, the second robot inherits the matching result or loop detection result of the first robot, and locates the second robot based on the first target image of the first robot; if they are inconsistent, the posture of the second robot at the team fixed point is adjusted to obtain a new image collected by the second robot at the team fixed point, that is, the third image, so as to judge whether the posture of the second robot corresponding to the third image is consistent with the posture of the first robot corresponding to the first image. If they are consistent, the second robot inherits the matching result or loop detection result of the first robot, and locates the second robot based on the first target image of the first robot, thereby realizing the inheritance of image matching results of robots with the same posture and the same role at the team fixed point, reducing the data processing amount of the scheduling equipment, and improving the efficiency of robot positioning.

[0129] Figure 5 This is a flow chart of a robot positioning method provided by another embodiment of the present disclosure. The robot positioning method provided by this embodiment is executed by a scheduling device, such as Figure 5 As shown, the robot positioning method provided in this embodiment includes the following steps:

[0130] Step S501: According to a first image collected by a first robot at a team-forming fixed point, a first target image matching the first image is determined from an environment image library.

[0131] Step S502: acquiring state parameters of the first robot when acquiring the first image, and sending the first image and the state parameters to the second robot, so as to control the second robot to adjust the state of the second robot based on the state parameters.

[0132] The state parameter includes the first posture of the first robot when acquiring the first image.

[0133] Specifically, after the first robot collects the first image at the team fixed point, it can send the state parameters when collecting the first image and the first image to the scheduling device. The scheduling device sends the state parameters and the first image to the second robot, so that the second robot adjusts the posture of the second robot at the team fixed point based on the state parameters, collects the second image, and determines whether the collected second image matches the first image. If the similarity is greater than a preset value, if so, it is determined that the posture of the second robot at the team fixed point is consistent with the first posture of the first robot, and a posture consistency message is generated.

[0134] Specifically, the second robot can determine whether the second image collected by the second robot at the team fixed point matches the first image; if they match, it is determined that the current posture of the second robot at the team fixed point is consistent with the first posture; if they do not match, the posture of the second robot is fine-tuned, or the posture of the second robot is adjusted based on the posture difference between the current posture and the first posture, and a new image is collected during the period when the second robot adjusts its posture, and it is determined whether there is an image in the new image that matches the first image. If so, it is determined that the posture of the second robot is consistent with the first posture, and a posture consistency message is generated.

[0135] Optionally, the state parameters also include a first state parameter, which is used to describe the position parameter of the sensor turned on by the first robot when the team collects the first image at a fixed point; the first state parameter is used to control the second robot to turn on the sensor at the position corresponding to the first state parameter, so as to perform image acquisition based on each turned-on sensor.

[0136] Specifically, when the second robot walks to the team formation point, the sensor of the second robot can be turned on based on the first state parameter in the state parameter, so that the sensors of the second robot and the first robot turned on at the team formation point are consistent, such as both are rear view sensors and various side view sensors; and then the second image is collected based on the various sensors that are turned on.

[0137] Step S503: When receiving a posture consistency message fed back by the second robot, positioning the second robot is performed according to the first target image to update the environment image library or perform navigation of the second robot.

[0138] Among them, the posture consistency message is generated by the second robot when the second robot determines that the posture of the second robot at the team fixed point is consistent with the first posture.

[0139] Specifically, when the second robot determines that the image collected by the second robot at the team fixed point matches the first image or the similarity is greater than a preset value by image feature matching, it determines that the position and posture of the second robot at the team fixed point are consistent with the first position, then a position and posture consistency message is generated and sent to the scheduling device. After receiving the position and posture consistency message fed back by the second robot, the scheduling device directly locates the second robot based on the first target image of the positioning result of the first robot, thereby omitting the process of searching for an image matching the second image from the environmental image library, that is, omitting the process of closed-loop detection of the second image, reducing the amount of calculation of the scheduling device, and improving the positioning efficiency of the second robot at the team fixed point.

[0140] In this embodiment, for the scenario of robots or robot fleets forming a team, the first robot is a robot in the fleet that arrives at the teaming point first, and the second robot is the head robot in the fleet that arrives at the teaming point later. Based on the state parameters of the first robot when collecting the first image at the teaming point, the second robot is controlled to collect the second image with the same state parameters at the teaming point, and then the second robot determines whether the image features of the first image and the second image match, that is, determines whether the postures of the first robot and the second robot at the teaming point are consistent. If they are consistent, a posture consistency message is fed back to the scheduling device, and the scheduling device directly positions the second robot based on the first target image, thereby omitting the step of closed-loop detection or image matching of the second robot at the teaming point, reducing the computing overhead of the scheduling device and improving the efficiency of robot positioning.

[0141] Figure 6 A schematic diagram of the structure of a robot positioning device provided by an embodiment of the present disclosure is shown in FIG. Figure 6 As shown, the robot positioning device is applied to a scheduling device, and the device includes: a first determination module 610, a second image acquisition module 620, a posture determination module 630 and an image inheritance first module 640.

[0142] The first determination module 610 is used to determine a first target image matching the first image from the environment image library according to a first image collected by the first robot at the teaming fixed point; the second image acquisition module 620 is used to acquire a second image collected by the second robot at the teaming fixed point; the posture determination module 630 is used to determine whether the first posture of the second robot at the teaming fixed point is consistent with the second posture of the first robot at the teaming fixed point according to the first image and the second image; the image inheritance first module 640 is used to locate the second robot according to the first target image if the first posture is consistent with the second posture, so as to update the environment image library or navigate the second robot; wherein, at the teaming fixed point, the first robot and the second robot form a combined vehicle team, and the first robot reaches the teaming fixed point earlier than the second robot, the first robot walks in the form of a first sub-vehicle team before reaching the teaming fixed point, the first robot is any one of the first sub-vehicle team, the second robot walks in the form of a second sub-vehicle team before reaching the teaming fixed point, the second robot is the head robot of the second sub-vehicle team, and the number of robots included in the first sub-vehicle team and the second sub-vehicle team is at least 1.

[0143] Optionally, the first determining module 610 is specifically configured to:

[0144] Based on the closed-loop detection algorithm, according to the first image, it is determined whether there is an environmental image matching the first image in the environmental image library; if there is an environmental image matching the first image in the environmental image library, the closed-loop detection is successful, and the matched environmental image is determined as the first target image of the first image.

[0145] Optionally, the device further comprises:

[0146] a posture adjustment module, used for adjusting the posture of the second robot according to the first posture and the second posture if the first posture is inconsistent with the second posture; a third image acquisition module, used for acquiring at least one frame of the third image collected by the second robot during the posture adjustment of the second robot; a posture consistency judgment module, used for judging whether there is at least one frame of the third image corresponding to the third posture of the second robot that is consistent with the first posture; an image inheritance third module, used for positioning the second robot according to the first target image if there is at least one frame of the third image corresponding to the third posture of the second robot that is consistent with the first posture, so as to update the environmental image library or navigate the second robot.

[0147] Optionally, the device further comprises:

[0148] a second target image determination module, used to determine a second target image matching the second image from the environment image library based on the second image if the first posture is inconsistent with the second posture; and a second robot positioning module, used to position the second robot based on the second target image.

[0149] Optionally, the device further comprises:

[0150] The sensor activation module is used to determine the sensors activated by the second robot according to the role of the second robot in the combined vehicle fleet when determining the team formation point, wherein the roles in the vehicle fleet include the head robot, the tail robot and the middle robot.

[0151] The robot positioning device provided in the embodiment of the present disclosure can execute the present disclosure Figure 2 or Figure 4 The robot positioning method provided by the corresponding embodiment has the corresponding functional modules and beneficial effects of the execution method.

[0152] Figure 7 A schematic diagram of the structure of a robot positioning device provided by another embodiment of the present disclosure is shown in FIG. Figure 7 As shown, the robot positioning device is applied to a scheduling device, and the device includes: a second determination module 710, a state parameter sending module 720 and an image inheritance second module 730.

[0153] Among them, the second determination module 710 is used to determine the first target image matching the first image collected by the first robot at the team fixed point from the environmental image library; the state parameter sending module 720 is used to obtain the state parameters of the first image collected by the first robot, and send the first image and the state parameters to the second robot to control the second robot to adjust the state of the second robot based on the state parameters; wherein the state parameters include the first posture of the first robot when collecting the first image; the image inheritance second module 730 is used to position the second robot according to the first target image when receiving the posture consistency message fed back by the second robot, so as to update the environmental image library or navigate the second robot, wherein the posture consistency message is generated by the second robot when it determines that the second posture of the second robot at the team fixed point is consistent with the first posture.

[0154] Optionally, the second determining module 710 is specifically configured to:

[0155] Based on the closed-loop detection algorithm, according to the first image, it is determined whether there is an environmental image matching the first image in the environmental image library; if there is an environmental image matching the first image in the environmental image library, the closed-loop detection is successful, and the matched environmental image is determined as the first target image of the first image.

[0156] Optionally, the state parameters also include a first state parameter, which is used to describe the position parameter of the sensor turned on by the first robot when the team collects the first image at a fixed point; the first state parameter is used to control the second robot to turn on the sensor at the corresponding position in the first state parameter, so as to perform image acquisition based on each turned on sensor.

[0157] The robot positioning device provided in the embodiment of the present disclosure can execute the present disclosure Figure 5 The robot positioning method provided by the corresponding embodiment has the corresponding functional modules and beneficial effects of the execution method.

[0158] Figure 8 A schematic diagram of a scheduling device provided by an embodiment of the present disclosure is shown in FIG. Figure 8 As shown, the scheduling device includes: a memory 810, a processor 820 and a computer program.

[0159] The computer program is stored in the memory 810 and is configured to be executed by the processor 820 to implement the present disclosure. Figure 2 , Figure 4 and Figure 5 A robot positioning method provided in any one of the corresponding embodiments.

[0160] The memory 810 and the processor 820 are connected via a bus 830 .

[0161] For related instructions, please refer to Figure 2 , Figure 4 and Figure 5 The relevant descriptions and effects corresponding to the steps are understood, and no further elaboration is given here.

[0162] The present disclosure provides a storage system, which includes: a robot and Figure 8 The corresponding embodiment provides a scheduling device.

[0163] In some embodiments, the warehousing system further includes storage racks to store goods or boxes.

[0164] In some embodiments, the warehousing system further includes an operating table and transfer devices such as unloaders, elevators, and transport lines. The robot is used to transport goods or boxes to the operating table or a transfer device connected to the operating table to complete the order corresponding to the operating table.

[0165] An embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement the present disclosure. Figure 2 , Figure 4 and Figure 5 A robot positioning method provided in any one of the corresponding embodiments.

[0166] Among them, the computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0167] The present disclosure also provides a program product, which includes an executable computer program, which is stored in a readable storage medium. At least one processor of the scheduling device or the storage system can read the computer program from the readable storage medium, and at least one processor executes the computer program so that the robot positioning device implements the robot positioning method provided in the above various embodiments.

[0168] In the several embodiments provided in the present disclosure, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0169] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0170] In addition, each functional module in each embodiment of the present disclosure may be integrated into one processing unit, each module may exist physically separately, or two or more modules may be integrated into one unit. The above modules may be implemented in the form of hardware or hardware plus software functional units.

[0171] The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (English: processor) to perform some steps of the method described in each embodiment of the present disclosure.

[0172] It should be understood that the above processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or the processor can be any conventional processor, etc. The steps of the method disclosed in the present disclosure can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor.

[0173] The memory may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk memory, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk, etc.

[0174] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present disclosure is not limited to only one bus or one type of bus.

[0175] The above storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The storage medium can be any available medium that can be accessed by a general or special purpose computer.

[0176] An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the storage medium can also exist as discrete components in an electronic device or a main control device.

[0177] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0178] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than to limit them. Although the present disclosure has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present disclosure.

Claims

1. A robot positioning method, characterized in that: The method is applied to a scheduling device, and the method comprises: Determining, from an environment image library, a first target image matching the first image according to a first image collected by the first robot at a team formation point, wherein the team formation point is a location where the robots form a team; Acquire a second image collected by the second robot at the team fixed point; Determining, based on the first image and the second image, whether a second posture of the second robot at the team-forming fixed point is consistent with a first posture of the first robot at the team-forming fixed point; If the first posture is consistent with the second posture, positioning the second robot according to the first target image to update the environment image library or perform navigation of the second robot; Wherein, at the team formation point, the first robot and the second robot form a combined vehicle team, and the first robot reaches the team formation point earlier than the second robot, the first robot walks in the form of a first sub-vehicle team before reaching the team formation point, the first robot is any robot in the first sub-vehicle team, the second robot walks in the form of a second sub-vehicle team before reaching the team formation point, the second robot is the head robot of the second sub-vehicle team, and the number of robots included in the first sub-vehicle team and the second sub-vehicle team respectively is at least 1.

2. The method according to claim 1, characterized in that The determining, from an environment image library, a first target image matching the first image according to the first image collected by the first robot at the team formation fixed point includes: Based on a closed-loop detection algorithm, judging, according to the first image, whether there is an environmental image matching the first image in the environmental image library; If so, the closed-loop detection is successful, and the matched environment image is determined as the first target image of the first image.

3. The method according to claim 1, characterized in that If the first posture is inconsistent with the second posture, the method further includes: Adjusting the posture of the second robot according to the first posture and the second posture; During the period when the second robot performs position adjustment, acquiring at least one frame of a third image captured by the second robot; Determining whether there is at least one frame of the third image corresponding to a third posture of the second robot that is consistent with the first posture; If so, the second robot is positioned according to the first target image to update the environment image library or to navigate the second robot.

4. The method according to claim 1, characterized in that: If the first posture is inconsistent with the second posture, the method further includes: Determine, according to the second image, from the environment image library, a second target image matching the second image; According to the second target image, the environment image library is updated or navigation of the second robot is performed.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: When determining the team formation point, the sensors turned on by the second robot are determined according to the role of the second robot in the combined team, wherein the roles in the team include the head robot, the tail robot and the middle robot.

6. A robot positioning method, characterized in that: The method is applied to a scheduling device, and the method comprises: Determining, from an environment image library, a first target image matching the first image according to a first image collected by the first robot at a team formation point, wherein the team formation point is a location where the robots form a team; Acquire state parameters of the first robot when acquiring the first image, and send the first image and the state parameters to the second robot, so as to control the second robot to adjust the state of the second robot based on the state parameters; wherein the state parameters include the first position of the first robot when acquiring the first image; When receiving a posture consistency message fed back by the second robot, positioning the second robot according to the first target image to update the environment image library or perform navigation of the second robot, wherein the posture consistency message is generated when the second robot determines that the second posture of the second robot at the team fixed point is consistent with the first posture; Wherein, at the team formation point, the first robot and the second robot form a combined vehicle team, and the first robot reaches the team formation point earlier than the second robot, the first robot walks in the form of a first sub-vehicle team before reaching the team formation point, the first robot is any robot in the first sub-vehicle team, the second robot walks in the form of a second sub-vehicle team before reaching the team formation point, the second robot is the head robot of the second sub-vehicle team, and the number of robots included in the first sub-vehicle team and the second sub-vehicle team respectively is at least 1.

7. The method according to claim 6, characterized in that The state parameters also include a first state parameter, and the first state parameter is used to describe a position parameter of a sensor turned on when the first robot collects the first image; When the second robot walks to the team formation point, the first state parameter is used to control the second robot to turn on the sensors at the corresponding positions in the first state parameter, so as to perform image acquisition based on each turned-on sensor.

8. A robot positioning device, characterized in that: The device is applied to a scheduling device, and comprises: A first determination module is used to determine a first target image matching the first image from an environmental image library according to a first image collected by the first robot at a team formation point, wherein the team formation point is a location where the robots form a team; A second image acquisition module, used to acquire a second image collected by the second robot at the team fixed point; A posture determination module, used for determining whether a second posture of the second robot at the teaming fixed point is consistent with a first posture of the first robot at the teaming fixed point according to the first image and the second image; an image inheritance first module, for positioning the second robot according to the first target image to update the environment image library or to navigate the second robot if the first posture is consistent with the second posture; Wherein, at the team formation point, the first robot and the second robot form a combined vehicle team, and the first robot reaches the team formation point earlier than the second robot, the first robot walks in the form of a first sub-vehicle team before reaching the team formation point, the first robot is any robot in the first sub-vehicle team, the second robot walks in the form of a second sub-vehicle team before reaching the team formation point, the second robot is the head robot of the second sub-vehicle team, and the number of robots included in the first sub-vehicle team and the second sub-vehicle team respectively is at least 1.

9. A robot positioning device, characterized in that: The device is applied to a scheduling device, and comprises: A second determination module is used to determine a first target image matching the first image from an environmental image library according to a first image collected by the first robot at a team formation point, wherein the team formation point is a location where the robots form a team; a state parameter sending module, used for obtaining the state parameters of the first robot when acquiring the first image, and sending the first image and the state parameters to the second robot, so as to control the second robot to adjust the state of the second robot based on the state parameters; wherein the state parameters include the first position of the first robot when acquiring the first image; The image inheritance second module is used to, when receiving a posture consistency message fed back by the second robot, locate the second robot according to the first target image to update the environment image library or navigate the second robot, wherein the posture consistency message is generated when the second robot determines that the second posture of the second robot at the team fixed point is consistent with the first posture; Wherein, at the team formation point, the first robot and the second robot form a combined vehicle team, and the first robot reaches the team formation point earlier than the second robot, the first robot walks in the form of a first sub-vehicle team before reaching the team formation point, the first robot is any robot in the first sub-vehicle team, the second robot walks in the form of a second sub-vehicle team before reaching the team formation point, the second robot is the head robot of the second sub-vehicle team, and the number of robots included in the first sub-vehicle team and the second sub-vehicle team respectively is at least 1.

10. A scheduling device, characterized in that: include: memory and at least one processor; The memory stores computer-executable instructions; The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the robot positioning method according to any one of claims 1 to 7.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the processor executes the computer-executable instructions, the robot positioning method according to any one of claims 1 to 7 is implemented.

12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the robot positioning method according to any one of claims 1 to 7 is implemented.

Images