Methods and devices for recycling luggage carts

Abstract

This disclosure provides a method and apparatus for recycling luggage carts, relating to the field of robotics. The method includes: in response to arriving at a cart-finding point in a target area of ​​a plurality of areas at a recycling location, detecting luggage carts within the cart-finding point, wherein each area includes a cart-finding point and a stacking point, the cart-finding point being used by the robot to search for luggage carts, and the stacking point being used to stack luggage carts; in response to detecting a luggage cart, performing a cart grabbing operation and stacking the cart into a queue of luggage carts at the stacking point. This disclosure implements zoned management, thereby enabling more precise control of the robot to recycle by area. By setting cart-finding points and stacking points in areas of the recycling location, and by performing cart-finding at the cart-finding points and stacking at the stacking points, the robot can achieve automated luggage cart recycling.

Description

Technical Field

[0001] This disclosure relates to the field of robotics, and in particular to a method and apparatus for recycling luggage carts. Background Technology

[0002] In airports and other settings, the issue of baggage cart retrieval is frequently encountered. Currently, baggage cart retrieval primarily relies on manual labor.

[0003] However, manual baggage cart recycling suffers from numerous problems, including low efficiency and unstable handling capacity. Therefore, there is an urgent need for an automated baggage cart recycling method to avoid the problems encountered by manual recycling. Summary of the Invention

[0004] In view of this, the purpose of this disclosure is to provide a method and apparatus for recycling luggage carts, which can specifically solve existing problems.

[0005] Based on the above objectives, in a first aspect, this disclosure proposes a method for recycling luggage carts, applied to a robot, the method comprising: in response to arriving at a cart-finding point in a target area of ​​a plurality of areas to be recycled, detecting luggage carts within the cart-finding point, wherein each area includes a cart-finding point and a stacking point, the cart-finding point being used by the robot to search for luggage carts, and the stacking point being used to stack luggage carts; in response to detecting a luggage cart, performing a cart grabbing and stacking of the luggage cart into a queue of luggage carts in the stacking point.

[0006] In a second aspect, a method for recycling luggage carts is also provided, applied to an electronic device, the electronic device having a communication connection with a robot of any of the first aspects; the method includes: determining a target area for recycling in a plurality of areas of the recycling site, and sending a task instruction to an idle robot to instruct the recycling of luggage carts, so that the robot goes to and arrives at a car-finding point in the target area.

[0007] Thirdly, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor running the computer program to implement the method of the first aspect.

[0008] Fourthly, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the computer program to implement the method of the second aspect.

[0009] Fifthly, a computer-readable storage medium is also provided, on which a computer program is stored, said computer program being executed by a processor to implement the method described in any one of the first aspects.

[0010] In a sixth aspect, a computer program product is also provided, comprising a computer program that is executed by a processor to implement the method described in any one of the first aspects.

[0011] In summary, this disclosure offers at least the following advantages: It implements zoned management, enabling more precise control of the robot's recycling operations by area. By setting up vehicle-finding points and stacking points within the designated recycling areas, and by allowing the robot to locate vehicles at the finding points and stack them at the stacking points, the robot can automate the recycling of luggage carts. Furthermore, the robot can automatically detect luggage carts within the finding points, facilitating a smoother subsequent recycling process. Attached Figure Description

[0012] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the various drawings denote the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings depict only some embodiments disclosed in this disclosure and should not be construed as limiting the scope of this disclosure.

[0013] Figure 1a A flowchart of a method for recycling a luggage cart according to an embodiment of the present disclosure is shown; Figure 1b A schematic diagram of a robot in a luggage cart recycling method according to an embodiment of the present disclosure is shown; Figure 1c A schematic diagram showing the marking of the inspection box on the luggage cart is shown; Figure 1d The diagram shows the handles of the luggage cart and key points of the two handles; Figure 1e A schematic diagram showing the detection frame and key points of the first luggage cart facing the camera is shown; Figure 1f Another flowchart of a method for recycling a luggage cart according to an embodiment of the present disclosure is shown; Figure 2 Another flowchart of a method for recycling a luggage cart according to an embodiment of the present disclosure is shown; Figure 3 Another flowchart of a method for recycling a luggage cart according to an embodiment of the present disclosure is shown; Figure 4 A schematic diagram of a luggage cart recycling device according to an embodiment of the present disclosure is shown; Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure is shown; Figure 6 A schematic diagram of a storage medium provided according to an embodiment of the present disclosure is shown. Detailed Implementation

[0014] The present disclosure will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the invention. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0015] It should be noted that, unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other. This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0016] Figure 1a A method for retrieving a luggage cart according to this disclosure is shown. In embodiments of this disclosure, the method is applied to a robot, and the method includes: Step S101: In response to arriving at the vehicle search point of the target area in multiple areas of the recycling site, detect the luggage carts in the vehicle search point, wherein each area includes a vehicle search point and a stacking point, the vehicle search point is used for the robot to search for luggage carts, and the stacking point is used for stacking luggage carts.

[0017] In step S102, in response to the detection of a baggage car, the baggage car is grabbed and stacked into the baggage car queue at the stacking point.

[0018] In this embodiment, the robot, which is the main body executing the luggage cart retrieval method, can retrieve the luggage cart when it is detected. Figure 1b A schematic diagram of the robot is shown.

[0019] Each area can be configured with multiple vehicle-finding points and stacking points based on the size of the scene, i.e., the area size. Each stacking area designates an initial robot stacking point, denoted as the first stacking point of this area. The robot prioritizes stacking at this point, meaning that the stacking of luggage carts begins from here. After grabbing a cart, the robot can set a path, which can typically be a path from completing the grabbing to completing the stacking. Alternatively, the path can also be a path from completing the grabbing to moving to the stacking point, which can be the path the robot takes to transport the luggage cart.

[0020] This disclosed embodiment employs zoned management, enabling more precise control of the robot for recycling by area. Locating points and stacking points are set up within the designated recycling area, allowing the robot to locate carts at the locating points and stack them at the stacking points, thus automating the luggage cart recycling process. Furthermore, the robot can automatically detect luggage carts within the locating points, facilitating a smooth subsequent recycling process.

[0021] In some optional implementations of any embodiment of this disclosure, a first camera is provided on the upper front of the robot; the detection of luggage carts in the vehicle search point includes: using the first camera to detect luggage carts in the vehicle search point from the front of the robot; if no luggage cart is detected from the front, the robot is rotated horizontally by a rotatable component to adjust the first camera from a frontal view to another view for detection.

[0022] Among these alternative implementations, the upper part of the first camera can be the robot's head, or it could be the chest, etc.

[0023] Specifically, the first camera on the robot's head can be used to detect luggage carts. The detection model can be pre-collected, labeled, and trained with luggage cart data. Figure 1c The diagram illustrates the annotation of detection bounding boxes for luggage carts. The six blue dots in the diagram represent the key points of the luggage carts. The detection model used can be any deep learning model capable of performing detection, such as the YOLO series. A luggage cart can be considered detected when the confidence rate of the detection bounding box is ≥60% and there are ≥4 key points.

[0024] The vehicle location point cannot detect surrounding luggage carts 360 degrees in a single shot using the first camera. If no luggage cart is detected in the forward direction, rotatable components such as the head or chassis can be rotated to perform a 360-degree search. The appropriate rotation angle can be selected based on the horizontal viewing angle of the first camera. For example, if the horizontal viewing angle is 150°, only a 120-degree rotation to the left or right is needed. After rotation, the detection of the luggage cart frame and key points (overall vehicle key points or handle key points) can continue. If no luggage cart is found after rotation, it indicates that there is no luggage cart at the current location point, and navigation can proceed to the next location point according to the execution order of the various location points within the area.

[0025] These methods allow for the detection of luggage carts from multiple angles, thereby improving the recall rate of detection and avoiding detection failures.

[0026] In some optional implementations of any embodiment of this disclosure, the step of grabbing, transporting, and stacking the luggage cart into a queue of luggage carts at a stacking point includes: detecting the handle and handle key points of the detected luggage cart, obtaining a detection result, grabbing the handle of the luggage cart based on the detection result, and grabbing the luggage cart; within the vehicle search point, for a stacking point whose current capacity is not full, determining the first luggage cart in the luggage cart queue at the stacking point by detection; in response to determining that the robot and the first luggage cart have completed pose alignment, controlling the robot to move towards the first luggage cart until the stacking of the luggage cart is completed.

[0027] Among these optional implementations, the detection model can be trained in advance or in real time: data on the luggage cart handles is collected, the handles are labeled, and a luggage cart handle detection model is trained. Then, the model detects the handles and their key points. The robot gripper is then controlled to grasp the handle based on the key point positions, thus completing the luggage cart grabbing process.

[0028] Afterwards, the luggage carts can be moved. Specifically, based on the specified stacking order or the nearest principle, a suitable stacking area is selected, with each stacking area containing multiple stacking points. The robot navigates to the first stacking point of the selected stacking area. In this way, the robot can grab a cart and move it towards the queue of luggage carts waiting to be stacked.

[0029] Alignment algorithms such as ICP are used to align the robot's posture with the first baggage cart in the queue, ensuring stacking accuracy. The robot's chassis is controlled to move, ensuring the robot's center is aligned with the center of the baggage cart. After center alignment, the robot is controlled to move forward or backward towards the first baggage cart, stacking the baggage cart picked up by the robot into the baggage cart queue.

[0030] Figure 1d A diagram showing the handles of the luggage cart and the key points of the two handles is provided.

[0031] Figure 1e A schematic diagram showing the detection frame and key points of the first luggage cart facing the camera is shown.

[0032] If the capacity of the first stacking point is full, the luggage carts are stacked to other stacking points that are not yet full, such as the second stacking point. The stacking order of various stacking points in the same area or stacking zone can be preset. The robot can stack the luggage carts into the queue waiting to be stacked.

[0033] These methods enable precise vehicle gripping by detecting handlebars and key points. Furthermore, stacking can be performed after pose alignment to ensure stacking accuracy.

[0034] In some optional application scenarios of these implementations, the robot is equipped with a depth camera, which is used to collect the depth information of the first luggage cart. The depth camera is either the first camera or a second camera located on the back of the robot. The step of determining the first luggage cart in the luggage cart queue by detection includes: collecting the depth information of the luggage cart queue through the second camera, and segmenting the depth information of both the handle and the panel of the first luggage cart closest to the robot from the depth information. The pose alignment step includes: aligning the pose of the robot and the first luggage cart according to the segmented depth information.

[0035] In these optional application scenarios, in order for the first camera to better locate luggage carts, the first camera needs to have a wider and higher field of view, while the second camera needs to detect luggage carts that are shorter. Therefore, the height of the first camera can be higher than that of the second camera.

[0036] The pose alignment step can be performed by an electronic device or a robot. The pose here can include orientation and position.

[0037] Model training can be performed in advance or in real-time: Data on the luggage cart queue is collected, and key points of the first luggage cart facing the camera are labeled. A deep model (YOLOv8) can be used to train the luggage cart key point detection model. Based on the luggage cart's posture, a path is dynamically planned to a designated position in front of the luggage carts to be stacked. This path can be flexibly configured according to the actual scenario, ensuring that the robot's rear camera can see the handle and panel of the cart in front of the queue. The depth camera collects the depth information of the luggage cart queue, and by setting a reasonable threshold, the depth information of the handle and panel of the first luggage cart in the queue is segmented. Specifically, the depth information can refer to the horizontal distance from the depth camera to the luggage cart (e.g., the luggage cart panel).

[0038] These application scenarios can use depth information to align the poses of the robot and the first luggage cart, enabling accurate detection of the luggage cart.

[0039] Figure 1f Another flowchart of a luggage cart retrieval method according to an embodiment of this disclosure is shown. This flowchart illustrates an incremental search strategy for a cart-finding point. When the robot reaches a designated area cart-finding point, it uses a head-mounted camera to detect luggage carts within the scene. Here, the designated area is also the target area. If a luggage cart is detected, it is grabbed, moved, and stacked. If not, the robot continues to detect luggage carts by rotating left or right by a specified angle. If a cart is detected after continued detection, the robot grabs, moves, and stacks it. If no cart is detected after continued detection, the robot moves to the next cart-finding point and returns to the step of the robot using its head-mounted camera to detect luggage carts within the scene.

[0040] Figure 2 A method for recycling a luggage cart according to an embodiment of this disclosure is shown. Figure 2 As shown, the method for recycling luggage carts is applied to an electronic device that has a communication connection with the robot in any of the above implementations. The method includes: step S201, determining the target area for recycling in multiple areas of the recycling site; step S202, sending a task instruction to an idle robot to recycle the luggage carts, wherein each area includes a search point and a stacking point, the search point is used for the robot to search for luggage carts, and the stacking point is used for stacking luggage carts.

[0041] In this embodiment, the electronic device can be a terminal or a server. The idle robot receives a task instruction to find a vehicle and move it to the stack. The robot proceeds to the first vehicle-finding point in the functional area to begin the task. After completing the search of the area or stack area, the robot returns idle status information, and the electronic device receives the idle status information sent by the idle robot after completing the retrieval of each vehicle-finding point.

[0042] In this embodiment, the electronic device can assign the idle robot the task of collecting luggage carts in the target area. In this way, the idle robot can collect luggage carts in the target area to realize the automation of luggage cart collection.

[0043] In some optional implementations of this embodiment, each area has a corresponding priority; among the multiple areas of the recycling site, determining the target area to be recycled includes: determining the recycling priority for the multiple areas of the recycling site, the priority being used to indicate the degree of demand for robot recycling of luggage carts; and determining the target area to be recycled in descending order of priority.

[0044] Among these implementation methods, prioritization can be used to understand the degree of demand for recycling, thereby determining a more accurate and reasonable target area.

[0045] In some optional application scenarios of these implementation methods, the priority determination step includes: determining the historical score and real-time score of each of the plurality of regions, wherein the historical score is positively correlated with the frequency of baggage cart occurrence in the region and negatively correlated with the time taken to retrieve baggage carts in the region, and the real-time score is negatively correlated with the remaining capacity of the stacking point and the path distance of the robot; calculating the total priority score of each region based on the historical score and the real-time score, and determining the priority of the plurality of regions based on the total priority score.

[0046] In these optional application scenarios, the entity responsible for prioritizing tasks can be electronic devices, robots, or other electronic equipment. Both historical and real-time scoring are related to the real-time demand for luggage cart retrieval.

[0047] For example, the priority of a functional area = a1 × historical score + (1-a1) × real-time score.

[0048] Wherein, historical score = frequency of luggage cart occurrence in the area × a2 + 1 / (average luggage cart retrieval time in the area) × (1-a2), real-time score = 1 / (remaining capacity at the stacking point) × a3 + 1 / (path distance) × (1-a3).

[0049] a1, a2, and a3 are set based on experience.

[0050] Each functional area has a designated sequence of vehicle-finding points, which can be defined by combining the site layout and real-time stacking status. For a given area, the robot moves sequentially through the vehicle-finding points in that area to retrieve the vehicle. Subsequent complex grasping, moving, and stacking operations are only initiated when the head camera detects the luggage cart at a vehicle-finding point (confidence rate ≥60% and ≥3 key points). The optimal vehicle-finding point sequence can be generated in real-time using a preset algorithm, taking into account the site layout and the real-time stacking status of each vehicle-finding point.

[0051] These application scenarios can obtain more comprehensive evaluation data on priorities through real-time and historical scoring, thereby improving the accuracy of priority determination.

[0052] In some optional implementations of this embodiment, the step of determining the multiple areas may include: acquiring environmental information obtained by the robot scanning the recycling site using sensors; constructing a grid map of the recycling site based on the environmental information; and dividing the grid map into multiple areas according to function.

[0053] In these alternative implementations, the steps for determining multiple regions can be performed by the aforementioned electronic devices, or by a robot or other electronic devices.

[0054] The robot can use the LiDAR on its chassis to scan the environment and build a grid map of the real-world scene. This map is used for subsequent area (which may include stacking areas) and stacking point division, as well as path planning. Multiple functional areas can be divided within the built map according to the specific needs of the scene. For example, if the location is an airport, these areas could include boarding gates, baggage carousels, parking lots, and ride-hailing waiting areas.

[0055] These implementations can provide accurate raster maps by scanning environmental information in real time, thereby helping to improve the accuracy of area division.

[0056] In some optional implementations of this embodiment, the steps for determining the vehicle search points and stacking points include: setting multiple vehicle search points in each area based on the detection distance of the robot luggage cart's sensors; setting multiple stacking points in each area based on at least one of actual needs and historical stacking settings, and setting a stacking capacity for each stacking point; adjusting the location of the area boundaries and the density of the points in the areas between the multiple areas based on at least one of historical data and real-time data of the luggage cart, wherein the historical data and real-time data are used to reflect the degree of demand for robot-recovered luggage carts.

[0057] In these implementations, the entity determining the vehicle location and stacking points can be electronic equipment, a robot, or other electronic devices. Locations refer to vehicle location points and / or stacking points. Specifically, vehicle location points can be set based on experience or the maximum distance the robot's camera can detect for luggage carts. For example, if the camera can detect luggage carts within 15 meters, each functional area can be divided into a rectangular area of ​​<30m*30m (the vehicle location point is located at the center of this area). Stacking points are set according to actual needs or can be reused from previous manual vehicle operation settings. Furthermore, the capacity can be dynamically adjusted; specifically, in response to meeting preset adjustment conditions or automatically, based on historical data such as the frequency of luggage cart occurrences in a certain area, or real-time feedback such as a certain area's stacking points being full, the area boundaries and location density can be dynamically adjusted.

[0058] For example, multiple functional areas can be flexibly divided on the 3D map built by LiDAR, such as boarding gate area, baggage carousel area, and parking area. Multiple "car-finding points" and "stacking points" can be customized for each area, and the capacity of the stacking points can be set, such as 10 baggage carts per stacking point in the boarding gate area.

[0059] These implementation methods allow for the appropriate setting of vehicle-finding points and stacking points based on the robot's detection capabilities. Furthermore, by dynamically adjusting the location of area boundaries and the density of points within the area, refined area management can be achieved.

[0060] like Figure 3 As shown, another flowchart illustrates the baggage cart recycling method.

[0061] This disclosure provides a luggage cart recycling device for performing the luggage cart recycling method described in the above embodiments, such as... Figure 4 As shown, the device 400 includes: a detection unit 401 configured to detect luggage carts within a location finding point in a target area of ​​a plurality of areas to be recycled, wherein each area includes a location finding point and a stacking point, the location finding point being used for a robot to search for luggage carts and the stacking point being used for stacking luggage carts; and a stacking unit 402 configured to grab a luggage cart and stack it into a queue of luggage carts in a stacking point in response to the detection of a luggage cart.

[0062] The luggage cart recycling device and the luggage cart recycling method provided in the above embodiments of this disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the applications stored therein.

[0063] This disclosure also provides an electronic device corresponding to the baggage cart recycling method provided in the foregoing embodiments, for performing the baggage cart recycling method described above. This disclosure does not limit the scope of the embodiments.

[0064] Please refer to Figure 5 This illustrates a schematic diagram of an electronic device provided by some embodiments of the present disclosure. For example... Figure 5 As shown, the electronic device 50 includes: a processor 500, a memory 501, a bus 502, and a communication interface 503. The processor 500, the communication interface 503, and the memory 501 are connected via the bus 502. The memory 501 stores a computer program that can run on the processor 500. When the processor 500 runs the computer program, it executes the method provided in any of the foregoing embodiments of this disclosure.

[0065] The memory 501 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 503 (which can be wired or wireless), such as the Internet, wide area network, local area network, or metropolitan area network.

[0066] Bus 502 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The memory 501 is used to store programs. After receiving an execution instruction, the processor 500 executes the program. The luggage cart recycling method disclosed in any of the foregoing embodiments of this disclosure can be applied to the processor 500, or implemented by the processor 500.

[0067] The processor 500 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 500 or by instructions in software form. The processor 500 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this disclosure. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this disclosure can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules may reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 501. The processor 500 reads the information in memory 501 and, in conjunction with its hardware, completes the steps of the above method.

[0068] The electronic device provided in this disclosure and the luggage cart recycling method provided in this disclosure are based on the same inventive concept and have the same beneficial effects as the methods they employ, operate, or implement.

[0069] This disclosure also provides a computer-readable storage medium corresponding to the baggage cart recycling method provided in the foregoing embodiments. Please refer to [link / reference]. Figure 6 The computer-readable storage medium shown is an optical disc 60, on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it executes the baggage cart recycling method provided in any of the foregoing embodiments.

[0070] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical and magnetic storage media, which will not be elaborated here.

[0071] The computer-readable storage medium provided in the above embodiments of this disclosure and the luggage cart recycling method provided in the embodiments of this disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the applications stored therein.

[0072] It should be noted that: In the foregoing text, the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in this disclosure is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0073] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this disclosure.

[0074] The embodiments of this disclosure have been described above with reference to the accompanying drawings. These are merely specific implementations of this disclosure, but this disclosure is not limited to the specific implementations described above. The specific implementations described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this disclosure without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this disclosure.

Claims

1. A method for recycling luggage carts, characterized in that, Applied to robots, the method includes: In response to arriving at a vehicle search point in a target area of ​​a recycling site, the system detects luggage carts within the vehicle search point, wherein each area includes a vehicle search point and a stacking point, the vehicle search point being used by the robot to search for luggage carts and the stacking point being used to stack luggage carts; In response to the detection of a baggage cart, the baggage cart is grabbed and stacked into the baggage cart queue at the stacking point.

2. The method according to claim 1, characterized in that, The robot has a first camera mounted on its upper front. The detection of luggage carts within the vehicle search point includes: Using the first camera, the robot detects luggage carts within the vehicle search point from the front. If no luggage cart is detected from the front, the robot rotates horizontally using its rotatable components to adjust the first camera from a frontal view to another view for detection.

3. The method according to claim 1, characterized in that, The process of grabbing the baggage car and stacking it into the baggage car queue at the stacking point includes: The detection results are obtained by examining the handle and key points of the detected luggage cart. The handle of the luggage cart is then grasped based on the detection results to grab the luggage cart. Within the vehicle search point, for stacking points that are not currently full, the first luggage car in the luggage car queue at that stacking point is determined by detection; In response to determining that pose alignment has been completed between the robot and the first luggage cart, the robot is controlled to move toward the first luggage cart until the stacking of the luggage cart is completed.

4. The method according to claim 3, characterized in that, The robot is equipped with a depth camera, which is used to collect depth information of the first luggage cart. The depth camera can be the first camera or a second camera located on the back of the robot. The step of determining the first baggage car in the baggage car queue at the stacking point by detection includes: The second camera collects depth information of the luggage cart queue, and from the depth information, it segments the depth information of the handle and panel of the first luggage cart closest to the robot. The pose alignment step includes: Based on the segmented depth information, the robot and the first luggage cart are pose aligned.

5. A method for recycling luggage carts, characterized in that, Applied to an electronic device, wherein the electronic device has a communication connection with the robot of any one of claims 1-4; the method includes: Among the multiple areas of the recycling site, a target area for recycling is determined, and a task instruction to recycle the luggage cart is sent to an idle robot so that the robot can go to and reach the vehicle location in the target area.

6. The method according to claim 5, characterized in that, Each region has a corresponding priority; Among the multiple areas of the site to be recycled, the target area for recycling is identified, including: For multiple areas of the proposed recycling site, a recycling priority is determined, the priority being used to indicate the degree of need for robotic baggage cart recycling; The target areas to be reclaimed are determined in descending order of priority.

7. The method according to claim 6, characterized in that, The steps for determining the priority include: The historical score and real-time score of each of the multiple regions are determined. The historical score is positively correlated with the frequency of luggage cart occurrence in the region and negatively correlated with the recovery time of luggage carts in the region. The real-time score is negatively correlated with the remaining capacity of the stacking point and the path distance of the robot. Based on the historical and real-time scores, a priority score is calculated for each region, and the priority of the multiple regions is determined based on the priority score.

8. The method according to claim 5, characterized in that, The steps for determining the multiple regions include: The robot uses sensors to scan the recycling site to obtain environmental information. Based on the environmental information, construct a grid map of the recycling site; The grid map is divided into multiple areas according to function.

9. The method according to claim 5, characterized in that, The steps for determining the vehicle search point and stacking point include: In each area, multiple vehicle search points are set up based on the detection distance of the robot luggage cart's sensors; In each region, multiple stacking points are set up based on actual needs and at least one of historical stacking settings, and the stacking capacity is set for each stacking point; Based on at least one of the historical and real-time data of the luggage cart, the location of the area boundaries and the density of points in the areas are adjusted, wherein the historical and real-time data are used to reflect relevant data on the robot's collection of luggage carts.

10. A luggage cart recycling device, characterized in that, The device, applied to robots, includes: The detection unit is configured to detect luggage carts within a target area in response to arrival at a car-finding point in a plurality of areas at a recycling site, wherein each area includes a car-finding point and a stacking point, the car-finding point being used by the robot to search for luggage carts and the stacking point being used to stack luggage carts. The stacking unit is configured to grab the baggage car and stack it into the baggage car queue at the stacking point in response to the detection of the baggage car.

Images