Robot elevator selection methods, elevator selection devices, robots and computer program products

Abstract

This application discloses a robot elevator selection method, a robot elevator selection device, a robot, and a computer program product. The robot is equipped with a robotic arm capable of interacting with elevators. During elevator selection, the robot first performs an initial elevator selection based on the floor information corresponding to the cross-floor task to determine the first candidate elevator that can assist in completing the cross-floor task. It then proceeds to the first call point of the first candidate elevator, calls the elevator via the robotic arm, and obtains the status information of each second candidate elevator within a preset range for a second elevator selection. This second selection filters out the target elevator expected to arrive at the current floor first from among the second candidate elevators. This second selection avoids excessively long waiting times for the target elevator selected by the robot, ensuring the robot's elevator-riding efficiency. Throughout the process, the robot does not need to communicate with the elevator directly; it autonomously calls the elevator through interaction with the elevator via the robotic arm, selecting elevators once before and once after calling, ultimately determining the most efficient target elevator and proceeding to wait for it. This shortens the robot's waiting time and improves the execution efficiency of cross-floor tasks.

Description

Technical Field

[0001] This application belongs to the field of robotics technology, and in particular relates to a robot ladder selection method, a robot ladder selection device, a robot, and a computer program product. Background Technology

[0002] When a robot performs a task that spans multiple floors, selecting the appropriate elevator is a crucial step. In related technologies, if there are multiple elevators on the same floor, the robot selects one through the elevator control system's elevator boarding module and keeps the elevator door open until the robot successfully enters.

[0003] However, this solution relies on communication between the elevator and the control system, requiring the integration of the elevator protocol with the robot. Many elevators lack this capability, necessitating costly retrofits, and different elevator models require individual adaptation. Furthermore, some manufacturers and users are unwilling to open the communication interface, which may limit the robot's elevator-riding function and reduce its applicability in various scenarios.

[0004] However, if the robot does not communicate with the elevator, it is difficult to guarantee the robot's elevator-riding efficiency when there are multiple elevators available nearby.

[0005] Therefore, a highly efficient and low-cost method for robot ladder selection is urgently needed. Summary of the Invention

[0006] This application provides a robot elevator selection method, a robot elevator selection device, a robot, and a computer program product. The robot does not need to communicate with the elevator. It interacts with the elevator through a robotic arm to autonomously call the elevator. It selects elevators once before and after calling the elevator, and finally determines the most efficient target elevator and goes to wait for it. This can shorten the time required for the robot to wait for the elevator and improve the execution efficiency of cross-floor tasks.

[0007] In a first aspect, this application provides a robot elevator selection method, wherein the robot is equipped with a robotic arm for interacting with elevator buttons; the elevator selection method includes:

[0008] After receiving a cross-floor task, at least one first candidate elevator is determined based on the robot's departure floor and the destination floor corresponding to the cross-floor task; the candidate elevator is the elevator that the robot can take from the departure floor to the destination floor;

[0009] Move to the first call point corresponding to the first candidate elevator;

[0010] The robotic arm is controlled to activate the target elevator call button; the first target direction of the elevator corresponding to the target elevator call button is consistent with the robot's target elevator riding direction.

[0011] Obtain the status information of the second candidate elevator within a preset range;

[0012] The target elevator is selected from the second candidate elevators based on the departure floor, arrival floor, and status information; the target elevator is the second candidate elevator that is expected to arrive at the departure floor first.

[0013] Wait for the elevator at the second call point corresponding to the target elevator.

[0014] Secondly, this application provides a robot elevator selection device, wherein the robot is equipped with a robotic arm for interacting with elevator buttons; the robot elevator selection device includes:

[0015] The first elevator selection module is used to determine at least one first candidate elevator based on the robot's departure floor and the destination floor corresponding to the cross-floor task after receiving the cross-floor task; the candidate elevator is the elevator that the robot can take from the departure floor to the destination floor;

[0016] The motion module is used to move to the first call point corresponding to the first candidate elevator;

[0017] The control module is used to control the robotic arm to activate the target call button.

[0018] The first acquisition module is used to acquire the status information of the second candidate elevator within a preset range; the first target running direction of the elevator corresponding to the target elevator call button is consistent with the robot's target elevator riding direction.

[0019] The second elevator selection module is used to select the target elevator from the second candidate elevators based on the departure floor, arrival floor, and various status information; the target elevator is the second candidate elevator that arrives at the departure floor first in advance.

[0020] The motion module is also used to wait for the elevator at the second call point corresponding to the target elevator.

[0021] Thirdly, this application provides a robot including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described in the first aspect.

[0022] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method described in the first aspect above.

[0023] Fifthly, this application provides a computer program product comprising a computer program that, when executed by one or more processors, implements the steps of the method described in the first aspect.

[0024] The advantages of this application compared to existing technologies are as follows: For robots equipped with robotic arms capable of interacting with elevators, during elevator selection, an initial elevator selection can be performed based on the floor information corresponding to the cross-floor task to determine the first candidate elevator that can take you from the starting floor to the destination floor. To shorten waiting time, the robot can first go to the first call point of the first candidate elevator and activate the corresponding call button through the robotic arm. After calling the elevator, to ensure that the most efficient elevator can be used to reach the destination floor, the robot can obtain the status information of each second candidate elevator within a preset range to perform a second elevator selection based on the status information, that is, to select the target elevator that is expected to arrive at the current floor first from among the second candidate elevators. Throughout the entire process, the robot does not need to communicate with the elevator. Calling the elevator after the first selection ensures that the waiting elevator can go to the destination floor. Obtaining the status information of the second candidate elevators within a preset range after calling the elevator allows for a second selection, effectively utilizing waiting time to determine the target elevator that is closest and has the shortest waiting time. The robot can go to its second call point in advance to wait before the target elevator arrives, further shortening the waiting time required for the robot and improving the execution efficiency of cross-floor tasks.

[0025] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 This is a schematic diagram of the physical structure of the robot provided in the embodiments of this application;

[0028] Figure 2 This is a flowchart illustrating the robot ladder selection method provided in the embodiments of this application;

[0029] Figure 3 This is a schematic diagram of the structure of the robot ladder selection device provided in the embodiments of this application;

[0030] Figure 4 This is a schematic diagram of the robot provided in the embodiments of this application. Detailed Implementation

[0031] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0032] In related technologies, robot elevator selection relies on communication between the elevator and its control system, requiring the elevator protocol to be compatible with robot communication. However, many existing elevators lack the communication capabilities to interface with robots, necessitating system modifications. This not only increases modification and deployment costs but also raises questions about the willingness of elevator manufacturers and users to open communication interfaces to third parties, potentially preventing robots from using the elevator and reducing its applicability and scope. Conversely, without communication with the elevator, robot efficiency is compromised when multiple elevators are available nearby.

[0033] To address this problem, this application proposes a robot elevator selection method. By modifying the robot's hardware and software, the robot gains the ability to actively interact with elevators. Without communicating with the elevator itself, the robot arm autonomously calls for elevators, performing elevator screening before and after each call to determine the most efficient target elevator that can reach the desired floor. Before the target elevator arrives, the robot moves to its second call point to wait, effectively shortening the waiting time and improving the efficiency of cross-floor tasks. The control method proposed in this application will be described below through specific embodiments.

[0034] The elevator selection method for robots provided in this application can be applied to robots equipped with robotic arms for interacting with elevator buttons. This elevator-riding method can also be applied to electronic devices that can establish a communication connection with the robot and control the robot based on that connection, or to cloud servers, etc. Examples include mobile phones, tablets, in-vehicle devices, augmented reality (AR) / virtual reality (VR) devices, laptops, ultra-mobile personal computers (UMPCs), netbooks, personal digital assistants (PDAs), and other electronic devices. This application does not limit the specific type of electronic device.

[0035] Optionally, to enable the robot to interact with an elevator at a certain distance from it by controlling the robotic arm with minimal movement—for example, allowing the robot to stand at the elevator entrance and interact with the call button on one side—sensors for detecting elevator information can be installed on the robotic arm. Based on such a robotic arm, the robot can precisely control the end effector of the robotic arm to call the elevator according to the detected elevator information, thereby improving the flexibility of the robot's interaction with the elevator.

[0036] In some embodiments, see Figure 1 , Figure 1 A schematic diagram of the structure of a robot 1 is shown. For ease of explanation, only the parts relevant to this application are shown in the figure. The robot 1 includes a body 10, on which a first sensor 11 is disposed. A robotic arm 20 is disposed on each side of the body 10. Each robotic arm 20 includes a robotic arm end cap 21 and a second sensor 22 disposed on the robotic arm.

[0037] The first sensor 11 is mainly used to detect surrounding environmental information, enabling the robot 1 to move without collision based on this information. The second sensor 22 is mainly used to detect elevator information, allowing the robot 1 to interact with the elevator by controlling the robotic arm 20 to ride the elevator. The first sensor 11 can also assist the second sensor 22 in detecting elevator information. For example, both the first sensor 11 and the second sensor 22 can be image sensors. The second sensor 22 can be a stereo vision image sensor. The robotic arm has a large range of motion. By setting up two robotic arms 20, regardless of which side of the robot 1 the elevator button is on, the robot can move within a certain distance without moving itself by controlling the robotic arm 20 on the side adjacent to the elevator button to detect the button information based on the corresponding second sensor 22, and then control the end effector 21 of the robotic arm to press the target elevator call button based on the button information.

[0038] To illustrate the technical solution proposed in this application, the following description will use a robot with the above-described structure as the execution subject to illustrate various embodiments.

[0039] Figure 2 A schematic flowchart of the robot elevator selection method provided in this application is shown. The robot elevator selection method includes:

[0040] Step 210: After receiving the cross-floor task, the robot determines at least one first candidate elevator based on its own departure floor and the arrival floor corresponding to the cross-floor task.

[0041] The task information for cross-floor tasks includes the target floor. For example, in a delivery task, if the item needs to be delivered from the 8th floor to the 1st floor, then both the 8th and 1st floors are target floors, which are the floors the robot arrives at during its elevator ride. By combining this information with the floor the robot is on when it receives the task, we can determine how many elevator rides are required. For instance, if the robot receives the delivery task on the 5th floor, it needs to go from the 5th floor to the 8th floor, and then from the 8th floor to the 1st floor. Since the departure and arrival floors are different for the two elevator rides, and the overall process is the same for each ride, the subsequent solutions will be described using a single elevator ride process.

[0042] In high-rise buildings, different elevators may have limited access to certain floors. To improve elevator efficiency, before each elevator call, the robot can select at least one suitable candidate elevator based on its current departure and arrival floors. This ensures that the elevator can take the robot from its departure floor to its current destination floor, thus guaranteeing a smooth elevator ride. For example, if the robot receives a delivery task on the 5th floor to deliver items from the 8th floor to the 1st floor, then the departure floor is the 5th floor, and the current destination floor is the 8th floor. After the robot arrives at the 8th floor to retrieve the items, the departure floor is the 8th floor, and the current destination floor is the 1st floor.

[0043] For example, suppose a high-rise building has 12 elevators, 6 on the east side and 6 on the west side. Of the 6 elevators on the east / west side, 3 can go to lower floors and 3 can go to higher floors. Without considering the distance to the target floor, if the target floor is a lower floor, the robot can identify the 6 elevators on the east and west sides that can go to the lower floor as the first candidate elevators.

[0044] Preliminary elevator screening before calling an elevator increases the probability that the selected first-choice elevator can directly reach the destination floor from the departure floor, thus improving the robot's success rate in reaching the destination floor in one trip and increasing the robot's elevator usage efficiency. If no elevator can directly reach the destination floor from the departure floor, the robot can choose to take a connecting elevator, and the elevator that can reach the connecting floor will be selected as the first-choice elevator.

[0045] Step 220: The robot moves to the first call point corresponding to the first candidate elevator.

[0046] After the initial elevator selection, the robot can move to the first call point corresponding to the first candidate elevator in order to board the elevator as quickly as possible. If there are multiple first candidate elevators, there are various strategies to determine which first candidate elevator's first call point to go to.

[0047] For example, if the first candidate elevators are distributed in different areas of the building, and the number of first candidate elevators in each area is less than a set number, such as 1, in order to shorten the time required to reach the first call point, the nearest first candidate elevator can be selected for call.

[0048] For example, if the first candidate elevators are distributed in different areas of the building and the number of candidate elevators in each area is different, in order to get on the elevator as soon as possible, you can choose any one of the first candidate elevators in the area with the most first candidate elevators to call for the elevator.

[0049] For example, if the first elevators are scattered in different areas of the building, the robot can select the first candidate elevator corresponding to the shortest comprehensive path based on the target location of the floor to be reached and the robot's current location to call the elevator.

[0050] For example, if the first elevators are distributed in different areas of the building and the distance between each area is greater than a set value, the current robot can communicate with the robots in the elevators to obtain the current status of the elevators occupied by other robots, such as the floor they are on and their up and down information, and determine the first candidate elevator that will arrive at the departure floor within a preset time period from the first candidate elevators.

[0051] In other words, if there are multiple first candidate elevators, different selection strategies can be determined according to specific needs. Of course, the selection strategies can also be combined. For example, the first candidate elevator that is closest and relatively concentrated can be selected for elevator calling. In this embodiment, no specific limitations are made.

[0052] Furthermore, it's worth noting that a call point can also be a waiting point (usually directly in front of the elevator door). For example, if a robot's robotic arm is equipped with sensors and has a large range of motion, it can interact with the call button even when it's in a waiting point. However, if the robot's robotic arm lacks sensors or its range of motion is insufficient, the robot will rely on onboard sensors to detect elevator information. In this case, the robot's call point will be a location closer to the call button, such as a certain distance directly in front of the button, rather than a waiting point.

[0053] Step 230: The robot controls the robotic arm to activate the target elevator call button.

[0054] The direction the robot travels from its starting floor to its destination floor is its target elevator direction. To call the elevator accurately, the robot can press the corresponding elevator call button based on this target direction. For example, if the target elevator direction is upward (from the 22nd to the 28th floor), the robot can determine that the target elevator call button is the upward button.

[0055] Once the target elevator call button is identified, the robot can control its robotic arm to activate it. Specifically, the robot can use relevant sensors to detect and calculate the operation point where the target elevator call button will be pressed in real time, and then control the robotic arm to move to that operation point to press the target elevator call button, thereby activating the button and calling for elevator access.

[0056] Step 240: The robot acquires the status information of the second candidate elevator within the preset range.

[0057] Step 250: The robot selects the target elevator from the second candidate elevators based on the departure floor, arrival floor, and various status information.

[0058] There may be multiple elevators near the first elevator call point. Therefore, after calling an elevator, in order to board an elevator in the shortest possible time, the robot can identify a second candidate elevator within a preset range. This preset range can be defined based on the robot's location, for example, with the first elevator call point as the center and a preset distance value as the radius; or, if the building has an elevator area, the preset range can be determined based on the elevator area where the first elevator call point is located.

[0059] The second candidate elevator within the preset range can be the first candidate elevator corresponding to the first call point, or it can include other first candidate elevators within the range.

[0060] In order to make effective use of the waiting time after calling the elevator, the robot can obtain the information status of each second candidate elevator, and then combine the departure floor and the arrival floor to select a second elevator from each second candidate elevator, and determine the second candidate elevator that is expected to arrive at the departure floor first, i.e., the target elevator.

[0061] For example, the robot completes the elevator call at the first elevator waiting point, and this elevator call command can correspond to multiple second candidate elevators. For instance, there may be multiple elevators and multiple elevator call buttons in an elevator area. After each elevator call button receives an elevator call command, it will synchronize with all elevators in the current area that can execute the elevator call command (downward or upward). These elevators can all be used as second candidate elevators.

[0062] Step 260: The robot waits to board the elevator at the second call point corresponding to the target elevator.

[0063] The target elevator is the most efficient elevator predicted. In order to enter the target elevator efficiently and in a timely manner, the robot can wait at the second call point corresponding to the target elevator.

[0064] It is understandable that the target elevator may be the first candidate elevator when calling for an elevator. In this case, the robot can wait for the elevator in place. However, if the target elevator is not the first candidate elevator when calling for an elevator, the robot can go to the second elevator call point corresponding to the target elevator in order to take the elevator.

[0065] In this embodiment, for a robot equipped with a robotic arm capable of interacting with elevators, during the elevator selection process, an initial elevator selection can be performed based on the floor information corresponding to the cross-floor task to determine the first candidate elevator that can take you from the starting floor to the destination floor. To shorten the waiting time, the robot can first go to the first call point of the first candidate elevator and activate the corresponding call button through the robotic arm. After calling the elevator, to ensure that it can take the most efficient elevator to the destination floor, the robot can obtain the status information of each second candidate elevator within a preset range to perform a second elevator selection based on the status information, that is, to select the target elevator that is expected to reach the current floor first from each of the second candidate elevators. Throughout the process, the robot does not need to communicate with the elevator; it achieves autonomous elevator calling through interaction with the elevator via the robotic arm, selecting elevators once before and after calling the elevator, and finally determining the target elevator that is expected to be the most efficient and going there to wait for it. This can shorten the waiting time required for the robot and improve the execution efficiency of cross-floor tasks.

[0066] In some embodiments, in order to accurately predict the most efficient target elevator, the aforementioned step 250 specifically includes:

[0067] Step A1: For each second candidate elevator, the robot calculates the cost value corresponding to the second candidate elevator based on the departure floor, arrival floor, the state information corresponding to the second candidate elevator, and the preset cost function.

[0068] Because each candidate elevator operates differently, the cost for the robot to travel from the departure floor to the arrival floor varies depending on the candidate elevator. To quantify this difference, for each candidate elevator, the robot can calculate its corresponding cost based on the departure floor, arrival floor, the elevator's real-time status information, and a preset cost function. This allows for accurate estimation of the most efficient elevator and optimization of elevator selection decisions.

[0069] Step A2: The robot identifies the second candidate elevator corresponding to the minimum cost value as the target elevator.

[0070] The cost-benefit ratio reflects the time and resource costs incurred by the robot in selecting the second candidate elevator. A lower cost-benefit ratio means a better match between the departure and arrival floors and the corresponding second candidate elevator's path, allowing the robot to use the elevator with lower time and energy costs. By comparing the cost-benefit ratios of each second candidate elevator, the robot can optimize its elevator-using strategy, quickly selecting the optimal elevator from multiple options to improve task efficiency and resource utilization.

[0071] In this embodiment, the robot can calculate the cost of taking each second candidate elevator by using the real-time status information of the departure floor, the arrival floor, and each second candidate elevator, as well as a preset cost function. In other words, the efficiency of different second candidate elevators is quantified. By comparing the cost of each second candidate elevator, the robot can select the most efficient elevator as the target elevator from multiple elevators, so as to make full and effective use of elevator resources and shorten the waiting time.

[0072] In some embodiments, in order to accurately calculate the cost value corresponding to each second candidate elevator, the aforementioned step A1 specifically includes:

[0073] Step A11: The robot determines the target operating mode of the elevator before boarding the elevator based on the current operating direction, the first target operating direction, and the second target operating direction.

[0074] The status information includes the current floor and current direction of travel of the elevator. Based on the different status information of the elevator, the robot determines the different operating modes of the elevator before boarding it.

[0075] For example, suppose the robot wants to go from the 5th floor to the 9th floor. At this time, the current floor of the elevator is the 7th floor and the current direction of operation is upward. Before the elevator reaches the 5th floor, its operation mode is estimated to be: first go up to the top floor, then go down to the 1st floor, and then go to the 5th floor.

[0076] For example, suppose the robot wants to go from the 5th floor to the 9th floor. At this time, the current floor of the elevator is the 3rd floor and the current direction of operation is upward. Then, before the elevator reaches the 5th floor, its operation mode is estimated to be: go directly upward to the 3rd floor.

[0077] Based on this, after knowing the status information of the second candidate elevator, the target operating mode that matches the status information can be determined from each operating mode based on the relationship between the status information and the operating mode.

[0078] Step A12: The robot determines the target cost function from multiple cost functions based on the target operating mode.

[0079] Step A13: Calculate the cost value corresponding to the second candidate elevator based on the objective cost function.

[0080] Different operating modes may have different cost values. In order to accurately calculate the cost value corresponding to each second candidate elevator based on the cost function, multiple cost functions can be set, and a corresponding cost function can be set for each operating mode.

[0081] For example, suppose the cost function is denoted as G(k), and the starting floor F of the robot is known. c Arrive at floor F oThe total number of floors in the elevator is L, and the cost of opening it at least once is C.

[0082] The current floors of all second-choice elevators are E = {E1, E2, E3, ..., E...} n The current running direction (stationary = 0, up = 1, down = -1) is {S1, S2, S3, ..., S...}. n}

[0083] Does the robot need to go up or down? o =sgn(F o -F c The corresponding elevator also needs to run in the same direction.

[0084] Taking any second candidate elevator as an example, assume E = E k S = S k When S k When the value is 0, the elevator remains stationary and can directly proceed to the starting floor where the robot is located; ideally, the cost is minimized at this point: G(k) = |E k -F c |

[0085] However, in practical applications, it may also be affected by E k S k and E k -F c The magnitude of these three values ​​affects the complexity of the elevator's operation mode, resulting in different parameters for the cost function. Specifically, please refer to the table below. Table 1 shows the evaluation functions corresponding to different elevator operation modes, where L represents the total number of floors. In this example, it is assumed that L is a fixed value and greater than 10.

[0086] Table 1 Cost functions corresponding to different operating modes

[0087]

[0088] Based on the relationship between operating modes and cost functions, after determining the target operating mode, the robot can select the target cost function that matches the target operating mode from multiple cost functions. Each second candidate elevator can have its cost value calculated using the matched target cost function, thus accurately quantifying the cost of the robot using different second candidate elevators.

[0089] In this embodiment, each second candidate elevator is matched with a corresponding target cost function based on its target operating mode. This ensures that the calculation method of the cost value is adapted to the current operating mode of the elevator, facilitating a quick and accurate determination of the cost of riding the elevator. As a result, the robot can more accurately evaluate the selection cost of each second candidate elevator, thereby improving the accuracy of the target elevator selection. When constructing the cost function, the robot's riding direction, the current state of the elevator, and the influence of the elevator's on / off switch are fully considered, which improves the accuracy of the prediction, making it easier for the robot to find the optimal target elevator and improving riding efficiency.

[0090] In some embodiments, to further improve the accuracy of cost value calculation, before calculating the cost value corresponding to the second candidate elevator based on the objective cost function, the following steps are also included:

[0091] Step B1: If the second candidate elevator is a preset elevator, the robot obtains the elevator attributes of the second candidate elevator.

[0092] Step B2: The robot optimizes the cost function based on the elevator attributes.

[0093] Preset elevators refer to elevators with special attributes, such as elevators that only stop on odd-numbered floors or only on high floors. In this case, the time required to pass through the same number of floors is shorter than that of an elevator that can stop on all floors.

[0094] Therefore, in order to make the cost function more consistent with the elevator attributes of the second candidate elevator, the robot can first determine whether the second candidate elevator is a preset elevator. If the elevator is a preset elevator, the cost function can be optimized according to the elevator attributes. For example, for an elevator that only stops on the upper floors, the corresponding cost value can be set according to the number of floors on the lower floors, and the cost function of the second candidate elevator can be optimized through the cost value.

[0095] For example, the robot can obtain the elevator attributes corresponding to different preset elevators in advance. During the elevator ride, the robot can collect relevant information through sensors or communicate with the elevator robot to obtain the corresponding attribute information. The robot can then match the attribute information with the elevator attributes corresponding to different preset elevators. If a match is found, the second candidate elevator can be determined as the preset elevator.

[0096] Accordingly, step A13 includes:

[0097] B21. The robot calculates the cost value corresponding to the second candidate elevator based on the optimized cost function.

[0098] It is understandable that if the second candidate elevator is a candidate elevator, then when calculating the cost value of the second candidate elevator, the optimized cost function of the second candidate elevator can be used to calculate the cost value, thereby further improving the accuracy of the cost value calculation.

[0099] In this embodiment, for a second candidate elevator with special attributes, especially an elevator whose attributes affect the calculation of cost value, the robot can obtain the elevator attributes of the second candidate elevator to optimize the corresponding cost function, and calculate the cost value of the second candidate elevator through the optimized cost function, so as to improve the accuracy of the cost value calculation.

[0100] In some embodiments, to improve the flexibility and efficiency of the robot in acquiring elevator information, the robot can obtain the status information of the second candidate elevator through the following steps:

[0101] Step C1: At the first call point, the robot controls the movement of the image sensor to collect elevator data in order to determine the status information based on the elevator data.

[0102] And / or, in step C2, communicate with the robot riding the elevator to obtain status information.

[0103] The robot can obtain the status information of the second candidate elevator in two ways. The robot can choose one of the two methods or combine the two methods. There is no specific limitation.

[0104] In the first approach, the robot can collect elevator information using its onboard image sensors. For example, the robot can deploy a trained detection model, input the acquired elevator image into the model to obtain detection results, and extract the elevator's status information. Alternatively, the robot can employ traditional OCR (Optical Character Recognition) algorithms to acquire elevator images via image sensors to recognize text or numbers on the elevator panel, determining key information such as the elevator's current floor, direction of travel, and status. By combining these technologies, the robot can acquire and analyze the status information of a second candidate elevator in real time, providing support for elevator selection decisions.

[0105] The robot is equipped with image sensors for collecting elevator information, such as a first sensor 11 located on the robot's head and a second sensor 22 located on the robot's robotic arm. For example, both the first sensor 11 and the second sensor 22 can be image sensors. The robot can control the movement of its robotic arm at a first call point, thereby moving the second sensor 22 to capture images and obtain elevator data from multiple candidate elevators. This allows the robot to obtain the status information of the candidate elevators without communicating with the elevators or other robots.

[0106] If there are multiple second candidate elevators and the interval between the status panels of the second candidate elevators is greater than a predetermined value, an observation point can be set in advance. The observation point is set between the status panels of the multiple second candidate elevators. After the robot completes the elevator call at the first call point, it goes to the observation point and uses the first sensor 11 set on the head to obtain elevator data of the multiple second candidate elevators by rotating the robot in place.

[0107] If the first sensor 11 cannot completely acquire elevator data for the second candidate elevator at the observation point, the missing area of ​​the status panel is determined based on the image information captured by the first sensor 11. The robot remains at the observation point, and the second sensor 22 is controlled to move and capture images of the missing area, thus achieving complete elevator data acquisition. The robot can rotate in place at the observation point and / or control the movement of the second sensor without moving the entire robot, thereby reducing the impact on people entering and exiting the elevator and improving the integrity of the elevator data.

[0108] In another approach, robots can communicate with other elevator-riding robots to share key information such as the elevator's current floor, direction of travel, and status. By exchanging information, robots can understand in real time the elevator's availability, estimated arrival time, and whether other robots are already preparing to board, thereby optimizing their own elevator-riding decisions. This collaborative approach not only reduces resource conflicts but also improves overall elevator efficiency, especially in scenarios where multiple robots are performing tasks simultaneously, enabling more intelligent scheduling and path planning.

[0109] In this embodiment of the application, the robot can flexibly obtain the status information of the second candidate elevator in a variety of ways, which can improve the efficiency of status information acquisition and help improve elevator riding efficiency.

[0110] In some embodiments, for a robot to autonomously acquire elevator information and select a target elevator, a complex algorithm needs to be configured. This not only increases the computational load but also places higher demands on the robot's hardware performance. To improve the compatibility of this application with robots of different performance levels, the robot can perform the following steps:

[0111] Step D1: The robot generates guidance text based on the departure floor, arrival floor, status information, and each second candidate elevator.

[0112] To reduce computational load, the robot can generate guidance text based on the departure floor, the target arrival floor, and the status information of each elevator. This guidance text contains key parameters for elevator selection; for example, it may include "The robot's departure floor is X, and the destination floor is Y; Elevator A's current floor is M1, and its direction of travel is upward; Elevator A's current floor is M2, and its direction of travel is downward... Please determine which elevator will arrive at floor X first."

[0113] Step D2: The robot sends the guidance text to the preset model.

[0114] Step D3: The robot determines the target elevator based on the output of the preset model.

[0115] The guidance text is input into the preset model, which can make a decision based on the content of the guidance text and output which second candidate elevator arrives at the departure floor first, that is, which second candidate elevator can be used as the target elevator by the robot.

[0116] For example, the preset model can be a large model. Large models have powerful computing capabilities and can be used directly without user training. They can more efficiently and accurately determine the target elevator that is expected to arrive first based on the guidance text.

[0117] In this embodiment, the robot generates guidance text based on the departure floor, the target arrival floor, and the status information of each elevator, describing key parameters. Next, the robot sends this guidance text to a pre-set large-scale model. This model, after training, can comprehensively evaluate elevator status and floor requirements to analyze suitable target elevators. Finally, based on the output of the large-scale model, the robot determines the final target elevator to ensure its riding efficiency and task success rate. This process enables the robot to effectively select target elevators, eliminating the need for additional training by the user and reducing the robot's computational load. Thus, even robots with average performance can apply the elevator riding method of this application, improving the applicability of the method.

[0118] In some embodiments, in order to control the robotic arm to interact precisely with the target elevator call button and activate the target elevator call button, the robot may perform the following steps:

[0119] Step E1: The robot controls the robotic arm to move from the safe point to the detection point.

[0120] Step E2: At the detection point, the robot detects the button information of the elevator call button based on the sensors set on the robotic arm.

[0121] During the robot's movement, its robotic arm is positioned at a safe point, where it is less likely to collide with other objects, effectively ensuring the safety of the robot's movement.

[0122] For example, the safety points can be the default settings when the robot leaves the factory, or they can be set according to customer needs. Usually, the robotic arm is in a state of retraction that is close to the robot body, similar to a human arm. In this state, the robotic arm is not easy to interfere with the outside world, which can effectively ensure the safety of the robot during movement.

[0123] Once the robot moves to the first call point, the robotic arm can be controlled to move from the safety point to the detection point, so that the button information of the elevator call button can be detected by the sensors set on the robotic arm.

[0124] Step E3: The robot calculates the operation point corresponding to the target call button based on the button information and detection point.

[0125] After obtaining the button information, the robot can calculate the operation point corresponding to pressing the target elevator call button based on the button information and detection point of the target elevator call button. By calculating the operation point corresponding to pressing the target elevator call button based on the real-time collected button information and the first detection point, the robot can improve the reliability of the operation point and thus increase the probability of the robot successfully calling the elevator by pressing the button.

[0126] Step E4: The robot controls the robotic arm to move to the operation point and presses the target call button corresponding to the preset position to activate the target call button.

[0127] After calculating the precise operation point, the robot can control the robotic arm at the detection point to move to the operation point and press the target call button to activate the target call button.

[0128] In this embodiment, by setting safety points, detection points, and calculated operation points, the robot can accurately drive the robotic arm to interact smoothly with the target elevator call button, effectively improving elevator riding efficiency. The entire process does not require communication between the robot and the elevator, so there is no need to modify the elevator, ensuring the robot's applicability to various scenarios.

[0129] In some embodiments, after executing step E4, the robot can control the robotic arm to move to the detection point and detect the elevator call button information to determine whether the target elevator call button has been successfully activated. If it has been successfully activated, the robot controls the robotic arm to move to a safe point to facilitate subsequent movement. If it has not been successfully activated, the robot returns to executing step E2 and its subsequent steps until it is determined that the target elevator call button has been successfully activated.

[0130] In some embodiments, if the target elevator call button that the robot wants to activate may have already been activated before the robot interacts with the target elevator call button, in order to reduce useless operations, the robot can first determine whether the target elevator call button has been activated before executing step E3. If it has been activated, step 240 can be executed directly; if it has not been activated, step E3 and subsequent steps are executed until the target elevator call button is activated.

[0131] In some embodiments, the button information includes the relative position information between the target call button and the sensor. To accurately calculate the operation point, the aforementioned step 230 specifically includes:

[0132] Step A1: The robot calculates the first pose transformation matrix between the target call button and the sensor based on the relative position information.

[0133] The robot can establish a reference frame based on the sensor, and combine this relative position information to calculate the first pose transformation matrix from the location of the target elevator call button to the location of the sensor, which can be denoted as...

[0134] Step A2: The robot obtains the second pose transformation matrix between the end effector of the robotic arm and the robot's calibrated position when the robotic arm is at the detection point.

[0135] Given that the robot's current location is the detection point, the robot can obtain the second pose transformation matrix from the position of the robotic arm's end effector to the robot's calibrated position at the detection point, which can be denoted as: Typically, the robot's calibrated position is a relatively unchanging location, such as the center of the robot's base or the center of the robot body. Using these positions as reference points, the robot can more accurately control the movement of its robotic arm.

[0136] Step A3: The robot calculates the first operation point based on the first pose transformation matrix, the second pose transformation matrix, and the third pose transformation matrix between the robotic arm end effector and the sensor.

[0137] Since the position between the robotic arm's end effector and the sensor is relatively fixed, the robot can also obtain a third pose transformation matrix from the sensor's position to the position of the robotic arm's end effector, which can be denoted as...

[0138] Given that the positional relationship between the robotic arm's end effector (when located at the detection point) and the robot's calibrated position, as well as the positional relationship between the robotic arm's end effector and the sensors mounted on the robotic arm, are relatively fixed, therefore and It can be pre-calibrated and used as known parameters in subsequent calculations to improve computational efficiency.

[0139] To facilitate the robot's end effector pressing the target elevator call button, the location of the target elevator call button can be transformed into a coordinate system established based on the robot's calibrated position using three pose transformation matrices. Specifically, the pose transformation matrix corresponding to the first operation point... The calculation formula is as follows:

[0140]

[0141] The first pose transformation matrix defines the position of the target call button relative to the sensor, but this is still different from the reference frame of the robotic arm. The second pose transformation matrix transforms the reference frame of the robotic arm's end effector to the reference frame of the robot's calibrated position. The third pose transformation matrix then aligns the sensor and the robotic arm's end effector to ensure consistency in the final operation.

[0142] In this embodiment, combining multiple pose transformations effectively ensures the accuracy of robot operations. Each pose transformation matrix provides precise descriptions of position and orientation; combining them multiple times eliminates measurement errors from a single data source and accumulates compensation for multiple small-range errors. Furthermore, different pose matrices can integrate the coordinate systems of the sensors, the robotic arm's end effector, and the calibration point, ensuring coordination among various parts during operation and preventing error accumulation. Multiple transformations also adapt to complex scenarios and dynamic changes, enabling the robot to update and correct the first operating point in real time, achieving higher accuracy and stability in the pressing operation.

[0143] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0144] Corresponding to the robot ladder selection method in the above embodiment, Figure 3 The diagram shows a structural block diagram of the robot ladder selection device 3 provided in the embodiment of this application. For ease of explanation, only the parts related to the embodiment of this application are shown.

[0145] Reference Figure 3 The robot elevator selection device 3 includes:

[0146] The first elevator selection module 31 is used to determine at least one first candidate elevator based on the robot's departure floor and the destination floor corresponding to the cross-floor task after receiving the cross-floor task; the candidate elevator is the elevator that the robot can take from the departure floor to the destination floor.

[0147] Motion module 32 is used to move to the first call point corresponding to the first candidate elevator;

[0148] Control module 33 is used to control the robotic arm to activate the target call button;

[0149] The first acquisition module 34 is used to acquire the status information of the second candidate elevator within a preset range; the first target running direction of the elevator corresponding to the target elevator call button is consistent with the robot's target elevator riding direction.

[0150] The second elevator selection module 35 is used to select a target elevator from the second candidate elevators based on the departure floor, arrival floor and various status information; the target elevator is the second candidate elevator that arrives at the departure floor first in advance.

[0151] Motion module 32 is also used to wait for the elevator at the second call point corresponding to the target elevator.

[0152] Optionally, the second elevator selection module 35 includes:

[0153] The calculation unit is used to calculate the cost value of each second candidate elevator based on the departure floor, arrival floor, the state information corresponding to the second candidate elevator, and a preset cost function.

[0154] The elevator selection unit is used to determine the second candidate elevator corresponding to the minimum cost as the target elevator.

[0155] Optionally, the status information includes the current floor and current direction of travel of the elevator; there are multiple cost functions; the calculation unit is specifically used for:

[0156] Based on the current running direction, the first target running direction, and the second target running direction, the target running mode of the elevator before the robot takes the elevator is determined; each elevator running mode is set with a corresponding cost function.

[0157] The target cost function is determined from multiple cost functions based on the target operating mode; the second target operating direction is the direction corresponding to the elevator's movement from the current floor to the destination floor;

[0158] The cost value corresponding to the second candidate elevator is calculated based on the objective cost function.

[0159] Optionally, the robot elevator selection device 3 may include:

[0160] The second acquisition module is used to acquire the elevator attributes of the second candidate elevator if the second candidate elevator is a preset elevator before calculating the cost value corresponding to the second candidate elevator based on the target cost function.

[0161] The optimization module is used to optimize the cost function based on elevator properties;

[0162] Accordingly, the computing unit is specifically used for:

[0163] The cost value corresponding to the second candidate elevator is calculated based on the optimized cost function.

[0164] Optionally, the robot is equipped with an image sensor for collecting elevator information; the first acquisition module 34 is specifically used for:

[0165] At the first call point, the robot controls the movement of the image sensor to collect elevator data in order to determine the status information based on the elevator data;

[0166] And / or, communicate with the robot riding the elevator to obtain status information.

[0167] Optionally, the second elevator selection module 35 can be used for:

[0168] Guide text is generated based on the departure floor, arrival floor, status information, and each second candidate elevator.

[0169] The guidance text is sent to the preset model; the preset model is used to output the target elevator based on the guidance text.

[0170] The target elevator is determined based on the output of the preset model.

[0171] Optionally, the control module 33 is specifically used for:

[0172] Control the robotic arm to move from the safe point to the detection point;

[0173] At the detection points, the button information of the elevator call button is detected based on the sensors set on the robotic arm;

[0174] Calculate the operation point corresponding to the target elevator call button based on button information and detection point location;

[0175] Control the robotic arm to move to the operating point, press the target button corresponding to the preset position to activate the target call button.

[0176] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0177] Figure 4 This is a schematic diagram of the physical structure of a robot provided in one embodiment of this application. Figure 4 As shown, the robot 4 in this embodiment includes: at least one processor 40 ( Figure 4 Only one processor is shown in the diagram. A memory 41 and a computer program 42 stored in the memory 41 and executable on at least one processor 40 are also shown. When the processor 40 executes the computer program 42, it implements the steps in any of the robot ladder selection method embodiments described above, for example... Figure 2 Steps 210-260 are shown.

[0178] The processor 40 can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0179] In some embodiments, memory 41 may be an internal storage unit of robot 4, such as a hard disk or memory of robot 4. In other embodiments, memory 41 may also be an external storage device of robot 4, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on robot 4.

[0180] Furthermore, the memory 41 may include both internal storage units and external storage devices of the robot 4. The memory 41 is used to store operating devices, application programs, bootloaders, data, and other programs, such as program code for computer programs. The memory 41 can also be used to temporarily store data that has been output or will be output.

[0181] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the above device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0182] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0183] This application provides a computer program product that, when run on a robot, enables the robot to perform the steps described in the above-described method embodiments.

[0184] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to a photographic device / electronic device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, such as a USB flash drive, a portable hard drive, a magnetic disk, or an optical disk.

[0185] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0186] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0187] In the embodiments provided in this application, it should be understood that the disclosed apparatus / network devices and methods can be implemented in other ways. For example, the apparatus / network device embodiments described above are merely illustrative. For instance, the division of modules or units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0188] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0189] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for selecting ladders by a robot, characterized in that, The robot is equipped with a robotic arm for interacting with elevator buttons; the elevator selection method includes: After receiving a cross-floor task, at least one first candidate elevator is determined based on the robot's departure floor and the destination floor corresponding to the cross-floor task; the candidate elevator is an elevator that the robot can take from the departure floor to the destination floor; Move to the first call point corresponding to the first candidate elevator; The robotic arm is controlled to activate the target elevator call button; the first target running direction of the elevator corresponding to the target elevator call button is consistent with the robot's target elevator riding direction. Obtain the status information of the second candidate elevator within a preset range; A target elevator is selected from the second candidate elevators based on the departure floor, the arrival floor, and each of the status information; the target elevator is the second candidate elevator that is expected to arrive at the departure floor first. Wait for the elevator at the second call point corresponding to the target elevator.

2. The robot ladder selection method as described in claim 1, characterized in that, The step of selecting a target elevator from the second candidate elevators based on the departure floor, the arrival floor, and each of the status information includes: For each second candidate elevator, the cost value corresponding to the second candidate elevator is calculated based on the departure floor, the arrival floor, the state information corresponding to the second candidate elevator, and a preset cost function. The second candidate elevator corresponding to the minimum cost value is determined as the target elevator.

3. The robot ladder selection method as described in claim 2, characterized in that, The status information includes the current floor and current direction of travel of the elevator; there are multiple cost functions; the calculation of the cost value corresponding to the second candidate elevator based on the departure floor, the arrival floor, the status information of the second candidate elevator, and the preset cost functions includes: Based on the current running direction, the first target running direction, and the second target running direction, the target running mode of the elevator is determined before the robot takes the elevator; each elevator running mode is set with a corresponding cost function. A target cost function is determined from multiple cost functions based on the target operating mode; the second target operating direction is the direction corresponding to the elevator's movement from the current floor to the destination floor; The cost value corresponding to the second candidate elevator is calculated based on the objective cost function.

4. The robot ladder selection method as described in claim 3, characterized in that, Before calculating the cost value corresponding to the second candidate elevator based on the objective cost function, the method further includes: If the second candidate elevator is a preset elevator, then obtain the elevator attributes of the second candidate elevator; Optimize the cost function based on the elevator attributes; Accordingly, calculating the cost value corresponding to the second candidate elevator based on the objective cost function includes: The cost value corresponding to the second candidate elevator is calculated based on the optimized cost function.

5. The robot ladder selection method as described in any one of claims 1-4, characterized in that, The robot is equipped with an image sensor for collecting elevator information; acquiring the status information of a second candidate elevator within a preset range includes: At the first elevator call point, the robot controls the movement of the image sensor to collect elevator data, so as to determine the status information based on the elevator data; And / or, communicate with the robot riding the elevator to obtain the status information.

6. The robot ladder selection method according to any one of claims 1 to 4, characterized in that, The step of selecting a target elevator from the second candidate elevators based on the departure floor, the arrival floor, and each of the status information includes: Based on the departure floor, the arrival floor, and each of the status information and each of the second candidate elevators, guide text is generated; The guidance text is sent to a preset model; the preset model is used to output the target elevator based on the guidance text. The target elevator is determined based on the output of the preset model.

7. The robot ladder selection method according to any one of claims 1 to 4, characterized in that, The control of the robotic arm to activate the target elevator call button includes: Control the robotic arm to move from the safe point to the detection point; At the detection point, the button information of the elevator call button is detected based on the sensor installed on the robotic arm; Calculate the operation point corresponding to the target elevator call button based on the button information and the detection point; Control the robotic arm to move to the operation point and press the target call button corresponding to the preset position to activate the target call button.

8. A robot ladder selection device, characterized in that, The robot is equipped with a robotic arm for interacting with elevator buttons; the robot's elevator selection device includes: The first elevator selection module is used to determine at least one first candidate elevator based on the robot's departure floor and the arrival floor corresponding to the cross-floor task after receiving the cross-floor task; the candidate elevator is an elevator that the robot can take from the departure floor to the arrival floor; The motion module is used to move to the first call point corresponding to the first candidate elevator; The control module is used to control the robotic arm to activate the target elevator call button; The first acquisition module is used to acquire the status information of the second candidate elevator within a preset range; the first target running direction of the elevator corresponding to the target elevator call button is consistent with the target elevator riding direction of the robot. The second elevator selection module is used to select a target elevator from the second candidate elevators based on the departure floor, the arrival floor, and each of the status information; the target elevator is the second candidate elevator that arrives at the departure floor first. The motion module is also used to wait for the elevator at the second call point corresponding to the target elevator.

9. A robot comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the robot ladder selection method as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by one or more processors, it implements the robot ladder selection method as described in any one of claims 1 to 7.

Images