A method, device, equipment and storage medium for target following

Abstract

The present invention discloses a method, device, equipment and storage medium for target following. The method is applied to a robot and includes: obtaining environmental point cloud data of the current environment, and judging whether there is a target object in the current environment according to the environmental point cloud data. If there is a target object, obtaining the point cloud data of the target object as target point cloud data, and monitoring the target object based on the target point cloud data. If it is monitored that the target object stays in a set area and the stay time exceeds a first set duration, then determining the set area as the target docking area and moving to the target docking area. By monitoring the target object, this method autonomously completes the determination of the moving target location, saves the interaction between humans and the robot, enables the smooth cooperation between the target object and the robot, avoids inconveniencing the movement of the target object when following the target object throughout the process, and ensures the work efficiency of the target object and the robot.

Description

Technical Field

[0001] The present invention belongs to the technical field of robot control, and particularly relates to a method, device, equipment and storage medium for target following. Background Art

[0002] Currently, in scenarios such as the delivery of items in health stations and the examination of patients in hospital wards, the role of robots is often to replace humans in carrying items such as meals and inspection tools. The main requirements for robots are that they need to carry objects smoothly to the working area where the staff stays, then wait for the staff to complete their operations in the working area, and then follow the staff to the next working area. In such scenarios where movement is required in cooperation with the staff, the collaboration and coordination between robots and staff are particularly important.

[0003] However, for current robots used for following a target, when following a target object, they will strictly track the position and state of the target object. Due to real-time following, it is very likely to interfere with the movement of the target object during the following process. In addition, when the target object moves to the next working area, it needs to interact with the robot to enable the robot to determine the next target position. Frequent interaction requirements will lead to a decrease in the work efficiency of the target object and a poor following experience. Summary of the Invention

[0004] The present invention provides a method, device, equipment and storage medium for target following, so as to solve the problem that current robots used for following a target are difficult to achieve target following without interaction during the working process and can also ensure the following experience of the target object.

[0005] According to one aspect of the present invention, a method for target following is provided. The method is applied to a robot and includes:

[0006] Obtain the environmental point cloud data of the current environment, and determine whether there is a target object in the current environment according to the environmental point cloud data;

[0007] If there is a target object, obtain the point cloud data of the target object as the target point cloud data;

[0008] Based on the target point cloud data, monitor the target object. If it is monitored that the target object stays in the set area and the stay time exceeds the first set duration, then determine the set area as the target docking area and move to the target docking area.

[0009] According to one aspect of the present invention, a device for target following is provided. The device is applied to a robot and includes:

[0010] A target object judgment module, configured to obtain environmental point cloud data of the current environment, and determine whether there is a target object in the current environment according to the environmental point cloud data;

[0011] A target point cloud data acquisition module, configured to, if there is a target object, acquire the point cloud data of the target object as target point cloud data;

[0012] A monitoring module, configured to monitor the target object based on the target point cloud data;

[0013] A moving module, configured to, if it is monitored that the target object stays in a set area and the staying time exceeds a first set duration, determine the set area as a target docking area, and move to the target docking area.

[0014] According to another aspect of the present invention, there is provided an electronic device, including:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute a method for target following according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement a method for target following according to any embodiment of the present invention when executed.

[0019] The technical solution of the embodiment of the present invention provides a method for target following, which is applied to a robot. The method includes: obtaining environmental point cloud data of the current environment, and determining whether there is a target object in the current environment according to the environmental point cloud data. If there is a target object, acquire the point cloud data of the target object as target point cloud data, monitor the target object based on the target point cloud data. If it is monitored that the target object stays in a set area and the staying time exceeds a first set duration, determine the set area as a target docking area, and move to the target docking area. This method can autonomously complete the determination of the moving target location by monitoring the target object, saving the interaction between humans and the robot, making the cooperation between the target object and the robot smooth, avoiding inconvenience to the movement of the target object when following the target object throughout the process, and ensuring the work efficiency of the target object and the robot.

[0020] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0022] Figure 1 is a flowchart of a target following method provided according to Embodiment 1 of the present invention;

[0023] Figure 2 is a schematic diagram of a robot and a target object provided according to Embodiment 1 of the present invention;

[0024] Figure 3 is a schematic diagram of environmental point cloud provided according to Embodiment 1 of the present invention;

[0025] Figure 4 is a schematic diagram of a set area provided according to Embodiment 1 of the present invention;

[0026] Figure 5 is a schematic structural diagram of a target following device provided according to Embodiment 2 of the present invention;

[0027] Figure 6 is a schematic structural diagram of an electronic device for implementing the target following method of the embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] In order to enable those skilled in the art to better understand the solutions of the present invention, the following clearly and completely describes the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the description, claims and above-mentioned drawings of the present invention are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0030] Embodiment 1

[0031] Figure 1 The figure is a flowchart of a method for target following provided in Embodiment 1 of the present invention. This method is applied to a robot. The robot can be a robot for carrying meals, a robot for carrying inspection equipment, etc., and can cooperate with a following target to complete work tasks. The robot can be an indoor robot or an outdoor robot.

[0032] In a general scenario, the robot only needs to make a corresponding path plan according to the given target instruction and combine the deployment information to reach the specified target site. Human operation often only occurs in the starting and ending links. However, in scenarios such as the delivery of items in a health station and nucleic acid testing, the role of the robot is often to replace humans to carry items such as meals and detection tools and participate in the work process of the staff. The staff will go to different target sites according to the actual work situation, such as different wards, etc. In such a case, it is necessary to have multiple interactions between humans and the robot so that the target end point of the robot continuously changes with the change of the work location of the staff.

[0033] During the process of the staff going to a new target site, the robot needs to identify the specified staff and perform real-time motion following on the staff. During the process of the staff operating and moving near the site, the robot can shield the following target and maintain a stopped state so that the staff can pick up and place items.

[0034] Based on such scenario applications, the key points lie in the following three aspects: the following motion made by the robot is smooth and stable, ensuring the safety of the items carried by the robot, without tipping over or bumping; the second is the detection of the target object to ensure that the robot does not lose the target object; finally, the selection of the target site and the docking strategy to ensure that the robot can accurately cooperate with the target object tacitly and complete the work.

[0035] This method can be executed by a target following device, which can be implemented in the form of hardware and / or software.

[0036] As Figure 1 shown, this method includes the following steps:

[0037] S110. Obtain the environmental point cloud data of the current environment, and determine whether there is a target object in the current environment according to the environmental point cloud data.

[0038] The robot can scan the current environment through a lidar to obtain the environmental point cloud data of the current environment. The environmental point cloud data can be the three-dimensional position information, intensity, color, etc. of all the environmental points scanned currently.

[0039] In the application scenario of this target following method, it can be realized that a robot is associated with a target object for following.

[0040] The target object can be other mobile robots or a human body, that is, the target human body. Exemplarily, the lidar of the robot can be used to scan the target human body in advance. When scanning the target human body, in order to obtain more accurate feature data of the target human body, the target human body can stand in a place without background interference for scanning, and multiple scans are performed to obtain point cloud data. After obtaining the point cloud data of the target human body, filtering, segmentation, and feature extraction steps can be performed to obtain the feature data of the target human body, and the obtained feature data of the target human body can be pre-recorded in the robot.

[0041] The collected environmental point cloud data can be subjected to filtering, segmentation, and feature extraction steps. The feature data corresponding to the pre-stored target human body can be compared with the feature data obtained after processing the environmental point cloud data. If there is feature data with a high similarity to the feature data corresponding to the target human body in the feature data obtained after processing the environmental point cloud data, it can be considered that there is a target object in the current environment.

[0042] In one embodiment, the environmental point cloud data includes the reflectivity of the environmental point cloud, and step S110 includes:

[0043] S110-1. Compare the reflectivity of each environmental point cloud with a preset reflectivity threshold;

[0044] S110-2. If there is an environmental point cloud with a reflectivity greater than or equal to the reflectivity threshold, it is determined that there is a target object.

[0045] In order to easily adapt different objects to become target objects and make the transformation of target objects faster and more convenient, the target objects can be made to carry iconic items that can be easily identified by the lidar, such as reflective strips, which can increase the reflectivity of the point cloud so that it can be distinguished from other point clouds in the environment.

[0046] The reflectivity of an object's surface is used to record the intensity of the return signal. When the LiDAR acquires an environmental point cloud, it can determine the reflectivity of the environment point cloud based on the intensity of the return signal. This can be determined based on the landmark items carried by the target object. For example, if the landmark item is a reflective strip, the specific reflectivity threshold can be determined based on an intensity value of 185.

[0047] For example, on the same floor of a hospital, multiple medical staff may need to use robots to carry items at different time periods. In order to save the initial work of entering human feature data and reduce the storage requirements for the robot, when a medical staff needs to use the robot, the medical staff can carry a reflective strip. In order to better identify the reflective strip and not be restricted by the height of the target object, the target person can place the reflective strip on the leg when carrying it, for example, by tying it to the leg with a rope.

[0048] refer to Figure 2 A schematic diagram of a robot and a target object, a is the robot, b is the laser radar, c is the target object, and d is the reflective strip. When the laser radar scans the current environment, if there is a target object with a reflective strip bound to its legs in the environment, Figure 3 As shown in the schematic diagram of an environment point cloud, we can get the following Figure 3 Point cloud distribution, where the point cloud in part D is obtained after scanning the reflective strip.

[0049] When determining whether there is a point cloud obtained by scanning reflective strips in the environment, the reflectivity of the environmental point cloud can be compared with a preset reflectivity threshold. When there is an environmental point cloud with a reflectivity greater than or equal to the reflectivity threshold, it can be considered that the target object exists.

[0050] In specific implementation, factors such as the number and distance of environmental point clouds with a reflectivity greater than or equal to the reflectivity threshold can also be combined to jointly determine whether there is a target object. Exemplarily, if there are only 2 environmental point clouds with a reflectivity greater than or equal to the reflectivity threshold, and when the reflective strips carried by the target object are present in the environment, the point clouds with strong reflectivity obtained by scanning will be far more than 2. It can be determined that these two point clouds do not come from the reflective strips. Then, even if there are environmental point clouds with a reflectivity greater than or equal to the reflectivity threshold, it can be determined that there is no target object in the current environment. A very small number of environmental point clouds with high reflectivity are likely to be only interference from other easily reflective objects in the environment.

[0051] S120. If there is a target object, obtain the point cloud data of the target object as the target point cloud data.

[0052] When it is determined that there is a target object in the current environment, the point cloud data of the target object can be determined from the environmental point cloud data. The point cloud data can include the point cloud coordinates corresponding to the target object. It should be noted that this does not refer to the point cloud coordinates of all the point clouds in the space occupied by the target object, but the point cloud coordinates that can be used to represent the target object. For example, when a reflective strip is tied to the leg of the target object and the lidar determines the existence of the target object through the comparison of reflectivity, the point cloud corresponding to the reflective strip at this time is the point cloud corresponding to the target object.

[0053] In one embodiment, the environmental point cloud data further includes the point cloud coordinates of the environmental point clouds, and step S120 includes the following steps:

[0054] S120-1. If there is a target object, use the environmental point clouds with a reflectivity greater than or equal to the reflectivity threshold as candidate target object point clouds;

[0055] S120-2. Segment the candidate target object point clouds to obtain one or more point cloud clusters;

[0056] S120-3. Determine the average reflectivity of each point cloud cluster, and use the point clouds in the point cloud cluster with the maximum average reflectivity as the target object point clouds, and determine the target point cloud data of the target object point clouds.

[0057] All candidate target object point clouds can be traversed, and all candidate target object point clouds can be segmented by the distance and curvature between adjacent two points. Exemplarily, when the distance between two candidate target object point clouds is greater than 0.2 m and the curvature is greater than 0.15, it can be considered that segmentation is performed at these two candidate target object point clouds, that is, these two points are used as point cloud clustering points.

[0058] After determining each point cloud cluster, the average reflectivity of each point cloud cluster can be determined by determining the number of point clouds in each point cloud cluster and obtaining the reflectivity corresponding to each point cloud in each point cloud cluster. The point clouds in the point cloud cluster with the maximum average reflectivity are used as the target object point clouds, and the target object point cloud data can be obtained from the environmental point cloud data.

[0059] S130. Based on the target point cloud data, monitor the target object. If it is monitored that the target object stays in the set area and the stay time exceeds the first set duration, then determine the set area as the target docking area and move to the target docking area.

[0060] After determining the target object point cloud, the target object can be monitored according to the target point cloud data. During the monitoring process, since the time interval between each frame of environmental point cloud data obtained by lidar scanning is determined, the displacement of the target object can be determined through the specific positions of the target object in adjacent frames. Whether the displacement is reasonable can be judged according to the speed range of the target object. If it is unreasonable, it may be that the target point cloud data of the current frame does not correspond to the actual target object, that is, there is a situation of point cloud jump. Then, the target point cloud data of the current frame can be excluded, and the monitoring can continue based on the target point cloud data of the next frame.

[0061] Exemplarily, when the target object is a human body, after determining that the displacement between two adjacent frames is too large, it can be determined that the target point cloud data of this frame does not belong to the target object, because there will be no displacement exceeding the normal movement speed of the human body according to the normal movement speed of the human body.

[0062] During the monitoring process, the specific position of the target object can be determined in real time, and whether the target object stays can be determined by determining the displacement within the unit time for adjacent frames. The set area can be set according to the specific working environment and the specific working cooperation situation with the target object. If there is only one set area due to the requirements of the working environment, when it is monitored that the target object stays in the set area and the stay time exceeds the first set duration, it can be considered that the target object has a need to summon the robot, and then the set area can be used as the target docking area and go there. The specific position information of the set area can be set in the robot in advance.

[0063] If the work of the target object requires continuous walking in the area, it can be considered that when the target object stops walking, there is a need to summon the robot, and then the position where the target object is located can be regarded as the set area and go to this set area.

[0064] When moving towards the target docking area, a smooth movement trajectory can be planned in real time based on the current self-positioning information, the position information of the target docking area, and the current environment, and the movement can be carried out according to the real-time planned movement trajectory.

[0065] By monitoring the staying position and staying duration of the target object to determine whether to move, and completing the self-determined destination of movement, the interaction between humans and robots can be greatly saved, making the work cooperation between the target object and the robot smooth. It can not only help the target object complete part of the work, but also avoid inconveniencing the movement of the target object when following the target object throughout the process, ensuring the work efficiency of the target object and the robot. At the same time, it also well avoids the situation that when following the target object closely throughout the process, due to the irregular movement of the target object during the movement process, the movement direction and movement speed of the robot will change frequently.

[0066] In one embodiment, the target point cloud data includes the point cloud coordinates of the target object point cloud. Based on the target point cloud data, monitoring the target object includes the following steps:

[0067] Monitor the point cloud coordinates of the target object point cloud and update the point cloud coordinates of the target object point cloud in real time.

[0068] When monitoring the target object, it can be to monitor the point cloud coordinates of the target object, track the point cloud coordinates of the target object in real time, and update the point cloud coordinates in real time. Using the real-time updated point cloud coordinates, information such as the position where the target object is located and whether there is a staying situation can be determined in real time.

[0069] In one embodiment, when there are multiple set areas, based on the target point cloud data, monitoring the target object further includes:

[0070] Obtain the position information of all set areas;

[0071] Based on the point cloud coordinates of the target object point cloud, judge whether the target object stops moving. If the target object stops moving, start timing the staying time;

[0072] Match the point cloud coordinates of the target object point cloud with the position information to judge in real time whether the target object is located in the set area.

[0073] Multiple set areas can be set according to the working environment and the cooperation content between the target object and the robot, and the position information of the set areas can be entered into the robot in advance.

[0074] Based on whether there are changes in the point cloud coordinates of the target object's point cloud in consecutive multiple frames, it can be determined whether the target object has stopped moving. Exemplarily, if the point cloud coordinates of the target object's point cloud do not change in a number of consecutive frames, it can be considered that the target object is in a state of stopped movement. Once it is determined that the target object has stopped moving, the residence time can be started to be timed.

[0075] The current position of the target object can be determined through the point cloud coordinates of the target object's point cloud, and then it can be matched with the position information of each preset area stored in advance. It can be determined whether the target object is located in the preset area by identifying whether the position of the preset area contains the point cloud coordinates corresponding to the target object's stay.

[0076] Exemplarily, referring to Figure 4 a schematic diagram of a preset area, when the working environment is a room with neat arrangement and the staff performs operations at the door of each room, the area within a certain range of the door of each room can be set as the preset area, such as Figure 4 the dotted circles in. When the target object needs to work in a certain room, it can stay in the preset area at the door of the room so that the lidar of the robot can scan to determine the target docking area. In order to enable the target object to stay in the preset area more accurately, all preset areas can be marked, and the target object can stay accurately in the preset area according to the marks of the preset area. At this time, the robot can accurately determine the target docking area.

[0077] In one embodiment, the method further includes the following steps:

[0078] If it is monitored that the target object stays outside the preset area and the residence time exceeds the second preset duration, then based on the point cloud coordinates and position information of the target object's point cloud, the distances between the target object and each preset area are determined;

[0079] The positioning information of the robot is determined, and based on the distances and the positioning information, the target docking area is determined from multiple preset areas, and the robot moves to the target docking area.

[0080] During the process of the target object working, there may be a situation where the robot needs to be summoned but the target object does not stay correctly in the preset area. At this time, the robot can perform self-judgment of the target docking area through the point cloud coordinates of the target object's point cloud, the position information of each preset area, and its own positioning information. In a specific implementation, when it is monitored that the target object stays outside the preset area and the residence time exceeds the second preset duration, different self-judgment strategies for the target docking point can be adopted in different working scenarios.

[0081] Exemplarily, referring to Figure 4, consider the rectangular frame c as the target object and the rectangular frame a as the robot. The movement direction of the target object can be determined by the change in the point cloud coordinates of the target object's point cloud over multiple consecutive frames. For example, the movement direction of the target object is from Room 3 to Room 5. However, the target object does not stay in the set area in front of Room 3 nor in the set area in front of Room 5, but stays at a position between Room 3 and Room 5.

[0082] The distance between the target object and each preset area can be determined through the point cloud coordinates of the target object's point cloud and the position information of each set area. By the two set areas that are closest to the target object, it can be determined that the current target object is located between the set area in front of Room 5 and the set area in front of Room 3.

[0083] After determining the set area in front of Room 3 and the set area in front of Room 5, its own positioning can be determined, and then the distances between the robot and the set area in front of Room 3 and the set area in front of Room 5 can be determined respectively. Since the movement direction of the target object is from Room 3 to Room 5 and the work of the target object is completed at the entrance of each room, it can be considered that the target object has exceeded the set area corresponding to Room 3 at this time, that is, there is no need to work in Room 3. Then, it can be determined that the target docking area at this time is the set area corresponding to Room 5, which is relatively far from the robot.

[0084] In this working scenario, since the work points are arranged horizontally, the two set areas that are closest to the target object can be determined first, and then the set area that is farther from the robot in the movement direction of the target object among these two set areas can be used as the target docking area.

[0085] In one embodiment, after moving to the target docking area, the method further includes the following steps:

[0086] Judge whether the target object is in the target docking area according to the target point cloud data;

[0087] If so, stop moving in the target docking area;

[0088] If not, continue to execute the monitoring of the target object based on the target point cloud data.

[0089] When the robot moves to the target docking area, only the target point cloud data can be obtained in real time to judge whether the target object is also within the range of the target docking area. If so, the target object can be shielded and kept in a stationary state to cooperate with the work of the target object. For example, the target object needs to pick up items from the robot, etc.

[0090] When it is determined that the target object has left the current target docking area, the steps of monitoring the target object can be continued to determine the next target docking area according to the monitoring results.

[0091] An embodiment of the present invention provides a method for target following. The method is applied to a robot and includes: obtaining environmental point cloud data of the current environment, and determining whether there is a target object in the current environment according to the environmental point cloud data. If there is a target object, obtaining the point cloud data of the target object as target point cloud data, and monitoring the target object based on the target point cloud data. If it is monitored that the target object stays in a set area and the stay time exceeds a first set duration, the set area is determined as the target docking area and the robot moves to the target docking area. This method can autonomously complete the determination of the following destination by monitoring the target object, saving the interaction between humans and the robot, making the work cooperation between the target object and the robot smooth, avoiding inconvenience to the movement of the target object when following the target object throughout the process, and ensuring the work efficiency of the target object and the robot.

[0092] Embodiment 2

[0093] Figure 5 FIG. 10 is a schematic structural diagram of a target following device provided in Embodiment 2 of the present invention. The device is applied to a robot and includes:

[0094] A target object determination module 510, configured to obtain environmental point cloud data of the current environment and determine whether there is a target object in the current environment according to the environmental point cloud data;

[0095] A target point cloud data acquisition module 520, configured to obtain the point cloud data of the target object as target point cloud data if there is a target object;

[0096] A monitoring module 530, configured to monitor the target object based on the target point cloud data;

[0097] A moving module 540, configured to determine the set area as the target docking area and move to the target docking area if it is monitored that the target object stays in the set area and the stay time exceeds a first set duration.

[0098] In one embodiment, the environmental point cloud data includes the reflectivity of the environmental point cloud;

[0099] The target object determination module 510 includes the following sub-modules:

[0100] A comparison sub-module, configured to compare the reflectivity of each environmental point cloud with a preset reflectivity threshold;

[0101] A target object determination module, which is used to determine that there is a target object when there is environmental point cloud with a reflectivity greater than or equal to the reflectivity threshold.

[0102] In one embodiment, the environmental point cloud data further includes the point cloud coordinates of the environmental point cloud. The target point cloud data acquisition module 520 includes the following sub-modules:

[0103] A candidate target object point cloud determination sub-module, which is used to, if there is a target object, use the environmental point cloud with a reflectivity greater than or equal to the reflectivity threshold as the candidate target object point cloud;

[0104] A segmentation sub-module, which is used to segment the candidate target object point cloud to obtain one or more point cloud clusters;

[0105] A target point cloud data determination sub-module, which is used to determine the average reflectivity of each point cloud cluster, and use the point cloud in the point cloud cluster with the maximum average reflectivity as the target object point cloud, and determine the target point cloud data of the target object point cloud.

[0106] In one embodiment, the target point cloud data includes the point cloud coordinates of the target object point cloud. The monitoring module 530 includes the following sub-modules:

[0107] An update sub-module, which is used to monitor the point cloud coordinates of the target object point cloud and update the point cloud coordinates of the target object point cloud in real time.

[0108] In one embodiment, when there are multiple set areas, the monitoring module 530 further includes the following sub-modules:

[0109] A position information acquisition sub-module, which is used to acquire the position information of all the set areas;

[0110] A timing sub-module, which is used to judge whether the target object stops moving based on the point cloud coordinates of the target object point cloud. If the target object stops moving, start timing the stay time;

[0111] A position matching sub-module, which is used to match the point cloud coordinates of the target object point cloud with the position information to judge in real time whether the target object is located in the set area.

[0112] In one embodiment, the device further includes the following module:

[0113] A distance determination module, which is used to, when it is monitored that the target object stays outside the set area and the stay time exceeds the second set duration, determine the distance between the target object and each set area based on the point cloud coordinates of the target object point cloud and the position information;

[0114] A target docking area determination module, configured to determine the positioning information of the robot, and determine a target docking area from multiple set areas according to the distance and the positioning information, and move to the target docking area.

[0115] In one embodiment, the device further includes the following modules:

[0116] A target object position judgment module, configured to judge whether the target object is in the target docking area according to the target point cloud data;

[0117] An execution module, configured to stop moving in the target docking area when it is determined that the target object is in the target docking area; if it is determined that the target object is not in the target docking area, then call the monitoring module 530. [[ID=ll]]

[0118] The target following device provided by the embodiment of the present invention can implement the target following method provided by the first embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method.

[0119] Embodiment III

[0120] Figure 6 FIG. shows a schematic structural diagram of an electronic device 10 that can be used to implement the embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device (such as a helmet, glasses, a watch, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0121] As Figure 6 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0122] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0123] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method of target following.

[0124] In some embodiments, a method of target following can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of a method of target following described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute a method of target following by any other suitable means (e.g., by means of firmware).

[0125] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGA), application-specific integrated circuits (ASIC), application-specific standard products (ASSP), systems-on-a-chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: implemented in one or more computer programs, the one or more computer programs can be executed and / or interpreted on a programmable system including at least one programmable processor, the programmable processor can be a special or general programmable processor, can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0126] A computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, a special purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine, or entirely on a remote machine or server.

[0127] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0128] In order to provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, speech input, or tactile input).

[0129] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected with each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0130] A computing system can include a client and a server. The client and the server are generally far from each other and typically interact through a communication network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0131] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0132] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for target following, characterized in that, The method is applied to a robot, and the method includes: Obtain the environmental point cloud data of the current environment, and determine whether there is a target object in the current environment according to the environmental point cloud data; If there is a target object, obtain the point cloud data of the target object as the target point cloud data; wherein, the target point cloud data includes the point cloud data of the target object; Based on the target point cloud data, monitor the target object. If it is monitored that the target object stays in the set area and the stay time exceeds the first set duration, then determine the set area as the target docking area and move to the target docking area; When there are multiple set areas, the monitoring of the target object based on the target point cloud data further includes: Obtain the position information of all the set areas; Based on the point cloud coordinates of the target object point cloud, judge whether the target object stops moving. If the target object stops moving, start timing the stay time; Match the point cloud coordinates of the target object point cloud with the position information, and judge in real time whether the target object is located in the set area.

2. The method according to claim 1, wherein The environmental point cloud data includes the reflectivity of the environmental point cloud; The judging whether there is a target object in the current environment according to the environmental point cloud data includes: comparing the reflectivity of each environmental point cloud with a preset reflectivity threshold; If there is an environmental point cloud whose reflectivity is greater than or equal to the reflectivity threshold, it is determined that there is a target object.

3. The method according to claim 2, wherein The environmental point cloud data further includes the point cloud coordinates of the environmental point cloud. If there is a target object, obtaining the point cloud data of the target object as the target point cloud data includes: If there is a target object, use the environmental point cloud whose reflectivity is greater than or equal to the reflectivity threshold as the candidate target object point cloud; Segment the candidate target object point cloud to obtain one or more point cloud clusters; Determine the average reflectivity of each point cloud cluster, and use the point cloud in the point cloud cluster with the maximum average reflectivity as the target object point cloud, and determine the target point cloud data of the target object point cloud.

4. The method according to claim 3, characterized in that The target point cloud data includes the point cloud coordinates of the target object point cloud. Monitoring the target object based on the target point cloud data includes: Monitor the point cloud coordinates of the target object point cloud and update the point cloud coordinates of the target object point cloud in real time.

5. The method according to claim 1, characterized in that, The method further includes: If it is monitored that the target object stays outside the set area and the stay time exceeds the second set duration, then based on the point cloud coordinates of the target object point cloud and the position information, determine the distance between the target object and each set area; Determine the positioning information of the robot, and according to the distance and the positioning information, determine the target docking area from multiple set areas and move to the target docking area.

6. The method according to any one of claims 1-5, characterized in that After moving to the target docking area, it further includes: Judge whether the target object is in the target docking area according to the target point cloud data; If so, stop moving in the target docking area; Otherwise, continue to execute the monitoring of the target object based on the target point cloud data.

7. A device for target following, characterized in that, The device is applied to a robot, and the device includes: A target object judgment module, configured to obtain environmental point cloud data of the current environment, and judge whether there is a target object in the current environment according to the environmental point cloud data; A target point cloud data acquisition module, configured to, if there is a target object, acquire the point cloud data of the target object as target point cloud data; wherein, the target point cloud data includes the point cloud data of the target object; A monitoring module, configured to monitor the target object based on the target point cloud data; A moving module, configured to, if it is monitored that the target object stays in a set area and the stay time exceeds a first set duration, determine the set area as a target docking area, and move to the target docking area; The monitoring module further includes the following sub-modules: A location information acquisition sub-module, configured to acquire the location information of all the set areas; A timing sub-module, configured to judge whether the target object stops moving based on the point cloud coordinates of the target object point cloud. If the target object stops moving, start timing the stay time; A location matching sub-module, configured to match the point cloud coordinates of the target object point cloud with the location information, and judge in real time whether the target object is located in the set area.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor, so that the at least one processor can execute a method for target following according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, and the computer instructions are used to implement a method for target following according to any one of claims 1-6 when executed by a processor.

Images