A control method, device, robot and storage medium

Abstract

The present invention discloses a control method, device, robot and storage medium. The method includes: determining the presence of a mobile obstacle based on image information and radar point cloud information in the direction of the robot's movement, and determining the type information and motion information of the mobile obstacle when the mobile obstacle exists; if the type information is a large obstacle, and the motion information is relative motion, then determining the relative position of the robot and the narrow road based on the robot's current position, and determining a reference path based on the relative position, the current position and the map path information; controlling the robot to travel along the reference path to avoid the mobile obstacle. The present invention solves the problem that existing robots need to stop and avoid obstacles when encountering obstacles during operation in narrow roads, resulting in unnecessary time waste. At the same time, different reference paths are formulated taking into account the type of obstacles faced by the robot, the current position, the relative position between the robot and the narrow road, and the map path information, thereby avoiding unnecessary waiting time.

Description

Technical Field

[0001] The present invention relates to the field of robotics technology, and in particular to a control method, device, robot and storage medium. Background Art

[0002] With the rapid development of automation technology and artificial intelligence, intelligent mobile electronic devices, such as smart mobile robots, have been applied in various scenarios. The cleaning and catering industries, as labor-intensive and repetitive industries, are undergoing a period of transition due to labor shortages and rising labor costs. Smart mobile robots can use unmanned driving technology to complete simple and repetitive cleaning and delivery tasks, significantly reducing labor costs and automating tasks such as cleaning and food delivery.

[0003] When an obstacle appears in the direction of travel and encounters a narrow road during intelligent driving, the electronic device needs to circumvent the obstacle. In such scenarios, it is often necessary to control the electronic device to wait for a certain period of time and then execute the corresponding path planning to achieve the purpose of circumventing the obstacle.

[0004] However, since the corresponding traffic path in the narrow road scenario is narrow, even if the electronic device stops and waits for an obstacle that has completely blocked the narrow road, the impact of the obstacle cannot be eliminated. No matter where the electronic device is located in the narrow road, it must stop and wait when encountering an obstacle, which increases the waiting time and makes it difficult for the electronic device to complete the preset task within the specified time, reducing the user experience. Summary of the Invention

[0005] The present invention provides a control method, device, robot and storage medium, which enrich the types of information that the robot needs to consider when avoiding obstacles when operating in narrow lanes, avoid meaningless waiting time, improve the robot's obstacle avoidance efficiency, prevent channel congestion, ensure the timeliness of the robot's task execution, and enhance the user experience.

[0006] According to one aspect of the present invention, there is provided a control method, the method comprising:

[0007] Determine the presence of moving obstacles based on image information and radar point cloud information in the robot's travel direction, and determine the type and motion information of the moving obstacles if they exist;

[0008] If the type information is a large obstacle and the motion information is opposite motion, the relative position of the robot and the narrow path is determined based on the robot's current position, and the reference path is determined based on the relative position, current position, and map path information;

[0009] Control the robot to follow the reference path to avoid moving obstacles.

[0010] According to another aspect of the present invention, there is provided a control device, the device comprising:

[0011] An information determination module is used to determine the presence of a moving obstacle based on image information and radar point cloud information in the direction of the robot's travel, and to determine the type and motion information of the moving obstacle if one exists;

[0012] A reference path determination module is configured to determine the relative position of the robot and the narrow path based on the robot's current position if the type information indicates a large obstacle and the motion information indicates opposite motion, and to determine a reference path based on the relative position, the current position, and the map path information;

[0013] The driving control module is used to control the robot to drive along the reference path to avoid moving obstacles.

[0014] According to another aspect of the present invention, there is provided a robot comprising:

[0015] A camera is used to collect image information in the direction of the robot's movement;

[0016] Radar, used to collect radar point cloud information in the direction of the robot's movement;

[0017] A controller, used to control the robot to travel along the determined reference path;

[0018] at least one processor, and

[0019] a memory communicatively connected to at least one processor; wherein,

[0020] The memory stores a computer program that can be executed by at least one processor. The computer program is executed by the at least one processor so that the at least one processor can execute the control method of any embodiment of the present invention.

[0021] According to another aspect of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the control method of any embodiment of the present invention when executed.

[0022] The present invention discloses a control method, device, and robot storage medium. The method determines the presence of a mobile obstacle based on image information and radar point cloud information in the robot's direction of travel, and determines the type and motion information of the mobile obstacle when the mobile obstacle exists. If the type information indicates a large obstacle and the motion information indicates opposite motion, the method determines the relative position of the robot and a narrow road based on the robot's current position, and determines a reference path based on the relative position, the current position, and map path information. The robot is controlled to travel along the reference path to avoid the mobile obstacle. The technical solution provided by the present invention solves the problem that existing robots need to stop and avoid obstacles when encountering obstacles in narrow roads, resulting in unnecessary time waste. When avoiding obstacles in the robot's direction of travel, the method simultaneously considers the type of obstacle faced by the robot, the current position, the relative position between the robot and the narrow road, and the map path information, and formulates different reference paths for different determined situations, thereby avoiding unnecessary waiting time, improving the robot's obstacle avoidance efficiency, and avoiding channel congestion caused by stopping and avoiding due to the narrow width of the narrow road itself. The method ensures the efficiency of the robot's execution of its own tasks and improves the user experience.

[0023] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended 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

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 A flow chart of a control method provided by an embodiment of the present invention;

[0026] Figure 2 A flow chart of another control method provided by an embodiment of the present invention;

[0027] Figure 3 An example diagram of a plan for determining an alternative path as a reference path provided by an embodiment of the present invention;

[0028] Figure 4 An example diagram of a first avoidance path planning provided by an embodiment of the present invention;

[0029] Figure 5 An example diagram of a first fallback path and subsequent path planning provided by an embodiment of the present invention;

[0030] Figure 6 A flow chart of another control method provided by an embodiment of the present invention;

[0031] Figure 7 An example diagram of a second avoidance path planning provided by an embodiment of the present invention;

[0032] Figure 8 A flow chart of another control method provided by an embodiment of the present invention;

[0033] Figure 9 A schematic structural diagram of a control device provided by an embodiment of the present invention;

[0034] Figure 10 A schematic structural diagram of a robot provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0035] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0036] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0037] Figure 1 A flowchart of a control method provided in an embodiment of the present invention. This embodiment is applicable to situations where a robot avoids obstacles while operating in a narrow path. The method can be executed by a control device, which can be implemented in the form of hardware and / or software. The control device can be configured on a robot. The robot can be an intelligent motion robot for performing tasks such as cleaning or delivering food, or other electronic devices with intelligent driving and obstacle avoidance requirements. The embodiment of the present invention does not limit this.

[0038] like Figure 1 As shown, a control method provided by an embodiment of the present invention specifically includes the following steps:

[0039] S101. Determine the presence of a moving obstacle based on image information and radar point cloud information in the robot's moving direction, and determine the type and motion information of the moving obstacle if the moving obstacle exists.

[0040] In this embodiment, image information can be specifically understood as images captured by an image acquisition device mounted on the robot, reflecting the environmental conditions in the robot's direction of travel. Exemplarily, the image acquisition device can be an RGB camera mounted on the front of the robot, or other devices capable of capturing image data, and this embodiment is not limited thereto. Radar point cloud information can be specifically understood as a spatial point dataset scanned by a radar device. Optionally, the radar device can be a lidar or other type of radar capable of capturing image points, and this embodiment is not limited thereto. The presence of mobile obstacles can be specifically understood as information, determined based on image information and radar point cloud information, indicating whether there are obstacles in the robot's direction of travel that could affect its ability to follow the planned path. The type of mobile obstacle can be specifically understood as information indicating whether a mobile obstacle completely blocks a narrow path or actively obstructs the robot's movement. Exemplarily, the type information can include small obstacles and large obstacles. Small obstacles can also be categorized as pedestrians, which could actively interfere with the robot's movement, and small non-pedestrian obstacles, which would not. This embodiment does not limit the specific classification of information types. The motion information of the moving obstacle can be specifically understood as information indicating the motion state of the moving obstacle relative to the robot, which may include the relative speed and relative direction of the two. This embodiment does not limit the specific content of the motion information.

[0041] Specifically, when performing tasks such as food delivery or cleaning, the robot will travel along a pre-planned path. During this process, the robot will acquire real-time image information and radar point cloud information in its direction of travel to determine whether there are obstacles ahead so that it can circumvent them in a timely manner. However, since the planned path often includes narrow roadways, the robot is often limited by the road width and cannot determine a clear obstacle avoidance strategy when navigating these areas. This increases the waiting time required for the robot to avoid obstacles and makes it difficult for the robot to complete its tasks on schedule. Therefore, when the robot is performing tasks in narrow roadways, the robot will use image and radar information acquisition equipment installed on the robot to acquire image information and radar point cloud information in its direction of travel. The acquired information is processed and identified to determine whether there are moving obstacles in the robot's direction of travel. If a moving obstacle is determined to be present, the acquired radar point cloud information can be used to classify and identify the type of the identified moving obstacle. Furthermore, the motion information of the moving obstacle relative to the robot can be determined based on the radar point cloud information collected at different times.

[0042] S102. If the type information is a large obstacle and the motion information is opposite motion, the relative position of the robot and the narrow path is determined according to the current position of the robot, and a reference path is determined according to the relative position, the current position, and the map path information.

[0043] In this embodiment, a large obstacle can be understood as one that blocks the narrow passage, making it difficult for the robot to circumvent it. For example, large obstacles can be crowds, carts, and linen carts, etc., although this is not a limitation in this embodiment of the present invention. The robot's current position can be understood as the robot's current position on a map, as determined by a positioning device on the robot. The relative position can be understood as the robot's current position relative to the narrow passage. For example, if the robot's current position on the map is within an area with a preset radius and centered at the narrow passage entrance, the robot's relative position relative to the narrow passage can be considered to be within the narrow passage entrance area. If the robot's current position on the map is within the narrow passage but not within the narrow passage entrance area, the robot's relative position relative to the narrow passage can be considered to be within the narrow passage interior area. Map path information can be understood as a set of information on paths allowed on a map for tasks that the robot can perform, including information such as the path's starting and ending points, path width, and path length. This is not a limitation in this embodiment of the present invention. The reference path can be specifically understood as the path that the robot needs to travel, which is planned to avoid moving obstacles.

[0044] Specifically, if the robot determines that the moving obstacle in the direction of travel is a large obstacle moving in the opposite direction to it, it can be considered that the moving obstacle has blocked most of the narrow road, and it is difficult for the robot to directly bypass the moving obstacle based on its location. At this time, the robot can obtain its own position information at the current moment through a positioning device set in the robot, that is, determine the current position of the robot, and then project the current position onto the map where the robot performs the task, and clarify the relative position relationship between the robot and the narrow road. Because the map path information of multiple navigable paths in the map where the robot performs the task includes map path information, the robot can determine the least cost avoidance strategy that can be taken to avoid the moving obstacle based on the current position, relative position and map path information, and determine the reference path that the robot can travel based on the avoidance strategy.

[0045] In an embodiment of the present invention, a method for avoiding large obstacles blocking the narrow road is determined by simultaneously considering the current position of the robot in the map, the relative position relative to the narrow road, and the map path information. Due to the introduction of reference to the relative position and map path information, the choices when determining the reference path are richer and more in line with the operating requirements of the robot during actual operation, which facilitates the robot to select the strategy with the highest traffic efficiency for reference path planning, thereby improving the robot's travel efficiency and enhancing the user experience.

[0046] S103: Control the robot to travel along the reference path to avoid moving obstacles.

[0047] Specifically, the robot can be controlled to travel directly along the reference path according to the generated reference path to avoid moving obstacles. Alternatively, after the reference path is generated, the generated reference path can be optimized to obtain an optimized reference path, and the robot can be controlled to travel along the optimized reference path to avoid moving obstacles. At the same time, if it is determined based on the surrounding environment information collected by the robot that the generated reference path needs to be corrected, the reference path can be corrected based on the determined correction distance to obtain a corrected path, and the robot can be controlled to travel along the corrected path to avoid moving obstacles. The embodiments of the present invention do not limit the specific method of traveling according to the reference path.

[0048] The technical solution of the embodiment of the present invention determines the presence of a moving obstacle based on image information and radar point cloud information in the direction of the robot's travel, and determines the type and motion information of the moving obstacle when the moving obstacle exists. If the type information indicates a large obstacle and the motion information indicates opposite motion, the relative position of the robot and the narrow road is determined based on the robot's current position, and a reference path is determined based on the relative position, current position, and map path information. The robot is controlled to travel along the reference path to avoid the moving obstacle. The technical solution provided by the present invention solves the problem that existing robots must stop and avoid obstacles when encountering obstacles during operation in narrow roads, resulting in unnecessary time waste. When avoiding obstacles in the direction of travel of the robot, the type of obstacle encountered, current position, relative position between the robot and the narrow road, and map path information are simultaneously considered, and different reference paths are formulated for different determined situations. This avoids unnecessary waiting time, improves the robot's obstacle avoidance efficiency, and avoids channel congestion caused by stopping and avoiding due to the narrow width of the narrow road itself, ensuring the efficiency of the robot's execution of its own tasks and improving the user experience.

[0049] Figure 2 This is a flow chart of another control method provided by an embodiment of the present invention. This embodiment is further optimized based on the above embodiment. Figure 2 As shown, the specific steps include:

[0050] S201: Determine the presence of a moving obstacle based on image information.

[0051] Specifically, the image information in the direction of movement of the robot acquired by an image acquisition device installed on the robot is processed by boundary extraction, parameter matching, etc. to determine whether there are obstacles that will affect the movement of the robot.

[0052] S202: If a moving obstacle exists, determine a target detection area based on the image information.

[0053] In this embodiment, the target detection area can be specifically understood as an area where the moving obstacle is located and can be used to detect specific information of the moving obstacle.

[0054] Specifically, if the presence of a mobile obstacle is present, in order to ensure that the robot can adopt the least costly method when avoiding the obstacle, it is necessary to further determine the type information and motion information of the mobile obstacle. At this time, the boundary information of the mobile obstacle is extracted from the image information, and the area formed by the boundary information, or the standard area formed by extending a preset distance outward from the area formed by the boundary information, is determined as the target detection area.

[0055] S203: Perform cluster analysis on the radar point cloud information within the target detection area to determine the type information and motion information of the moving obstacle.

[0056] Specifically, radar point cloud information collected by a radar device installed on the robot within the target detection area is extracted, the radar point cloud information within the target detection area is determined as target radar point cloud information, cluster analysis is performed on the target radar point cloud information, and the type information of the mobile obstacle corresponding to the target radar point cloud information is determined according to the predetermined cluster label. At the same time, the moving state of the mobile obstacle is determined according to the determined position of the mobile obstacle, and the moving speed of the mobile obstacle relative to the robot is determined based on the target radar point cloud information collected at different times. The collection of information such as the moving state and the moving speed is determined as the motion information of the mobile obstacle.

[0057] S204: If the type information is a large obstacle and the motion information is opposite motion, the relative position of the robot and the narrow path is determined based on the current position of the robot.

[0058] S205: Determine whether there is at least one alternative path in the map path information. If so, execute step S206; if not, execute step S207.

[0059] In this embodiment, the alternative path can be specifically understood as a path in the map that can be used to replace the narrow path where the robot is located and reach the same end point.

[0060] Specifically, based on the task information performed by the robot at the current moment, the terminal position that the robot needs to reach after passing through the narrow road is determined. According to the current position and the terminal position of the robot, the map path information is searched, and the path that can reach the terminal position from the current position is determined as the alternative path for the robot to perform the current task. If there is at least one alternative path in the map path information, it can be considered that the robot can complete the task without passing through the current narrow road, and step S206 is executed at this time; otherwise, it can be considered that if the robot wants to complete the current task, it must pass through the narrow road and needs to bypass or wait for moving obstacles, and step S207 is executed at this time.

[0061] S206: Determine the candidate path with the shortest distance among the candidate paths as the reference path, and execute step S210.

[0062] Specifically, in order to ensure the efficiency of the robot's execution of the current task, when it is determined that there is a large obstacle moving in the opposite direction of the robot's travel direction and there is an alternative path to the end position in the map, due to the unclear passing time of the moving obstacle or the avoidance risk in the narrow road, the robot will directly choose to change the route and reach the end position through a smooth alternative path to complete the task. When there are multiple alternative paths, in order to ensure efficiency, the alternative path with the shortest distance can be determined as the reference path, and step S210 is executed after the reference path is determined.

[0063] For example, Figure 3 An example diagram of a plan for determining an alternative path as a reference path provided by an embodiment of the present invention is shown in FIG. Figure 3 As shown in the figure, the triangle represents the robot, the rectangle represents the moving obstacle, and the dotted line represents the planned path. When the robot faces a moving obstacle in a narrow road and there are other alternative paths in the map path information, the robot will select the shortest of the alternative paths as the reference path and directly switch paths instead of avoiding or waiting for the moving obstacle on the spot, which improves the task processing speed.

[0064] S207: Determine whether the relative position belongs to the narrow passage entrance area. If so, execute step S208; if not, execute step S209.

[0065] In this embodiment, the narrow passage entrance area can be specifically understood as an area that allows for direct exit for vehicles that have not yet entered the narrow passage, or have only initially entered the narrow passage. Optionally, the narrow passage entrance area can be defined as an area on the map with the narrow passage entrance as the center and a preset radius as the radius. The narrow passage area can be divided into the narrow passage entrance area and the narrow passage interior area. Specifically, if the robot is not within the narrow passage entrance area when it enters the narrow passage, it is in the narrow passage interior area.

[0066] Specifically, when it is determined based on the map path information that the robot has no alternative path to perform the current task, it can be considered that the robot must pass through the narrow road, that is, it must bypass the moving obstacle. At this time, it is determined whether the relative position of the robot and the narrow road is located in the narrow road entrance area. If so, it can be considered that it is very convenient for the robot to exit the narrow road. Compared with the solution of staying in the narrow road waiting for the moving obstacle to pass, which has the risk of hindering the passage of the moving obstacle, the solution of exiting the narrow road so that the moving obstacle can pass through the narrow road without obstacle will be more practical and will improve the obstacle avoidance efficiency. At this time, step S208 is executed; otherwise, it can be considered that the robot is already in the internal area of ​​the narrow road, and it will take a long time to retreat to the outside of the narrow road, and more complex path planning is required. In order to improve the obstacle avoidance efficiency, it is more practical to stay in the narrow road waiting for the moving obstacle to pass. At this time, step S209 is executed.

[0067] S208: Construct a first retreat path based on the current position and the preset narrow road entrance safety point, determine the first retreat path as a reference path, and execute step S210.

[0068] In this embodiment, the narrow passage entrance safety point can be specifically understood as a pre-set safe position outside the narrow passage entrance that does not affect moving obstacles and the passage of other people or objects, and can avoid collisions. The first retreat path can be specifically understood as the path the robot takes from its current position to the safe area outside the narrow passage.

[0069] Specifically, taking the current position as the starting point and the preset narrow road entrance safety point as the end point, path planning is performed in combination with the surrounding environment information obtained from the map, and the planned path is determined as the first retreat path, so that the robot can safely drive to the safe area outside the narrow road entrance according to the first retreat path. At this time, the first retreat path is determined as the reference path, and step S210 is executed after the reference path is determined.

[0070] S209 , determining an offset direction and an offset distance based on the current position and the edge line information of the narrow road, determining a first avoidance path constructed based on the current position, the offset direction, and the offset distance as a reference path, and executing step S210 .

[0071] In this embodiment, edge line information can be specifically understood as the position information of the two boundaries of the narrow road. The offset direction can be specifically understood as the direction in which the robot is expected to move, and the offset distance can be specifically understood as the distance the robot is expected to move in the offset direction. The first avoidance path can be specifically understood as the path planned for the robot to avoid a moving obstacle.

[0072] Specifically, in order to give way to a moving obstacle, the robot needs to stop at the edge of a narrow road to allow the moving obstacle to pass. The edge line where the robot should stop in the narrow road is determined based on the current position of the robot and the edge line information of the narrow road, and then the offset direction and offset distance required for the robot to reach the edge line are determined. With the edge line as the end point and the current position as the starting point, path planning is performed in combination with the surrounding environment information obtained from the map, and the planned path is determined as the first avoidance path, so that the robot can safely drive to the edge line of the narrow road according to the first avoidance path to avoid the moving obstacle. At this time, the first avoidance path is determined as the reference path, and step S210 is executed after the reference path is determined.

[0073] Furthermore, determining the offset direction and offset distance based on the current position and the edge line information of the narrow road may specifically include the following steps:

[0074] S2091, determining the edge line closest to the current position in the narrow road as the target edge line based on the edge line information;

[0075] S2092: Determine the horizontal distance between the target edge line and the current position as the offset distance, and determine the horizontal direction of the target edge line relative to the current position as the offset direction.

[0076] For example, Figure 4 An example diagram of a first avoidance path planning provided by an embodiment of the present invention is shown as follows: Figure 4 As shown in the figure, the triangle represents the robot and the rectangle represents the moving obstacle. When the robot faces a large obstacle moving towards it, it will select the edge line closer to it in the narrow path as the target edge line, determine the direction of movement toward the target edge line as the offset direction, and determine the distance moved horizontally to the target edge line as the offset distance. Based on the offset direction, offset distance, current position, robot's travel speed and the travel speed of the moving obstacle, a path planning method is used to plan a path that enables the robot to move to the target edge line, and this path is determined as the first avoidance path.

[0077] S210: Control the robot to travel along the reference path to avoid moving obstacles.

[0078] Furthermore, if the reference path is the first retreat path, after controlling the robot to travel along the reference path to avoid the moving obstacle, the method further includes:

[0079] After stopping for a second preset time, the robot is controlled to travel along the original path of the robot, and returns to execute the steps of determining the presence of a mobile obstacle based on image information and radar point cloud information in the direction of movement of the robot, and determining the type information and motion information of the mobile obstacle when the mobile obstacle exists.

[0080] In this embodiment, the second preset time can be understood as a pre-set time, which can generally be considered to be the time required for a moving obstacle to pass through the narrow passage. This preset time can be set based on statistical conditions or adaptively set based on actual conditions such as the position and movement speed of the moving obstacle in the narrow passage. This embodiment of the present invention is not limited to this. The original path can be understood as a pre-planned path for the robot before performing the current task.

[0081] Specifically, when the reference path is the first retreat path, and the robot is controlled to travel along the reference path to avoid the moving obstacle, it can be considered that the robot has returned to the safe area outside the narrow passage entrance. At this time, there are no other obstacles in the narrow passage that could affect the moving obstacle's movement. Since the moving obstacle is moving in the opposite direction of the robot, that is, if the moving obstacle is moving normally, it will exit the narrow passage entrance after a certain period of time, and the narrow passage after it exits can be passed by the robot. Therefore, the robot can be controlled to wait at a preset narrow passage entrance safety point for a second preset time. After waiting, it can be assumed that the moving obstacle is no longer in the narrow passage. At this time, the robot is controlled to travel along the original path to perform the task, and during execution, image information and radar point cloud information in the direction of the robot's movement are acquired, and the execution returns to step S201 and subsequent steps.

[0082] For example, Figure 5 An example diagram of a first fallback path and subsequent path planning provided by an embodiment of the present invention is shown as follows: Figure 5 As shown, the triangle represents the robot and the rectangle represents the moving obstacle. When the robot faces a large obstacle moving towards it and is located in the narrow road entrance area, it will first plan a first retreat path as shown in circle 1 in the figure based on its current position and the preset narrow road entrance safety point, so that the robot returns to the narrow road entrance along the first retreat path and stays at the narrow road entrance for a second preset time. After the second preset time, it returns to the original path from the preset narrow road entrance safety point along the path as shown in circle 2 in the figure.

[0083] Furthermore, if the reference path is the first avoidance path, after controlling the robot to travel along the reference path to avoid the moving obstacle, the method further includes:

[0084] controlling the robot to determine the presence of a large obstacle after stopping for a third preset time;

[0085] If the presence of a large obstacle is Yes, a replanned path is generated based on the current position, map path information, and the robot's original path;

[0086] Control the robot to drive along the replanned path.

[0087] In this embodiment, the third preset time can be understood as a pre-set time, which is generally considered to be the time it takes for a moving obstacle in a narrow path to pass through the robot's position without other interference and under the condition that the robot avoids it. This preset time can be set based on statistical conditions or adaptively set based on actual conditions such as the position and movement speed of the moving obstacle in the narrow path. This embodiment of the present invention is not limited to this. Re-planning the path can be specifically understood as the path re-planned by the robot to achieve the task processing purpose when it determines that the robot faces a large obstacle that cannot be circumvented.

[0088] Specifically, when the reference path is the first avoidance path, and the robot is controlled to dock at the edge of the narrow road according to the reference path to wait for the large obstacle to pass, after waiting for the third preset time, it can be considered that if the large obstacle is not blocked by the docked robot, it will pass the robot's position. At this time, the robot uses the collected image information and radar point cloud information of the direction of travel to re-determine the existence of the large obstacle in front of it. If the large obstacle still exists, it can be considered that even if the robot docks to make way for the large obstacle, the large obstacle cannot be passed. At this time, another path for the robot to complete the task can be determined based on the robot's current position, map path information and the robot's original path, or a path can be planned that allows the robot to exit the narrow road and wait for the large obstacle to pass. It can be used as a re-planned path, and the robot is controlled to travel along the re-planned path to ensure the execution of the task.

[0089] The technical solution of the embodiment of the present invention, when it is determined that there is a large obstacle in front of the robot, based on whether there is an alternative path in the map path information and whether the robot is located in the narrow road entrance area, formulates different handling methods for different scenarios, such as changing route according to the alternative path, exiting the narrow road and waiting, and waiting by the side of the narrow road. When facing different situations, the robot can choose the reference path with the lowest time cost, avoid unnecessary waiting time, and improve the robot's obstacle avoidance efficiency. At the same time, after handling according to the planned reference path, the subsequent path planning operation is promptly adopted after waiting for a preset time, which ensures the robot's execution efficiency of the task it carries and improves the user experience.

[0090] Figure 6 This is a flow chart of another control method provided by an embodiment of the present invention. This embodiment is further optimized based on the above embodiment. Figure 6 As shown, the specific steps include:

[0091] S301: Determine the presence of a moving obstacle based on image information.

[0092] S302: If a moving obstacle exists, determine a target detection area based on the image information.

[0093] S303: Perform cluster analysis on the radar point cloud information within the target detection area to determine the type information and motion information of the moving obstacle.

[0094] S304. If the type information is a small non-pedestrian obstacle and the motion information is opposite motion, determine a second avoidance path based on the robot's current position, motion information and the robot's original path, and determine the second avoidance path as the reference path.

[0095] In this embodiment, the second avoidance path can be specifically understood as a path planned for the robot to avoid a moving obstacle in a narrow passage.

[0096] Specifically, when the moving obstacle encountered by the robot is a small non-pedestrian obstacle, it can be assumed that the robot can bypass the obstacle in a narrow path, and the moving obstacle will not actively affect the movement of the robot. At this time, based on the current position of the robot, the motion information of the moving obstacle relative to the robot, and the original path that the robot was originally going to travel, a second avoidance path can be determined to bypass the moving obstacle and then return to the original path, and the second avoidance path can be determined as the reference path.

[0097] For example, Figure 7 An example diagram of a second avoidance path planning provided by an embodiment of the present invention is shown in FIG. Figure 7 As shown, the triangle represents the robot and the circle represents the moving obstacle. When the robot faces a small obstacle that is moving in the opposite direction to it and is not a pedestrian, it can select the edge line of the narrow road that is closer to it as the target edge line, determine the direction of movement toward the target edge line as the offset direction, and determine the distance of horizontal movement to the target edge line as the offset distance. The path planning method is used to plan a path that allows the robot to move to the target edge line and pass the moving obstacle, and this path is determined as the second avoidance path. Optionally, the robot can also determine the distance between the two edge lines of the small obstacle relative to the narrow road, and determine the edge line on the side with the wider distance as the target edge line for the robot to use for path planning, so that the robot can pass through the wider area between the small obstacle and the narrow road boundary to avoid collision. The embodiment of the present invention does not limit the method of determining the second avoidance path.

[0098] S305: Control the robot to travel along the reference path to avoid moving obstacles.

[0099] The technical solution of the embodiment of the present invention, when it is determined that the obstacle in front of the robot is a small non-pedestrian obstacle, determines a second avoidance path for avoiding the small obstacle based on the robot's current position, motion information and the robot's original path. In the determination process, the possibility of the robot's passing is fully considered, avoiding collisions between the obstacle and the robot, and making the determined avoidance path more consistent with the original path, thereby ensuring the robot's task execution efficiency and improving the user experience.

[0100] Figure 8 This is a flow chart of another control method provided by an embodiment of the present invention. This embodiment is further optimized based on the above embodiment. Figure 8 As shown, the specific steps include:

[0101] S401: Determine the presence of a moving obstacle based on image information.

[0102] S402: If a moving obstacle exists, determine a target detection area based on the image information.

[0103] S403: Perform cluster analysis on the radar point cloud information within the target detection area to determine the type information and motion information of the moving obstacle.

[0104] S404: If the type information is pedestrian and the motion information is moving toward each other, control the robot to stop for a first preset time.

[0105] In this embodiment, the first preset time can be specifically understood as a pre-set time used to determine whether pedestrians will interfere with the robot. It is understood that when a robot encounters pedestrians during operation, pedestrians often actively interfere with and "teasing" the robot, potentially blocking the robot's movement. If the robot immediately replans and executes its path upon encountering a pedestrian, it may be blocked again. When performing tasks such as serving food, frequent path changes can lead to problems such as spilled food. To avoid this situation, the first preset time is set in this embodiment of the present invention to allow the robot to wait in order to determine whether the robot will be affected by pedestrians' active teasing.

[0106] Optionally, during the first preset time that the robot is waiting, the robot may maintain a real-time state of facing the pedestrian, and when the robot has a display screen, the robot may prompt the pedestrian to avoid the robot's path on the display screen.

[0107] S405: Determine the presence of pedestrians, and determine a reference path based on the presence of pedestrians.

[0108] Specifically, after the robot stops for the first preset time, it can determine the presence of pedestrians again to clarify whether the pedestrians have the possibility of actively affecting the robot, and then re-plan the path when the pedestrians are still present. When the pedestrians are not present, the original planned path can be determined as the reference path.

[0109] Furthermore, the reference path is determined based on the presence of pedestrians, which can be achieved in the following ways:

[0110] If the pedestrian presence condition is yes, then determining a third avoidance path based on the robot's current position, motion information, and the robot's original path, and determining the third avoidance path as a reference path;

[0111] If the pedestrian presence condition is not present, the original path of the robot is determined as the reference path.

[0112] In this embodiment, the third avoidance path can be specifically understood as a path planned for the robot to avoid moving obstacles of pedestrians in a narrow passage.

[0113] Specifically, if the robot determines the pedestrian is still present after waiting, it can plan an avoidance path for the pedestrian as a small obstacle in the narrow path. The specific path planning method can be the same as the planning method for the second avoidance path. If the robot determines the pedestrian is no longer present after waiting, the original path of the robot can be directly determined as the reference path, avoiding the tedious path replanning.

[0114] S406: Control the robot to travel along the reference path to avoid moving obstacles.

[0115] According to the technical solution of the embodiment of the present invention, when the robot determines that the obstacle in front of the robot is a pedestrian, the robot stops moving for a first preset time to avoid the obstacle through the subjective initiative of the pedestrian, thereby reducing the amount of calculation required for path planning by the robot itself. At the same time, it is easier to determine whether the pedestrian is engaging in teasing behavior, thereby avoiding problems such as spilling food due to multiple re-path planning, thereby ensuring the robot's task execution efficiency and improving the user experience.

[0116] Figure 9 A schematic diagram of the structure of a control device provided by an embodiment of the present invention is shown in FIG. Figure 9 As shown, the control device includes: an information determination module 51 , a reference path determination module 52 and a driving control module 53 .

[0117] The information determination module 51 is used to determine the presence of a mobile obstacle based on the image information and radar point cloud information in the direction of the robot's movement, and to determine the type information and motion information of the mobile obstacle when the mobile obstacle exists; the reference path determination module 52 is used to determine the relative position of the robot and the narrow road based on the robot's current position if the type information is a large obstacle and the motion information is relative motion, and to determine the reference path based on the relative position, the current position and the map path information; the driving control module 53 is used to control the robot to drive along the reference path to avoid the mobile obstacle.

[0118] The technical solution of the embodiment of the present invention solves the problem that existing robots have to stop and avoid obstacles when encountering obstacles during operation in narrow roads, which leads to unnecessary waste of time. When the robot avoids obstacles in the direction of travel, the obstacle type faced by the robot, the current position, the relative position between the robot and the narrow road, and the map path information are taken into consideration at the same time, and different reference paths are formulated for different situations determined, thereby avoiding unnecessary waiting time, improving the robot's obstacle avoidance efficiency, and avoiding channel congestion caused by stopping and avoiding due to the narrow width of the narrow road itself, thereby ensuring the robot's execution efficiency of the task it carries and improving the user experience.

[0119] Optionally, the information determination module 51 includes:

[0120] an obstacle situation determination unit, configured to determine the presence of a moving obstacle based on image information;

[0121] a detection area determination unit, configured to determine a target detection area based on image information if a moving obstacle exists;

[0122] The information determination unit is used to perform cluster analysis on the radar point cloud information within the target detection area to determine the type information and motion information of the moving obstacle.

[0123] Optionally, if the type information is a large obstacle and the motion information is opposite motion, the reference path determination module 52 is specifically configured to:

[0124] If there is at least one alternative path in the map path information, the alternative path with the shortest distance among the alternative paths is determined as the reference path;

[0125] If the relative position belongs to the narrow road entrance area and there is no alternative path in the map path information, a first fallback path is constructed based on the current position and the preset narrow road entrance safety point, and the first fallback path is determined as the reference path;

[0126] If the relative position belongs to the internal area of ​​the narrow road and there is no alternative path in the map path information, the offset direction and offset distance are determined based on the current position and the edge line information of the narrow road, and the first avoidance path constructed based on the current position, offset direction and offset distance is determined as the reference path.

[0127] Optionally, determining an offset direction and an offset distance based on the current position and the edge line information of the narrow road includes:

[0128] According to the edge line information, the edge line closest to the current position in the narrow road is determined as the target edge line;

[0129] The horizontal distance between the target edge line and the current position is determined as the offset distance, and the horizontal direction of the target edge line relative to the current position is determined as the offset direction.

[0130] Optionally, the reference path determination module 52 is further configured to:

[0131] If the type information is a small non-pedestrian obstacle and the motion information is opposite motion, a second avoidance path is determined based on the robot's current position, motion information, and the robot's original path, and the second avoidance path is determined as the reference path.

[0132] Optionally, the reference path determination module 52 is further configured to:

[0133] If the type information is pedestrian and the motion information is moving towards each other, control the robot to stop for a first preset time;

[0134] Determine the pedestrian presence of pedestrians and determine a reference path based on the pedestrian presence.

[0135] Optionally, a reference path is determined based on the presence of pedestrians, including:

[0136] If the pedestrian presence condition is yes, then determining a third avoidance path based on the robot's current position, motion information, and the robot's original path, and determining the third avoidance path as a reference path;

[0137] If the pedestrian presence condition is not present, the original path of the robot is determined as the reference path.

[0138] Furthermore, if the reference path is the first retreat path, after controlling the robot to travel along the reference path to avoid the moving obstacle, the method further includes:

[0139] After stopping for a second preset time, the robot is controlled to travel along the original path of the robot, and returns to execute the steps of determining the presence of a mobile obstacle based on image information and radar point cloud information in the direction of movement of the robot, and determining the type information and motion information of the mobile obstacle when the mobile obstacle exists.

[0140] Furthermore, if the reference path is the first avoidance path, after controlling the robot to travel along the reference path to avoid the moving obstacle, the method further includes:

[0141] controlling the robot to determine the presence of a large obstacle after stopping for a third preset time;

[0142] If the presence of a large obstacle is Yes, a replanned path is generated based on the current position, map path information, and the robot's original path;

[0143] Control the robot to drive along the replanned path.

[0144] A control device provided in an embodiment of the present invention can execute the control method provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0145] Figure 10 A schematic diagram of the structure of a robot provided by an embodiment of the present invention is shown in FIG. Figure 10 As shown, the robot includes: a camera 61, a radar 62, a controller 63, at least one processor 64, a memory 65 communicatively connected to the at least one processor, an input device 66 and an output device 67. Figure 10 In the figure, a processor 64 is used as an example; the camera 61, radar 62, controller 63, processor 64, memory 65, input device 66 and output device 67 in the robot can be connected by a bus or other means. Figure 10 The bus connection is taken as an example.

[0146] Among them, the camera 61 is used to collect image information in the direction of the robot's movement;

[0147] Radar 62, used to collect radar point cloud information in the direction of the robot's movement;

[0148] The controller 63 is used to control the robot to travel according to the determined reference path.

[0149] Memory 65, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the control method in the embodiments of the present invention. Processor 64 executes the software programs, instructions, and modules stored in memory 65 to perform various robot functions and data processing, thereby implementing the aforementioned control method.

[0150] The memory 65 may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function; the data storage area may store data generated based on the terminal's use. Furthermore, the memory 65 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state memory device. In some instances, the memory 65 may further include memory remotely located relative to the processor 64, and such remote memory may be connected to the robot via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0151] The input device 66 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the robot. The output device 67 may include a display device such as a display screen.

[0152] An embodiment of the present invention further provides a computer-readable storage medium storing computer instructions. The computer instructions can be used to cause a processor to implement a control method when executed. The method includes:

[0153] Determine the presence of moving obstacles based on image information and radar point cloud information in the robot's travel direction, and determine the type and motion information of the moving obstacles if they exist;

[0154] If the type information is a large obstacle and the motion information is opposite motion, the relative position of the robot and the narrow path is determined based on the robot's current position, and the reference path is determined based on the relative position, current position, and map path information;

[0155] Control the robot to follow the reference path to avoid moving obstacles.

[0156] Of course, the computer instructions of a computer-readable storage medium provided by an embodiment of the present invention are not limited to the above method operations, and can also execute related operations in the control method provided by any embodiment of the present invention.

[0157] Through the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented with the help of software and necessary general-purpose hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various embodiments of the present invention.

[0158] It is worth noting that in the above-mentioned device embodiment, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0159] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed 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. This is not limited herein.

[0160] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A control method, characterized in that: include: Determine the presence of a moving obstacle based on image information and radar point cloud information in the direction of travel of the robot, and determine the type and motion information of the moving obstacle if the moving obstacle exists; If the type information is a large obstacle and the motion information is opposite motion, determining the relative position of the robot and the narrow path according to the current position of the robot, and determining a reference path according to the relative position, the current position, and the map path information; Controlling the robot to travel along the reference path to avoid the moving obstacle; The determining of the reference path according to the relative position, the current position and the map path information includes: If there is at least one alternative path in the map path information, determining the alternative path with the shortest distance among the alternative paths as the reference path; If the relative position belongs to a narrow road entrance area and no alternative path exists in the map path information, constructing a first fallback path according to the current position and a preset narrow road entrance safety point, and determining the first fallback path as a reference path; If the relative position belongs to the internal area of ​​the narrow road and there is no alternative path in the map path information, the offset direction and offset distance are determined based on the current position and the edge line information of the narrow road, and a first avoidance path constructed based on the current position, the offset direction and the offset distance is determined as the reference path.

2. The method according to claim 1, characterized in that Determining the presence of a moving obstacle based on image information and radar point cloud information in the direction of travel of the robot, wherein determining the type and motion information of the moving obstacle when the moving obstacle exists includes: determining the presence of a moving obstacle based on the image information; If the moving obstacle exists, determining a target detection area based on the image information; Cluster analysis is performed on the radar point cloud information within the target detection area to determine the type information and motion information of the moving obstacle.

3. The method according to claim 1, characterized in that The determining of the offset direction and offset distance according to the current position and the edge line information of the narrow road includes: determining the edge line closest to the current position in the narrow lane as a target edge line according to the edge line information; A horizontal distance between the target edge line and the current position is determined as an offset distance, and a horizontal direction of the target edge line relative to the current position is determined as an offset direction.

4. The method according to claim 1, wherein After determining the type information and movement information of the moving obstacle when the moving obstacle exists, the method further includes: If the type information is a small non-pedestrian obstacle and the motion information is opposite motion, a second avoidance path is determined based on the current position of the robot, the motion information and the original path of the robot, and the second avoidance path is determined as the reference path.

5. The method according to claim 1, wherein After determining the type information and movement information of the moving obstacle when the moving obstacle exists, the method further includes: If the type information is a pedestrian and the movement information is moving towards each other, controlling the robot to stop for a first preset time; A pedestrian presence condition of the pedestrian is determined, and a reference path is determined according to the pedestrian presence condition.

6. The method according to claim 5, characterized in that The determining of a reference path according to the presence of the pedestrian includes: If the pedestrian presence condition is yes, determining a third avoidance path according to the current position of the robot, the motion information, and the original path of the robot, and determining the third avoidance path as a reference path; If the pedestrian presence condition is that the pedestrian does not exist, the original path of the robot is determined as the reference path.

7. The method according to claim 1, characterized in that If the reference path is the first retreat path, after controlling the robot to travel along the reference path to avoid the moving obstacle, the method further includes: The robot is controlled to travel along the original path of the robot after stopping for a second preset time, and returns to execute the steps of determining the presence of a mobile obstacle based on the image information and radar point cloud information in the direction of robot travel, and determining the type information and motion information of the mobile obstacle when the mobile obstacle exists.

8. The method according to claim 1, characterized in that If the reference path is a first avoidance path, after controlling the robot to travel along the reference path to avoid the moving obstacle, the method further includes: controlling the robot to determine the presence of the large obstacle after stopping for a third preset time; If the presence of the large obstacle is yes, generating a replanned path according to the current position, the map path information and the original path of the robot; The robot is controlled to travel along the replanned path.

9. A control device, characterized in that: include: An information determination module is used to determine the presence of a moving obstacle based on image information and radar point cloud information in the direction of travel of the robot, and to determine the type and motion information of the moving obstacle when the moving obstacle exists; a reference path determination module, configured to determine, if the type information indicates a large obstacle and the motion information indicates opposite motion, a relative position between the robot and the narrow path based on the robot's current position, and determine a reference path based on the relative position, the current position, and map path information; A driving control module, configured to control the robot to drive along the reference path to avoid the moving obstacle; The reference path determination module is specifically configured to: If there is at least one alternative path in the map path information, determining the alternative path with the shortest distance among the alternative paths as the reference path; If the relative position belongs to a narrow road entrance area and no alternative path exists in the map path information, constructing a first fallback path according to the current position and a preset narrow road entrance safety point, and determining the first fallback path as a reference path; If the relative position belongs to the internal area of ​​the narrow road and there is no alternative path in the map path information, the offset direction and offset distance are determined based on the current position and the edge line information of the narrow road, and a first avoidance path constructed based on the current position, the offset direction and the offset distance is determined as the reference path.

10. A robot, characterized in that: The robot comprises: A camera, used to collect image information in the direction of travel of the robot; Radar, used to collect radar point cloud information in the direction of travel of the robot; A controller, configured to control the robot to travel along the determined reference path; 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. The computer program is executed by the at least one processor to enable the at least one processor to perform the control method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the control method according to any one of claims 1 to 8 when executed.

Images