Nothing Special   »   [go: up one dir, main page]

CN114625132B - Robot avoidance method and system - Google Patents

Robot avoidance method and system Download PDF

Info

Publication number
CN114625132B
CN114625132B CN202210193094.3A CN202210193094A CN114625132B CN 114625132 B CN114625132 B CN 114625132B CN 202210193094 A CN202210193094 A CN 202210193094A CN 114625132 B CN114625132 B CN 114625132B
Authority
CN
China
Prior art keywords
path
robot
judging
speed
moving
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202210193094.3A
Other languages
Chinese (zh)
Other versions
CN114625132A (en
Inventor
周振海
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Baolaiwei Intelligent Technology Co ltd
Original Assignee
Shenzhen Baolaiwei Intelligent Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Baolaiwei Intelligent Technology Co ltd filed Critical Shenzhen Baolaiwei Intelligent Technology Co ltd
Priority to CN202210193094.3A priority Critical patent/CN114625132B/en
Publication of CN114625132A publication Critical patent/CN114625132A/en
Application granted granted Critical
Publication of CN114625132B publication Critical patent/CN114625132B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02Control of position or course in two dimensions
    • G05D1/021Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0223Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02Control of position or course in two dimensions
    • G05D1/021Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0231Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
    • G05D1/0246Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Electromagnetism (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
  • Manipulator (AREA)

Abstract

The application relates to a robot avoiding method and a system, and relates to the technical field of robots, wherein the robot avoiding method comprises the steps of detecting whether a moving object exists in a rear preset range when a robot moves along a first path; if so, obtaining a first speed of the object based on the position change of the object; judging whether the first speed is greater than the moving speed of the robot; if so, generating a pre-judging path based on the position change of the object; and judging whether the pre-judging path has an intersection with the first path; if so, controlling the robot to move to a second path when the object moves to a first range of the robot; and the second path and the pre-judging path have no crossing point. The application has the effect of reducing the possibility of collision between the robot and the obstacle moving backward.

Description

机器人避让方法及系统Robot avoidance method and system

技术领域Technical Field

本申请涉及机器人的技术领域,尤其是涉及机器人避让方法及系统。The present application relates to the technical field of robots, and in particular to a robot avoidance method and system.

背景技术Background Art

机器人(Robot)是一种能够半自主或全自主工作的智能机器。随着科技的进步,越来越多的机器人出现在日常工作及生活中。A robot is an intelligent machine that can work semi-autonomously or fully autonomously. With the advancement of technology, more and more robots are appearing in our daily work and life.

在相关技术中,机器人的控制系统通常有自行规划路径的能力,机器人的控制系统可以在机器人发生碰撞后改变机器人的运动方向。在一些更为先进的机器人中,遇到固定障碍物时,机器人可以依赖自身的控制系统对当前移动路径重新进行规划,实现障碍物的自主避让,进行自主移动。In related technologies, the robot's control system usually has the ability to plan its own path, and the robot's control system can change the robot's direction of movement after a collision. In some more advanced robots, when encountering fixed obstacles, the robot can rely on its own control system to re-plan the current moving path, achieve autonomous obstacle avoidance, and move autonomously.

针对上述中的相关技术,发明人发现:机器人通常能够对固定的障碍物进行自主避让,但是对于后方移动的障碍物难以进行避让。With respect to the above-mentioned related technologies, the inventors found that: the robot can usually autonomously avoid fixed obstacles, but it is difficult to avoid obstacles moving from behind.

发明内容Summary of the invention

为了减少机器人与后方移动的障碍物发生碰撞的可能性,本申请提供了机器人避让方法及系统。In order to reduce the possibility of a robot colliding with an obstacle moving from behind, the present application provides a robot avoidance method and system.

第一方面,本申请提供的机器人避让方法采用如下的技术方案。In a first aspect, the robot avoidance method provided in the present application adopts the following technical solution.

机器人避让方法,包括:Robot avoidance methods, including:

当机器人沿着第一路径移动时,检测后方预设范围内是否存在移动的物体;如果是,则基于所述物体的位置变化得到所述物体的第一速度;When the robot moves along the first path, detecting whether there is a moving object within a preset range behind; if yes, obtaining a first speed of the object based on a position change of the object;

判断所述第一速度是否大于所述机器人的移动速度;如果是,则基于所述物体的位置变化生成预判路径;以及,determining whether the first speed is greater than the moving speed of the robot; if so, generating a predicted path based on the position change of the object; and,

判断所述预判路径是否与所述第一路径存在交叉点;如果是,则在所述物体移动至所述机器人的第一范围时,控制所述机器人往第二路径移动;所述第二路径与所述预判路径不存在交叉点。Determine whether the predicted path has an intersection with the first path; if so, when the object moves to the first range of the robot, control the robot to move to a second path; the second path has no intersection with the predicted path.

通过采用上述技术方案,机器人基于物体的位置变化,结合不同时刻采集的位置能够得到物体的位置变化进而得到物体的第一速度;控制器将得到的第一速度与机器人的移动速度进行比较,从而判断第一速度是否大于机器人的移动速度;当移动的物体的第一速度大于机器人的移动速度时,则意味着物体有一定的概率会从后方超过机器人;当预判路径与第一路径存在交叉点时,则物体存在于机器人碰撞的可能性或者机器人存在干扰物体移动的可能性;因此在物体移动至机器人的第一范围时,控制器控制机器人往第二路径移动;由于第二路径与预判路径不存在交叉点,从而减少机器人与物体发生碰撞的可能性,或者减少机器人对物体造成阻挡的可能性;从而减少机器人与后方移动的障碍物发生碰撞的可能性。By adopting the above technical solution, the robot can obtain the position change of the object based on the position change of the object combined with the positions collected at different times and then obtain the first speed of the object; the controller compares the obtained first speed with the moving speed of the robot to determine whether the first speed is greater than the moving speed of the robot; when the first speed of the moving object is greater than the moving speed of the robot, it means that there is a certain probability that the object will overtake the robot from the rear; when the predicted path and the first path have an intersection, there is a possibility that the object will collide with the robot or the robot may interfere with the movement of the object; therefore, when the object moves to the first range of the robot, the controller controls the robot to move to the second path; since the second path and the predicted path do not have an intersection, the possibility of the robot colliding with the object is reduced, or the possibility of the robot blocking the object is reduced; thereby reducing the possibility of the robot colliding with an obstacle moving from the rear.

可选的,在控制所述机器人往第二路径移动之后,还包括:Optionally, after controlling the robot to move toward the second path, the method further includes:

判断所述物体是否由后方超过所述机器人;如果是,则控制所述机器人移动至第一路径中并沿第一路径继续移动。Determine whether the object exceeds the robot from the rear; if so, control the robot to move into the first path and continue to move along the first path.

通过采用上述技术方案,通常情况下,第一路径是为机器人分配的最优路径;当物体超过机器人后,由于物体的移动速度大于机器人的移动速度,即使机器人重新回到第一路径,机器人也不易与上述的物体发生碰撞;机器人回归第一路径并沿第一路径继续移动,无需再次为机器人规划、生成新的路径。By adopting the above technical solution, under normal circumstances, the first path is the optimal path assigned to the robot; when the object exceeds the robot, since the moving speed of the object is greater than the moving speed of the robot, even if the robot returns to the first path, the robot is not likely to collide with the above object; the robot returns to the first path and continues to move along the first path, and there is no need to plan and generate a new path for the robot again.

可选的,在所述机器人沿着第一路径移动之前,还包括:设置所述机器人的工作场景;Optionally, before the robot moves along the first path, the method further includes: setting a working scene for the robot;

在检测到后方存在移动的物体之后,还包括:对移动的物体进行身份识别得到物体的身份信息;以及,After detecting that there is a moving object behind, the method further includes: identifying the moving object to obtain identity information of the object; and,

在生成预判路径之后还包括:基于所述工作场景以及所述身份信息对所述预判路径进行修正。After generating the predicted path, the method further includes: modifying the predicted path based on the working scenario and the identity information.

可选的,所述基于所述工作场景以及所述身份信息对所述预判路径进行修正包括:Optionally, the modifying the predicted path based on the working scenario and the identity information includes:

基于所述工作场景以及所述身份信息调取若干历史路径;所述历史路径为移动的所述物体在所述工作场景下的历史路径;Retrieving a plurality of historical paths based on the working scene and the identity information; the historical paths are historical paths of the moving object in the working scene;

根据某一历史路径与其余历史路径的重合度得到每一历史路径的第一评分;The first score of each historical path is obtained according to the overlap between a certain historical path and other historical paths;

根据历史路径与所述预判路径的重合度得到每一历史路径的第二评分;Obtaining a second score for each historical path according to the degree of overlap between the historical path and the predicted path;

结合所述第一评分及所述第二评分得到每一历史路径的第三得分;以及,combining the first score and the second score to obtain a third score for each historical path; and,

选取第三得分最高的所述历史路径对所述预判路径进行修正。The historical path with the third highest score is selected to correct the predicted path.

通过采用上述技术方案,不同的工作场景对应着不同的空间排布,机器人能够移动的范围不同,物体移动的常规路径不同;第一评分用于反映该物体如果按照以往的路径移动时更可能选择哪条历史路径;第二评分用于反映该物体当下更可能选择哪条历史路径;结合历史路径及预判路径得到第三评分最高的历史路径对预判路径进行修正,进而使得预判路径更加精确地预测物体移动的路径。By adopting the above technical solution, different working scenes correspond to different spatial arrangements, the range of movement of the robot is different, and the conventional paths of object movement are different; the first score is used to reflect which historical path the object is more likely to choose if it moves along the previous path; the second score is used to reflect which historical path the object is more likely to choose at the moment; the historical path and the predicted path are combined to obtain the third historical path with the highest score to correct the predicted path, so that the predicted path can more accurately predict the path of the object's movement.

可选的,对所述预判路径进行修正后,还包括:Optionally, after the predicted path is corrected, the method further includes:

实时结合物体的位置变化得到实际移动路径;The actual moving path is obtained by combining the position changes of the object in real time;

计算所述实际移动路径与所述预判路径的重合度;Calculating the degree of overlap between the actual moving path and the predicted path;

判断实际移动路径与预判路径的所述重合度是否大于预设数值;如果否,则结合物体的位置变化重新生成预判路径;以及,Determine whether the overlap between the actual moving path and the predicted path is greater than a preset value; if not, regenerate the predicted path in combination with the position change of the object; and,

重新结合历史路径对重新生成的预判路径进行修正。The regenerated predicted path is corrected by recombining the historical path.

通过采用上述技术方案,控制器将物体的实际移动路径与预判路径进行比较,得到两者的重合度;此后,控制器判断重合度是否大于预设数值;如果两者的重合度小于预设数值,则反映出当前的预判路径不够准确,因此需要对预判路径重新生成并进行修正。By adopting the above technical solution, the controller compares the actual moving path of the object with the predicted path to obtain the degree of overlap between the two; thereafter, the controller determines whether the degree of overlap is greater than a preset value; if the degree of overlap between the two is less than the preset value, it reflects that the current predicted path is not accurate enough, so the predicted path needs to be regenerated and corrected.

可选的,得到物体的身份信息之后,还包括:Optionally, after obtaining the identity information of the object, the following is also included:

基于所述身份信息判断所述物体是否为儿童或者是否为宠物;如果是,则控制所述机器人立即往不与所述预判路径交叉的路径移动。Based on the identity information, it is determined whether the object is a child or a pet; if so, the robot is controlled to immediately move to a path that does not intersect with the predicted path.

通过采用上述技术方案,当判断物体为儿童或者为宠物后,机器人立即往不与预判路径交叉的路径移动,减少儿童或者宠物与移动的机器人发生碰撞的可能性。By adopting the above technical solution, when the object is determined to be a child or a pet, the robot immediately moves to a path that does not intersect with the predicted path, thereby reducing the possibility of collision between the child or pet and the moving robot.

可选的,在判断所述物体为儿童后,还包括:Optionally, after determining that the object is a child, the method further includes:

判断所述预判路径是否经过所述工作场景中的危险区域;如果是,发出警示信息。Determine whether the predicted path passes through a dangerous area in the work scene; if so, issue a warning message.

通过采用上述技术方案,在判断物体为儿童后,机器人判断预判路径是否经过工作场景中的危险区域,当预判路径经过危险区域时,机器人发出警示信息,进而对其它人进行提醒,能够更好地保护儿童。By adopting the above technical solution, after determining that the object is a child, the robot determines whether the predicted path passes through a dangerous area in the work scene. When the predicted path passes through a dangerous area, the robot issues a warning message and then reminds other people, thereby better protecting children.

第二方面,本申请提供的机器人避让系统采用如下的技术方案。In the second aspect, the robot avoidance system provided in this application adopts the following technical solution.

机器人避让系统,包括:Robot avoidance system, including:

检测模块,用于当机器人沿着第一路径移动时,检测后方是否存在移动的物体;如果是,则基于所述物体的位置变化得到所述物体的第一速度;A detection module, configured to detect whether there is a moving object behind the robot when the robot moves along the first path; if yes, obtain a first speed of the object based on a position change of the object;

速度判断模块,用于判断所述第一速度是否大于所述机器人的移动速度;A speed determination module, used to determine whether the first speed is greater than the moving speed of the robot;

预判路径生成模块,用于在所述第一速度大于所述机器人的移动速度时,基于所述物体的位置变化生成预判路径;A predicted path generation module, configured to generate a predicted path based on a position change of the object when the first speed is greater than a moving speed of the robot;

交叉点判断模块,用于判断所述预判路径是否与所述第一路径存在交叉点;以及,an intersection determination module, used to determine whether the predicted path has an intersection with the first path; and

路径控制模块,用于在所述预判路径与所述第一路径存在交叉点,在所述物体移动至所述机器人的第一范围时,控制所述机器人往第二路径移动;所述第二路径与所述预判路径不存在交叉点。A path control module is used to control the robot to move to a second path when there is an intersection between the predicted path and the first path and when the object moves to a first range of the robot; the second path does not have an intersection with the predicted path.

第三方面,本申请公开一种计算机设备,包括存储器和服务器,所述存储器上存储有被服务器加载并执行上述的任一方法的计算机程序。In a third aspect, the present application discloses a computer device, including a memory and a server, wherein the memory stores a computer program that is loaded by the server and executes any of the above methods.

第四方面,本申请公开一种计算机可读存储介质,存储有能够被服务器加载并执行上述的任一方法的计算机程序In a fourth aspect, the present application discloses a computer-readable storage medium storing a computer program that can be loaded by a server and execute any of the above methods.

附图说明BRIEF DESCRIPTION OF THE DRAWINGS

图1是本申请实施例机器人避让方法的其中一实施方式的流程图;FIG1 is a flow chart of one implementation of a robot avoidance method according to an embodiment of the present application;

图2是本申请对预判路径进行修正其中一种实施方式的流程图;FIG2 is a flow chart of one implementation method of correcting the predicted path in the present application;

图3是本申请实施例的机器人避让方法的另一实施方式的流程图;FIG3 is a flow chart of another implementation of the robot avoidance method according to an embodiment of the present application;

图4是本申请实施例机器人避让系统的其中一实施方式的系统框图;FIG4 is a system block diagram of one implementation of the robot avoidance system according to an embodiment of the present application;

图中,401、检测模块;402、速度判断模块;403、预判路径生成模块;404、交叉点判断模块;405、路径控制模块。In the figure, 401 is a detection module; 402 is a speed judgment module; 403 is a predicted path generation module; 404 is an intersection judgment module; 405 is a path control module.

具体实施方式DETAILED DESCRIPTION

为了使本申请的目的、技术方案及优点更加清楚明白,以下结合附图1-4及实施例,对本申请进行进一步详细说明。应当理解,此处所描述的具体实施例仅用以解释本申请,并不用于限定本申请。In order to make the purpose, technical solution and advantages of the present application more clear, the present application is further described in detail below in conjunction with Figures 1-4 and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application and are not used to limit the present application.

本申请实施例公开机器人避让方法。参照图1,作为机器人避让方法的一种实施方式,该方法包括以下步骤:The present application embodiment discloses a robot avoidance method. Referring to FIG1 , as an implementation of the robot avoidance method, the method includes the following steps:

步骤101、当机器人沿着第一路径移动时,检测后方预设范围内是否存在移动的物体;如果是,则执行步骤102。Step 101 : When the robot moves along a first path, detect whether there is a moving object within a preset range behind; if yes, execute step 102 .

具体的,机器人上设置的激光传感器、图像采集设备等数据采集设备能够在机器人工作时采集周围的数据,机器人的控制器对采集的这些数据进行处理后能够判别在机器人的预设范围内是否存在移动的物体。移动的物体包括但不限于移动的人、移动的动物及移动的机器等。第一路径为机器人执行某项指令时其移动的路径。上述的后方可以理解为:机器人由A地点往B地点移动,在这个过程中,某个物体移动的方向与机器人移动的方向近似或相同,且该物体与B点的距离大于机器人与B点的距离,则机器人判定该移动的物体位于其后方。设置预设范围能够便于机器人的控制器在机器人的后方存在移动的物体时进行数据处理及对机器人的移动方向或移动路径进行控制。控制器可以根据机器人的大小以及工作场景对预设范围进行配置。例如:小型机器人的预设范围一般小于大型机器人的预设范围;住宅面积小的工作场景相较于住宅面积大的工作场景,机器人的预设范围也可以适应性减少。Specifically, the data acquisition devices such as laser sensors and image acquisition devices provided on the robot can collect surrounding data when the robot is working. After processing the collected data, the controller of the robot can determine whether there is a moving object within the preset range of the robot. Moving objects include but are not limited to moving people, moving animals, and moving machines. The first path is the path of the robot when it executes a certain instruction. The above-mentioned rear can be understood as: the robot moves from point A to point B. During this process, the direction of movement of a certain object is similar to or the same as the direction of movement of the robot, and the distance between the object and point B is greater than the distance between the robot and point B. Then the robot determines that the moving object is located behind it. Setting a preset range can facilitate the controller of the robot to process data and control the moving direction or moving path of the robot when there is a moving object behind the robot. The controller can configure the preset range according to the size of the robot and the working scene. For example: the preset range of a small robot is generally smaller than the preset range of a large robot; the preset range of the robot can also be adaptively reduced in a working scene with a small residential area compared to a working scene with a large residential area.

步骤102、基于物体的位置变化得到物体的第一速度。Step 102: Obtain a first velocity of the object based on a position change of the object.

具体的,机器人的控制器基于数据采集设备所采集的数据能够得到上述移动的物体的位置变化。例如,机器人的控制器可以通过数据采集设备实时采集物体的位置,结合不同时刻采集的位置能够得到物体的位置变化进而得到物体的第一速度;第一速度用于反映物体移动的快慢。Specifically, the robot controller can obtain the position change of the moving object based on the data collected by the data collection device. For example, the robot controller can collect the position of the object in real time through the data collection device, and can obtain the position change of the object by combining the positions collected at different times and then obtain the first speed of the object; the first speed is used to reflect the speed of the object's movement.

步骤103、判断第一速度是否大于机器人的移动速度;如果是,则执行步骤104。Step 103 , determining whether the first speed is greater than the moving speed of the robot; if so, executing step 104 .

具体的,控制器将得到的第一速度与机器人的移动速度进行比较,从而判断第一速度是否大于机器人的移动速度;当移动的物体的第一速度大于机器人的移动速度时,则意味着物体有一定的概率会从后方超过机器人。Specifically, the controller compares the obtained first speed with the moving speed of the robot to determine whether the first speed is greater than the moving speed of the robot; when the first speed of the moving object is greater than the moving speed of the robot, it means that there is a certain probability that the object will overtake the robot from behind.

步骤104、基于物体的位置变化生成预判路径。Step 104: Generate a predicted path based on the position change of the object.

具体的,通常来说,物体移动时的路径近似于一条射线,控制器通过物体的位置变化形成这条射线的一部分片段,将上述片段进行延长即可得到预判路径。Specifically, generally speaking, the path of an object when it moves is approximately similar to a ray. The controller forms a segment of this ray through the position change of the object, and the predicted path can be obtained by extending the segment.

步骤105、判断预判路径是否与第一路径存在交叉点;如果是,则执行步骤106。Step 105 , determine whether the predicted path has an intersection with the first path; if so, execute step 106 .

具体的,上述的交叉点可以理解为预判路径与第一路径相重合的部分,当预判路径与第一路径存在交叉点时,则物体存在于机器人碰撞的可能性或者机器人存在干扰物体移动的可能性。Specifically, the above-mentioned intersection can be understood as the part where the predicted path and the first path overlap. When the predicted path and the first path have an intersection, there is a possibility that the robot will collide with the object or the robot may interfere with the movement of the object.

步骤106、在物体移动至机器人的第一范围时,控制机器人往第二路径移动;第二路径与预判路径不存在交叉点。Step 106: When the object moves to the first range of the robot, the robot is controlled to move to the second path; there is no intersection between the second path and the predicted path.

具体的,在物体移动至机器人的第一范围时,控制器控制机器人往第二路径移动;由于第二路径与预判路径不存在交叉点,从而减少机器人与物体发生碰撞的可能性,或者减少机器人对物体造成阻挡的可能性。根据机器人的移动速度以及物体的第一速度不同,第一范围可以进行扩大或者缩小;例如,机器人的移动速度相较于第一速度低很多,则第一范围可以适当增加,从而为机器人在第二路径移动提供更多的时间。Specifically, when the object moves to the first range of the robot, the controller controls the robot to move to the second path; since there is no intersection between the second path and the predicted path, the possibility of collision between the robot and the object or the possibility of the robot blocking the object is reduced. Depending on the movement speed of the robot and the first speed of the object, the first range can be expanded or reduced; for example, if the movement speed of the robot is much lower than the first speed, the first range can be appropriately increased to provide more time for the robot to move on the second path.

作为机器人避让方法的另一种实施方式,在控制机器人往第二路径移动之后,还包括:判断物体是否由后方超过机器人;如果是,则控制机器人移动至第一路径中并沿第一路径继续移动。As another implementation of the robot avoidance method, after controlling the robot to move to the second path, it also includes: determining whether the object exceeds the robot from the rear; if so, controlling the robot to move to the first path and continue moving along the first path.

具体的,通常情况下,第一路径是为机器人分配的最优路径;当物体超过机器人后,由于物体的移动速度(即第一速度)大于机器人的移动速度,即使机器人重新回到第一路径,机器人也不易与上述的物体发生碰撞。机器人回归第一路径并沿第一路径继续移动,无需再次为机器人规划、生成新的路径,节省了算力。Specifically, usually, the first path is the optimal path assigned to the robot; when the object exceeds the robot, since the moving speed of the object (i.e., the first speed) is greater than the moving speed of the robot, even if the robot returns to the first path, it is unlikely for the robot to collide with the above-mentioned object. The robot returns to the first path and continues to move along the first path, and there is no need to plan and generate a new path for the robot again, saving computing power.

作为机器人避让方法的另一种实施方式,在机器人沿着第一路径移动之前,还包括:设置机器人的工作场景;As another implementation of the robot avoidance method, before the robot moves along the first path, it also includes: setting a working scene of the robot;

在检测到后方存在移动的物体之后,还包括:对移动的物体进行身份识别得到物体的身份信息;以及,After detecting that there is a moving object behind, the method further includes: identifying the moving object to obtain identity information of the object; and,

在生成预判路径之后还包括:基于工作场景以及身份信息对预判路径进行修正。After the predicted path is generated, the method further includes: modifying the predicted path based on the work scenario and identity information.

具体的,机器人的工作场景即机器人工作时所处的场景,工作场景包括但不限于卧室、厨房、客厅及办公室,不同的工作场景对应着不同的空间排布,机器人能够移动的范围不同,物体移动的常规路径不同。对移动的物体进行身份识别可以是通过图像采集设备采集物体的图像,利用图像识别算法得到物体的身份信息。同一身份信息的物体在对应的场景内移动时,移动的路径一般存在相似性。例如,办公室内的员工,如果该员工通常情况下离开工位,要不是前往洗手间,要不是前往饮水机处接水,要不是下班回家,那么该员工下次离开工位时,有较大概率是前述三条路径的其中一条,因此控制器可以基于工作场景以及身份信息对预判路径进行修正,便于辅助推测物体的移动路径。Specifically, the robot's working scene is the scene in which the robot is working. The working scene includes but is not limited to bedrooms, kitchens, living rooms and offices. Different working scenes correspond to different spatial arrangements, the range of movement of the robot is different, and the conventional paths of object movement are different. The identity recognition of a moving object can be performed by capturing an image of the object through an image acquisition device, and obtaining the identity information of the object using an image recognition algorithm. When objects with the same identity information move in the corresponding scene, the paths of movement generally have similarities. For example, if an employee in an office usually leaves his workstation, he either goes to the bathroom, goes to a water dispenser to get water, or goes home after get off work, then the next time the employee leaves his workstation, there is a high probability that he will take one of the above three paths. Therefore, the controller can correct the predicted path based on the working scene and identity information to assist in inferring the moving path of the object.

基于工作场景以及身份信息对预判路径进行修正包括以下步骤:Correcting the predicted path based on the work scenario and identity information includes the following steps:

步骤201、基于工作场景以及身份信息调取若干历史路径;历史路径为移动的物体在工作场景下的历史路径。Step 201: retrieve several historical paths based on the work scene and identity information; the historical paths are historical paths of the moving object in the work scene.

具体的,若干历史路径反映了该物体在该工作场景中通常使用的路径,可以预先存储不同身份信息的物体在该工作场景中的若干历史路径。Specifically, the plurality of historical paths reflect the paths that the object usually uses in the working scene, and the plurality of historical paths of objects with different identity information in the working scene may be pre-stored.

步骤202、根据某一历史路径与其余历史路径的重合度得到每一历史路径的第一评分。Step 202: Obtain a first score for each historical path according to the degree of overlap between a certain historical path and other historical paths.

具体的,第一评分可以是根据某一历史路径与其它历史路径的重合度的评分进行求和取平均值处理得到的。第一评分用于反映该物体如果按照以往的路径移动时更可能选择哪条历史路径。Specifically, the first score may be obtained by summing and averaging scores of the overlap between a certain historical path and other historical paths. The first score is used to reflect which historical path the object is more likely to choose if it moves along the previous path.

步骤203、根据历史路径与预判路径的重合度得到每一历史路径的第二评分。Step 203: Obtain a second score for each historical path according to the degree of overlap between the historical path and the predicted path.

具体的,由于物体并非总是机械、重复的运动,控制器根据每一历史路径与预判路径的重合度得到每一历史路径的第二评分;第二评分用于反映该物体当下更可能选择哪条历史路径。Specifically, since objects do not always move mechanically and repetitively, the controller obtains a second score for each historical path based on the degree of overlap between each historical path and the predicted path; the second score is used to reflect which historical path the object is more likely to choose at the moment.

步骤204、结合第一评分及第二评分得到每一历史路径的第三得分。Step 204: Combine the first score and the second score to obtain a third score for each historical path.

具体的,第三得分可以通过第一评分及第二评分进行加权取平均得到;可以根据物体的身份信息配置第一评分及第二评分的权重。例如:某一物体习惯于每次走相同或相似的路径,则可以增加第一评分的权重。Specifically, the third score can be obtained by weighted average of the first score and the second score; the weights of the first score and the second score can be configured according to the identity information of the object. For example, if an object is accustomed to taking the same or similar path every time, the weight of the first score can be increased.

步骤205、选取第三评分最高的历史路径对预判路径进行修正。Step 205: Select the historical path with the third highest score to correct the predicted path.

具体的,结合历史路径及预判路径得到第三评分最高的历史路径对预判路径进行修正。上述的修正即增加预判路径与第三评分最高的历史路径的重合度;通过选取第三评分最高的历史路径对预判路径进行修正,能够使得预判路径更加精确地预测物体移动的路径。Specifically, the predicted path is corrected by combining the historical path and the predicted path to obtain the third highest-scoring historical path. The above correction is to increase the overlap between the predicted path and the third highest-scoring historical path; by selecting the third highest-scoring historical path to correct the predicted path, the predicted path can be made to more accurately predict the path of the object's movement.

作为机器人避让方法的另一种实施方式,对预判路径进行修正后,还包括以下步骤:As another implementation of the robot avoidance method, after the predicted path is corrected, the following steps are also included:

步骤301、实时结合物体的位置变化得到实际移动路径。Step 301: Obtain the actual moving path in real time in combination with the position change of the object.

步骤302、计算实际移动路径与预判路径的重合度。Step 302: Calculate the degree of overlap between the actual moving path and the predicted path.

步骤303、判断实际移动路径与预判路径的重合度是否大于预设数值;如果否,则执行步骤304。Step 303 , determine whether the overlap between the actual moving path and the predicted path is greater than a preset value; if not, execute step 304 .

步骤304、结合物体的位置变化重新生成预判路径。Step 304: regenerate the predicted path based on the position change of the object.

步骤305、重新结合历史路径对重新生成的预判路径进行修正。Step 305: Re-combine the historical path to correct the regenerated predicted path.

具体的,由于物体并非总是机械、重复的运动,机器人的控制器将物体的实际移动路径与预判路径进行比较,得到两者的重合度。此后,控制器判断重合度是否大于预设数值;如果两者的重合度小于预设数值,则反映出当前的预判路径不够准确,因此需要对预判路径重新生成并进行修正。Specifically, since objects do not always move mechanically and repeatedly, the robot controller compares the actual moving path of the object with the predicted path to obtain the overlap between the two. After that, the controller determines whether the overlap is greater than a preset value; if the overlap is less than the preset value, it reflects that the current predicted path is not accurate enough, so the predicted path needs to be regenerated and corrected.

作为机器人避让方法的另一种实施方式,得到物体的身份信息之后,还包括:基于身份信息判断物体是否为儿童或者是否为宠物;如果是,则控制机器人立即往不与预判路径交叉的路径移动。As another implementation of the robot avoidance method, after obtaining the identity information of the object, it also includes: judging whether the object is a child or a pet based on the identity information; if so, controlling the robot to immediately move to a path that does not intersect the predicted path.

具体的,由于儿童与宠物的移动速度通常是不规律,容易发生变化的,为了减少机器人在移动过程中与宠物或者儿童发生碰撞,因此在本实施例中,当判断物体为儿童或者为宠物后,机器人立即往不与预判路径交叉的路径移动,减少儿童或者宠物与移动的机器人发生碰撞的可能性。Specifically, since the movement speed of children and pets is usually irregular and prone to change, in order to reduce the possibility of collision between the robot and pets or children during movement, in this embodiment, when the object is determined to be a child or a pet, the robot immediately moves to a path that does not intersect with the predicted path, thereby reducing the possibility of collision between the child or pet and the moving robot.

在判断物体为儿童后,上述方法还包括:判断预判路径是否经过工作场景中的危险区域;如果是,发出警示信息。After determining that the object is a child, the above method further includes: determining whether the predicted path passes through a dangerous area in the work scene; if so, issuing a warning message.

具体的,危险区域包括水池、放置有危险物品(例如刀具)的区域,在判断物体为儿童后,机器人判断预判路径是否经过工作场景中的危险区域,当预判路径经过危险区域时,机器人发出警示信息,警示信息可以是警示灯闪烁,也可以是发出语音提示信息,进而对其它人进行提醒,能够更好地保护儿童。Specifically, dangerous areas include pools and areas where dangerous objects (such as knives) are placed. After determining that the object is a child, the robot determines whether the predicted path passes through the dangerous area in the work scene. When the predicted path passes through the dangerous area, the robot issues a warning message. The warning message can be a flashing warning light or a voice prompt message, thereby reminding other people and better protecting children.

基于上述的机器人避让方法,本申请还提供了机器人避让系统,包括:Based on the above robot avoidance method, the present application also provides a robot avoidance system, including:

检测模块401,用于当机器人沿着第一路径移动时,检测后方是否存在移动的物体;如果是,则基于物体的位置变化得到物体的第一速度;The detection module 401 is used to detect whether there is a moving object behind the robot when the robot moves along the first path; if yes, obtain a first speed of the object based on the position change of the object;

速度判断模块402,用于判断第一速度是否大于机器人的移动速度;The speed determination module 402 is used to determine whether the first speed is greater than the moving speed of the robot;

预判路径生成模块403,用于在第一速度大于机器人的移动速度时,基于物体的位置变化生成预判路径;A predicted path generation module 403, configured to generate a predicted path based on a position change of the object when the first speed is greater than a moving speed of the robot;

交叉点判断模块404,用于判断预判路径是否与第一路径存在交叉点;以及,The intersection determination module 404 is used to determine whether the predicted path has an intersection with the first path; and

路径控制模块405,用于在预判路径与第一路径存在交叉点,在物体移动至机器人的第一范围时,控制机器人往第二路径移动;第二路径与预判路径不存在交叉点。The path control module 405 is used to control the robot to move to the second path when there is an intersection between the predicted path and the first path and the object moves to the first range of the robot; the second path does not have an intersection with the predicted path.

本申请实施例还公开一种计算机设备。The embodiment of the present application also discloses a computer device.

具体来说,该设备包括存储器和服务器,存储器上存储有能够被服务器加载并执行上述任意机器人避让方法的计算机程序。Specifically, the device includes a memory and a server, and the memory stores a computer program that can be loaded by the server and execute any of the above-mentioned robot avoidance methods.

本申请实施例还公开一种计算机可读存储介质。The embodiment of the present application also discloses a computer-readable storage medium.

具体来说,该计算机可读存储介质,其存储有能够被服务器加载并执行如上述任意机器人避让方法的计算机程序,该计算机可读存储介质例如包括:U盘、移动硬盘、只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,RAM)、磁碟或者光盘等各种可以存储程序代码的介质。Specifically, the computer-readable storage medium stores a computer program that can be loaded by the server and execute any of the robot avoidance methods described above. The computer-readable storage medium includes, for example, a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

以上均为本申请的较佳实施例,并非依此限制本申请的保护范围,本说明书(包括摘要和附图)中公开的任一特征,除非特别叙述,均可被其他等效或者具有类似目的的替代特征加以替换。即,除非特别叙述,每个特征只是一系列等效或类似特征中的一个例子而已。The above are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Any feature disclosed in this specification (including the abstract and drawings), unless otherwise stated, can be replaced by other equivalent or alternative features with similar purposes. That is, unless otherwise stated, each feature is only an example of a series of equivalent or similar features.

Claims (9)

1. The robot avoiding method is characterized by comprising the following steps:
Setting a working scene of the robot;
Detecting whether a moving object exists in a rear preset range or not when the robot moves along a first path; if so, carrying out identity recognition on the moving object to obtain identity information of the object, and obtaining a first speed of the object based on the position change of the object;
judging whether the first speed is greater than the moving speed of the robot; if so, generating a pre-judging path based on the position change of the object; correcting the prejudgment path based on the working scene and the identity information; and
Judging whether the pre-judging path and the first path have an intersection point or not; if so, controlling the robot to move to a second path when the object moves to a first range of the robot; and the second path and the pre-judging path have no crossing point.
2. The robot avoidance method of claim 1, further comprising, after controlling the movement of the robot toward the second path:
Judging whether the object exceeds the robot from the rear; and if so, controlling the robot to move into the first path and continue to move along the first path.
3. The robot avoidance method of claim 1 wherein the modifying the predicted path based on the working scenario and the identity information comprises:
invoking a plurality of history paths based on the working scene and the identity information; the historical path is the historical path of the moving object in the working scene;
Obtaining a first score of each historical path according to the coincidence degree of a certain historical path and the rest historical paths;
obtaining a second score of each historical path according to the coincidence degree of the historical path and the prejudging path;
combining the first score and the second score to obtain a third score of each historical path; and
And selecting the history path with the highest third score to correct the pre-judging path.
4. The robot avoidance method of claim 3, further comprising, after correcting the predicted path:
Combining the position change of the object in real time to obtain an actual moving path;
Calculating the coincidence ratio of the actual moving path and the prejudging path;
Judging whether the overlap ratio of the actual moving path and the pre-judging path is larger than a preset value; if not, regenerating a pre-judging path by combining the position change of the object; and
And correcting the regenerated pre-judging path by combining the history path again.
5. The robot avoidance method of claim 1, further comprising, after obtaining the identity information of the object:
judging whether the object is a child or a pet based on the identity information; if so, the robot is controlled to immediately move to a path which does not intersect with the pre-judging path.
6. The robot avoidance method of claim 5, further comprising, after determining that the object is a child:
Judging whether the pre-judging path passes through a dangerous area in the working scene or not; if yes, sending out warning information.
7. Robot dodges system, its characterized in that includes:
A detection module (401) for setting a working scene of the robot, and detecting whether a moving object exists behind when the robot moves along a first path; if so, carrying out identity recognition on the moving object to obtain identity information of the object, and obtaining a first speed of the object based on the position change of the object;
A speed determination module (402) configured to determine whether the first speed is greater than a moving speed of the robot;
A pre-judgment path generation module (403) for generating a pre-judgment path based on a change in the position of the object when the first speed is greater than the moving speed of the robot; correcting the prejudgment path based on the working scene and the identity information; a crossing point judging module (404) for judging whether crossing points exist between the pre-judging path and the first path; and
A path control module (405) for controlling the robot to move to a second path when the object moves to a first range of the robot when the intersection point exists between the pre-determined path and the first path; and the second path and the pre-judging path have no crossing point.
8. A computer device, characterized by: comprising a memory and a server, said memory having stored thereon a computer program for loading and executing by the server a method according to any of claims 1 to 6.
9. A computer readable storage medium, characterized in that a computer program is stored which can be loaded by a server and which performs the method according to any one of claims 1 to 6.
CN202210193094.3A 2022-02-28 2022-02-28 Robot avoidance method and system Active CN114625132B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210193094.3A CN114625132B (en) 2022-02-28 2022-02-28 Robot avoidance method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210193094.3A CN114625132B (en) 2022-02-28 2022-02-28 Robot avoidance method and system

Publications (2)

Publication Number Publication Date
CN114625132A CN114625132A (en) 2022-06-14
CN114625132B true CN114625132B (en) 2024-10-15

Family

ID=81900217

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210193094.3A Active CN114625132B (en) 2022-02-28 2022-02-28 Robot avoidance method and system

Country Status (1)

Country Link
CN (1) CN114625132B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115167477A (en) * 2022-08-23 2022-10-11 广东爱吉尔机器人科技有限公司 Resource-limited central centralized dynamic path planning method and electronic equipment

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105253033A (en) * 2015-10-22 2016-01-20 北京新能源汽车股份有限公司 Vehicle control system
CN108733044A (en) * 2017-09-29 2018-11-02 北京猎户星空科技有限公司 Barrier-avoiding method, device, robot and computer readable storage medium

Family Cites Families (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4346472B2 (en) * 2004-02-27 2009-10-21 株式会社ザナヴィ・インフォマティクス Traffic information prediction device
JP4581528B2 (en) * 2004-07-26 2010-11-17 株式会社デンソー In-vehicle control device
JP4699426B2 (en) * 2006-08-08 2011-06-08 パナソニック株式会社 Obstacle avoidance method and obstacle avoidance moving device
JP2011224679A (en) * 2010-04-16 2011-11-10 Toyota Motor Corp Reaction robot, reaction control method, and reaction control program
KR101673307B1 (en) * 2014-12-19 2016-11-22 현대자동차주식회사 Navigation system and path prediction method thereby, and computer readable medium for performing the same
CN107544514B (en) * 2017-09-29 2022-01-07 广州唯品会研究院有限公司 Robot obstacle avoiding method and device, storage medium and robot
CN108415417A (en) * 2018-01-19 2018-08-17 华南理工大学 A kind of robot obstacle-avoiding system and method based on the prediction of barrier motion state
CN108556842A (en) * 2018-03-05 2018-09-21 浙江吉利汽车研究院有限公司 Actively accelerate control method, device and the controller of collision avoidance
CN109144065B (en) * 2018-08-29 2021-08-13 广州安商智能科技有限公司 Robot avoidance method and device
CN109048910B (en) * 2018-08-29 2020-08-14 广州市君望机器人自动化有限公司 Robot avoidance pre-judging method and device
WO2020113187A1 (en) * 2018-11-30 2020-06-04 Sanjay Rao Motion and object predictability system for autonomous vehicles
US10534956B1 (en) * 2019-04-25 2020-01-14 Alclear, Llc Using identity information to facilitate interaction with people moving through areas
CN112650235A (en) * 2020-03-11 2021-04-13 南京奥拓电子科技有限公司 Robot obstacle avoidance control method and system and robot
CN112060090B (en) * 2020-09-01 2021-11-26 深圳优地科技有限公司 Robot avoidance method, device and computer readable storage medium
CN112405533A (en) * 2020-11-06 2021-02-26 深圳优地科技有限公司 Robot avoidance method, device, equipment and storage medium

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105253033A (en) * 2015-10-22 2016-01-20 北京新能源汽车股份有限公司 Vehicle control system
CN108733044A (en) * 2017-09-29 2018-11-02 北京猎户星空科技有限公司 Barrier-avoiding method, device, robot and computer readable storage medium

Also Published As

Publication number Publication date
CN114625132A (en) 2022-06-14

Similar Documents

Publication Publication Date Title
CN108628319B (en) Intelligent obstacle avoidance system of sweeping robot
CN108852182B (en) Intelligent obstacle avoidance method for sweeping robot
KR102335309B1 (en) to automatically park a vehicle in a parking lot
WO2019179441A1 (en) Focus tracking method and device of smart apparatus, smart apparatus, and storage medium
KR20210068446A (en) Terrain Awareness Step Planning System
WO2019041755A1 (en) Cleaning robot control method and cleaning robot
CN105182983A (en) Face real-time tracking method and face real-time tracking system based on mobile robot
WO2020211610A1 (en) Method and apparatus for recognising state of mobile robot, mobile robot, and storage medium
CN113064408B (en) Autonomous robot, control method thereof, and computer storage medium
KR100962593B1 (en) Method and apparatus for area based control of vacuum cleaner, and recording medium thereof
CN114625132B (en) Robot avoidance method and system
KR102510840B1 (en) Server for controlling autonomous driving of mobile robot in non-avoidable obstacles that are not damaged when hit, method and program
CN114564022A (en) Robot collision processing method and device
WO2024093989A1 (en) Obstacle avoidance method and system for robot
WO2024066308A1 (en) Golf cart following method and apparatus, and storage medium
CN117032213A (en) Method for escaping from trapping of movable robot, storage medium and movable robot
CN114518744A (en) Robot escaping method and device, robot and storage medium
CN115629612A (en) Obstacle avoidance method, device, equipment and storage medium
CN114326712B (en) Robot navigation path generation method, robot, device and storage medium
CN114527754A (en) Obstacle processing method and device based on omnibearing signal, computer equipment and storage medium
CN113467468A (en) Embedded robot intelligent obstacle avoidance system and method
CN117796711B (en) Method for processing escape of robot, robot and storage medium
CN112775971A (en) Method for improving safety performance, robot control cabinet and storage medium
CN118716013B (en) Obstacle avoidance method of intelligent mower, medium and product
CN113311847B (en) Driving method of disinfection device and disinfection device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CP03 Change of name, title or address

Address after: Building B2501, Shangrong Industrial Plant, No. 2 Baolong Fifth Road, Baolong Community, Baolong Street, Longgang District, Shenzhen City, Guangdong Province, 518000

Patentee after: Shenzhen Baolaiwei Intelligent Technology Co.,Ltd.

Country or region after: China

Address before: 518172 A810, block a, Rongchao Yinglong building, longfu Road, Shangjing community, Longcheng street, Longgang District, Shenzhen, Guangdong

Patentee before: SHENZHEN BAOLAIWEI INTELLIGENT TECHNOLOGY Co.,Ltd.

Country or region before: China

CP03 Change of name, title or address