CN115661386A - Environment map optimization method and device, robot and readable storage medium - Google Patents
Environment map optimization method and device, robot and readable storage mediumDownload PDFInfo
- Publication number
- CN115661386A CN115661386ACN202211275631.5ACN202211275631ACN115661386ACN 115661386 ACN115661386 ACN 115661386ACN 202211275631 ACN202211275631 ACN 202211275631ACN 115661386 ACN115661386 ACN 115661386A
- Authority
- CN
- China
- Prior art keywords
- robot
- environment map
- information
- coordinate information
- current
- 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.)
- Pending
Links
Images
Landscapes
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
Description
Translated fromChinese技术领域technical field
本发明涉及地图构建技术领域，尤其涉及一种环境地图优化方法、装置、机器人及可读存储介质。The present invention relates to the technical field of map construction, in particular to an environment map optimization method, device, robot and readable storage medium.
背景技术Background technique
随着机器人技术的发展，各种类型的机器人被广泛应用于人类日常生活的各个领域。With the development of robot technology, various types of robots are widely used in various fields of human daily life.
现有的机器人对所在环境进行环境地图构建的过程中，往往通过激光雷达传感器进行定位导航，在激光雷达扫射时，由于被扫描物体与该激光雷达之间的距离较远，或，该激光雷达相对于该被扫描物体的扫描入射角较大，导致得到的扫描结果容易出现畸变，即该扫描结果会存在较大的误差，从而导致该机器人构建的目标环境地图不够准确，影响了该目标环境地图的质量。In the process of building an environmental map for the existing robot, the laser radar sensor is often used for positioning and navigation. When the laser radar scans, due to the long distance between the scanned object and the laser radar, or the laser radar Compared with the scanning incident angle of the scanned object, the scanned result is prone to distortion, that is, there will be a large error in the scanned result, which leads to the inaccurate target environment map constructed by the robot, which affects the target environment. The quality of the map.
发明内容Contents of the invention
本发明提供一种环境地图优化方法、装置、机器人及可读存储介质，用以解决现有技术中机器人构建的目标环境地图不够准确，影响了该目标环境地图的质量的缺陷，实现对待识别物体对应的第一直线信息进行相应处理，得到较为准确的该第一直线信息对应地标点所对应的第二坐标信息，并基于该第二坐标信息，优化当前环境地图，可得到较为准确的目标环境地图，从而提高了该目标环境地图的质量。The present invention provides an environment map optimization method, device, robot and readable storage medium, which are used to solve the defect that the target environment map constructed by the robot in the prior art is not accurate enough, which affects the quality of the target environment map, and realize the object to be identified The corresponding first straight line information is processed accordingly to obtain more accurate second coordinate information corresponding to the landmark point corresponding to the first straight line information, and based on the second coordinate information, the current environment map can be optimized to obtain a more accurate The target environment map, thereby improving the quality of the target environment map.
本发明提供一种环境地图优化方法，包括：The present invention provides an environment map optimization method, comprising:
在初始化阶段，获取当前环境地图及待识别物体对应的第一直线信息；In the initialization phase, obtain the current environment map and the first straight line information corresponding to the object to be identified;
在下一时间步，根据该第一直线信息，确定该待识别物体对应的地标点在机体坐标系下的第一坐标信息，该机体坐标系与机器人对应；In the next time step, according to the first straight line information, determine the first coordinate information of the landmark point corresponding to the object to be identified in the body coordinate system, and the body coordinate system corresponds to the robot;
利用该第一坐标信息，对该机器人的当前位姿进行优化，得到优化位姿，并基于该优化位姿，确定该地标点对应的第一实际观测值在世界坐标系下的第二坐标信息；Using the first coordinate information, optimize the current pose of the robot to obtain an optimized pose, and based on the optimized pose, determine the second coordinate information of the first actual observation value corresponding to the landmark point in the world coordinate system ;
利用该第二坐标信息，对该当前环境地图进行更新，得到目标环境地图。The current environment map is updated by using the second coordinate information to obtain the target environment map.
根据本发明提供的一种环境地图优化方法，该根据该第一直线信息，确定该待识别物体对应的地标点在机体坐标系下的第一坐标信息，包括：根据该第一直线信息，确定该待识别物体对应的地标点及该地标点对应的第一实际观测值，该第一实际观测值包括该地标点与该机器人之间的第一距离值和第一角度值；根据该第一实际观测值，确定该地标点在机体坐标系下的第一坐标信息。According to an environment map optimization method provided by the present invention, according to the first straight line information, determining the first coordinate information of the landmark point corresponding to the object to be recognized in the body coordinate system includes: according to the first straight line information , determine the landmark point corresponding to the object to be recognized and the first actual observation value corresponding to the landmark point, the first actual observation value includes the first distance value and the first angle value between the landmark point and the robot; according to the The first actual observation value is to determine the first coordinate information of the landmark point in the body coordinate system.
根据本发明提供的一种环境地图优化方法，该利用该第一坐标信息，对该机器人的当前位姿进行优化，得到优化位姿，包括：在该机体坐标系下，对该第一坐标信息进行拟合，得到第二直线信息；将该第一坐标信息在该第二直线信息上进行投影，得到第一投影值；利用该第一投影值，对该机器人的当前位姿进行优化，得到优化位姿。According to an environment map optimization method provided by the present invention, using the first coordinate information to optimize the current pose of the robot to obtain the optimized pose includes: under the body coordinate system, the first coordinate information Perform fitting to obtain the second straight line information; project the first coordinate information on the second straight line information to obtain the first projection value; use the first projection value to optimize the current pose of the robot to obtain Optimize the pose.
根据本发明提供的一种环境地图优化方法，该基于该优化位姿，确定该地标点对应的第一实际观测值在世界坐标系下的第二坐标信息，包括：基于该优化位姿，将该第二直线信息在世界坐标系下进行转换，得到第三直线信息，并将该地标点对应的第一实际观测值在该第三直线信息上进行投影，得到第一子坐标信息；基于该优化位姿，将该第一实际观测值在该世界坐标系下进行转换，得到第二子坐标信息。According to an environment map optimization method provided by the present invention, determining the second coordinate information of the first actual observation value corresponding to the landmark point in the world coordinate system based on the optimized pose includes: based on the optimized pose, The second line information is converted in the world coordinate system to obtain the third line information, and the first actual observation value corresponding to the landmark point is projected on the third line information to obtain the first sub-coordinate information; based on the The pose is optimized, and the first actual observed value is transformed in the world coordinate system to obtain the second sub-coordinate information.
根据本发明提供的一种环境地图优化方法，该利用该第二坐标信息，对该当前环境地图进行更新，得到目标环境地图，包括：基于该第一子坐标信息及该第二子坐标信息，利用扩展卡尔曼滤波器，估计得到该地标点对应的目标坐标点；利用该目标坐标点，对该当前环境地图进行更新，得到目标环境地图。According to an environment map optimization method provided by the present invention, using the second coordinate information to update the current environment map to obtain a target environment map includes: based on the first sub-coordinate information and the second sub-coordinate information, The target coordinate point corresponding to the landmark point is estimated by using the extended Kalman filter; the current environment map is updated by using the target coordinate point to obtain the target environment map.
根据本发明提供的一种环境地图优化方法，该利用该第一投影值，对该机器人的当前位姿进行优化，得到优化位姿，包括：根据该第一投影值，使用扩展卡尔曼滤波器对该机器人的当前位姿进行优化，得到优化位姿。According to an environment map optimization method provided by the present invention, using the first projection value to optimize the current pose of the robot to obtain the optimized pose includes: using an extended Kalman filter according to the first projection value The current pose of the robot is optimized to obtain the optimized pose.
根据本发明提供的一种环境地图优化方法，该获取当前环境地图及待识别物体对应的第一直线信息，包括：确定待识别物体与机器人之间的当前距离值；在该当前距离值位于预设距离范围内的情况下，获取该待识别物体对应的第一直线信息，并获取该机器人所在环境的当前环境地图。According to an environment map optimization method provided by the present invention, the acquisition of the current environment map and the first line information corresponding to the object to be identified includes: determining the current distance value between the object to be identified and the robot; when the current distance value is located at If it is within the preset distance range, the first straight line information corresponding to the object to be identified is obtained, and the current environment map of the environment where the robot is located is obtained.
本发明还提供一种环境地图优化装置，包括：The present invention also provides an environment map optimization device, including:
获取模块，用于在初始化阶段，获取当前环境地图及待识别物体对应的第一直线信息；The acquisition module is used to acquire the current environment map and the first straight line information corresponding to the object to be identified during the initialization phase;
处理模块，用于在下一时间步，根据该第一直线信息，确定该待识别物体对应的地标点在机体坐标系下的第一坐标信息，该机体坐标系与机器人对应；利用该第一坐标信息，对该机器人的当前位姿进行优化，得到优化位姿，并基于该优化位姿，确定该地标点对应的第一实际观测值在世界坐标系下的第二坐标信息；利用该第二坐标信息，对该当前环境地图进行更新，得到目标环境地图。The processing module is used to determine the first coordinate information of the landmark point corresponding to the object to be recognized in the body coordinate system in the next time step according to the first straight line information, and the body coordinate system corresponds to the robot; using the first Coordinate information, optimize the current pose of the robot to obtain the optimized pose, and based on the optimized pose, determine the second coordinate information of the first actual observation value corresponding to the landmark point in the world coordinate system; use the first The two-coordinate information is used to update the current environment map to obtain the target environment map.
本发明还提供一种机器人，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述程序时实现如上述任一种所述环境地图优化方法。The present invention also provides a robot, including a memory, a processor, and a computer program stored on the memory and operable on the processor. When the processor executes the program, the environment map optimization method described in any of the above is implemented. .
本发明还提供一种非暂态计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现如上述任一种所述环境地图优化方法。The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the environment map optimization method described in any one of the above-mentioned methods is realized.
本发明还提供一种计算机程序产品，包括计算机程序，所述计算机程序被处理器执行时实现如上述任一种所述环境地图优化方法。The present invention also provides a computer program product, including a computer program, when the computer program is executed by a processor, the environment map optimization method described in any one of the above methods is implemented.
本发明提供的环境地图优化方法、装置、机器人及可读存储介质，通过在初始化阶段，获取当前环境地图及待识别物体对应的第一直线信息；在下一时间步，根据所述第一直线信息，确定所述待识别物体对应的地标点在机体坐标系下的第一坐标信息，所述机体坐标系与机器人对应；利用所述第一坐标信息，对所述机器人的当前位姿进行优化，得到优化位姿，并基于所述优化位姿，确定所述地标点对应的第一实际观测值在世界坐标系下的第二坐标信息；利用所述第二坐标信息，对所述当前环境地图进行更新，得到目标环境地图。该方法用以解决现有技术中机器人构建的目标环境地图不够准确，影响了该目标环境地图的质量的缺陷，实现对待识别物体对应的第一直线信息进行相应处理，得到较为准确的该第一直线信息对应地标点所对应的第二坐标信息，并基于该第二坐标信息，优化当前环境地图，可得到较为准确的目标环境地图，从而提高了该目标环境地图的质量。The environment map optimization method, device, robot, and readable storage medium provided by the present invention obtain the current environment map and the first straight line information corresponding to the object to be identified in the initialization stage; at the next time step, according to the first straight line information Line information, determine the first coordinate information of the landmark point corresponding to the object to be identified in the body coordinate system, and the body coordinate system corresponds to the robot; use the first coordinate information to determine the current pose of the robot Optimizing, obtaining the optimized pose, and based on the optimized pose, determining the second coordinate information of the first actual observation value corresponding to the landmark point in the world coordinate system; using the second coordinate information, the current The environment map is updated to obtain the target environment map. This method is used to solve the defect that the target environment map constructed by the robot is not accurate enough in the prior art, which affects the quality of the target environment map, and realizes corresponding processing of the first straight line information corresponding to the object to be recognized, and obtains a more accurate first line information. The line information corresponds to the second coordinate information corresponding to the landmark point, and based on the second coordinate information, the current environment map is optimized to obtain a more accurate target environment map, thereby improving the quality of the target environment map.
附图说明Description of drawings
为了更清楚地说明本发明或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍，显而易见地，下面描述中的附图是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to more clearly illustrate the present invention or the technical solutions in the prior art, the accompanying drawings that need to be used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings in the following description are the present invention. For some embodiments of the invention, those skilled in the art can also obtain other drawings based on these drawings without creative effort.
图1是本发明提供的环境地图优化方法的流程示意图；Fig. 1 is a schematic flow chart of an environment map optimization method provided by the present invention;
图2是本发明提供的环境地图优化装置的结构示意图；Fig. 2 is a schematic structural diagram of an environment map optimization device provided by the present invention;
图3是本发明提供的机器人的结构示意图。Fig. 3 is a schematic structural diagram of the robot provided by the present invention.
具体实施方式Detailed ways
为使本发明的目的、技术方案和优点更加清楚，下面将结合本发明中的附图，对本发明中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. Obviously, the described embodiments are part of the embodiments of the present invention , but not all examples. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.
需要说明的是，本发明实施例涉及的机器人指的是在计算机编程下能够自动进行一系列复杂动作的机器，可在各种复杂的环境代替人类工作。It should be noted that the robot involved in the embodiments of the present invention refers to a machine that can automatically perform a series of complex actions under computer programming, and can replace human work in various complex environments.
可选的，机器人上可设有数据采集装置，该数据采集装置能够扫描并采集预设距离范围内待识别物体对应的参数数据。Optionally, a data acquisition device may be provided on the robot, and the data acquisition device can scan and collect parameter data corresponding to objects to be identified within a preset distance range.
其中，预设距离范围指的是以数据采集装置为圆心，以可探测距离为半径构成的距离范围，可选的，该预设距离范围可以是该数据采集装置出厂前设置的，也可以是用户自定义的，此处不作具体限定；Among them, the preset distance range refers to the distance range formed with the data acquisition device as the center and the detectable distance as the radius. Optionally, the preset distance range can be set before the data acquisition device leaves the factory, or it can be User-defined, not specifically limited here;
待识别物体指的是待识别直线物体，具有直线在仿射变换下能够保持直线不变形，其中，在仿射变换下能够保持直线不变形指的是将一个平面的点映射到另一个平面内的二维投影，仿射变换保持了二维图形的“平直性”，即原来是直线的地方还是直线；The object to be recognized refers to the straight line object to be recognized, which has a straight line that can keep the straight line without deformation under the affine transformation. Among them, the ability to keep the straight line without deformation under the affine transformation refers to mapping points on one plane to another plane The two-dimensional projection of , the affine transformation maintains the "straightness" of the two-dimensional graphics, that is, the place where the original line is a straight line is still a straight line;
可选的，该待识别物体可以包括但不限于：在狭长通道下的墙体、室内物体中的床体及其它直线物体等。Optionally, the object to be identified may include but not limited to: a wall under a long and narrow passage, a bed in an indoor object, and other linear objects.
可选的，数据采集装置可以包括但不限于：距离传感器及深度视觉(Red GreenBlue-Depth，RGB-D)摄像头等。Optionally, the data acquisition device may include but not limited to: a distance sensor and a depth vision (Red Green Blue-Depth, RGB-D) camera, and the like.
其中，距离传感器可用于直接获取待识别物体与数据采集装置之间的距离值，可选的，该距离传感器可以包括但不限于：光学距离传感器、红外距离传感器及超声波距离传感器等；Wherein, the distance sensor can be used to directly obtain the distance value between the object to be identified and the data acquisition device. Optionally, the distance sensor can include but not limited to: optical distance sensor, infrared distance sensor and ultrasonic distance sensor, etc.;
RGB-D摄像头可用于采集待识别物体对应的图像，并从图像中确定该待识别物体对应的参数数据。The RGB-D camera can be used to collect the image corresponding to the object to be identified, and determine the parameter data corresponding to the object to be identified from the image.
可选的，参数数据可以包括但不限于以下至少一项：机器人对应机体坐标系下待识别物体的坐标信息、该待识别物体与数据采集装置之间的距离值，以及该待识别物体相较于该数据采集装置的角度值等。Optionally, the parameter data may include but not limited to at least one of the following: the coordinate information of the object to be identified in the body coordinate system corresponding to the robot, the distance value between the object to be identified and the data acquisition device, and the comparison between the object to be identified The angle value of the data acquisition device, etc.
其中，机体坐标系也可称为传感器坐标系，指的是固定在机器人上的遵循右手法则的三维正交直角坐标系，其中，该机体坐标系的原点O可位于机器人的质心，该机体坐标系的OX轴位于机器人所在环境对应参考平面内平行于机身轴线并指向该机器人的前方，OY轴垂直于该参考平面并指向该机器人的右方，OZ轴在该参考平面内垂直于XOY平面，指向该机器人的下方；Among them, the body coordinate system can also be called the sensor coordinate system, which refers to a three-dimensional orthogonal rectangular coordinate system fixed on the robot and follows the right-hand rule. The origin O of the body coordinate system can be located at the center of mass of the robot, and the body coordinate system The OX axis of the system is located in the reference plane corresponding to the environment where the robot is located, parallel to the axis of the fuselage and pointing to the front of the robot, the OY axis is perpendicular to the reference plane and points to the right of the robot, and the OZ axis is perpendicular to the XOY plane in the reference plane , pointing down the robot;
坐标信息指的是待识别物体在机体坐标系中，在OX轴上的坐标位置X、在OY轴上的坐标位置Y及在OZ轴上的坐标位置Z；The coordinate information refers to the coordinate position X on the OX axis, the coordinate position Y on the OY axis and the coordinate position Z on the OZ axis of the object to be identified in the body coordinate system;
所在环境指的是机器人的运动环境，可以包括但不限于：室内、停车场及操场等。The environment refers to the movement environment of the robot, which may include but not limited to: indoors, parking lots, playgrounds, etc.
需要说明的是，本发明实施例涉及的执行主体可以是环境地图优化装置，也可以是机器人，下面以机器人为例对本发明实施例进行进一步地说明。It should be noted that the execution subject involved in the embodiment of the present invention may be an environment map optimization device or a robot, and the embodiment of the present invention will be further described below taking a robot as an example.
如图1所示，是本发明提供的环境地图优化方法的流程示意图，可以包括：As shown in Figure 1, it is a schematic flow chart of the environment map optimization method provided by the present invention, which may include:
101、在初始化阶段，获取当前环境地图及待识别物体对应的第一直线信息。101. In the initialization phase, acquire the current environment map and the first straight line information corresponding to the object to be identified.
其中，第一直线信息指的是待识别物体对应的直线数据，该第一直线信息的数量为至少一个，该第一直线信息可用l1、l2、…、ln来表示，n≥1，例如：床体右侧面任意两个点所构成的直线数据该床体对应的第一直线信息。Wherein, the first straight line information refers to the straight line data corresponding to the object to be identified, the number of the first straight line information is at least one, and the first straight line information can be represented by l1 , l2 , ..., ln , n≥1, for example: the straight line data formed by any two points on the right side of the bed, and the first straight line information corresponding to the bed.
机器人在初始化阶段，可以在当前时刻(也可称为：当前时间步)下对所在环境进行广视角扫描，得到扫描结果，该扫描结果中可以包括该所在环境中存在的物体(例如：床体、足球等)；然后，该机器人基于该扫描结果，对该机器人进行初始化，得到当前环境地图M，该当前环境地图M能够大范围地覆盖该所在环境，但是该当前环境地图M是不够准确的；然后，该机器人在该扫描结果中确定该所在环境存在待识别物体的情况下，可以利用直线在仿射变换下保持直线不变形，对该待识别物体进行拟合，得到第一直线信息，该第一直线信息用于该机器人后续对该当前环境地图M进行更新，以得到较为准确的目标环境地图。In the initialization stage, the robot can scan the environment at a wide angle at the current moment (also called: current time step) to obtain the scanning result, which can include objects in the environment (for example: bed body , football, etc.); then, based on the scanning result, the robot initializes the robot to obtain the current environment map M, which can cover the environment in a large area, but the current environment map M is not accurate enough ; Then, when the robot determines that there is an object to be recognized in the environment in the scanning result, it can use the straight line to keep the straight line unchanged under the affine transformation, and fit the object to be recognized to obtain the first straight line information , the first straight line information is used by the robot to subsequently update the current environment map M to obtain a more accurate target environment map.
在一些实施例中，机器人获取当前环境地图及待识别物体对应的第一直线信息，可以包括：机器人确定待识别物体与机器人之间的当前距离值；该机器人在当前距离值位于预设距离范围内的情况下，获取待识别物体对应的第一直线信息，并获取机器人所在环境的当前环境地图。In some embodiments, the robot obtains the current environment map and the first straight line information corresponding to the object to be identified, which may include: the robot determines the current distance value between the object to be identified and the robot; the robot is located at a preset distance at the current distance value In the case of within the range, obtain the first straight line information corresponding to the object to be recognized, and obtain the current environment map of the environment where the robot is located.
机器人在确定待识别物体之后，可以获取该待识别物体与该机器人之间的当前距离值，并判断该当前距离值与预设距离范围的关系。如果该当前距离值位于该预设距离范围内，那么，该机器人可以直接对该待识别物体进行拟合，得到第一直线信息；如果该当前距离值未位于该预设距离范围内，那么，该机器人可以进行运动并实时采集当前距离值，直达采集到的当前距离值能够位于该预设距离范围内，此时，该机器人可以确定该待识别物体对应的第一直线信息。After the robot determines the object to be recognized, it can obtain the current distance value between the object to be recognized and the robot, and judge the relationship between the current distance value and the preset distance range. If the current distance value is within the preset distance range, then the robot can directly fit the object to be identified to obtain the first straight line information; if the current distance value is not within the preset distance range, then , the robot can move and collect the current distance value in real time until the collected current distance value can be within the preset distance range, at this time, the robot can determine the first straight line information corresponding to the object to be recognized.
示例性的，假设预设距离范围为(1米，3米)。如果机器人采集待识别物体与该机器人之间的当前距离值为2.5米，该当前距离值2.5米位于预设距离范围(1米，3米)内，那么，该机器人可以确定该待识别物体对应的第一直线信息；如果机器人采集待识别物体与该机器人之间的当前距离值为4米，该当前距离值4米未位于预设距离范围(1米，3米)内，那么，该机器人可以朝向该待识别物体进行移动，直到该待识别物体与该机器人之间的当前距离值能够位于预设距离范围(1米，3米)内，此时，该机器人可以确定该待识别物体对应的第一直线信息。Exemplarily, it is assumed that the preset distance range is (1 meter, 3 meters). If the robot collects a current distance value of 2.5 meters between the object to be recognized and the robot, and the current distance value of 2.5 meters is within the preset distance range (1 meter, 3 meters), then the robot can determine that the object to be recognized corresponds to If the robot collects the current distance value of 4 meters between the object to be identified and the robot, and the current distance value of 4 meters is not within the preset distance range (1 meter, 3 meters), then the The robot can move towards the object to be identified until the current distance value between the object to be identified and the robot can be within the preset distance range (1 meter, 3 meters), at this time, the robot can determine the object to be identified The corresponding first straight line information.
可选的，机器人在初始化阶段之前，可以响应用户的输入操作，获取待识别物体。Optionally, before the initialization stage, the robot may respond to user input operations to acquire objects to be recognized.
也就是说，用户可以向机器人输入操作，该输入操作包括待识别物体对应的相关信息；然后，该机器人响应输入操作，并基于该相关信息，获取待识别物体。That is to say, the user can input an operation to the robot, and the input operation includes relevant information corresponding to the object to be recognized; then, the robot responds to the input operation and obtains the object to be recognized based on the relevant information.
可选的，机器人存储有直线物体对应的至少一种特征，该直线物体的数量为至少一个。机器人在检测到预设距离范围内存在物体时，可以采集该物体对应的当前特征；然后，该机器人将该当前特征与存储的特征进行匹配，在匹配成功的情况下，将该物体确定为待识别物体。Optionally, the robot stores at least one feature corresponding to the straight-line object, and the number of the straight-line object is at least one. When the robot detects that there is an object within the preset distance range, it can collect the current feature corresponding to the object; then, the robot matches the current feature with the stored feature, and if the matching is successful, the object is determined to be Identify objects.
机器人可以基于先验知识，可以准确地识别出周围的物体是否为待识别直线物体。Based on prior knowledge, the robot can accurately identify whether the surrounding objects are linear objects to be identified.
机器人将当前特征与存储的特征进行匹配，在匹配失败的情况下，控制该机器人处于待机/关机状态，以节省该机器人的使用功耗。The robot matches the current feature with the stored feature, and if the matching fails, the robot is controlled to be in a standby/off state to save the power consumption of the robot.
102、在下一时间步，根据第一直线信息，确定待识别物体对应的地标点在机体坐标系下的第一坐标信息。102. In the next time step, according to the first straight line information, determine the first coordinate information of the landmark point corresponding to the object to be recognized in the body coordinate system.
其中，下一时间步与上述当前时间步是相邻的；Wherein, the next time step is adjacent to the above current time step;
机体坐标系与机器人对应；The body coordinate system corresponds to the robot;
地标点指的是待识别物体在第一直线信息上的至少两个关键点，该地标点可用P1、P2、…、Pm来表示，m＞1；Landmark points refer to at least two key points of the object to be recognized on the first straight line information, the landmark points can be represented by P1 , P2 , ..., Pm , m>1;
第一坐标信息指的是待识别物体在机体坐标系中，在OX轴上的坐标位置X1、在OY轴上的坐标位置Y1及在OZ轴上的坐标位置Z1，该第一坐标信息可用
在一些实施例中，机器人根据第一直线信息，确定待识别物体对应的地标点在机体坐标系下的第一坐标信息，可以包括：机器人根据第一直线信息，确定待识别物体对应的地标点及地标点对应的第一实际观测值；该机器人根据第一实际观测值，确定地标点在机体坐标系下的第一坐标信息。In some embodiments, the robot determines the first coordinate information of the landmark point corresponding to the object to be recognized in the body coordinate system according to the first straight line information, which may include: the robot determines the first coordinate information of the landmark point corresponding to the object to be recognized according to the first straight line information The landmark point and the first actual observation value corresponding to the landmark point; the robot determines the first coordinate information of the landmark point in the body coordinate system according to the first actual observation value.
其中，第一实际观测值可以包括地标点与机器人之间的第一距离值和第一角度值，该第一实际观测值可用z1、z2、…、zm来表示。Wherein, the first actual observation value may include a first distance value and a first angle value between the landmark point and the robot, and the first actual observation value may be represented by z1 , z2 , . . . , zm .
机器人在获取第一直线信息之后，在下一时间步，可以从该第一直线信息中确定待识别物体对应的地标点，进而确定该地标点与该机器人之间的第一距离值和第一角度值，即确定第一实际观测值；然后，该机器人可以对该第一距离值及该第一角度值进行计算，准确地得到该地标点在机体坐标系下的第一坐标信息。After the robot acquires the first straight line information, in the next time step, it can determine the landmark point corresponding to the object to be recognized from the first straight line information, and then determine the first distance value and the second distance value between the landmark point and the robot. An angle value is to determine the first actual observation value; then, the robot can calculate the first distance value and the first angle value to accurately obtain the first coordinate information of the landmark point in the body coordinate system.
103、利用第一坐标信息，对机器人的当前位姿进行优化，得到优化位姿，并基于优化位姿，确定地标点对应的第一实际观测值在世界坐标系下的第二坐标信息。103. Using the first coordinate information, optimize the current pose of the robot to obtain the optimized pose, and based on the optimized pose, determine the second coordinate information of the first actual observation value corresponding to the landmark point in the world coordinate system.
其中，世界坐标系指的是在机器人所在环境中用来描述该机器人与待识别物体的位置的参考坐标系；Among them, the world coordinate system refers to the reference coordinate system used to describe the position of the robot and the object to be identified in the environment where the robot is located;
第二坐标信息指的是第一实际观测值在世界坐标系中，在OX轴上的坐标位置X2、在OY轴上的坐标位置Y2及在OZ轴上的坐标位置Z2，地标点Pm对应的第一实际观测值zm在世界坐标系下的第二坐标信息可用(X2m，Y2m，Z2m)表示。The second coordinate information refers to the first actual observed value in the world coordinate system, the coordinate position X2 on the OX axis, the coordinate position Y2 on the OY axis, and the coordinate position Z2 on the OZ axis, landmark points The second coordinate information of the first actual observed value zm corresponding to Pm in the world coordinate system can be represented by (X2m , Y2m , Z2m ).
机器人可以先获取该机器人的当前位姿X，由于该当前位姿X不够准确，所以，该机器人在获取地标点对应的第一坐标信息之后，可以利用该第一坐标信息，对该当前位姿X进行优化，得到较为准确的优化位姿X′；然后，该机器人再基于该优化位姿X′，准确确定该地标点的第一实际观测值在世界坐标系下的第二坐标信息。The robot can first obtain the current pose X of the robot. Since the current pose X is not accurate enough, after the robot obtains the first coordinate information corresponding to the landmark point, it can use the first coordinate information to determine the current pose X. X is optimized to obtain a more accurate optimized pose X′; then, based on the optimized pose X′, the robot accurately determines the second coordinate information of the first actual observation value of the landmark point in the world coordinate system.
在一些实施例中，机器人利用第一坐标信息，对机器人的当前位姿进行优化，得到优化位姿，可以包括：机器人在机体坐标系下，对第一坐标信息进行拟合，得到第二直线信息；该机器人将第一坐标信息在第二直线信息上进行投影，得到第一投影值；该机器人利用第一投影值，对机器人的当前位姿进行优化，得到优化位姿。In some embodiments, the robot uses the first coordinate information to optimize the current pose of the robot to obtain the optimized pose, which may include: the robot fits the first coordinate information in the body coordinate system to obtain the second straight line information; the robot projects the first coordinate information on the second line information to obtain a first projection value; the robot uses the first projection value to optimize the current pose of the robot to obtain an optimized pose.
其中，第二直线信息指的是对获取的第一坐标信息进行重新拟合后得到的直线数据，该第二直线信息可用
第一投影值可用
机器人在获取该机器人的优化位姿的过程中，可以在获取第一坐标信息之后，先在机体坐标系下，将这些第一坐标信息进行拟合，得到第二直线信息；然后，该机器人再将该第一坐标信息在该第二直线信息上进行投影，得到第一投影值，由于这些第一投影值较为准确，所以，该机器人可以直接将这些第一投影值作为相应地标点对应的第三实际观测值，并基于该第三实际观测值，对该机器人的当前位姿进行优化，得到较为准确的优化位姿。In the process of obtaining the optimal pose of the robot, the robot can firstly fit the first coordinate information in the body coordinate system after obtaining the first coordinate information to obtain the second straight line information; then, the robot can The first coordinate information is projected on the second straight line information to obtain first projection values. Since these first projection values are relatively accurate, the robot can directly use these first projection values as the corresponding punctuation points. Three actual observation values, and based on the third actual observation value, optimize the current pose of the robot to obtain a more accurate optimized pose.
其中，第三实际观测值可以包括地标点与机器人之间的第三距离值和第三角度值。Wherein, the third actual observed value may include a third distance value and a third angle value between the landmark point and the robot.
在一些实施例中，机器人利用第一投影值，对机器人的当前位姿进行优化，得到优化位姿，可以包括：机器人根据第一投影值，使用扩展卡尔曼滤波器对机器人的当前位姿进行优化，得到优化位姿。In some embodiments, the robot uses the first projection value to optimize the current pose of the robot to obtain the optimized pose. Optimize to get the optimized pose.
其中，扩展卡尔曼滤波器指的是是标准卡尔曼滤波在非线性情形下的一种扩展形式，该扩展卡尔曼滤波器是一种高效率的递归滤波器，也可称为自回归滤波器，该扩展卡尔曼滤波可以基于观测值，利用泰勒级数展开将非线性系统线性化，然后，采用卡尔曼滤波框架对当前位姿进行滤波和优化。Among them, the extended Kalman filter refers to an extended form of the standard Kalman filter in nonlinear situations. The extended Kalman filter is a high-efficiency recursive filter, which can also be called an autoregressive filter. , the extended Kalman filter can be based on observations, using Taylor series expansion to linearize the nonlinear system, and then using the Kalman filter framework to filter and optimize the current pose.
由于第一投影值较为准确，所以，机器人在将该第一投影值作为相应地标点对应的第三实际观测值之后，可以将该第三实际观测值作为该机器人最终优化位姿时所需要用到的观测值，然后；该机器人再基于该观测值，使用扩展卡尔曼滤波器对该机器人的当前位姿进行优化，就可以得到较为准确的优化位姿。Since the first projection value is relatively accurate, after the robot uses the first projection value as the third actual observation value corresponding to the corresponding punctuation point, it can use the third actual observation value as the final optimization pose of the robot. Then, based on the observed value, the robot uses the extended Kalman filter to optimize the current pose of the robot, and a more accurate optimized pose can be obtained.
在一些实施例中，机器人基于优化位姿，确定地标点对应的第一实际观测值在世界坐标系下的第二坐标信息，可以包括：机器人基于优化位姿，将第二直线信息在世界坐标系下进行转换，得到第三直线信息，并将地标点对应的第一实际观测值在第三直线信息上进行投影，得到第一子坐标信息；该机器人基于优化位姿，将第一实际观测值在世界坐标系下进行转换，得到第二子坐标信息。In some embodiments, the robot determines the second coordinate information of the first actual observation value corresponding to the landmark point in the world coordinate system based on the optimized pose, which may include: the robot bases the optimized pose on the second line information in the world coordinate system to obtain the third line information, and project the first actual observation value corresponding to the landmark point on the third line information to obtain the first sub-coordinate information; based on the optimized pose, the robot converts the first actual observation value The value is transformed in the world coordinate system to obtain the second sub-coordinate information.
其中，第三直线信息可用l′1、l′2、…、l′n来表示；Wherein, the third line information can be represented by l′1 , l′2 , ..., l′n ;
第一子坐标信息可用
第二子坐标信息可用z′1、z′2、…、z′n来表示。The second sub-coordinate information can be represented by z′1 , z′2 , . . . , z′n .
机器人在获取地标点对应的第一实际观测值在世界坐标系下的第二坐标信息的过程中，可以基于得到的优化位姿，确定第二直线信息在世界坐标系下对应的第三直线信息，并将该第一实际观测值在该第三直线坐标系下进行投影，得到第一子坐标信息；该机器人还可以基于该优化位姿，确定该第一实际观测值在该世界坐标系下的第二子坐标信息。In the process of obtaining the second coordinate information of the first actual observation value corresponding to the landmark point in the world coordinate system, the robot can determine the third line information corresponding to the second line information in the world coordinate system based on the obtained optimized pose , and project the first actual observation value in the third linear coordinate system to obtain the first sub-coordinate information; the robot can also determine that the first actual observation value is in the world coordinate system based on the optimized pose The second sub-coordinate information of .
也就是说，该第二坐标信息可以包括第一子坐标信息及第二子坐标信息，由于优化位姿是较为准确的，所以，该第一子坐标信息及该第二子坐标信息也都是较为准确的。That is to say, the second coordinate information may include the first sub-coordinate information and the second sub-coordinate information. Since the optimized pose is relatively accurate, the first sub-coordinate information and the second sub-coordinate information are both more accurate.
需要说明的是，机器人获取第一子坐标信息与获取第二子坐标信息的时序不限。It should be noted that there is no limit to the time sequence in which the robot acquires the first sub-coordinate information and the second sub-coordinate information.
104、利用第二坐标信息，对当前环境地图进行更新，得到目标环境地图。104. Utilize the second coordinate information to update the current environment map to obtain the target environment map.
机器人在将第一实际观测值进行处理之后，得到较为准确的第二坐标信息；然后，该机器人再利用第二坐标信息，对当前环境地图进行优化和更新，能够得到准确性较高的目标环境地图，该目标环境地图的质量较佳。After the robot processes the first actual observation value, it obtains more accurate second coordinate information; then, the robot uses the second coordinate information to optimize and update the current environment map, and can obtain a target environment with higher accuracy map, the quality of the target environment map is better.
在一些实施例中，机器人利用第二坐标信息，对当前环境地图进行更新，得到目标环境地图，可以包括：机器人基于第一子坐标信息及第二子坐标信息，利用扩展卡尔曼滤波器，估计得到地标点对应的目标坐标点；该机器人利用目标坐标点，对当前环境地图进行更新，得到目标环境地图。In some embodiments, the robot uses the second coordinate information to update the current environment map to obtain the target environment map, which may include: based on the first sub-coordinate information and the second sub-coordinate information, the robot estimates Obtain the target coordinate point corresponding to the landmark point; the robot uses the target coordinate point to update the current environment map to obtain the target environment map.
机器人在获取第一子坐标信息之后，可以将该第一子坐标信息作为地标点分别对应的目标预测值；该机器人在获取第二子坐标信息之后，可以将该第二子坐标信息作为该地标点分别对应的目标观测值；然后，该机器人基于该目标预测值及该目标观测值，利用扩展卡尔曼滤波器对该地标点的坐标位置进行估计，得到该地标点对应的目标坐标点，该目标坐标点较为准确，此时，该机器人再基于该准确的目标坐标点，对当前环境地图进行更新，得到准确性较高的目标环境地图。After the robot obtains the first sub-coordinate information, it can use the first sub-coordinate information as the target prediction value corresponding to the landmark points respectively; after the robot obtains the second sub-coordinate information, it can use the second sub-coordinate information as the landmark The target observation values corresponding to the punctuation points; then, based on the target prediction value and the target observation value, the robot uses the extended Kalman filter to estimate the coordinate position of the landmark point to obtain the target coordinate point corresponding to the landmark point. The target coordinate point is relatively accurate. At this time, the robot updates the current environment map based on the accurate target coordinate point to obtain a target environment map with high accuracy.
在本发明实施例中，在初始化阶段，获取当前环境地图及待识别物体对应的第一直线信息；在下一时间步，根据第一直线信息，确定待识别物体对应的地标点在机体坐标系下的第一坐标信息，机体坐标系与机器人对应；利用第一坐标信息，对机器人的当前位姿进行优化，得到优化位姿，并基于优化位姿，确定地标点对应的第一实际观测值在世界坐标系下的第二坐标信息；利用第二坐标信息，对当前环境地图进行更新，得到目标环境地图。该方法用以解决现有技术中机器人构建的目标环境地图不够准确，影响了该目标环境地图的质量的缺陷，实现对待识别物体对应的第一直线信息进行相应处理，得到较为准确的该第一直线信息对应地标点所对应的第二坐标信息，并基于该第二坐标信息，优化当前环境地图，可得到较为准确的目标环境地图，从而提高了该目标环境地图的质量。In the embodiment of the present invention, in the initialization stage, the current environment map and the first straight line information corresponding to the object to be recognized are obtained; at the next time step, according to the first straight line information, the landmark point corresponding to the object to be recognized is determined in the body coordinates The first coordinate information under the system, the body coordinate system corresponds to the robot; use the first coordinate information to optimize the current pose of the robot, obtain the optimized pose, and determine the first actual observation corresponding to the landmark point based on the optimized pose The value is the second coordinate information in the world coordinate system; the current environment map is updated by using the second coordinate information to obtain the target environment map. This method is used to solve the defect that the target environment map constructed by the robot is not accurate enough in the prior art, which affects the quality of the target environment map, and realizes corresponding processing of the first straight line information corresponding to the object to be recognized, and obtains a more accurate first line information. The line information corresponds to the second coordinate information corresponding to the landmark point, and based on the second coordinate information, the current environment map is optimized to obtain a more accurate target environment map, thereby improving the quality of the target environment map.
下面对本发明提供的环境地图优化装置进行描述，下文描述的环境地图优化装置与上文描述的环境地图优化方法可相互对应参照。The environment map optimization device provided by the present invention is described below, and the environment map optimization device described below and the environment map optimization method described above can be referred to in correspondence.
如图2所示，是本发明提供的环境地图优化装置的结构示意图，可以包括：As shown in Figure 2, it is a schematic structural diagram of the environment map optimization device provided by the present invention, which may include:
获取模块201，用于在初始化阶段，获取当前环境地图及待识别物体对应的第一直线信息；An acquisition module 201, configured to acquire the current environment map and the first straight line information corresponding to the object to be identified during the initialization phase;
处理模块202，用于在下一时间步，根据该第一直线信息，确定该待识别物体对应的地标点在机体坐标系下的第一坐标信息，该机体坐标系与机器人对应；利用该第一坐标信息，对该机器人的当前位姿进行优化，得到优化位姿，并基于该优化位姿，确定该地标点对应的第一实际观测值在世界坐标系下的第二坐标信息；利用该第二坐标信息，对该当前环境地图进行更新，得到目标环境地图。The processing module 202 is used to determine the first coordinate information of the landmark point corresponding to the object to be recognized in the body coordinate system in the next time step according to the first straight line information, and the body coordinate system corresponds to the robot; One coordinate information, optimize the current pose of the robot to obtain the optimized pose, and based on the optimized pose, determine the second coordinate information of the first actual observation value corresponding to the landmark point in the world coordinate system; use the The second coordinate information is to update the current environment map to obtain the target environment map.
可选的，处理模块202，具体用于根据该第一直线信息，确定该待识别物体对应的地标点及该地标点对应的第一实际观测值，该第一实际观测值包括该地标点与该机器人之间的第一距离值和第一角度值；根据该第一实际观测值，确定该地标点在机体坐标系下的第一坐标信息。Optionally, the processing module 202 is specifically configured to determine the landmark point corresponding to the object to be recognized and the first actual observation value corresponding to the landmark point according to the first straight line information, the first actual observation value includes the landmark point A first distance value and a first angle value from the robot; according to the first actual observation value, the first coordinate information of the landmark point in the body coordinate system is determined.
可选的，处理模块202，具体用于在该机体坐标系下，对该第一坐标信息进行拟合，得到第二直线信息；将该第一坐标信息在该第二直线信息上进行投影，得到第一投影值；利用该第一投影值，对该机器人的当前位姿进行优化，得到优化位姿。Optionally, the processing module 202 is specifically configured to fit the first coordinate information in the body coordinate system to obtain second straight line information; project the first coordinate information on the second straight line information, A first projection value is obtained; using the first projection value, the current pose of the robot is optimized to obtain an optimized pose.
可选的，处理模块202，具体用于基于该优化位姿，将该第二直线信息在世界坐标系下进行转换，得到第三直线信息，并将该地标点对应的第一实际观测值在该第三直线信息上进行投影，得到第一子坐标信息；基于该优化位姿，将该第一实际观测值在该世界坐标系下进行转换，得到第二子坐标信息。Optionally, the processing module 202 is specifically configured to convert the second line information in the world coordinate system based on the optimized pose to obtain the third line information, and convert the first actual observation value corresponding to the landmark point in Projecting on the third line information to obtain first sub-coordinate information; based on the optimized pose, transforming the first actual observation value in the world coordinate system to obtain second sub-coordinate information.
可选的，处理模块202，具体用于基于该第一子坐标信息及该第二子坐标信息，利用扩展卡尔曼滤波器，估计得到该地标点对应的目标坐标点；利用该目标坐标点，对该当前环境地图进行更新，得到目标环境地图。Optionally, the processing module 202 is specifically configured to use the extended Kalman filter to estimate and obtain the target coordinate point corresponding to the landmark point based on the first sub-coordinate information and the second sub-coordinate information; using the target coordinate point, The current environment map is updated to obtain the target environment map.
可选的，处理模块202，具体用于根据该第一投影值，使用扩展卡尔曼滤波器对该机器人的当前位姿进行优化，得到优化位姿。Optionally, the processing module 202 is specifically configured to use an extended Kalman filter to optimize the current pose of the robot according to the first projection value, to obtain an optimized pose.
可选的，处理模块202，具体用于确定待识别物体与机器人之间的当前距离值；Optionally, the processing module 202 is specifically configured to determine the current distance value between the object to be identified and the robot;
获取模块201，具体用于在该当前距离值位于预设距离范围内的情况下，获取该待识别物体对应的第一直线信息，并获取该机器人所在环境的当前环境地图。The obtaining module 201 is specifically configured to obtain the first straight line information corresponding to the object to be recognized and obtain the current environment map of the environment where the robot is located when the current distance value is within a preset distance range.
如图3所示，是本发明提供的机器人的结构示意图，该机器人可以包括：处理器(processor)310、通信接口(Communications Interface)320、存储器(memory)330和通信总线340，其中，处理器310，通信接口320，存储器330通过通信总线340完成相互间的通信。处理器310可以调用存储器330中的逻辑指令，以执行环境地图优化方法，该方法包括：在初始化阶段，获取当前环境地图及待识别物体对应的第一直线信息；在下一时间步，根据该第一直线信息，确定该待识别物体对应的地标点在机体坐标系下的第一坐标信息，该机体坐标系与机器人对应；利用该第一坐标信息，对该机器人的当前位姿进行优化，得到优化位姿，并基于该优化位姿，确定该地标点对应的第一实际观测值在世界坐标系下的第二坐标信息；利用该第二坐标信息，对该当前环境地图进行更新，得到目标环境地图。As shown in Fig. 3, it is the structural representation of the robot that the present invention provides, and this robot can comprise: processor (processor) 310, communication interface (Communications Interface) 320, memory (memory) 330 and
此外，上述的存储器330中的逻辑指令可以通过软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：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。In addition, the above-mentioned logic instructions in the
另一方面，本发明还提供一种计算机程序产品，所述计算机程序产品包括计算机程序，计算机程序可存储在非暂态计算机可读存储介质上，所述计算机程序被处理器执行时，计算机能够执行上述各方法所提供的环境地图优化方法，该方法包括：在初始化阶段，获取当前环境地图及待识别物体对应的第一直线信息；在下一时间步，根据该第一直线信息，确定该待识别物体对应的地标点在机体坐标系下的第一坐标信息，该机体坐标系与机器人对应；利用该第一坐标信息，对该机器人的当前位姿进行优化，得到优化位姿，并基于该优化位姿，确定该地标点对应的第一实际观测值在世界坐标系下的第二坐标信息；利用该第二坐标信息，对该当前环境地图进行更新，得到目标环境地图。On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can Execute the environment map optimization method provided by the above methods, the method includes: in the initialization stage, obtain the current environment map and the first straight line information corresponding to the object to be identified; in the next time step, according to the first straight line information, determine The first coordinate information of the landmark point corresponding to the object to be identified is in the body coordinate system, and the body coordinate system corresponds to the robot; using the first coordinate information, the current pose of the robot is optimized to obtain the optimized pose, and Based on the optimized pose, determine the second coordinate information of the first actual observation value corresponding to the landmark point in the world coordinate system; use the second coordinate information to update the current environment map to obtain the target environment map.
又一方面，本发明还提供一种非暂态计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现以执行上述各方法提供的环境地图优化方法，该方法包括：在初始化阶段，获取当前环境地图及待识别物体对应的第一直线信息；在下一时间步，根据该第一直线信息，确定该待识别物体对应的地标点在机体坐标系下的第一坐标信息，该机体坐标系与机器人对应；利用该第一坐标信息，对该机器人的当前位姿进行优化，得到优化位姿，并基于该优化位姿，确定该地标点对应的第一实际观测值在世界坐标系下的第二坐标信息；利用该第二坐标信息，对该当前环境地图进行更新，得到目标环境地图。In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it is implemented to execute the environment map optimization method provided by the above methods, the method includes : In the initialization phase, obtain the current environment map and the first straight line information corresponding to the object to be recognized; in the next time step, according to the first straight line information, determine the first line of the landmark point corresponding to the object to be recognized in the body coordinate system Coordinate information, the body coordinate system corresponds to the robot; use the first coordinate information to optimize the current pose of the robot to obtain the optimized pose, and based on the optimized pose, determine the first actual position corresponding to the landmark point The second coordinate information of the observed value in the world coordinate system; using the second coordinate information, the current environment map is updated to obtain the target environment map.
以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性的劳动的情况下，即可以理解并实施。The device embodiments described above are only illustrative, and the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in One place, or it can be distributed to multiple network elements. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. It can be understood and implemented by those skilled in the art without any creative effort.
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到各实施方式可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件。基于这样的理解，上述技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品可以存储在计算机可读存储介质中，如ROM/RAM、磁碟、光盘等，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行各个实施例或者实施例的某些部分所述的方法。Through the above description of the implementations, those skilled in the art can clearly understand that each implementation can be implemented by means of software plus a necessary general hardware platform, and of course also by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the prior art can be embodied in the form of software products, and the computer software products can be stored in computer-readable storage media, such as ROM/RAM, magnetic discs, optical discs, etc., including several instructions to make a computer device (which may be a personal computer, server, or network device, etc.) execute the methods described in various embodiments or some parts of the embodiments.
最后应说明的是：以上实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的精神和范围。Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still be Modifications are made to the technical solutions described in the foregoing embodiments, or equivalent replacements are made to some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211275631.5ACN115661386A (en) | 2022-10-18 | 2022-10-18 | Environment map optimization method and device, robot and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211275631.5ACN115661386A (en) | 2022-10-18 | 2022-10-18 | Environment map optimization method and device, robot and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115661386Atrue CN115661386A (en) | 2023-01-31 |
Family
ID=84989499
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211275631.5APendingCN115661386A (en) | 2022-10-18 | 2022-10-18 | Environment map optimization method and device, robot and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115661386A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117173237A (en)* | 2023-09-07 | 2023-12-05 | 恒睿(重庆)人工智能技术研究院有限公司 | Positioning mark, identification method and system thereof, control device and storage medium |
- 2022
- 2022-10-18CNCN202211275631.5Apatent/CN115661386A/enactivePending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117173237A (en)* | 2023-09-07 | 2023-12-05 | 恒睿(重庆)人工智能技术研究院有限公司 | Positioning mark, identification method and system thereof, control device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111476841B (en) | A method and system for recognition and positioning based on point cloud and image | |
| JP4375320B2 (en) | Mobile robot | |
| JP7351892B2 (en) | Obstacle detection method, electronic equipment, roadside equipment, and cloud control platform | |
| CN112070770A (en) | A Synchronous Construction Method of High-precision 3D Map and 2D Grid Map | |
| CN110118556A (en) | A kind of robot localization method and device based on covariance mixing together SLAM | |
| KR102490521B1 (en) | Automatic calibration through vector matching of the LiDAR coordinate system and the camera coordinate system | |
| US20190221000A1 (en) | Depth camera 3d pose estimation using 3d cad models | |
| CN107358629A (en) | Figure and localization method are built in a kind of interior based on target identification | |
| WO2019136613A1 (en) | Indoor locating method and device for robot | |
| CN115639547A (en) | Multi-line laser radar and GNSS-INS combined calibration method, system and medium | |
| CN106323286B (en) | A kind of robot coordinate system and the transform method of three-dimensional measurement coordinate system | |
| JP2018173882A (en) | Information processing apparatus, method, and program | |
| CN113361365A (en) | Positioning method and device, equipment and storage medium | |
| CN116380039B (en) | Mobile robot navigation system based on solid-state laser radar and point cloud map | |
| WO2023273169A1 (en) | Vision and laser-fused 2.5d map construction method | |
| CN113091736A (en) | Robot positioning method, device, robot and storage medium | |
| KR20210116161A (en) | Heterogeneous sensors calibration method and apparatus using single checkerboard | |
| CN114926549A (en) | Three-dimensional point cloud processing method, device, equipment and storage medium | |
| CN118310531A (en) | Cross-scene positioning method and system for robot with coarse-to-fine point cloud registration | |
| CN116563491A (en) | A digital twin scene modeling and calibration method | |
| CN115661386A (en) | Environment map optimization method and device, robot and readable storage medium | |
| CN115773759A (en) | Indoor positioning method, device, equipment and storage medium for autonomous mobile robot | |
| KR101054520B1 (en) | How to recognize the location and direction of the indoor mobile robot | |
| CN115200601A (en) | Navigation method, device, wheeled robot and storage medium | |
| CN118482711A (en) | Method and system for improving richness of mapping |
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 |