技术领域Technical field
本发明涉及扫描仪自动测量技术领域，具体涉及一种基于扫描仪视觉引导的机器人路径规划系统和方法。The invention relates to the technical field of scanner automatic measurement, and in particular to a robot path planning system and method based on scanner visual guidance.
背景技术Background technique
三维扫描仪自动化测量是由多自由度机器人(一般是6自由度)携带激光三维扫描仪，沿着规划的路径移动，从多个视点对物体进行扫描测量，从而获得完整的三维数据。在测量过程中，视点直接决定了三维扫描仪的测量位置和姿态，测量得到的三维数据在很大程度上会受到视点的影响。同时，由于机器人带动扫描仪沿路径移动，测量路径也就决定了测量任务的可行性和测量效率。许多物体结构复杂，由于视觉遮挡，所需要的测量视点非常多，测量路径也非常复杂，这会增加测量时间。现阶段都是依靠有经验的人工，根据自己的经验对机器人进行示教，完成测量视点的路径规划。这一过程非常耗时，由于人工在规划过程中，缺乏示教的参考方法和依据，仅仅凭借经验示教过程无法准确地选择最合适的点位，很难获得最优的测量视点和路径。实际情况往往是，人工规划完成一次后，试运行会发现扫描效果不佳，需反复修改调试点位，这会增加不必要的视点数量和测量时间，无法发挥出自动化测量设备的最大效能。大批量、高速在线测量是未来的数字工厂检测的方向，流水生产线对每一件产品的调试、检测时间有严格的要求，仅仅凭借人工经验进行示教效率低下，难以满足工厂制造的要求。Three-dimensional scanner automated measurement is a multi-degree-of-freedom robot (usually 6 degrees of freedom) carrying a laser three-dimensional scanner, moving along a planned path, scanning and measuring objects from multiple viewpoints, thereby obtaining complete three-dimensional data. During the measurement process, the viewpoint directly determines the measurement position and attitude of the 3D scanner, and the measured 3D data will be affected by the viewpoint to a large extent. At the same time, since the robot drives the scanner to move along the path, the measurement path also determines the feasibility and measurement efficiency of the measurement task. Many objects have complex structures. Due to visual occlusion, many measurement viewpoints are required and the measurement paths are also very complex, which will increase the measurement time. At this stage, we rely on experienced humans to teach the robot based on their own experience and complete the path planning of the measurement viewpoint. This process is very time-consuming. Due to the lack of reference methods and basis for teaching during the manual planning process, it is impossible to accurately select the most appropriate point by relying solely on the experience teaching process, and it is difficult to obtain the optimal measurement viewpoint and path. The actual situation is often that after manual planning is completed once, the scanning effect will be found to be poor during the trial run, and the debugging points need to be modified repeatedly. This will increase the number of unnecessary viewpoints and measurement time, and will not be able to maximize the performance of the automated measurement equipment. Large-volume, high-speed online measurement is the future direction of digital factory inspection. The assembly line has strict requirements on the debugging and inspection time of each product. Teaching based on manual experience alone is inefficient and difficult to meet the requirements of factory manufacturing.
现有技术中通过研究自动测量视点与路径规划的方式以实现大批量自动化的目的，该类技术通过分析和量化工件参照模型、测量设备和测量任务需求三者间的相互关系制定约束条件，由约束条件自动筛选或创建出最优视点，并规划测量路径，期望通过完全自动的方式来实现路点规划。但是，目前这类方法大多停留于研究阶段，离实际应用尚有一定差距，同时自动规划技术需要考虑的因素和条件众多，研究难度大，其过程也离不开人工干预，对操作者的技能要求较高；且此类方法所生成的视点要求使用机械臂离线仿真软件配套完成，一套离线仿真软件成本十分高，从能效上来讲，此类方法并没有很好地适应当前三维测量行业实际情况。In the existing technology, automatic measurement viewpoints and path planning are studied to achieve the purpose of mass automation. This type of technology formulates constraints by analyzing and quantifying the interrelationships between the workpiece reference model, measurement equipment and measurement task requirements. Automatically filter or create optimal viewpoints based on constraints, and plan measurement paths. It is expected to realize route point planning in a completely automatic manner. However, most of these methods currently remain in the research stage, and there is still a certain gap between them and practical applications. At the same time, automatic planning technology needs to consider many factors and conditions, making research difficult. The process is also inseparable from manual intervention, which requires the skills of the operator. The requirements are high; and the viewpoints generated by this method require the use of offline simulation software for the robotic arm. The cost of a set of offline simulation software is very high. In terms of energy efficiency, this method is not well adapted to the current reality of the three-dimensional measurement industry. Condition.
发明内容Contents of the invention
本发明的目的在于克服上述技术不足，针对现有三维扫描仪自动化测量的路径规划技术中过于依赖专业人员示教经验这一问题，提出一种基于扫描仪视觉引导的机器人路径规划系统和方法，以解决人工经验所导致的扫描质量不一致和示教过程效率低问题，本方法相较尚处于研究阶段的全自动路径规划方法，更适合当前工业实际应用需要，具有更好的实用性。The purpose of the present invention is to overcome the above technical deficiencies, and to solve the problem that the existing path planning technology for automatic measurement of three-dimensional scanners relies too much on the teaching experience of professionals, and proposes a robot path planning system and method based on scanner visual guidance. In order to solve the problems of inconsistent scanning quality and low efficiency of the teaching process caused by manual experience, this method is more suitable for current industrial practical application needs and has better practicability than the fully automatic path planning method that is still in the research stage.
为达到上述技术目的，本发明采取了以下技术方案：In order to achieve the above technical objectives, the present invention adopts the following technical solutions:
第一方面，本发明提供了一种基于扫描仪视觉引导的机器人路径规划系统，In a first aspect, the present invention provides a robot path planning system based on scanner visual guidance,
包括：三维扫描仪、路径规划模块、视觉引导模块和机器人；Includes: 3D scanner, path planning module, visual guidance module and robot;
所述三维扫描仪固定连接于所述机器人的端部，用于创建待检测工件表面的三维数据；The three-dimensional scanner is fixedly connected to the end of the robot and is used to create three-dimensional data of the surface of the workpiece to be inspected;
所述路径规划模块分别与所述三维扫描仪通信连接，用于基于预设的扫描视点确定机器人的最优运动轨迹；The path planning module is communicatively connected to the three-dimensional scanner, and is used to determine the optimal motion trajectory of the robot based on a preset scanning viewpoint;
所述视觉引导模块，用于确定在所述最优运动轨迹中的目标扫描视点，实时可视化显示所述三维扫描仪的位姿与所述目标扫描视点之间的位姿偏差并引导所述三维扫描仪到达指定位置；The visual guidance module is used to determine the target scanning viewpoint in the optimal motion trajectory, visually display the posture deviation between the three-dimensional scanner's posture and the target scanning viewpoint in real time, and guide the three-dimensional The scanner reaches the designated location;
所述机器人具有多自由度，用于根据所述位姿偏差调整所述三维扫描仪的位姿直至与所述目标视点重合。The robot has multiple degrees of freedom and is used to adjust the posture of the three-dimensional scanner according to the posture deviation until it coincides with the target viewpoint.
在一些实施例中，所述路径规划模块包括坐标系转换单元、扫描视点确定单元和最优路径规划单元；In some embodiments, the path planning module includes a coordinate system conversion unit, a scanning viewpoint determination unit and an optimal path planning unit;
所述坐标系转换单元用于以待检测工件为参考对象定义基准坐标系，将所述三维扫描仪的位姿转换至所述基准坐标系下，确定坐标统一信号；The coordinate system conversion unit is used to define a reference coordinate system using the workpiece to be detected as a reference object, convert the posture of the three-dimensional scanner to the reference coordinate system, and determine a unified coordinate signal;
所述扫描视点确定单元，用于基于所述基准坐标系，根据所述待检测工件的测量特征位置处的点位信息，确定多个扫描视点信号；The scanning viewpoint determination unit is configured to determine multiple scanning viewpoint signals based on the reference coordinate system and the point information at the measurement feature position of the workpiece to be detected;
所述最优路径规划单元与所述扫描视点确定单元通信连接，用于接收所述扫描视点信号，并根据预设的路径规划算法，对所述多个扫描视点进行最优化排序，获得机器人最优路径顺序。The optimal path planning unit is communicatively connected to the scanning viewpoint determination unit, and is used to receive the scanning viewpoint signal, and perform optimal sorting of the multiple scanning viewpoints according to a preset path planning algorithm to obtain the optimal path for the robot. Optimal path order.
在一些实施例中，所述视觉引导模块包括导入单元、显示单元、位姿偏差生成单元、引导式交互模块和动态提示模块；In some embodiments, the visual guidance module includes an introduction unit, a display unit, a posture deviation generation unit, a guided interaction module and a dynamic prompt module;
所述导入单元与所述显示单元通信连接，用于导入将所述待检测工件模型、所述多个扫描视点和所述基准坐标系；The import unit is communicatively connected to the display unit and is used to import the workpiece model to be inspected, the multiple scanning viewpoints and the reference coordinate system;
所述显示单元用于根据导入的所述待检测工件模型、所述多个扫描视点和所述基准坐标系，实时可视化显示所述三维扫描仪与所述多个扫描视点中的目标扫描视点之间的位姿关系，并生成位姿关系指令；The display unit is used to visually display the three-dimensional scanner and the target scanning viewpoint among the plurality of scanning viewpoints in real time according to the imported workpiece model, the plurality of scanning viewpoints and the reference coordinate system. pose relationship between them, and generate pose relationship instructions;
所述移动路径生成单元与所述显示单元通信连接，用于接收所述位姿关系指令，并根据所述位姿关系指令，确定所述三维扫描仪相对于所述目标扫描视点的位姿偏差，以及当前所述目标扫描视点相对于所述最优运动轨迹中的下一个扫描视点的移动方向；The movement path generation unit is communicatively connected to the display unit, and is configured to receive the pose relationship instruction, and determine the pose deviation of the three-dimensional scanner relative to the target scanning viewpoint according to the pose relationship instruction. , and the movement direction of the current target scanning viewpoint relative to the next scanning viewpoint in the optimal motion trajectory;
所述引导式交互模块，用于基于所述位姿偏差，提供所述三维扫描仪与所述目标视点之间偏差直观度量程度；The guided interaction module is used to provide an intuitive measurement of the degree of deviation between the three-dimensional scanner and the target viewpoint based on the pose deviation;
所述动态提示模块，用于根据所述三维扫描仪与所述目标视点之间的位姿关系给出相应提示。The dynamic prompt module is used to give corresponding prompts according to the pose relationship between the three-dimensional scanner and the target viewpoint.
第二方面，本发明还提供了一种基于扫描仪视觉引导的机器人路径规划方法，应用于上述任一项所述的基于扫描仪视觉引导的机器人路径规划系统，包括：In a second aspect, the present invention also provides a robot path planning method based on scanner vision guidance, which is applied to any of the above-mentioned robot path planning systems based on scanner vision guidance, including:
获取多个扫描视点；Acquire multiple scanning viewpoints;
采用预设的路径规划算法，对所述多个扫描视点进行最优化排序，获得机器人最优运动轨迹；Using a preset path planning algorithm, the multiple scanning viewpoints are optimally sorted to obtain the optimal motion trajectory of the robot;
实时可视化显示所述最优运动轨迹和所述三维扫描仪的扫描位姿，并根据所述三维扫描仪的扫描位姿与所述最优运动轨迹中的目标扫描视点之间的位姿偏差，通过所述机器人调整所述三维扫描仪的位姿直至与所述目标扫描视点重合。Real-time visual display of the optimal movement trajectory and the scanning posture of the three-dimensional scanner, and based on the posture deviation between the scanning posture of the three-dimensional scanner and the target scanning viewpoint in the optimal movement trajectory, The robot adjusts the posture of the three-dimensional scanner until it coincides with the target scanning viewpoint.
在一些实施例中，在获取扫描视点之前，包括采用预设的坐标转换法，以待检测工件坐标系为基准坐标系，将所述三维扫描仪的坐标转换至所述基准坐标系下，其包括：In some embodiments, before acquiring the scanning viewpoint, a preset coordinate conversion method is used to convert the coordinates of the three-dimensional scanner to the reference coordinate system using the coordinate system of the workpiece to be detected as the reference coordinate system. include:
标定多个工件上的特征；Calibrate features on multiple workpieces;
分别获取扫描仪坐标系下所述特征的坐标以及工件坐标系下所述特征的关键点坐标；Obtain the coordinates of the feature in the scanner coordinate system and the key point coordinates of the feature in the workpiece coordinate system respectively;
基于扫描仪坐标系下所述特征的坐标以及工件坐标系下所述特征的关键点坐标，根据预设的坐标系转换关系，将所述三维扫描仪的坐标转换至所述基准坐标系下。Based on the coordinates of the feature in the scanner coordinate system and the key point coordinates of the feature in the workpiece coordinate system, the coordinates of the three-dimensional scanner are converted to the reference coordinate system according to the preset coordinate system conversion relationship.
在一些实施例中，所述获取多个扫描视点，包括：In some embodiments, acquiring multiple scanning viewpoints includes:
基于所述基准坐标系，根据待检测工件的测量特征位姿处的点位信息，确定多个扫描视点。Based on the reference coordinate system, multiple scanning viewpoints are determined according to the point information at the measurement characteristic pose of the workpiece to be detected.
在一些实施例中，所述扫描视点包括所述待检测工件的位姿信息和角度信息。In some embodiments, the scanning viewpoint includes pose information and angle information of the workpiece to be inspected.
在一些实施例中，所述通过所述机器人调整所述三维扫描仪的位姿直至与所述目标扫描视点重合包括：In some embodiments, adjusting the posture of the three-dimensional scanner by the robot until it coincides with the target scanning viewpoint includes:
获取到达当前扫描视点后的所述三维扫描仪的实时位姿信息；Obtain the real-time pose information of the three-dimensional scanner after reaching the current scanning viewpoint;
获取所述实时位姿信息与所述当前扫描视点之间的位姿偏差；Obtain the pose deviation between the real-time pose information and the current scanning viewpoint;
若所述位姿偏差小于预设的偏差阈值，则确定所述当前扫描视点规划成功。If the pose deviation is less than the preset deviation threshold, it is determined that the current scanning viewpoint planning is successful.
在一些实施例中，当所述位姿偏差小于预设的偏差阈值，当前扫描视点规划成功之后，还包括：In some embodiments, when the pose deviation is less than a preset deviation threshold and the current scanning viewpoint is successfully planned, the method further includes:
根据所述当前所述扫描视点相对于所述最优路径中下一个扫描视点的移动方向，进入下一个扫描视点的点位规划。According to the movement direction of the current scanning viewpoint relative to the next scanning viewpoint in the optimal path, the point planning of the next scanning viewpoint is entered.
在一些实施例中，在进入下一个扫描视点的点位规划之前通过所述视觉引导模块给下一次规划提示。In some embodiments, the next planning prompt is given through the visual guidance module before entering the point planning of the next scanning viewpoint.
与现有技术相比，本发明提供的基于扫描仪视觉引导的机器人路径规划系统和方法，首先根据待检测工件的特征信息预先确定好三维扫描仪的扫描视点，然后采用路径规划模块基于预设的扫描视点确定机器人的最优运动轨迹，并且利用视觉引导模块实时显示最优运动轨迹、三维扫描仪的位姿与目标扫描视点之间的位姿关系，并根据实时显示的位姿关系通过机器人调整三维扫描仪移动的位姿直至与目标扫描视点重合，进行扫描。本发明帮助人工规划最优路径提供视觉参考依据，快速完成示教过程，提高现场调试效率，同时提升所规划路径的质量，克服了依赖于具体机器人型号和离线仿真软件的问题。Compared with the existing technology, the robot path planning system and method based on scanner vision guidance provided by the present invention first predetermines the scanning viewpoint of the three-dimensional scanner based on the characteristic information of the workpiece to be detected, and then uses the path planning module to based on the preset The scanning viewpoint determines the optimal motion trajectory of the robot, and the visual guidance module is used to display the optimal motion trajectory, the pose relationship between the 3D scanner's pose and the target scanning viewpoint in real time, and the robot passes the robot based on the real-time displayed pose relationship. Adjust the moving posture of the 3D scanner until it coincides with the target scanning viewpoint and scan. The invention helps manual planning of the optimal path, provides a visual reference basis, quickly completes the teaching process, improves on-site debugging efficiency, improves the quality of the planned path, and overcomes the problem of dependence on specific robot models and offline simulation software.
附图说明Description of the drawings
图1是本发明提供的基于扫描仪视觉引导的机器人路径规划系统的一实施例的结构示意图；Figure 1 is a schematic structural diagram of an embodiment of a robot path planning system based on scanner visual guidance provided by the present invention;
图2是本发明提供的基于扫描仪视觉引导的机器人路径规划系统中，路径规划模块一实施例的示意图；Figure 2 is a schematic diagram of an embodiment of a path planning module in the robot path planning system based on scanner visual guidance provided by the present invention;
图3是本发明提供的基于扫描仪视觉引导的机器人路径规划系统中，视觉引导模块的一实施例的示意图；Figure 3 is a schematic diagram of an embodiment of the visual guidance module in the robot path planning system based on scanner visual guidance provided by the present invention;
图4是本发明提供的基于扫描仪视觉引导的机器人路径规划系统中，视觉引导模块实时显示一实施例的示意图；Figure 4 is a schematic diagram of an embodiment of real-time display of the visual guidance module in the robot path planning system based on scanner visual guidance provided by the present invention;
图5是本发明提供的基于扫描仪视觉引导的机器人路径规划方法一实施例的流程图；Figure 5 is a flow chart of an embodiment of a robot path planning method based on scanner visual guidance provided by the present invention;
图6是本发明提供的基于扫描仪视觉引导的机器人路径规划方法中，聚类分析一实施的示意图；Figure 6 is a schematic diagram of an implementation of cluster analysis in the robot path planning method based on scanner visual guidance provided by the present invention;
图7是本发明提供的基于扫描仪视觉引导的机器人路径规划方法中，步骤S503的一实施例的示意图；Figure 7 is a schematic diagram of an embodiment of step S503 in the robot path planning method based on scanner visual guidance provided by the present invention;
图8是本发明提供的基于扫描仪视觉引导的机器人路径规划方法中，扫描仪视觉引导机器人路径规划的另一实施例的流程示意图。8 is a schematic flowchart of another embodiment of the scanner vision-guided robot path planning method in the robot path planning method based on scanner vision guidance provided by the present invention.
具体实施方式Detailed ways
为了使本发明的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本发明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仅用以解释本发明，并不用于限定本发明。In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention and are not intended to limit the present invention.
本发明实施例提供一种基于扫描仪视觉引导的机器人路径规划系统1，请参阅图1-图3，包括：三维扫描仪11、路径规划模块12、视觉引导模块13和机器人14；The embodiment of the present invention provides a robot path planning system 1 based on scanner visual guidance. Please refer to Figures 1-3. It includes: a three-dimensional scanner 11, a path planning module 12, a visual guidance module 13 and a robot 14;
所述三维扫描仪固定连接于所述机器人的末端，用于创建待检测工件表面的三维数据；The three-dimensional scanner is fixedly connected to the end of the robot and is used to create three-dimensional data of the surface of the workpiece to be inspected;
所述路径规划模块分别与所述三维扫描仪通信连接，用于基于预设的扫描视点确定机器人的最优运动轨迹；The path planning module is communicatively connected to the three-dimensional scanner, and is used to determine the optimal motion trajectory of the robot based on a preset scanning viewpoint;
所述视觉引导模块，用于确定在所述最优运动轨迹中的目标扫描视点，实时可视化显示所述三维扫描仪的位姿与所述目标扫描视点之间的位姿偏差并引导所述三维扫描仪到达指定位姿；The visual guidance module is used to determine the target scanning viewpoint in the optimal motion trajectory, visually display the posture deviation between the three-dimensional scanner's posture and the target scanning viewpoint in real time, and guide the three-dimensional The scanner reaches the specified position;
所述机器人具有多自由度，用于根据所述位姿偏差调整所述三维扫描仪的位姿直至与所述目标视点重合。The robot has multiple degrees of freedom and is used to adjust the posture of the three-dimensional scanner according to the posture deviation until it coincides with the target viewpoint.
在本实施例中，首先根据待检测工件的特征信息预先确定好三维扫描仪的扫描视点，然后采用路径规划模块基于预设的扫描视点确定机器人的最优运动轨迹，并且利用视觉引导模块实时显示最优运动轨迹、三维扫描仪的位姿与目标扫描视点之间的位姿关系，并根据实时显示的位姿关系通过机器人调整三维扫描仪移动的位姿直至与目标扫描视点重合，进行扫描。本发明帮助人工规划最优路径提供视觉参考依据，快速完成示教过程，提高现场调试效率，同时提升所规划路径的质量，克服了依赖于具体机器人型号和离线仿真软件的问题，In this embodiment, the scanning viewpoint of the three-dimensional scanner is first determined in advance based on the characteristic information of the workpiece to be inspected, and then the path planning module is used to determine the optimal motion trajectory of the robot based on the preset scanning viewpoint, and the visual guidance module is used to display it in real time. The optimal motion trajectory, the posture relationship between the three-dimensional scanner's posture and the target scanning viewpoint, and based on the real-time displayed posture relationship, the robot adjusts the moving posture of the three-dimensional scanner until it coincides with the target scanning viewpoint, and then scans. The invention helps manual planning of the optimal path, provides a visual reference, quickly completes the teaching process, improves on-site debugging efficiency, and at the same time improves the quality of the planned path, overcoming the problem of relying on specific robot models and offline simulation software.
需要说明的是，三维扫描仪可包括手持式激光扫描仪、跟踪式三维扫描仪、拍照式面阵扫描仪等类型的三维扫描仪(即具备双目立体视觉功能的扫描仪)。It should be noted that 3D scanners may include handheld laser scanners, tracking 3D scanners, photographic area array scanners and other types of 3D scanners (i.e. scanners with binocular stereo vision functions).
需要说明的是，扫描视点是以预设的方法规划出来的且以离散的形式存在的。It should be noted that the scanning viewpoint is planned in a preset method and exists in a discrete form.
进一步的，根据设定的扫描视点规划最优运动路径，包括以使扫描仪沿扫描视点所形成的路径行走路径尽量短。可以理解的是，选择不同的起点对应的最优运动路径不同。Further, planning the optimal motion path according to the set scanning viewpoint includes making the scanner travel path as short as possible along the path formed by the scanning viewpoint. It is understandable that the optimal motion paths corresponding to different starting points are different.
在一些实施例中，请参阅图2，所述路径规划模块12包括坐标系转换单元121、扫描视点确定单元122和最优路径规划单元123；In some embodiments, please refer to Figure 2, the path planning module 12 includes a coordinate system conversion unit 121, a scanning viewpoint determination unit 122 and an optimal path planning unit 123;
所述坐标系转换单元用于以待检测工件为参考对象定义基准坐标系，将所述三维扫描仪的位姿转换至所述基准坐标系下，确定坐标统一信号；The coordinate system conversion unit is used to define a reference coordinate system using the workpiece to be detected as a reference object, convert the posture of the three-dimensional scanner to the reference coordinate system, and determine a unified coordinate signal;
所述扫描视点确定单元，用于接收所述坐标统一信号，并基于所述基准坐标系，根据所述待检测工件的测量特征位姿处的点位信息，确定多个扫描视点信号；The scanning viewpoint determination unit is configured to receive the coordinate unified signal, and determine multiple scanning viewpoint signals based on the point information at the measurement feature pose of the workpiece to be detected based on the reference coordinate system;
所述最优路径规划单元与所述扫描视点确定单元通信连接，用于接收所述扫描视点信号，并根据预设的路径规划算法，对所述多个扫描视点进行最优化排序，获得机器人最优路径顺序。The optimal path planning unit is communicatively connected to the scanning viewpoint determination unit, and is used to receive the scanning viewpoint signal, and perform optimal sorting of the multiple scanning viewpoints according to a preset path planning algorithm to obtain the optimal path for the robot. Optimal path order.
在本实施例中，在进行视觉引导之前，按照初步规划的路径进行扫描，即可得到待检测工件的初步模型，通过对初步模型进行分析和计算，获得初步模型存在的缺失，通过缺失反馈三维扫描仪的视点优化工作，以使三维扫描仪获得的待检测工件数据更加完整，即在初步规划的扫描路径基础上调整扫描视点和扫描路径，从而克服了仅依赖人工经验反复修改和调试路径的问题，提高了三维扫描仪的路径调试效率。In this embodiment, before visual guidance is performed, a preliminary model of the workpiece to be inspected can be obtained by scanning according to the initially planned path. By analyzing and calculating the preliminary model, the deficiencies in the preliminary model are obtained, and three-dimensional feedback is provided through the deficiencies. The scanner's viewpoint is optimized to make the workpiece data to be inspected obtained by the 3D scanner more complete, that is, the scanning viewpoint and scanning path are adjusted based on the initially planned scanning path, thus overcoming the problem of repeatedly modifying and debugging the path based solely on manual experience. This problem improves the path debugging efficiency of 3D scanners.
在一个具体的实施例中，首先采用预设的坐标转换法，以待检测工件坐标系为基准坐标系，将所述三维扫描仪的坐标转换至所述基准坐标系下；随后基于所述基准坐标系，根据待检测工件的测量特征位置处的点位信息，确定多个扫描视点；随后采用预设的路径规划算法，对所述多个扫描视点进行最优化排序，获得机器人最优运动路径；最后基于所述机器人最优运动路径，根据所述三维扫描仪的位姿与即将到达的所述扫描视点之间的位姿关系，操作所述三维扫描仪到达所述扫描视点。In a specific embodiment, a preset coordinate conversion method is first used, using the coordinate system of the workpiece to be detected as the reference coordinate system, to convert the coordinates of the three-dimensional scanner to the reference coordinate system; and then based on the reference The coordinate system determines multiple scanning viewpoints based on the point information at the measurement feature position of the workpiece to be inspected; then a preset path planning algorithm is used to optimally sort the multiple scanning viewpoints to obtain the optimal motion path of the robot. ; Finally, based on the optimal movement path of the robot and the posture relationship between the posture of the three-dimensional scanner and the scanning viewpoint to be reached, the three-dimensional scanner is operated to reach the scanning viewpoint.
需要说明的是，基于所述基准坐标系，对所述机器人和所述三维扫描仪进行手眼标定，得到所述机器人末端与所述三维扫描仪相对所述基准坐标系的坐标变换关系；获取所述三维扫描仪坐标系下，所述机器人的多组静态位姿；根据所述坐标变换关系以及所述三维扫描仪坐标系下的所述机器人的多组静态位姿，将所述机器人的多组静态位姿转换到所述基准坐标系下。进一步的，由于扫描仪是固定在机器人末端，因此手眼标定的过程可以是机器人末端与扫描仪之间的坐标变换关系的求解，具体的，将机器人与扫描仪的坐标均转换至待检测工件的坐标体系下，通过数据矩阵的形式进行表示。机器人末端与扫描仪之间的刚性变换矩阵，通过确定机器人末端与扫描仪之间的刚性变换矩阵，从而实现机器人末端与扫描仪之间的手眼标定，得到机器人末端与扫描仪之间的变换关系。从而当扫描仪按照扫描视点的最优路径行进时，机器人跟随运动。需要说明的是，本发明不限定具体的机器人，因此针对不同的机器人，其手眼标定的结果不一致。It should be noted that, based on the reference coordinate system, perform hand-eye calibration on the robot and the three-dimensional scanner to obtain the coordinate transformation relationship between the end of the robot and the three-dimensional scanner relative to the reference coordinate system; obtain the Multiple sets of static poses of the robot in the three-dimensional scanner coordinate system; according to the coordinate transformation relationship and the multiple sets of static poses of the robot in the three-dimensional scanner coordinate system, the multiple sets of static poses of the robot are The group of static poses is transformed into the reference coordinate system. Furthermore, since the scanner is fixed at the end of the robot, the hand-eye calibration process can be the solution of the coordinate transformation relationship between the end of the robot and the scanner. Specifically, the coordinates of the robot and the scanner are converted to the coordinates of the workpiece to be inspected. Under the coordinate system, it is expressed in the form of a data matrix. By determining the rigid transformation matrix between the robot end and the scanner, the hand-eye calibration between the robot end and the scanner is achieved, and the transformation relationship between the robot end and the scanner is obtained. . Thus, when the scanner follows the optimal path of the scanning viewpoint, the robot follows the motion. It should be noted that the present invention is not limited to a specific robot, so the hand-eye calibration results for different robots are inconsistent.
在一些实施例中，请参阅图3，所述视觉引导模块13包括导入单元131、显示单元132、位姿偏差生成单元133、引导式交互模块134和动态提示模块135；In some embodiments, please refer to Figure 3, the visual guidance module 13 includes an introduction unit 131, a display unit 132, a posture deviation generation unit 133, a guided interaction module 134 and a dynamic prompt module 135;
所述导入单元与所述显示单元通信连接，用于导入将所述待检测工件模型、所述多个扫描视点和所述基准坐标系；The import unit is communicatively connected to the display unit and is used to import the workpiece model to be inspected, the multiple scanning viewpoints and the reference coordinate system;
所述显示单元用于根据导入的所述待检测工件模型、所述多个扫描视点和所述基准坐标系，实时可视化显示所述三维扫描仪与所述多个扫描视点中的目标扫描视点之间的位姿关系，并生成位姿关系指令；The display unit is used to visually display the three-dimensional scanner and the target scanning viewpoint among the plurality of scanning viewpoints in real time according to the imported workpiece model, the plurality of scanning viewpoints and the reference coordinate system. pose relationship between them, and generate pose relationship instructions;
所述位姿偏差生成单元与所述显示单元通信连接，用于接收所述位姿关系指令，并根据所述位姿关系指令，确定所述三维扫描仪相对于所述目标扫描视点的位姿偏差，以及当前所述目标扫描视点相对于所述最优运动轨迹中的下一个扫描视点的移动方向；The pose deviation generating unit is communicatively connected to the display unit, and is used to receive the pose relationship instruction, and determine the pose of the three-dimensional scanner relative to the target scanning viewpoint according to the pose relationship instruction. Deviation, and the movement direction of the current target scanning viewpoint relative to the next scanning viewpoint in the optimal motion trajectory;
所述引导式交互模块，用于基于所述位姿偏差，提供所述三维扫描仪与所述目标视点之间偏差直观度量程度；The guided interaction module is used to provide an intuitive measurement of the degree of deviation between the three-dimensional scanner and the target viewpoint based on the pose deviation;
所述动态提示模块，用于根据所述三维扫描仪与所述目标视点之间的位姿关系给出相应提示。The dynamic prompt module is used to give corresponding prompts according to the pose relationship between the three-dimensional scanner and the target viewpoint.
在本实施例中，视觉引导模块通过实时显示最优运动路径，以及三维扫描仪当前的位姿及距离下一个目标扫描视点的距离、方向和移动的轨迹，从而操作者通过操纵机器人带动三维扫描仪按照视觉引导模块提供的路径和方向运动至目标扫描视点，通过视觉引导模块引导三维扫描仪的运动，避免了盲目的移动导致的扫描效率低的问题。In this embodiment, the visual guidance module displays the optimal movement path in real time, as well as the current posture of the 3D scanner and the distance, direction and movement trajectory from the next target scanning viewpoint, so that the operator drives the 3D scan by manipulating the robot. The scanner moves to the target scanning viewpoint according to the path and direction provided by the visual guidance module. The visual guidance module guides the movement of the 3D scanner, avoiding the problem of low scanning efficiency caused by blind movement.
进一步的，请参阅图4，图4以可视化界面引导示意图，图中通过在可视化界面的边界处提供引导条多个维度的实时显示三维扫描仪与目标视点之间的位姿关系及位姿偏差，可更加直观的指导操作者调整三维扫描仪的位姿。Further, please refer to Figure 4. Figure 4 is a schematic diagram of a visual interface guidance. The figure provides a guide bar at the boundary of the visual interface to display the posture relationship and posture deviation between the 3D scanner and the target viewpoint in real time in multiple dimensions. , which can guide the operator to adjust the posture of the 3D scanner more intuitively.
基于上述的基于扫描仪视觉引导的机器人路径规划系统，本发明还提供一种基于扫描仪视觉引导的机器人路径规划方法，请参阅图5，包括：Based on the above robot path planning system based on scanner vision guidance, the present invention also provides a robot path planning method based on scanner vision guidance, please refer to Figure 5, including:
S501、获取多个扫描视点；S501. Obtain multiple scanning viewpoints;
S502、采用预设的路径规划算法，对所述多个扫描视点进行最优化排序，获得机器人最优运动轨迹；S502. Use a preset path planning algorithm to optimally sort the multiple scanning viewpoints to obtain the optimal motion trajectory of the robot;
S503、实时可视化显示所述最优运动轨迹和所述三维扫描仪的扫描位姿，并根据所述三维扫描仪的扫描位姿与所述最优运动轨迹中的目标扫描视点之间的位姿偏差，通过所述机器人调整所述三维扫描仪的位姿直至与所述目标扫描视点重合。S503. Real-time visual display of the optimal movement trajectory and the scanning posture of the three-dimensional scanner, and based on the posture between the scanning posture of the three-dimensional scanner and the target scanning viewpoint in the optimal movement trajectory Deviation, the robot adjusts the posture of the three-dimensional scanner until it coincides with the target scanning viewpoint.
在本实施例中，通过获取扫描视点，随后根据扫描视点确定最优运动路径，最后通过实时显示最优路径、三维扫描仪的运动方向和运动距离等条件，操作三维扫描仪到达目标地点。In this embodiment, the 3D scanner is operated to reach the target location by acquiring the scanning viewpoint, then determining the optimal movement path based on the scanning viewpoint, and finally displaying conditions such as the optimal path, the movement direction and movement distance of the 3D scanner in real time.
进一步的，在本实施例中，通过将一系列的扫描视点按照最优路径的顺序进行视觉引导，在引导软件的可视化模块界面，按顺序显示出这些视点的角度信息、位置信息以及当前扫描视点相对于最优路径中下一个扫描视点的移动方向，通过计算扫描仪与当前扫描视点之间的位姿偏差，并将位姿偏差通过可视化的图形在可视化界面上显示出来，即可根据位姿偏差调整扫描仪的位姿，直至与当前的扫描视点重合。Furthermore, in this embodiment, a series of scanning viewpoints are visually guided in the order of the optimal path, and the angle information, position information and current scanning viewpoint of these viewpoints are sequentially displayed in the visualization module interface of the guidance software. Relative to the movement direction of the next scanning viewpoint in the optimal path, by calculating the pose deviation between the scanner and the current scanning viewpoint, and displaying the pose deviation on the visual interface through visual graphics, the pose can be calculated according to the pose The deviation adjusts the scanner's posture until it coincides with the current scanning viewpoint.
具体的，通过在可视化界面上将位姿偏差通过以可视化图像的形式显示出来，在一个具体的实施例，通常通过可视化界面显示三维扫描仪与基准位姿的偏差，结合顶部、左侧和右侧的指示条，只有当扫描仪对应的激光与三处的指示条位姿对准后，才表示扫描仪到达了指定位姿。通过这种方式，使得扫描仪的行进有明确的目标性和方向性，能够更加便捷地指导扫描仪定位。Specifically, the pose deviation is displayed in the form of a visual image on the visual interface. In a specific embodiment, the deviation between the three-dimensional scanner and the reference pose is usually displayed through the visual interface, combining the top, left and right Only when the corresponding laser of the scanner is aligned with the three indicator bars, does it mean that the scanner has reached the specified posture. In this way, the scanner's movement has a clear purpose and direction, which can guide the scanner's positioning more conveniently.
在步骤S502中，所述预设的路径规划算法包括枚举法、回溯法和贪心算法中的一种。In step S502, the preset path planning algorithm includes one of an enumeration method, a backtracking method, and a greedy algorithm.
在本实施例中，综合考虑算法的思路与时间复杂度，采用贪心算法来求取面扫描机器人系统的最短扫描路径。贪心算法是以分治策略为基础，将一个大问题分成若干个小问题，最后合并这些小问题的解求得结果。贪心算法求解该问题时，选取一个扫描视点作为起始点，查找下一扫描视点时只考虑与当前扫描视点距离最近的扫描视点作为下一点，直到所有的扫描视点都走完。由于每次做出选择时经过的都是最短距离，所以当所有扫描视点都走完回到起始位置时，走过的路径便是扫描机器人的最短路径。In this embodiment, a greedy algorithm is used to obtain the shortest scanning path of the surface scanning robot system by comprehensively considering the idea and time complexity of the algorithm. The greedy algorithm is based on the divide-and-conquer strategy, which divides a large problem into several small problems, and finally combines the solutions of these small problems to obtain the result. When the greedy algorithm solves this problem, it selects a scanning viewpoint as the starting point. When searching for the next scanning viewpoint, only the scanning viewpoint closest to the current scanning viewpoint is considered as the next point until all scanning viewpoints are completed. Since the shortest distance is traveled every time a selection is made, when all scanning viewpoints are returned to the starting position, the path traveled is the shortest path of the scanning robot.
具体算法思路如下：首先选取机器人的起始位置，作为扫描路径的起始扫描视点。在扫描视点数组中查找距离起始点位置最近的扫描视点作为扫描路径的第二个点，并进行标记。再在视点数组中查找与第二点扫描视点距离最近的未标记点作为扫描路径的第三个点，以此类推，直到视点数组中的所有视点均被标记。此时，视点数组中的所有点均被重新排序，将机器人初始位置的点与重新排序的视点按顺序依次连接，即生成了面扫描测量机器人的最短扫描路径。The specific algorithm idea is as follows: First, select the starting position of the robot as the starting scanning viewpoint of the scanning path. Find the scanning viewpoint closest to the starting point in the scanning viewpoint array as the second point of the scanning path, and mark it. Then find the unmarked point closest to the second scanning viewpoint in the viewpoint array as the third point of the scanning path, and so on until all viewpoints in the viewpoint array are marked. At this time, all points in the viewpoint array are reordered, and the points at the robot's initial position and the reordered viewpoints are connected in order, that is, the shortest scanning path of the surface scanning measurement robot is generated.
在一些实施例中，在获取扫描视点之前，包括采用预设的坐标转换法，以待检测工件坐标系为基准坐标系，将所述三维扫描仪的坐标转换至所述基准坐标系下，其包括：In some embodiments, before acquiring the scanning viewpoint, a preset coordinate conversion method is used to convert the coordinates of the three-dimensional scanner to the reference coordinate system using the coordinate system of the workpiece to be detected as the reference coordinate system. include:
标定多个工件上的特征；Calibrate features on multiple workpieces;
分别获取扫描仪坐标系下所述特征的坐标以及工件坐标系下所述特征的关键点坐标；Obtain the coordinates of the feature in the scanner coordinate system and the key point coordinates of the feature in the workpiece coordinate system respectively;
基于扫描仪坐标系下所述特征的坐标以及工件坐标系下所述特征的关键点坐标，根据预设的坐标系转换关系，将所述三维扫描仪的坐标转换至所述基准坐标系下。Based on the coordinates of the feature in the scanner coordinate system and the key point coordinates of the feature in the workpiece coordinate system, the coordinates of the three-dimensional scanner are converted to the reference coordinate system according to the preset coordinate system conversion relationship.
在本实施例中，首先通过在工件上任意位置指定至少4个特征，一方面三维扫描仪采集这些特征位置数据后并进行扫描特征提取，最后得到扫描仪坐标系下的特征关键点坐标；另一方面对至少4个特征进行数模特征提取，并根据工件CAD数模提取出这些特征在CAD数模中的关键点坐标；最后根据扫描仪坐标系下的特征关键点坐标和CAD数模中的关键点坐标的对应点，计算扫描仪坐标系到工件坐标系的转换关系。In this embodiment, first by specifying at least 4 features at any position on the workpiece, on the one hand, the three-dimensional scanner collects these feature position data and performs scanning feature extraction, and finally obtains the coordinates of the feature key points in the scanner coordinate system; another On the one hand, the digital model features are extracted for at least 4 features, and the key point coordinates of these features in the CAD digital model are extracted based on the workpiece CAD digital model; finally, based on the feature key point coordinates in the scanner coordinate system and the CAD digital model The corresponding points of the key point coordinates are used to calculate the conversion relationship between the scanner coordinate system and the workpiece coordinate system.
在一些实施例中，所述获取多个扫描视点，包括：In some embodiments, acquiring multiple scanning viewpoints includes:
基于所述基准坐标系，根据待检测工件的测量特征位置处的点位信息，确定多个扫描视点。Based on the reference coordinate system, multiple scanning viewpoints are determined according to the point information at the measurement feature position of the workpiece to be inspected.
在本实施例中，首先采用预设的聚类分析算法对待检测工件的三角网格进行分割处理，获得多个三角网格子区域；随后基于多个三角网格子区域，采用预设的最小包围盒法确定待检测工件的多个扫描视点。In this embodiment, a preset cluster analysis algorithm is first used to segment the triangular grid of the workpiece to be detected, and multiple triangular grid sub-areas are obtained; then based on the multiple triangular grid sub-areas, a preset minimum bounding box is used method to determine multiple scanning viewpoints of the workpiece to be inspected.
需要说明的是，三角网格是计算机图形学中用来描述各种不规则物体的一种数据结构，为了适应复杂曲面的待检测工件，本实施例首先对三角网络进行分割处理，获得多个三角网格子区域。It should be noted that the triangular mesh is a data structure used in computer graphics to describe various irregular objects. In order to adapt to the complex curved surface of the workpiece to be detected, this embodiment first performs segmentation processing on the triangular network to obtain multiple Triangular mesh subarea.
具体的，首先根据三角网格模型的特点，首先求取模型的高斯映射，映射的过程是这样的，将物体表面每一点的法向量的起点均平移至高斯球的球心，每个法向量都会与高斯球的球面有一个交点，这些所有交点的集合就是曲面的高斯映射。请参阅图6，图6为高斯映射原理图，点P为曲面S上一点，向量为点P的法向量，将法向量/>的起点平移至球心O处，则得到它与球面的交点K。依照如此方法，将曲面上所有的点的法向量移动到单位球的球心O处，得到法向量与球面交点的集合就是该曲面S的高斯映射。Specifically, first according to the characteristics of the triangular mesh model, the Gaussian mapping of the model is first obtained. The mapping process is as follows. The starting point of the normal vector of each point on the object surface is translated to the center of the Gaussian sphere. Each normal vector There will be an intersection point with the spherical surface of the Gaussian sphere, and the set of all these intersection points is the Gaussian map of the surface. Please refer to Figure 6, which is a schematic diagram of Gaussian mapping. Point P is a point on the surface S, and the vector is the normal vector of point P, change the normal vector/> The starting point is translated to the center O of the sphere, and its intersection point K with the sphere is obtained. According to this method, the normal vectors of all points on the surface are moved to the center O of the unit sphere, and the set of intersection points of the normal vectors and the sphere is the Gaussian map of the surface S.
随后基于高斯映射的结果，采用预设的聚类分析算法大致对三角网格进行分割，请参阅图7，图7为聚类分析示意图，点A，B为球面上两点，矢量OA与矢量OB之间的夹角为α，则点A点B对应的两三角面片之间法矢的夹角为α，α的大小又对应于点A，B间的距离，也就是弦AB。故两三角面片的法矢夹角越大时，弦AB也就越长，点A，点B之间的距离也就越大。所以，将法矢夹角相近的三角面片划分成一类实际上就是将球面上距离相近的映射点归为一类。按照三角面片法矢夹角进行聚类的问题也就被转化成了依照最短距离对数据点集进行聚类分析的过程。Then based on the results of Gaussian mapping, the preset cluster analysis algorithm is used to roughly segment the triangular mesh. Please refer to Figure 7. Figure 7 is a schematic diagram of cluster analysis. Points A and B are two points on the sphere. The vector OA and the vector The angle between OB is α, then the angle between the normal vectors of the two triangular patches corresponding to point A and point B is α, and the size of α corresponds to the distance between points A and B, which is the chord AB. Therefore, the greater the angle between the normal vectors of the two triangular patches, the longer the chord AB, and the greater the distance between point A and point B. Therefore, dividing triangular patches with similar normal angles into one category is actually grouping mapping points with similar distances on the sphere into one category. The problem of clustering according to the normal vector angle of the triangular patch is transformed into a process of clustering analysis of the data point set according to the shortest distance.
最后根据聚类分析后获得的大致类别，根据在这一类中各三角面片是否相互连接的方式，将这个大类划分为几个不相连接的独立的区域；再将这些平均法矢夹角相近的并且相邻的区域进行合并，组成新的更大的区域；反复如此进行操作，直到所有独立的区域与它们相邻的区域都不能再次合并为止，确定多个三角网格子区域。Finally, according to the general categories obtained after cluster analysis, and according to whether the triangular patches in this category are connected to each other, this category is divided into several independent areas that are not connected; then these average normal vectors are divided into Areas with similar corners and adjacent areas are merged to form a new larger area; this operation is repeated until all independent areas and their adjacent areas cannot be merged again, and multiple triangular grid sub-areas are determined.
进一步的，首先根据扫描仪的参数特点，建立符合扫描仪特点的扫描视锥体，以使处于视锥体内的区域可视。然后遍历上述所得到的三角网格子区域，按空间顺序选取其中一块子区域，将其投影到与该区域平均法向所垂直的二维平面上，得到该空间区域的二维投影面。根据扫描仪的视锥尺寸约束，选用扫描仪最佳扫描距离与二维投影面进行贴合，对该二维投影面进行全覆盖细分，获得一系列二维扫描视点。对于这些二维扫描视点，根据所在投影面所映射的三角网格区域内三维点的坐标平均值作为该扫描视点的三维位置，根据所映射三维点的法向量平均值作为扫描视点的角度朝向，如此即可确定一块子区域的序列扫描视点。依次遍历剩余子区域，则可完成对所有区域的扫描视点解算。Further, firstly, according to the parameter characteristics of the scanner, a scanning frustum that conforms to the characteristics of the scanner is established so that the area within the frustum is visible. Then traverse the triangular grid sub-regions obtained above, select one of the sub-regions in spatial order, and project it onto a two-dimensional plane perpendicular to the average normal direction of the region to obtain the two-dimensional projection surface of the spatial region. According to the scanner's frustum size constraints, the optimal scanning distance of the scanner is selected to fit the two-dimensional projection surface, and the two-dimensional projection surface is fully covered and subdivided to obtain a series of two-dimensional scanning viewpoints. For these two-dimensional scanning viewpoints, the coordinate average of the three-dimensional points in the triangular grid area mapped by the projection plane is used as the three-dimensional position of the scanning viewpoint, and the average normal vector of the mapped three-dimensional points is used as the angular orientation of the scanning viewpoint. In this way, the sequential scanning viewpoint of a sub-region can be determined. By traversing the remaining sub-regions in sequence, the scanning viewpoint solution for all regions can be completed.
在一些实施例中，所述扫描视点包括位置信息和角度信息。In some embodiments, the scanning viewpoint includes position information and angle information.
在本实施例中，扫描视点P(x,y,z,a,b,c)，其中abc为视点与三个方向的夹角，通过位置坐标信息和角度信息即可准确定位空间中的扫描视点。In this embodiment, the scanning viewpoint P (x, y, z, a, b, c), where abc is the angle between the viewpoint and the three directions, can accurately position the scan in the space through the position coordinate information and angle information. viewpoint.
在一些实施例中，所述通过所述机器人调整所述三维扫描仪的位姿直至与所述目标扫描视点重合包括：In some embodiments, adjusting the posture of the three-dimensional scanner by the robot until it coincides with the target scanning viewpoint includes:
获取到达当前扫描视点后的所述三维扫描仪的实时位姿信息；Obtain the real-time pose information of the three-dimensional scanner after reaching the current scanning viewpoint;
获取所述实时位姿信息与所述当前扫描视点之间的位姿偏差；Obtain the pose deviation between the real-time pose information and the current scanning viewpoint;
若所述位姿偏差小于预设的偏差阈值，则确定所述当前扫描视点规划成功。If the pose deviation is less than the preset deviation threshold, it is determined that the current scanning viewpoint planning is successful.
在本实施例中，为了提高路径规划的效率及容错率，设置偏差阈值以通过位姿偏差与偏差阈值之间的大小关系判断扫描仪是否到达指定位姿且是否符合定位标准。In this embodiment, in order to improve the efficiency and error tolerance of path planning, a deviation threshold is set to determine whether the scanner reaches the specified pose and meets the positioning standard based on the size relationship between the pose deviation and the deviation threshold.
在一些实施例中，若所述位姿偏差小于预设的偏差阈值，则说明当前扫描视点规划成功之后，包括：In some embodiments, if the pose deviation is less than the preset deviation threshold, it means that after the current scanning viewpoint planning is successful, the following steps include:
根据所述当前所述扫描视点相对于所述最优路径中下一个扫描视点的移动方向，进入下一个扫描视点点位的规划。According to the movement direction of the current scanning viewpoint relative to the next scanning viewpoint in the optimal path, the planning of the next scanning viewpoint is entered.
在本实施例中，按照最优路径的顺序，引导扫描仪沿着扫描视点行进，直至扫描完成所有最优路径中的扫描视点。In this embodiment, the scanner is guided to travel along the scanning viewpoints in the order of the optimal path until scanning of all scanning viewpoints in the optimal path is completed.
进一步的，一次规划完成后，如果进行扫描测试，发现某些位姿需要修改调整，则可对扫描视点数据进行调整，调整完成后，再次进入到规划引导模块；如果是少数的调整，再次的引导可以选择对改动的点进行规划，或者规划过程中跳过已确认的点；也可根据需要在规划过程中自主插入机器人路点，或者根据数据采集效果，删除冗余点，以达到最佳的规划效果。本发明给出的实施例只是本发明所涵盖的某种情形，其方法本身可涵盖多种实施例，包括用户的自主修改、点位的调整等操作。Furthermore, after a planning is completed, if a scan test is performed and it is found that some poses need to be modified, the scan viewpoint data can be adjusted. After the adjustment is completed, enter the planning guidance module again; if it is a small number of adjustments, again The guide can choose to plan the changed points, or skip confirmed points during the planning process; it can also independently insert robot waypoints during the planning process as needed, or delete redundant points based on the data collection effect to achieve the best results. planning effect. The embodiments provided by the present invention are only certain situations covered by the present invention, and the method itself can cover a variety of embodiments, including user's independent modification, point adjustment and other operations.
在一个具体的实施例，请参阅图8，首先通过特征标定法或标志点定位法对扫描仪与工件坐标系的位置关系进行标定，随后基于测量CAD导出法、面阵规划方法或交互编辑生成法中的一种确定工件坐标系下扫描仪的测量视点，并对多个测量视点进行最优路径排序，最后通过可视化显示或交互式视觉引导方式引导扫描仪到达指定位姿。In a specific embodiment, please refer to Figure 8. First, the positional relationship between the scanner and the workpiece coordinate system is calibrated through the feature calibration method or landmark point positioning method, and then generated based on the measurement CAD export method, area array planning method, or interactive editing. One of the methods determines the measurement viewpoint of the scanner in the workpiece coordinate system, sorts the optimal paths for multiple measurement viewpoints, and finally guides the scanner to the specified pose through visual display or interactive visual guidance.
以上所述本发明的具体实施方式，并不构成对本发明保护范围的限定。任何根据本发明的技术构思所做出的各种其他相应的改变与变形，均应包含在本发明权利要求的保护范围内。The above-described specific embodiments of the present invention do not limit the scope of the present invention. Any other corresponding changes and modifications made based on the technical concept of the present invention shall be included in the protection scope of the claims of the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311047256.3ACN116901079A (en) | 2023-08-17 | 2023-08-17 | A robot path planning system and method based on scanner visual guidance |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311047256.3ACN116901079A (en) | 2023-08-17 | 2023-08-17 | A robot path planning system and method based on scanner visual guidance |
| Publication Number | Publication Date |
|---|---|
| CN116901079Atrue CN116901079A (en) | 2023-10-20 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311047256.3APendingCN116901079A (en) | 2023-08-17 | 2023-08-17 | A robot path planning system and method based on scanner visual guidance |
| Country | Link |
|---|---|
| CN (1) | CN116901079A (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118123860A (en)* | 2024-04-17 | 2024-06-04 | 深圳职业技术大学 | Assembling robot and assembling method for special-shaped curved surface fittings in helicopter |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105834735A (en)* | 2016-04-19 | 2016-08-10 | 北京航空航天大学 | Automatic part assembling method based on laser tracker |
| WO2019138111A1 (en)* | 2018-01-15 | 2019-07-18 | Technische Universität München | Vision-based sensor system and control method for robot arms |
| CN114061486A (en)* | 2021-11-19 | 2022-02-18 | 南京航空航天大学 | Automatic measuring device and method for large-scale skin curved surface of airplane |
| CN114434036A (en)* | 2022-03-18 | 2022-05-06 | 南京航空航天大学 | Three-dimensional vision system and operation method for gantry robot welding of large ship structures |
| US20230150125A1 (en)* | 2020-04-27 | 2023-05-18 | Scalable Robotics Inc. | Robot Teaching with Scans and Geometries |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105834735A (en)* | 2016-04-19 | 2016-08-10 | 北京航空航天大学 | Automatic part assembling method based on laser tracker |
| WO2019138111A1 (en)* | 2018-01-15 | 2019-07-18 | Technische Universität München | Vision-based sensor system and control method for robot arms |
| US20230150125A1 (en)* | 2020-04-27 | 2023-05-18 | Scalable Robotics Inc. | Robot Teaching with Scans and Geometries |
| CN114061486A (en)* | 2021-11-19 | 2022-02-18 | 南京航空航天大学 | Automatic measuring device and method for large-scale skin curved surface of airplane |
| CN114434036A (en)* | 2022-03-18 | 2022-05-06 | 南京航空航天大学 | Three-dimensional vision system and operation method for gantry robot welding of large ship structures |
| Title |
|---|
| 梁延德等: "基于工业机器人的三维扫描技术研究", 组合机床与自动化加工技术, no. 2018, 31 August 2018 (2018-08-31), pages 57 - 59* |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118123860A (en)* | 2024-04-17 | 2024-06-04 | 深圳职业技术大学 | Assembling robot and assembling method for special-shaped curved surface fittings in helicopter |
| Publication | Publication Date | Title |
|---|---|---|
| US11648683B2 (en) | Autonomous welding robots | |
| CN114474041B (en) | Welding automation intelligent guiding method and system based on cooperative robot | |
| CN103678754B (en) | Information processor and information processing method | |
| CN110202573B (en) | Full-automatic hand-eye calibration and working plane calibration method and device | |
| CN110176078B (en) | Method and device for labeling training set data | |
| JP5113666B2 (en) | Robot teaching system and display method of robot operation simulation result | |
| CN103759635A (en) | Scanning measurement robot detection method allowing precision to be irrelevant to robot | |
| CN117381788A (en) | High-precision positioning and intelligent operation guiding method for composite robot | |
| CN115685988A (en) | A method and device for automatically generating spraying paths on free-form surfaces | |
| CN116901079A (en) | A robot path planning system and method based on scanner visual guidance | |
| US20230375334A1 (en) | Metrology 3d scanning system and method | |
| US20220410394A1 (en) | Method and system for programming a robot | |
| CN117436255A (en) | Virtual-real-fusion robot welding process evaluation method and system | |
| US20020120359A1 (en) | System and method for planning a tool path along a contoured surface | |
| Pachidis et al. | Vision-based path generation method for a robot-based arc welding system | |
| JP3765061B2 (en) | Offline teaching system for multi-dimensional coordinate measuring machine | |
| CN114888794B (en) | Robot man-machine interaction running path marking method and device | |
| Motta | An investigation of singularities in robot kinematic chains aiming at building robot calibration models for off-line programming | |
| CN113836745B (en) | Simulation system and method for intelligent inspection device | |
| CN119596823B (en) | Perception control system of mechanical lattice sand table module | |
| WO2025156086A1 (en) | Method, apparatus, device, medium and product for controlling a robot | |
| Filaretov et al. | A new approach to automatization of non-rigid parts machining at their deformation by using multilink manipulators with vision system | |
| Yang et al. | An Automatic Laser Scanning System for Objects with Unknown Model | |
| Idrees | Development of an automated industrial painting system with optimized quality and energy consumption | |
| CN119468975A (en) | A three-dimensional automatic scanning and measuring device and method for parts |
| 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 |