导向控制方法、装置、安检车辆、介质和程序产品Guidance control method, device, security vehicle, medium and program product
技术领域technical field
本公开的实施例涉及安全检查领域,具体涉及一种导向控制方法、装置、安检车辆、介质和程序产品。Embodiments of the present disclosure relate to the field of security inspection, and in particular, to a guidance control method, device, security inspection vehicle, medium, and program product.
背景技术Background technique
在安检车辆对被检查对象进行安全检查时,需要对车体进行导向控制以使得被检查对象相对地穿过安检车辆的安检门,从而实现安全检查。一种处理方式下,安检车辆的自动导向***大多使用单线激光雷达进行环境感知。由于单线激光雷达的检测能力有限,由单线激光雷达获取的检测信息仅支持针对安检车辆的直线导向控制。并且,由于单线激光雷达存在大面积检测盲区,导致安检车辆无法对位于检测盲区的障碍物进行有效避让。When a security inspection vehicle performs a security inspection on an object to be inspected, the vehicle body needs to be guided and controlled so that the object to be inspected relatively passes through the security inspection door of the security inspection vehicle, thereby realizing the security inspection. In one processing method, most of the automatic guidance systems of security inspection vehicles use single-line LiDAR for environmental perception. Due to the limited detection capability of single-line lidar, the detection information obtained by single-line lidar only supports linear guidance control for security inspection vehicles. In addition, because the single-line lidar has a large detection blind spot, the security inspection vehicle cannot effectively avoid obstacles located in the detection blind spot.
发明内容SUMMARY OF THE INVENTION
根据本公开实施例,提出了一种导向控制方法、装置、安检车辆、介质和程序产品。According to the embodiments of the present disclosure, a guidance control method, device, security inspection vehicle, medium and program product are provided.
在本公开的一个方面,提出了一种导向控制方法,应用于安检车辆,安检车辆包括车体、安检门和至少一个多线激光雷达。该方法包括:利用上述至少一个多线激光雷达获取安检车辆的环境点云数据;基于环境点云数据,确定位于安检车辆的外部环境中的多个基准物的位置信息;然后,基于多个基准物的位置信息,确定引导路径;接着,基于引导路径,对所述车体进行导向控制。其中,当安检车辆处于安检状态时,经过导向控制的车体带动安检门相对于位于外部环境中的被检查对象运动,以使被检查对象穿过安检门。In one aspect of the present disclosure, a guidance control method is proposed, which is applied to a security inspection vehicle. The security inspection vehicle includes a vehicle body, a security inspection door, and at least one multi-line laser radar. The method includes: using the above at least one multi-line laser radar to obtain environmental point cloud data of the security inspection vehicle; based on the environmental point cloud data, determining the position information of multiple reference objects located in the external environment of the security inspection vehicle; then, based on the plurality of benchmarks The position information of the object is used to determine a guide path; then, based on the guide path, the vehicle body is guided and controlled. Wherein, when the security inspection vehicle is in the security inspection state, the vehicle body under the guidance control drives the security inspection door to move relative to the inspected object located in the external environment, so that the inspected object passes through the security inspection door.
根据本公开实施例,上述至少一个多线激光雷达包括多个多线激光雷达。上述利用至少一个多线激光雷达获取安检车辆的环境点云数据包括:针对任一时刻,由多个多线激光雷达分别获取各自的点云数据。并且,将多个多线激光雷达中每个多线激光雷达的点云数据从每个多线激光雷达的坐标系转换至基准坐标系,以形成该任一时刻的环境点云数据。According to an embodiment of the present disclosure, the above-mentioned at least one multi-line lidar includes a plurality of multi-line lidars. The above-mentioned use of at least one multi-line laser radar to obtain the environmental point cloud data of the security inspection vehicle includes: at any moment, obtaining respective point cloud data from a plurality of multi-line laser radars. And, the point cloud data of each multi-line lidar in the multiple multi-line lidars are converted from the coordinate system of each multi-line lidar to the reference coordinate system to form the environmental point cloud data at any moment.
根据本公开实施例,上述方法还包括:在上述将多个多线激光雷达中每个多线激光雷达的点云数据从每个多线激光雷达的坐标系转换至基准 坐标系之前,基于每个多线激光雷达相对于车体的位置关系,确定每个多线激光雷达的坐标系与基准坐标系之间的旋转变换关系和平移变换关系。上述将多个多线激光雷达中每个多线激光雷达的点云数据从每个多线激光雷达的坐标系转换至基准坐标系包括:根据上述旋转变换关系和平移变换关系,将每个多线激光雷达的点云数据从每个多线激光雷达的坐标系转换至基准坐标系。According to an embodiment of the present disclosure, the method further includes: before converting the point cloud data of each multi-line lidar in the plurality of multi-line lidars from the coordinate system of each multi-line lidar to the reference coordinate system, based on each The positional relationship of each multi-line laser radar relative to the vehicle body is determined, and the rotational transformation relationship and translation transformation relationship between the coordinate system of each multi-line laser radar and the reference coordinate system are determined. The above-mentioned conversion of the point cloud data of each multi-line laser radar in the plurality of multi-line laser radars from the coordinate system of each multi-line laser radar to the reference coordinate system includes: The point cloud data of the line lidar is transformed from the coordinate system of each multi-line lidar to the reference coordinate system.
根据本公开实施例,上述方法还包括:在上述将多个多线激光雷达中每个多线激光雷达的点云数据从每个多线激光雷达的坐标系转换至基准坐标系之前,由每个多线激光雷达获取针对预定靶标的检测数据,并利用随机采样一致性算法从检测数据中提取用于表征预定靶标的同名向量表示和同名点表示。然后,基于罗德里格斯旋转方程对多个多线激光雷达各自的同名向量表示进行处理,以得到多个多线激光雷达中的任意一个多线激光雷达的坐标系与基准坐标系之间的旋转变换关系。并且,基于述多个多线激光雷达各自的同名点表示,确定多个多线激光雷达中的任意一个多线激光雷达的坐标系与基准坐标系之间的平移变换关系。在此基础上,上述将多个多线激光雷达中每个多线激光雷达的点云数据从每个多线激光雷达的坐标系转换至基准坐标系包括:根据多个多线激光雷达中的任意一个多线激光雷达的坐标系与基准坐标系之间的旋转变换关系和平移变换关系,将多个多线激光雷达的点云数据从多个多线激光雷达各自的坐标系转换至基准坐标系。According to an embodiment of the present disclosure, the above method further includes: before converting the point cloud data of each multi-line lidar in the plurality of multi-line lidars from the coordinate system of each multi-line lidar to the reference coordinate system, converting each A multi-line lidar obtains detection data for a predetermined target, and uses a random sampling consensus algorithm to extract the same-name vector representation and the same-name point representation for characterizing the predetermined target from the detection data. Then, based on the Rodrigues rotation equation, the respective vector representations of the same name of multiple multi-line lidars are processed to obtain the relationship between the coordinate system of any one of the multiple multi-line lidars and the reference coordinate system. Rotation transformation relationship. In addition, based on the point representation of the same name of each of the plurality of multi-line lidars, the translational transformation relationship between the coordinate system of any one of the plurality of multi-line lidars and the reference coordinate system is determined. On this basis, converting the point cloud data of each multi-line lidar in the multiple multi-line lidars from the coordinate system of each multi-line lidar to the reference coordinate system includes: The rotation transformation relationship and translation transformation relationship between the coordinate system of any multi-line lidar and the reference coordinate system, and the point cloud data of multiple multi-line lidars are converted from the respective coordinate systems of multiple multi-line lidars to reference coordinates. Tie.
根据本公开实施例,上述基于环境点云数据,确定位于安检车辆的外部环境中的多个基准物的位置信息包括:从环境点云数据中提取第一特征点云数据;对第一特征点云数据进行聚类,以得到多个聚类结果,该多个聚类结果分别作为多个基准物各自的子点云数据。然后,基于多个基准物各自的子点云数据,确定多个基准物各自的位置信息。According to an embodiment of the present disclosure, the above-mentioned determining the position information of multiple reference objects located in the external environment of the security inspection vehicle based on the environmental point cloud data includes: extracting first feature point cloud data from the environmental point cloud data; The cloud data is clustered to obtain multiple clustering results, and the multiple clustering results are respectively used as sub-point cloud data of multiple reference objects. Then, based on the sub-point cloud data of each of the plurality of reference objects, position information of each of the plurality of reference objects is determined.
根据本公开实施例,上述基于多个基准物的位置信息,确定引导路径包括:基于多个基准物各自的位置信息,进行曲线拟合,以得到拟合车道线。并且,基于所述拟合车道线,确定引导线,使得引导线上任一点与拟合车道线之间的距离为预定圆的半径。According to an embodiment of the present disclosure, the above-mentioned determining the guide path based on the position information of the plurality of reference objects includes: performing curve fitting based on the respective position information of the plurality of reference objects to obtain a fitted lane line. And, based on the fitting lane line, a guide line is determined so that the distance between any point on the guide line and the fitting lane line is the radius of a predetermined circle.
根据本公开实施例,上述预定圆的半径大于安检车辆的外接圆的半径。According to the embodiment of the present disclosure, the radius of the predetermined circle is larger than the radius of the circumscribed circle of the security inspection vehicle.
根据本公开实施例,上述方法还包括:从任一时刻的环境点云数据中提取第二特征点云数据;利用预定匹配算法,对任一时刻的第二特征点云数据与该任一时刻的在前一个时刻的第二特征点云数据之间进行匹配,以确定旋转矩阵和平移矩阵。然后基于旋转矩阵和平移矩阵,确定安检车辆在该任一时刻的姿态变化信息。According to an embodiment of the present disclosure, the above method further includes: extracting second feature point cloud data from environmental point cloud data at any moment; using a predetermined matching algorithm to compare the second feature point cloud data at any moment with the moment match between the second feature point cloud data at the previous moment to determine the rotation matrix and translation matrix. Then, based on the rotation matrix and the translation matrix, the attitude change information of the security inspection vehicle at any moment is determined.
根据本公开实施例,上述基于引导路径,对车体进行导向控制包括:根据引导路径和姿态变化信息,确定针对安检车辆的牵引力的大小和方向。再基于牵引力对车体进行导向控制。According to an embodiment of the present disclosure, the above-mentioned guiding control of the vehicle body based on the guiding path includes: determining the magnitude and direction of the traction force for the security inspection vehicle according to the guiding path and attitude change information. The body is then guided and controlled based on the traction force.
根据本公开实施例,上述方法还包括:基于环境点云数据,确定车体的轮廓信息以及至少一个障碍物的轮廓信息;然后针对上述至少一个障碍物中的每个障碍物,基于车体的轮廓信息和该障碍物的轮廓信息,确定车体与该障碍物之间的距离,并基于二者之间的距离确定排斥力的大小和方向。根据引导路径和姿态变化信息,确定针对安检车辆的牵引力的大小和方向。接着,基于牵引力以及针对上述至少一个障碍物的排斥力,确定综合牵引力,并基于该综合牵引力对车体进行导向控制。According to an embodiment of the present disclosure, the above method further includes: determining the contour information of the vehicle body and the contour information of at least one obstacle based on the environmental point cloud data; and then, for each obstacle in the at least one obstacle, based on the The contour information and the contour information of the obstacle determine the distance between the vehicle body and the obstacle, and determine the magnitude and direction of the repulsive force based on the distance between the two. According to the guidance path and attitude change information, determine the magnitude and direction of the traction force for the security inspection vehicle. Next, based on the traction force and the repulsive force with respect to the at least one obstacle, a comprehensive traction force is determined, and the vehicle body is guided and controlled based on the comprehensive traction force.
根据本公开实施例,上述基于牵引力以及针对上述至少一个障碍物的排斥力,确定综合牵引力包括:利用预设的第一权重和第二权重,对牵引力以及针对上述至少一个障碍物的排斥力进行加权求和,以得到综合牵引力。According to an embodiment of the present disclosure, the above-mentioned determining the comprehensive traction force based on the traction force and the repulsive force against the at least one obstacle includes: using a preset first weight and a second weight to perform a calculation on the traction force and the repulsive force against the at least one obstacle. Weighted summation to get combined traction.
在本公开的另一个方面,提出了一种导向控制装置,应用于安检车辆,安检车辆包括车体、安检门和至少一个多线激光雷达。导向控制装置包括:获取模块、第一确定模块、第二确定模块和控制模块。获取模块用于利用上述至少一个多线激光雷达获取安检车辆的环境点云数据。第一确定模块用于基于环境点云数据,确定位于安检车辆的外部环境中的多个基准物的位置信息。第二确定模块用于基于多个基准物的位置信息,确定引导路径。控制模块用于基于引导路径,对所述车体进行导向控制。其中,当安检车辆处于安检状态时,经过导向控制的车体带动安检门相对于位于外部环境中的被检查对象运动,以使被检查对象穿过安检门。In another aspect of the present disclosure, a guidance control device is proposed, which is applied to a security inspection vehicle. The security inspection vehicle includes a vehicle body, a security inspection door, and at least one multi-line laser radar. The guidance control device includes: an acquisition module, a first determination module, a second determination module and a control module. The acquisition module is used for acquiring the environmental point cloud data of the security inspection vehicle by using the above at least one multi-line laser radar. The first determining module is configured to determine, based on the environmental point cloud data, position information of multiple reference objects located in the external environment of the security inspection vehicle. The second determining module is configured to determine the guiding path based on the position information of the plurality of reference objects. The control module is used for guiding and controlling the vehicle body based on the guiding path. Wherein, when the security inspection vehicle is in the security inspection state, the vehicle body under the guidance control drives the security inspection door to move relative to the inspected object located in the external environment, so that the inspected object passes through the security inspection door.
在本公开的另一个方面,提出了一种安检车辆,包括:车体、安检门、至少一个多线激光雷达、存储器和至少一个处理器。存储器用于存储指令。 至少一个处理器执行存储在存储器中的指令,以实现如上任一实施例所述的方法。In another aspect of the present disclosure, a security inspection vehicle is proposed, comprising: a vehicle body, a security inspection door, at least one multi-line laser radar, a memory, and at least one processor. Memory is used to store instructions. At least one processor executes instructions stored in memory to implement a method as described in any of the above embodiments.
根据本公开实施例,当上述至少一个多线激光雷达包括多个多线激光雷达时,多个多线激光雷达中的至少两个多线激光雷达分散分布于车体外侧,以使该至少两个多线激光雷达的扫描范围覆盖车体周边360°。According to the embodiment of the present disclosure, when the above-mentioned at least one multi-line lidar includes a plurality of multi-line lidars, at least two multi-line lidars in the plurality of multi-line lidars are distributed outside the vehicle body, so that the at least two multi-line lidars are distributed outside the vehicle body. The scanning range of the two multi-line lidars covers 360° around the vehicle body.
根据本公开实施例,多个多线激光雷达中除所述至少两个多线激光雷达之外的至少一个多线激光雷达位于安检门的内侧。According to an embodiment of the present disclosure, at least one of the multiple multi-line laser radars other than the at least two multi-line laser radars is located inside the security gate.
在本公开的另一个方面,提出了一种计算机可读存储介质,其上存储有计算机指令,该计算机指令被处理器执行时实现如上任一实施例所述的方法。In another aspect of the present disclosure, a computer-readable storage medium is provided with computer instructions stored thereon, the computer instructions implementing the method described in any of the above embodiments when executed by a processor.
在本公开的另一个方面,提出了一种计算机程序产品,包括可执行指令,该指令被处理器执行时实现如上任一实施例所述的方法。In another aspect of the present disclosure, a computer program product is proposed, comprising executable instructions that, when executed by a processor, implement the method as described in any of the above embodiments.
根据本公开实施例的导向控制方案,针对处于安检状态下的安检车辆,利用至少一个多线激光雷达采集环境点云数据,基于该环境点云数据进行路径规划并进行导向控制,以使被检查物体相对地穿过安检车辆中的安检门。由于多线激光雷达具有相对更大的检测范围和更小的检测盲区,对周围环境信息的识别能力与抗干扰性更强,能够获取更为精确、全面的环境点云数据。该环境点云数据能够支持针对安检车辆在各种场所下进行各种类型路径的导向控制,提高了安检车辆的导向控制的环境适应性和灵活性,进而提高了安检车辆进行安全检查的适用范围。According to the guidance control solution of the embodiment of the present disclosure, for a security inspection vehicle in a security inspection state, at least one multi-line laser radar is used to collect environmental point cloud data, and path planning and guidance control are performed based on the environmental point cloud data, so that the inspected Objects relatively pass through a security gate in a security vehicle. Because multi-line lidar has a relatively larger detection range and smaller detection blind area, it has stronger ability to identify surrounding environmental information and anti-interference, and can obtain more accurate and comprehensive environmental point cloud data. The environmental point cloud data can support the guidance control of various types of paths for security inspection vehicles in various places, improve the environmental adaptability and flexibility of the guidance control of security inspection vehicles, and further improve the scope of application of security inspection vehicles for security inspections .
附图说明Description of drawings
为了更好地理解本公开实施例,将根据以下附图对本公开实施例进行详细描述:For a better understanding of the embodiments of the present disclosure, the embodiments of the present disclosure will be described in detail according to the following drawings:
图1示意性示出了根据本公开实施例的导向控制方法和装置的应用场景;FIG. 1 schematically shows an application scenario of the steering control method and apparatus according to an embodiment of the present disclosure;
图2示意性示出了根据本公开实施例的导向控制方法的流程图;FIG. 2 schematically shows a flowchart of a steering control method according to an embodiment of the present disclosure;
图3示意性示出了根据本公开实施例的安检车辆利用多线激光雷达进行环境感知的示例图;FIG. 3 schematically shows an example diagram of environment perception by a security inspection vehicle using a multi-line lidar according to an embodiment of the present disclosure;
图4示意性示出了根据本公开实施例的安检车辆的示例俯视图;FIG. 4 schematically shows an example top view of a security inspection vehicle according to an embodiment of the present disclosure;
图5A~图5B示意性示出了根据本公开另一实施例的安检车辆的示例 俯视图;5A-5B schematically illustrate example top views of a security inspection vehicle according to another embodiment of the present disclosure;
图6A~图6C示意性示出了根据本公开实施例的确定引导路径的过程示例图;6A-6C schematically illustrate exemplary diagrams of a process of determining a guide path according to an embodiment of the present disclosure;
图7示意性示出了根据本公开实施例的导向控制装置的框图;以及FIG. 7 schematically shows a block diagram of a steering control apparatus according to an embodiment of the present disclosure; and
图8示意性示出了根据本公开的实施例的适于实现上文描述的方法的安检车辆的示例结构图。FIG. 8 schematically shows an example structural diagram of a security inspection vehicle suitable for implementing the above-described method according to an embodiment of the present disclosure.
具体实施方式detailed description
下面将详细描述本公开实的具体实施例,应当注意,这里描述的实施例只用于举例说明,并不用于限制本公开实施例。在以下描述中,为了提供对本公开实施例的透彻理解,阐述了大量特定细节。然而,对于本领域普通技术人员显而易见的是:不必采用这些特定细节来实行本公开实施例。在其他实例中,为了避免混淆本公开实施例,未具体描述公知的结构、材料或方法。Specific embodiments of the present disclosure will be described in detail below. It should be noted that the embodiments described herein are only used for illustration and are not used to limit the embodiments of the present disclosure. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. It will be apparent, however, to one of ordinary skill in the art that these specific details need not be employed to practice embodiments of the present disclosure. In other instances, well-known structures, materials, or methods have not been described in detail in order to avoid obscuring the disclosed embodiments.
在整个说明书中,对“一个实施例”、“实施例”、“一个示例”或“示例”的提及意味着:结合该实施例或示例描述的特定特征、结构或特性被包含在本公开至少一个实施例中。因此,在整个说明书的各个地方出现的短语“在一个实施例中”、“在实施例中”、“一个示例”或“示例”不一定都指同一实施例或示例。此外,可以以任何适当的组合和/或子组合将特定的特征、结构或特性组合在一个或多个实施例或示例中。此外,本领域普通技术人员应当理解,这里使用的术语“和/或”包括一个或多个相关列出的项目的任何和所有组合。Throughout this specification, references to "one embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in the present disclosure in at least one embodiment. Thus, appearances of the phrases "in one embodiment," "in an embodiment," "one example," or "an example" in various places throughout this specification are not necessarily all referring to the same embodiment or example. Furthermore, the particular features, structures or characteristics may be combined in any suitable combination and/or subcombination in one or more embodiments or examples. Furthermore, those of ordinary skill in the art should understand that as used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
本公开的实施例提出了一种应用于安检车辆的导向控制方法和装置、安检车辆、介质和程序产品。其中,安检车辆可以包括车体、安检门和至少一个多线激光雷达。导向控制方法可以包括获取过程、第一确定过程、第二确定过程和控制过程。在获取过程,利用安检车辆的至少一个多线激光雷达获取安检车辆的环境点云数据。然后基于所获取的环境点云数据进行第一确定过程,以确定位于安检车辆的外部环境中的多个基准物的位置信息。再基于多个基准物的位置信息进行第二确定过程,以确定引导路径。接着基于引导路径进行控制过程,即对安检车辆的车体进行导向控制。其中,当安检车辆处于安检状态时,经过导向控制的车体带动安检门相对于 位于外部环境中的被检查对象运动,以使被检查对象穿过安检门。Embodiments of the present disclosure provide a guidance control method and device applied to a security inspection vehicle, a security inspection vehicle, a medium, and a program product. Wherein, the security inspection vehicle may include a vehicle body, a security inspection door and at least one multi-line laser radar. The steering control method may include an acquisition process, a first determination process, a second determination process, and a control process. In the acquisition process, at least one multi-line laser radar of the security inspection vehicle is used to acquire environmental point cloud data of the security inspection vehicle. Then, a first determination process is performed based on the acquired environment point cloud data to determine the position information of a plurality of reference objects located in the external environment of the security inspection vehicle. A second determination process is then performed based on the position information of the plurality of reference objects to determine the guide path. Next, the control process is performed based on the guidance path, that is, the guidance control is performed on the body of the security inspection vehicle. Wherein, when the security inspection vehicle is in the security inspection state, the vehicle body under the guidance control drives the security inspection door to move relative to the inspected object located in the external environment, so that the inspected object passes through the security inspection door.
图1示意性示出了根据本公开实施例的导向控制方法和装置的应用场景。需要注意的是,图1所示仅为可以应用本公开实施例的场景的示例,以帮助本领域技术人员理解本公开的技术内容,但并不意味着本公开实施例不可以用于其他设备、***、环境或场景。FIG. 1 schematically shows an application scenario of a steering control method and apparatus according to an embodiment of the present disclosure. It should be noted that FIG. 1 is only an example of a scenario to which the embodiments of the present disclosure can be applied, so as to help those skilled in the art to understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be applied to other devices , system, environment or scene.
如图1所示,示例性地展示了安检车辆110针对被检查对象120进行安全检查的场景。需要说明的是,本例及后文中参照车体坐标系o-xyz进行描述,其中x方向和y方向均平行于水平面,且x方向和y方向相互垂直,z方向垂直于水平面。本例中安检车辆110可以包括车体111、至少一个激光雷达112和安检门113。至少一个激光雷达112用于在安检车辆110行驶或静止过程中获取安检车辆110的环境信息。安检车辆110基于该环境信息可以对车体运动进行导向控制。当安检车辆110处于安检状态下,车体111与安检门113固定连接,车体111的运动可带动安检门113相对于被检查对象120运动,以使得被检查对象120穿过安检门113。例如,安检门113作为X射线检测设备,对穿过其中的被检查对象120进行X射线扫描,以获得被检查对象120的X射线透视图。示例性地,安检车辆110可以在如海关、港口、边境口岸等场所中针对如集装箱、大型车辆、小型车辆等被检查对象进行安全检查。通过X射线投射扫描图像确定被检查对象内部的货物材质、体积、数量等与核查清单是否相符,以及确定被检查对象是否存在危险物品和违禁物品等。As shown in FIG. 1 , a scene in which the security inspection vehicle 110 performs security inspection on the inspected object 120 is exemplarily shown. It should be noted that this example and the following are described with reference to the vehicle body coordinate system o-xyz, where the x and y directions are parallel to the horizontal plane, the x and y directions are perpendicular to each other, and the z direction is perpendicular to the horizontal plane. In this example, the security inspection vehicle 110 may include a vehicle body 111 , at least one lidar 112 and a security inspection door 113 . At least one lidar 112 is used to acquire environmental information of the security inspection vehicle 110 when the security inspection vehicle 110 is moving or stationary. Based on the environmental information, the security inspection vehicle 110 can guide and control the movement of the vehicle body. When the security inspection vehicle 110 is in the security inspection state, the vehicle body 111 is fixedly connected to the security inspection door 113 , and the movement of the vehicle body 111 can drive the security inspection door 113 to move relative to the inspected object 120 , so that the inspected object 120 passes through the security inspection door 113 . For example, the security gate 113 acts as an X-ray detection device, and performs X-ray scanning on the object under inspection 120 passing through it, so as to obtain an X-ray perspective view of the object under inspection 120 . Exemplarily, the security inspection vehicle 110 may perform security inspection on inspected objects such as containers, large vehicles, and small vehicles in places such as customs, ports, border crossings, and the like. Through the X-ray projection scanning image, it is determined whether the material, volume, quantity, etc. of the goods inside the inspected object are consistent with the checklist, and whether the inspected object has dangerous goods and prohibited items, etc.
在图1所示的例子中,当安检车辆处于安检状态时,安检门位于车体的一侧的外部,在其他例子中,安检门也可以位于车体的内部。被检查对象可以是运动或静止的。In the example shown in FIG. 1 , when the security inspection vehicle is in the security inspection state, the security inspection door is located outside one side of the vehicle body. In other examples, the security inspection door may also be located inside the vehicle body. The inspected object can be moving or stationary.
需要说明的是,本公开实施例所提供的导向控制方法可以由上述安检车辆110执行。相应地,本公开实施例所提供的导向控制装置可以设置于安检车辆110中。或者,本公开实施例所提供的导向控制方法也可以由不同于安检车辆110且能够与安检车辆110通信的服务器或服务器集群执行。相应地,本公开实施例所提供的导向控制装置也可以设置于不同于安检车辆110且能够与安检车辆110通信的服务器或服务器集群中。It should be noted that, the guidance control method provided by the embodiment of the present disclosure may be executed by the above-mentioned security inspection vehicle 110 . Correspondingly, the guidance control device provided by the embodiment of the present disclosure may be provided in the security inspection vehicle 110 . Alternatively, the guidance control method provided by the embodiment of the present disclosure may also be executed by a server or a server cluster that is different from the security inspection vehicle 110 and can communicate with the security inspection vehicle 110 . Correspondingly, the guidance control device provided by the embodiment of the present disclosure may also be provided in a server or a server cluster that is different from the security inspection vehicle 110 and can communicate with the security inspection vehicle 110 .
基于以上应用场景,在安检车辆对被检查对象进行安全检查时,需要 对车体进行导向控制以使得被检查对象相对地穿过安检车辆的安检门,从而实现安全检查。一种处理方式下,安检车辆的自动导向控制***大多使用单线激光雷达进行环境感知。由于单线激光雷达的检测能力有限,仅能够发射一条探测扫描线,且水平扫描角度最大仅可覆盖190°,环境识别能力较弱,对工作场地平整度与基准物的布置方式要求比较严格,环境适应性差。由单线激光雷达获取的检测信息仅支持针对安检车辆的直线导向控制,无法控制安检车辆进行转弯等运动。此外,由于单线激光雷达存在大面积检测盲区,导致安检车辆无法对位于检测盲区的障碍物进行有效避让。Based on the above application scenarios, when a security inspection vehicle conducts a safety inspection on the object to be inspected, it is necessary to conduct guidance control on the vehicle body so that the object to be inspected relatively passes through the security inspection door of the security inspection vehicle, so as to realize the safety inspection. In one processing method, most of the automatic guidance control systems of security inspection vehicles use single-line LiDAR for environmental perception. Due to the limited detection capability of single-line lidar, only one detection scan line can be emitted, and the maximum horizontal scanning angle can only cover 190°. The environment recognition ability is weak, and the requirements for the flatness of the workplace and the arrangement of the reference objects are relatively strict. Poor adaptability. The detection information obtained by the single-line lidar only supports the straight-line guidance control for the security inspection vehicle, and cannot control the security inspection vehicle to make turns and other movements. In addition, because the single-line lidar has a large detection blind spot, the security inspection vehicle cannot effectively avoid obstacles located in the detection blind spot.
根据本公开实施例,提供了一种导向控制方法,以进一步提高导向控制的环境适应性和灵活性。下面通过图例对该方法进行示例性说明。应注意,以下方法中各个操作的序号仅作为该操作的表示以便描述,而不应被看作表示该各个操作的执行顺序。除非明确指出,否则该方法不需要完全按照所示顺序来执行。According to the embodiments of the present disclosure, a steering control method is provided to further improve the environmental adaptability and flexibility of the steering control. The method is exemplified below by means of a legend. It should be noted that the sequence numbers of the respective operations in the following methods are only used as representations of the operations for the convenience of description, and should not be regarded as representing the execution order of the respective operations. The methods need not be performed in the exact order shown unless explicitly stated.
图2示意性示出了根据本公开实施例的导向控制方法的流程图。该导向控制方法可以应用于如图1所示的安检车辆,该安检车辆可以包括车体、安检门和至少一个多线激光雷达。FIG. 2 schematically shows a flowchart of a steering control method according to an embodiment of the present disclosure. The guidance control method can be applied to a security inspection vehicle as shown in FIG. 1 , and the security inspection vehicle may include a vehicle body, a security inspection door and at least one multi-line laser radar.
如图2所示,导向控制方法可以包括以下操作S210~S240。As shown in FIG. 2, the guidance control method may include the following operations S210-S240.
在操作S210,利用上述至少一个多线激光雷达获取安检车辆的环境点云数据。In operation S210, the environment point cloud data of the security inspection vehicle is acquired by using the above at least one multi-line lidar.
激光雷达作为安检车辆环境感知最为重要的传感器之一,不同的安装与使用方式,对环境感知的结果影响也不同。根据本公开的实施例,对安检车辆的自动导向***进行改进,以至少一个多线激光雷达代替单线激光雷达来进行环境感知。环境感知可以包括针对安检车辆自身姿态信息、轮廓信息的感知以及针对安检车辆的外部环境信息的感知。相较于单线激光雷达,多线激光雷达具有更大的检测范围和更小的检测盲区,能够实现更为准确的环境感知。多线激光雷达例如包括4线、16线、32线和64线激光雷达等,下面以16线激光雷达为例进行示例性说明。Lidar is one of the most important sensors for environmental perception of security inspection vehicles. Different installation and use methods have different effects on the results of environmental perception. According to the embodiments of the present disclosure, the automatic guidance system of the security inspection vehicle is improved, and at least one multi-line laser radar is used instead of the single-line laser radar for environmental perception. The environmental perception may include the perception of the security inspection vehicle's own posture information and contour information, and the perception of the external environment information of the security inspection vehicle. Compared with single-line lidar, multi-line lidar has a larger detection range and smaller detection blind area, which can achieve more accurate environmental perception. Multi-line lidars include, for example, 4-line, 16-line, 32-line, and 64-line lidars, etc. The 16-line lidar is used as an example for illustration below.
图3示意性示出了根据本公开实施例的安检车辆利用多线激光雷达进行环境感知的示例图。如图3所示,安检车辆310包括车体311和至少一 个多线激光雷达312,多线激光雷达312例如为16线激光雷达。16线激光雷达水平扫描范围可以达到360°,垂直方向扫描线达到16条,以2°的角度间隔均匀分布,扫描角度范围是-15°~+15°。与单线激光雷达相比,对周围环境信息的识别能力与抗干扰性更强,能够获取环境中基准物、障碍物等的稳定信息。在图3所示的例子中,安检车辆310的外部环境中存在基准物320。利用多线激光雷达312所获取的环境点云数据能够反映该基准物320的三维信息。FIG. 3 schematically shows an example diagram of environment perception by a security inspection vehicle using a multi-line lidar according to an embodiment of the present disclosure. As shown in FIG. 3 , the security inspection vehicle 310 includes a vehicle body 311 and at least one multi-line laser radar 312, and the multi-line laser radar 312 is, for example, a 16-line laser radar. The horizontal scanning range of the 16-line lidar can reach 360°, and the vertical scanning line can reach 16, which are evenly distributed at 2° angular intervals, and the scanning angle range is -15° to +15°. Compared with single-line LiDAR, it has stronger recognition ability and anti-interference ability for surrounding environment information, and can obtain stable information of reference objects and obstacles in the environment. In the example shown in FIG. 3 , the reference object 320 exists in the external environment of the security inspection vehicle 310 . The environmental point cloud data acquired by the multi-line lidar 312 can reflect the three-dimensional information of the reference object 320 .
继续参阅图2,在操作S220,基于环境点云数据,确定位于安检车辆的外部环境中的多个基准物的位置信息。Continuing to refer to FIG. 2 , in operation S220, based on the environmental point cloud data, position information of a plurality of reference objects located in the external environment of the security inspection vehicle is determined.
根据本公开的实施例,在进行安检车辆的导向控制时,需要在导向控制场地中预先设置多个基准物,以该多个基准物为参照来确定导向控制的引导路径。本操作S220即基于由多线激光雷达所获取的环境点云数据来确定预先设置的多个基准物的位置信息。According to the embodiments of the present disclosure, when the guidance control of the security inspection vehicle is performed, a plurality of reference objects need to be preset in the guidance control field, and the guidance path of the guidance control is determined by using the plurality of reference objects as a reference. This operation S220 is to determine the position information of a plurality of preset reference objects based on the environmental point cloud data acquired by the multi-line lidar.
在操作S230,基于多个基准物的位置信息,确定引导路径。In operation S230, a guide path is determined based on the position information of the plurality of reference objects.
在操作S240,基于引导路径,对车体进行导向控制。In operation S240, guidance control is performed on the vehicle body based on the guidance path.
根据本公开的实施例,当安检车辆处于安检状态时,经过导向控制的车体带动安检门相对于位于外部环境中的被检查对象运动,以使被检查对象穿过安检门,从而实现针对被检查对象的安全检查。当安检车辆处于非安检状态时,通过上述导向控制过程可以控制车体移动至预定位置、进行场地转移等。示例性地,在进行导向控制过程中,上述操作S210~S240可以周期性地执行,例如每隔预定时间间隔执行一次操作S210~S240,以实现针对安检车辆的实时导向控制。According to the embodiments of the present disclosure, when the security inspection vehicle is in the security inspection state, the vehicle body that has been guided and controlled drives the security inspection door to move relative to the inspected object located in the external environment, so that the inspected object passes through the security inspection door, so as to achieve the goal of targeting the inspected object. Check the object's security check. When the security inspection vehicle is in a non-security inspection state, the vehicle body can be controlled to move to a predetermined position, site transfer, etc., through the above-mentioned guidance control process. Exemplarily, during the guidance control process, the above-mentioned operations S210-S240 may be performed periodically, for example, operations S210-S240 are performed every predetermined time interval, so as to realize real-time guidance control for the security inspection vehicle.
本领域技术人员可以理解,根据本公开实施例的导向控制方法,针对处于安检状态下的安检车辆,利用至少一个多线激光雷达采集环境点云数据,基于该环境点云数据进行路径规划并进行导向控制,以使被检查物体相对地穿过安检车辆中的安检门。由于多线激光雷达具有相对更大的检测范围和更小的检测盲区,对周围环境信息的识别能力与抗干扰性更强,能够获取更为精确、全面的环境点云数据。该环境点云数据能够支持针对安检车辆在各种场所下进行各种类型路径的导向控制,提高了安检车辆的导向控制的环境适应性和灵活性,进而提高了安检车辆进行安全检查的适用 范围。Those skilled in the art can understand that, according to the guidance control method of the embodiment of the present disclosure, for a security inspection vehicle in a security inspection state, at least one multi-line laser radar is used to collect environmental point cloud data, and based on the environmental point cloud data, path planning and Guidance control so that the object to be inspected relatively passes through the security gate in the security vehicle. Because multi-line lidar has a relatively larger detection range and smaller detection blind area, it has stronger ability to identify surrounding environmental information and anti-interference, and can obtain more accurate and comprehensive environmental point cloud data. The environmental point cloud data can support the guidance control of various types of paths for security inspection vehicles in various places, improve the environmental adaptability and flexibility of the guidance control of security inspection vehicles, and further improve the scope of application of security inspection vehicles for security inspections .
根据本公开实施例,为获取到更为全面的环境点云数据,上述至少一个多线激光雷达可以包括多个多线激光雷达。当上述至少一个多线激光雷达包括多个多线激光雷达时,该多个多线激光雷达中的至少两个多线激光雷达分散分布于车体外侧,以使该至少两个多线激光雷达的扫描范围尽可能地覆盖车体周边360°。在一些情况下,由于车体形状或设备遮挡等原因,上述至少两个多线激光雷达的扫描范围无法达到360°。According to the embodiment of the present disclosure, in order to obtain more comprehensive environmental point cloud data, the above-mentioned at least one multi-line laser radar may include multiple multi-line laser radars. When the above-mentioned at least one multi-line lidar includes a plurality of multi-line lidars, at least two multi-line lidars in the plurality of multi-line lidars are distributed outside the vehicle body, so that the at least two multi-line lidars are distributed outside the vehicle body. The scanning range covers 360° around the vehicle body as much as possible. In some cases, the scanning range of the above at least two multi-line lidars cannot reach 360° due to the shape of the vehicle body or the occlusion of equipment.
图4示意性示出了根据本公开实施例的安检车辆的示例俯视图,示例性地展示了多线激光雷达在安检车辆上的一种设置方式。如图4所示,安检车辆410包括车体411和两个多线激光雷达4121~4122。示例性地,在o-xy平面上,两个多线激光雷达4121~4122设置于车体411的外侧,并关于车体411的中心点o对称设置。图4中展示了两个多线激光雷达4121~4122的扫描范围可以覆盖车体411周边360°,从而进一步减小安检车辆中激光雷达的检测盲区甚至实现无检测盲区。FIG. 4 schematically shows an example top view of a security inspection vehicle according to an embodiment of the present disclosure, and exemplarily shows an arrangement of a multi-line laser radar on a security inspection vehicle. As shown in FIG. 4 , the security inspection vehicle 410 includes a vehicle body 411 and two multi-line laser radars 4121 to 4122 . Exemplarily, on the o-xy plane, two multi-line lidars 4121 to 4122 are arranged on the outer side of the vehicle body 411 and symmetrically arranged with respect to the center point o of the vehicle body 411 . Figure 4 shows that the scanning range of the two multi-line lidars 4121-4122 can cover 360° around the vehicle body 411, thereby further reducing the detection blind spot of the lidar in the security inspection vehicle or even realizing no detection blind spot.
下面再结合两个例子对多线激光雷达的设置方式进行示例性说明。图5A示意性示出了根据本公开另一实施例的安检车辆的示例俯视图,图5B示意性示出了根据本公开另一实施例的安检车辆的示例俯视图。In the following, the setting method of the multi-line lidar is exemplarily described with reference to two examples. 5A schematically shows an example top view of a security inspection vehicle according to another embodiment of the present disclosure, and FIG. 5B schematically shows an example top view of a security inspection vehicle according to another embodiment of the present disclosure.
如图5A所示,安检车辆510包括车体511、第一多线激光雷达5121、第二多线激光雷达5122、第三多线激光雷达5123和安检门513。本例中,例如车体511为倒U形结构,安检门513位于车体511内侧,以形成检查通道。在安检过程中,该检查通道供被检查对象主动或被动地经过。第一多线激光雷达5121和第二多线激光雷达5122位于车体511外侧并关于车体511的中心点对称设置,与图4中两个多线激光雷达4121~4122的设置方式相同。第一多线激光雷达5121和第二多线激光雷达5122可以用于获取安检车辆外侧的环境点云数据,基于该环境点云数据例如可以提取外部环境中基准物、障碍物的位置信息和轮廓信息,提取安检车辆的轮廓信息,计算安检车辆的姿态信息等。第三多线激光雷达5123可以布置于安检门513的内侧,可以用于获取检查通道的环境点云数据,基于该环境点云数据可以确定检查通道内的相关信息,例如被检查物体在检查通道内的姿态信息、检查通道内是否存在其他障碍物信息等。As shown in FIG. 5A , the security inspection vehicle 510 includes a vehicle body 511 , a first multi-line lidar 5121 , a second multi-line lidar 5122 , a third multi-line lidar 5123 , and a security gate 513 . In this example, for example, the vehicle body 511 has an inverted U-shaped structure, and the security inspection door 513 is located inside the vehicle body 511 to form an inspection channel. During the security inspection process, the inspection channel is used for the object to be inspected to pass through actively or passively. The first multi-line laser radar 5121 and the second multi-line laser radar 5122 are located on the outside of the vehicle body 511 and are symmetrically arranged with respect to the center point of the vehicle body 511 , in the same manner as the two multi-line laser radars 4121 to 4122 in FIG. 4 . The first multi-line lidar 5121 and the second multi-line lidar 5122 can be used to obtain environmental point cloud data on the outside of the security inspection vehicle. Based on the environmental point cloud data, for example, the position information and contours of reference objects and obstacles in the external environment can be extracted. information, extract the contour information of the security inspection vehicle, calculate the posture information of the security inspection vehicle, etc. The third multi-line lidar 5123 can be arranged inside the security gate 513, and can be used to obtain the environmental point cloud data of the inspection channel. Based on the environmental point cloud data, relevant information in the inspection channel can be determined, for example, the object under inspection is in the inspection channel. attitude information, check whether there are other obstacles in the channel, etc.
如图5B所示,安检车辆510’包括车体511’、第一多线激光雷达5121’、第二多线激光雷达5122’、第三多线激光雷达5123’和安检门513’。本例中,安检车辆510’例如通过臂架展开或收起安检门513’。当安检门513’呈收起状态时,安检车辆510’处于非安检状态,可以进行场地转移等操作。此时,第一多线激光雷达5121’位于安检车辆的头部,第二多线激光雷达5122’位于安检车辆的尾部左侧,第三多线激光雷达5123’位于安检车辆的尾部右侧。三个多线激光雷达均可以用于获取安检车辆外侧的环境点云数据,以实现提取轮廓信息、计算姿态信息及避障功能等。当通过臂架展开安检门513’时,形成检查通道,安检车辆510’可以开始安检操作。此时,第三多线激光雷达5123’处于检查通道内,第三多线激光雷达5123’可以用于获取检查通道内的环境点云数据,以基于该环境点云数据可以确定检查通道内的相关信息,例如提供闯入人员识别、待检车辆车型识别、待检车辆速度位置测量等功能。其中图5B展示了上述处于安检状态的安检车辆510’。As shown in FIG. 5B, the security inspection vehicle 510' includes a vehicle body 511', a first multi-line laser radar 5121', a second multi-line laser radar 5122', a third multi-line laser radar 5123', and a security inspection door 513'. In this example, the security inspection vehicle 510' deploys or retracts the security inspection door 513', for example, through a boom. When the security inspection door 513' is in a retracted state, the security inspection vehicle 510' is in a non-security inspection state, and operations such as site transfer can be performed. At this time, the first multi-line lidar 5121' is located at the head of the security inspection vehicle, the second multi-line lidar 5122' is located on the left side of the rear of the security inspection vehicle, and the third multi-line lidar 5123' is located on the right side of the rear of the security inspection vehicle. All three multi-line lidars can be used to obtain environmental point cloud data outside the security inspection vehicle to extract contour information, calculate attitude information, and avoid obstacles. When the security inspection door 513' is unfolded through the boom, an inspection channel is formed, and the security inspection vehicle 510' can start the security inspection operation. At this time, the third multi-line laser radar 5123' is in the inspection channel, and the third multi-line laser radar 5123' can be used to obtain the environmental point cloud data in the inspection channel, so that the environment point cloud data in the inspection channel can be determined based on the environmental point cloud data. Relevant information, such as the identification of intruders, the identification of the vehicle type to be inspected, and the measurement of the speed and position of the vehicle to be inspected. 5B shows the above-mentioned security inspection vehicle 510' in a security inspection state.
根据本公开的实施例,上述利用至少一个多线激光雷达获取安检车辆的环境点云数据的过程可以包括:针对任一时刻,由多个多线激光雷达分别获取各自的点云数据,并且,将多个多线激光雷达中每个多线激光雷达的点云数据从每个多线激光雷达的坐标系转换至基准坐标系,以形成该任一时刻的环境点云数据。其中,每个多线激光雷达的点云数据是指由每个多线激光雷达所采集的点云数据,每个多线激光雷达的坐标系是指每个多线激光雷达的测量坐标系。本实施例的目的是将多个多线激光雷达各自采集的点云数据融合到同一基准坐标系下,即对多个多线激光雷达进行标定,以形成场景完整的环境点云数据。基准坐标系可以根据实际情况进行选择,例如可以是车体坐标系,或者可以是某一个多线激光雷达自身的坐标系,在此不做限制。According to an embodiment of the present disclosure, the above-mentioned process of obtaining environmental point cloud data of a security inspection vehicle by using at least one multi-line laser radar may include: at any moment, obtaining respective point cloud data from multiple multi-line laser radars, and, The point cloud data of each multi-line lidar in the multiple multi-line lidars are converted from the coordinate system of each multi-line lidar to the reference coordinate system to form environmental point cloud data at any time. Among them, the point cloud data of each multi-line lidar refers to the point cloud data collected by each multi-line lidar, and the coordinate system of each multi-line lidar refers to the measurement coordinate system of each multi-line lidar. The purpose of this embodiment is to fuse the point cloud data collected by multiple multi-line laser radars into the same reference coordinate system, that is, to calibrate multiple multi-line laser radars, so as to form complete environmental point cloud data of the scene. The reference coordinate system can be selected according to the actual situation, for example, it can be the vehicle body coordinate system, or it can be the coordinate system of a certain multi-line laser radar itself, which is not limited here.
示例性地,为完成上述标定过程,需要预先确定各个多线激光雷达自身的坐标系与基准坐标系之间的变换关系。例如,根据本公开实施例的导向控制方法还可以包括:在上述将多个多线激光雷达中每个多线激光雷达的点云数据从每个多线激光雷达的坐标系转换至基准坐标系之前,基于每个多线激光雷达相对于车体的位置关系,确定每个多线激光雷达的坐标系与基准坐标系之间的旋转变换关系和平移变换关系。上述将多个多线激光 雷达中每个多线激光雷达的点云数据从每个多线激光雷达的坐标系转换至基准坐标系包括:根据上述旋转变换关系和平移变换关系,将每个多线激光雷达的点云数据从每个多线激光雷达的坐标系转换至基准坐标系。Exemplarily, in order to complete the above calibration process, the transformation relationship between the coordinate system of each multi-line laser radar itself and the reference coordinate system needs to be predetermined. For example, the guidance control method according to the embodiment of the present disclosure may further include: converting the point cloud data of each multi-line lidar in the plurality of multi-line lidars from the coordinate system of each multi-line lidar to the reference coordinate system Previously, based on the positional relationship of each multi-line lidar relative to the vehicle body, the rotation transformation relationship and translation transformation relationship between the coordinate system of each multi-line lidar and the reference coordinate system were determined. The above-mentioned conversion of the point cloud data of each multi-line laser radar in the plurality of multi-line laser radars from the coordinate system of each multi-line laser radar to the reference coordinate system includes: The point cloud data of the line lidar is transformed from the coordinate system of each multi-line lidar to the reference coordinate system.
例如,一个多线激光雷达的坐标系为S
1,基准坐标系为S
2,两个坐标系之间存在旋转(R)和平移(T)的变换关系,可以按照公式(1)将该多线激光雷达的点云数据从坐标系S
1转换至坐标系S
2。
For example, the coordinate system of a multi-line lidar is S 1 , the reference coordinate system is S 2 , and there is a transformation relationship between the two coordinate systems of rotation (R) and translation (T). The point cloud data of the line lidar is transformed from the coordinate system S 1 to the coordinate system S 2 .
S
2=RS
1+T (1)
S 2 =RS 1 +T (1)
其中,例如R为3×3的旋转变换矩阵,T为3×1的平移变换矩阵。Among them, for example, R is a 3×3 rotation transformation matrix, and T is a 3×1 translation transformation matrix.
在已知安检车辆尺寸及各激光雷达安装位置的情况下,坐标系间的变换关系可基于上述实施例直接得出。在无法获取上述变换关系的情况下,可通过在多个激光雷达的共同观测区中放置标定预定靶标,根据在不同雷达坐标系下检测到的用于表征预定靶标的同名向量和同名点,采用罗德里格斯(Rodrigues)旋转方程求解上述旋转变换矩阵R,通过同名点在不同坐标系下的表示求解上述平移变换矩阵T。When the size of the security inspection vehicle and the installation position of each lidar are known, the transformation relationship between the coordinate systems can be directly obtained based on the above embodiment. In the case where the above transformation relationship cannot be obtained, the predetermined target can be calibrated by placing the calibration target in the common observation area of multiple lidars. The Rodrigues rotation equation is used to solve the above-mentioned rotation transformation matrix R, and the above-mentioned translation transformation matrix T is solved through the representation of the points with the same name in different coordinate systems.
示例性地,根据本公开实施例的导向控制方法还可以包括:在上述将多个多线激光雷达中每个多线激光雷达的点云数据从每个多线激光雷达的坐标系转换至基准坐标系之前,由每个多线激光雷达获取针对预定靶标的检测数据,并利用随机采样一致性(Random Sample Consensus,RANSAC)算法从每个多线激光雷达的检测数据中提取用于表征预定靶标的同名向量表示和同名点表示。Exemplarily, the guidance control method according to the embodiment of the present disclosure may further include: converting the point cloud data of each multi-line lidar in the plurality of multi-line lidars from the coordinate system of each multi-line lidar to a reference Before the coordinate system, the detection data for the predetermined target is obtained by each multi-line lidar, and the Random Sample Consensus (RANSAC) algorithm is used to extract the detection data from each multi-line lidar to characterize the predetermined target. The eponymous vector representation and the eponymous point representation of .
然后,基于罗德里格斯旋转方程对多个多线激光雷达各自的同名向量表示进行处理,以得到多个多线激光雷达中的任意两个多线激光雷达的坐标系之间的旋转变换关系。并且,基于述多个多线激光雷达各自的同名点表示,确定多个多线激光雷达中的任意两个多线激光雷达的坐标系之间的平移变换关系。Then, based on the Rodrigues rotation equation, the respective vector representations of the same name of multiple multi-line lidars are processed to obtain the rotational transformation relationship between the coordinate systems of any two multi-line lidars in the multiple multi-line lidars . And, based on the point representations of the same names of the plurality of multi-line lidars, the translational transformation relationship between the coordinate systems of any two multi-line lidars in the plurality of multi-line lidars is determined.
例如,在测量环境中放置一个预定靶标,该预定靶标具有三个可观测平面。利用多个多线激光雷达分别对其进行观测,以获取每个多线激光雷达针对预定靶标的检测数据。针对每个多线激光雷达的检测数据,执行如下操作:从检测数据中提取出预定靶标的子点云数据。然后,采用RANSAC算法针对预定靶标的子点云数据进行平面分割,以提取针对预定靶标的三 个可观测平面各自的平面参数。基于以上三个平面的平面参数,将三个平面的法向量作为同名向量,将三个平面的交点作为同名点。可以理解,基于每个多线激光雷达的检测数据,可以获得针对于该多线激光雷达的坐标系的一组同名向量表示和同名点表示。For example, a predetermined target with three observable planes is placed in the measurement environment. Use multiple multi-line lidars to observe them respectively to obtain the detection data of each multi-line lidar for the predetermined target. For the detection data of each multi-line lidar, the following operations are performed: the sub-point cloud data of the predetermined target is extracted from the detection data. Then, the RANSAC algorithm is used to perform plane segmentation on the sub-point cloud data of the predetermined target to extract the respective plane parameters of the three observable planes for the predetermined target. Based on the plane parameters of the above three planes, the normal vectors of the three planes are used as the vector with the same name, and the intersection of the three planes is used as the point with the same name. It can be understood that, based on the detection data of each multi-line lidar, a set of identically named vector representations and identically named point representations for the coordinate system of the multi-line lidar can be obtained.
根据Rodrigues旋转方程,只需要两组以上同名向量就可以求得坐标系间的旋转矩阵R,在此基础上已知至少一个同名点的坐标向量即可确定平移矩阵T。以此来实现针对任意一个多线激光雷达的坐标系与基准坐标系之间的旋转变换关系和平移变换关系的求解。According to the Rodrigues rotation equation, the rotation matrix R between coordinate systems can be obtained only by two or more sets of vectors with the same name. On this basis, the translation matrix T can be determined by knowing the coordinate vector of at least one point with the same name. In this way, the solution of the rotation transformation relationship and translation transformation relationship between the coordinate system of any multi-line laser radar and the reference coordinate system is realized.
在此基础上,上述将多个多线激光雷达中每个多线激光雷达的点云数据从每个多线激光雷达的坐标系转换至基准坐标系的过程可以包括:根据多个多线激光雷达中的任意一个多线激光雷达的坐标系与基准坐标系之间的旋转变换关系和平移变换关系,将多个多线激光雷达的点云数据从多个多线激光雷达各自的坐标系转换至基准坐标系。On this basis, the above process of converting the point cloud data of each of the multiple multi-line laser radars from the coordinate system of each multi-line laser radar to the reference coordinate system may include: The rotation transformation relationship and translation transformation relationship between the coordinate system of any multi-line lidar in the radar and the reference coordinate system, and the point cloud data of multiple multi-line lidars are converted from the respective coordinate systems of multiple multi-line lidars. to the base coordinate system.
通过上述实施例可将安检车辆中多个激光雷达的点云数据转换至同一基准坐标系下完成标定,针对每个测量时刻,可形成一帧描述车体周围完整环境信息的环境点云数据,以表征上文中如图4所示的外部环境信息。基于该环境点云数据中的第一特征点云数据可以确定外部环境中基准物的相关信息。若激光雷达安装位置附近无其他设备遮挡扫描线,可通过融合后的环境点云数据提取安检车辆的车体轮廓信息,也可以通过该环境点云数据提取安检车辆的外部环境中的障碍物的轮廓信息。根据车体轮廓信息和障碍物的轮廓信息可以在避障过程中用来判断障碍物与车体的距离。此外,针对每帧环境点云数据,根据环境点云数据的分布特性可以提取第二特征点云数据。对于相邻帧间的第二特征点云数据,可以通过预定匹配算法来迭代最近点(Iterative Closest Point,ICP)算法寻找帧间第二特征点云数据的最优匹配,可求得相邻帧的环境点云数据之间的刚体旋转矩阵R’和平移矩阵T’,从而可以确定安检车辆的姿态变化信息。示例性地,预定匹配算法例如可以为迭代最近点(Iterative Closest Point,ICP)算法,在其他例子中,预定匹配算法可以为各种ICP的改进算法,例如PL-ICP(Point to Line ICP,点至线迭代最近点)、N-ICP(Normal ICP,正则迭代最近点)、IMLS-ICP(Implicit Moving Least Square ICP,隐式移动最小二乘迭代最近 点),以及NDT(正态分布)等其他原理的匹配算法。需要说明的是,上述处理过程可以在安检车辆上进行,也可以在与安检车辆可通行的其他设备中进行。Through the above embodiment, the point cloud data of multiple laser radars in the security inspection vehicle can be converted to the same reference coordinate system to complete the calibration. For each measurement moment, a frame of environmental point cloud data describing the complete environmental information around the vehicle body can be formed. to characterize the external environment information shown in Figure 4 above. Based on the first feature point cloud data in the environmental point cloud data, relevant information of the reference object in the external environment can be determined. If there is no other device near the installation location of the lidar to block the scan line, the vehicle body contour information of the security inspection vehicle can be extracted from the fused environmental point cloud data, and the information of obstacles in the external environment of the security inspection vehicle can also be extracted from the environmental point cloud data. profile information. According to the contour information of the vehicle body and the contour information of the obstacle, it can be used to judge the distance between the obstacle and the vehicle body during the obstacle avoidance process. In addition, for each frame of environmental point cloud data, the second characteristic point cloud data can be extracted according to the distribution characteristics of the environmental point cloud data. For the second feature point cloud data between adjacent frames, a predetermined matching algorithm can be used to iteratively close the point (Iterative Closest Point, ICP) algorithm to find the optimal matching of the second feature point cloud data between frames, and adjacent frames can be obtained. The rigid body rotation matrix R' and the translation matrix T' between the environmental point cloud data, so that the attitude change information of the security inspection vehicle can be determined. Exemplarily, the predetermined matching algorithm can be, for example, an iterative Closest Point (Iterative Closest Point, ICP) algorithm, and in other examples, the predetermined matching algorithm can be an improved algorithm of various ICPs, such as PL-ICP (Point to Line ICP, point to line ICP) algorithm. To line iteration closest point), N-ICP (Normal ICP, regular iteration closest point), IMLS-ICP (Implicit Moving Least Square ICP, implicit moving least squares iteration closest point), and NDT (normal distribution) and other others Principle matching algorithm. It should be noted that, the above processing process can be performed on the security inspection vehicle, or can be performed in other devices that can pass through the security inspection vehicle.
下面就基于环境点云数据获取环境信息和车体自身信息,并基于环境信息和车体自身信息进行导向控制的过程进行示例性说明。The following is an exemplary description of the process of acquiring environmental information and vehicle body information based on environmental point cloud data, and performing steering control based on the environmental information and vehicle body information.
根据本公开实施例,基于环境点云数据,可以确定位于安检车辆的外部环境中的多个基准物的位置信息。该过程可以包括:从环境点云数据中提取第一特征点云数据;对第一特征点云数据进行聚类,以得到多个聚类结果,该多个聚类结果分别作为多个基准物各自的子点云数据。然后,基于多个基准物各自的子点云数据,确定多个基准物各自的位置信息。其中,第一特征点云数据为与预先设定的基准物的特征信息相匹配的点云数据。基准物例如可以是预定路标或其他预定目标物体,基准物可以设置在安检车辆车头装有多线激光雷达的车体一侧,例如在图5A所示的例子中,安检车辆的车头左侧装有第一多线激光雷达5121,故基准物可以布置在车体左侧的外部环境中,以保证利用第一多线激光雷达5121即可获取到针对基准物的精度较高的点云数据。在其他例子中,也可以在车体另外一侧设置辅助基准物,通过融合后的环境点云数据辅助车辆进行姿态调整。在确定多个基准物各自的位置信息之后,接着,基于所确定的多个基准物的位置信息,可以确定引导路径,从而可以根据该引导路径对安检车辆进行导向控制。According to the embodiment of the present disclosure, based on the environmental point cloud data, the position information of a plurality of reference objects located in the external environment of the security inspection vehicle can be determined. The process may include: extracting first feature point cloud data from environmental point cloud data; clustering the first feature point cloud data to obtain multiple clustering results, where the multiple clustering results are respectively used as multiple reference objects The respective sub-point cloud data. Then, based on the sub-point cloud data of each of the plurality of reference objects, position information of each of the plurality of reference objects is determined. The first feature point cloud data is point cloud data matched with the preset feature information of the reference object. For example, the reference object can be a predetermined road sign or other predetermined target object, and the reference object can be set on the side of the vehicle body equipped with the multi-line laser radar at the front of the security inspection vehicle. For example, in the example shown in FIG. There is the first multi-line laser radar 5121, so the reference object can be arranged in the external environment on the left side of the vehicle body to ensure that the first multi-line laser radar 5121 can be used to obtain high-precision point cloud data for the reference object. In other examples, an auxiliary reference object can also be set on the other side of the vehicle body, and the fused environment point cloud data can be used to assist the vehicle in performing attitude adjustment. After the position information of each of the plurality of reference objects is determined, then, based on the determined position information of the plurality of reference objects, a guide route can be determined, so that the security inspection vehicle can be guided and controlled according to the guide route.
示例性地,安检车辆可以包括两种运动模式:一是安检过程中的直线往返运动,二是在安检车辆转场过程中或者复杂安检过程中的沿轨迹曲线运动。根据本公开实施例的导向控制方案需保证安检车辆在运动中不会因道路条件、控制偏差等原因偏离原定路线,并可以提供回中功能。下面结合具体例子对确定引导路径的过程进行示例性说明。Exemplarily, the security inspection vehicle may include two motion modes: one is a linear reciprocating motion during the security inspection process, and the other is a trajectory curve motion during the security inspection vehicle transition process or a complex security inspection process. The guidance control scheme according to the embodiment of the present disclosure needs to ensure that the security inspection vehicle will not deviate from the original route due to road conditions, control deviations and other reasons during movement, and can provide a return-to-center function. The process of determining the guidance path will be exemplarily described below with reference to specific examples.
以采用路标基准物为自动导向控制***提供引导为例,在安检车辆行驶方向左侧摆放路标基准物,相邻路标之间的距离需小于车体宽度以免导向控制过程中将路标间的空隙识别为安检车辆的可通行区域。Taking the use of road sign datum objects to provide guidance for the automatic guidance control system as an example, place road sign datum objects on the left side of the security inspection vehicle's driving direction. A void is identified as a passable area for a security vehicle.
图6A~图6C示意性示出了根据本公开实施例的确定引导路径的过程示例图。6A to 6C schematically illustrate example diagrams of a process of determining a guide path according to an embodiment of the present disclosure.
如图6A所示,安检车辆610的外部环境中设置有多个路标基准物620,本例中路标基准物呈曲线放置,示例性展示了沿轨迹曲线导向控制的方案。根据环境点云数据可获得安检车辆的外部环境中的基准物信息。通过点云分割聚类方法分别获得针对每个基准物的子点云数据。从针对每个基准物的子点云数据中可以提取相应的基准物的位置信息。基于多个基准物各自的位置信息,进行曲线拟合,例如通过最小二乘法对多个基准物的位置信息进行分段线性拟合,以得到拟合车道线630。如图6B所示,在确定拟合车道线630后,基于拟合车道线630,确定引导线640,使得引导线640上任一点与拟合车道线630之间的距离为预定圆650的半径,该预定圆650的尺寸限定了安检车辆的横向姿态偏移空间。在后续导向控制过程中,可以将该引导线640作为安检车辆的导向路径。As shown in FIG. 6A , a plurality of road marking fiducials 620 are set in the external environment of the security inspection vehicle 610 . In this example, the road marking fiducials are placed in a curve, which exemplarily shows a solution for guiding control along a trajectory curve. According to the environmental point cloud data, the reference object information in the external environment of the security inspection vehicle can be obtained. The sub-point cloud data for each fiducial object are obtained by the point cloud segmentation and clustering method. From the sub-point cloud data for each fiducial object, the position information of the corresponding fiducial object can be extracted. Curve fitting is performed based on the respective position information of the plurality of reference objects, for example, piecewise linear fitting is performed on the position information of the plurality of reference objects by the least square method to obtain the fitted lane line 630 . As shown in FIG. 6B , after the fitting lane line 630 is determined, the guide line 640 is determined based on the fitting lane line 630, so that the distance between any point on the guide line 640 and the fitted lane line 630 is the radius of the predetermined circle 650, The size of the predetermined circle 650 defines the lateral attitude deviation space of the security inspection vehicle. In the subsequent guidance control process, the guidance line 640 may be used as a guidance path for the security inspection vehicle.
为保证安检车辆沿导向路径的顺利行进,避免碰撞基准物,上述通过拟合的车道线获得行车引导路径的方法可以如图6C所示。以车体坐标系原点为圆心,根据车体轮廓信息获得车体轮廓外接圆660。在此基础上保留车体运行时需要的安全距离r,可获得以车体坐标系原点为圆心的车辆安全运行的预定圆650。在图6B中,令该预定圆650以与拟合车道线630相切的方式运动,预定圆650的圆心的运动轨迹即为引导线640。根据本公开实施例的导向控制方案可以根据当前车体姿态信息,计算车辆运行方向和速度,在对车体进行导向控制的过程中使得车体坐标系原点尽可能在引导路径上沿轨迹运动。In order to ensure the smooth running of the security inspection vehicle along the guide path and avoid collision with the reference object, the above-mentioned method for obtaining the driving guide path through the fitted lane line may be shown in FIG. 6C . Taking the origin of the vehicle body coordinate system as the center of the circle, the circumscribed circle 660 of the vehicle body outline is obtained according to the vehicle body outline information. On this basis, the safety distance r required for the vehicle body to run is retained, and a predetermined circle 650 for the safe operation of the vehicle with the origin of the vehicle body coordinate system as the center of the circle can be obtained. In FIG. 6B , the predetermined circle 650 is made to move tangentially to the fitted lane line 630 , and the movement trajectory of the center of the predetermined circle 650 is the guide line 640 . The guidance control scheme according to the embodiment of the present disclosure can calculate the running direction and speed of the vehicle according to the current vehicle body attitude information, and make the origin of the vehicle body coordinate system move along the trajectory on the guidance path as much as possible during the guidance control process of the vehicle body.
在直线导向方案的例子中,基准物可以呈直线放置,根据本公开实施例的导向控制方案可以直接通过最小二乘法将基准物的位置信息拟合成一条直线拟合车道线,从而确定与该直线拟合车道线相距预定距离的引导线,令安检车辆沿引导线运动,完成导向控制工作。其中,为预留安全运动空间,引导线与拟合车道线之间的距离大于车体的外接圆半径。In the example of the straight-line guidance scheme, the reference object can be placed in a straight line, and the guidance control scheme according to the embodiment of the present disclosure can directly fit the position information of the reference object into a straight line fitting lane line through the least square method, so as to determine the alignment with the line. The straight line fits the guide line with the lane line at a predetermined distance, so that the security inspection vehicle moves along the guide line to complete the guidance control work. Among them, in order to reserve safe movement space, the distance between the guide line and the fitted lane line is greater than the radius of the circumcircle of the vehicle body.
在本公开的一个实施例中,上述基于引导路径,对车体进行导向控制的过程包括:根据上述确定的引导路径(例如引导线)和姿态变化信息,可以确定针对安检车辆的牵引力的大小和方向。再基于牵引力对车体进行自动导向控制,以使得安检车辆沿引导路径行驶。In an embodiment of the present disclosure, the above-mentioned process of performing guidance control on the vehicle body based on the guidance path includes: according to the above-determined guidance path (eg, guidance line) and attitude change information, the magnitude of the traction force for the security inspection vehicle and the direction. Then, based on the traction force, the vehicle body is automatically guided and controlled, so that the security inspection vehicle travels along the guiding path.
在本公开的另一个实施例中,在导向控制过程中,还可以评估外部环 境中的障碍物对安检车辆运行所产生的影响。例如,基于环境点云数据,可以确定车体的轮廓信息以及至少一个障碍物的轮廓信息。然后针对上述至少一个障碍物中的每个障碍物,基于车体的轮廓信息和该障碍物的轮廓信息,确定车体与该障碍物之间的距离,并基于二者之间的距离确定排斥力的大小和方向。根据引导路径和姿态变化信息,确定针对安检车辆的牵引力的大小和方向。接着,基于牵引力以及针对上述至少一个障碍物的排斥力,确定综合牵引力,并基于该综合牵引力对车体进行导向控制。In another embodiment of the present disclosure, during the guidance control process, the influence of obstacles in the external environment on the operation of the security inspection vehicle may also be evaluated. For example, based on the environmental point cloud data, contour information of the vehicle body and contour information of at least one obstacle may be determined. Then, for each obstacle in the at least one obstacle, the distance between the vehicle body and the obstacle is determined based on the contour information of the vehicle body and the contour information of the obstacle, and the rejection is determined based on the distance between the two. The magnitude and direction of the force. According to the guidance path and attitude change information, determine the magnitude and direction of the traction force for the security inspection vehicle. Next, based on the traction force and the repulsive force with respect to the at least one obstacle, a comprehensive traction force is determined, and the vehicle body is guided and controlled based on the comprehensive traction force.
示例性地,当障碍物与车体的距离在一定范围内时,障碍物会对车体产生排斥力作用。排斥力的大小与障碍物到车体的距离成反比,排斥力的方向为由障碍物指向车体。根据本公开实施例对车体产生的牵引力作用和排斥力作用形成综合牵引力,共同决定车体实际运行方向。例如通过公式(2)计算综合牵引力,如下式所示:Exemplarily, when the distance between the obstacle and the vehicle body is within a certain range, the obstacle will act as a repulsive force on the vehicle body. The magnitude of the repulsive force is inversely proportional to the distance from the obstacle to the vehicle body, and the direction of the repulsive force is from the obstacle to the vehicle body. According to the embodiment of the present disclosure, the traction force and the repulsion force generated by the vehicle body form a comprehensive traction force, which jointly determines the actual running direction of the vehicle body. For example, the comprehensive traction force is calculated by formula (2), as shown in the following formula:
ρ(θ)=μ
α·α+μ
β·β (2)
ρ(θ)=μ α ·α+μβ · β (2)
其中,ρ(θ)、α和β为向量形式,ρ(θ)表征综合牵引力,α表征牵引力,β表征排斥力,μ
α和μ
β分别为第一权重和第二权重,且μ
α+μ
β=1。μ
α和μ
β的值由导向控制策略决定,当μ
α>μ
β时,***表现为以导向为主;当μ
α<μ
β时,***表现为以避障为主。
Among them, ρ(θ), α and β are in vector form, ρ(θ) represents the comprehensive traction force, α represents the traction force, β represents the repulsive force, μ α and μ β are the first and second weights, respectively, and μ α + μβ =1. The values of μ α and μ β are determined by the steering control strategy. When μ α > μ β , the system is mainly guided; when μ α < μ β , the system is dominated by obstacle avoidance.
根据本公开的实施例的导向控制方案,控制车体沿计算出的行车引导线向前移动,同时根据障碍物的分布指示车体调整行车路线,直至安检车辆运行至行车引导线末端(即在车体运行方向前方检测不到基准物,无法获得向前的拟合车道线),即认为到达目的地,导向控制过程结束。According to the guidance control scheme of the embodiment of the present disclosure, the vehicle body is controlled to move forward along the calculated driving guidance line, and at the same time, the vehicle body is instructed to adjust the driving route according to the distribution of obstacles, until the security inspection vehicle runs to the end of the driving guidance line (that is, at the end of the driving guidance line). If the reference object is not detected in the front of the running direction of the vehicle body, and the forward fitting lane line cannot be obtained), it is considered that the destination is reached, and the guidance control process ends.
在本公开的其他实施例中,基于环境点云数据,还可以检测到如图5A~5B所示的检查通道内的相关信息。例如在检测到无关人员闯入检查通道、被检查对象偏离检查通道等突发情况时,根据预定策略可以进行报警并控制安检车辆停止安全检查过程。In other embodiments of the present disclosure, based on the environmental point cloud data, relevant information in the inspection channel as shown in FIGS. 5A to 5B can also be detected. For example, when it is detected that an unrelated person breaks into the inspection channel, the inspected object deviates from the inspection channel and other emergencies, according to a predetermined strategy, an alarm can be issued and the security inspection vehicle can be controlled to stop the security inspection process.
可以理解,基于上述各实施例的说明,根据本公开实施例的导向控制方案采用多线激光作为扫描装置,增强对环境中障碍物、基准物等的检测准确性,降低扫描盲区范围,提高安检车辆运行安全性。并且,通过对车体上多个多线激光雷达进行标定与点云数据的融合,方便获取车体轮廓信息、车体姿态信息与周围环境信息,提高定位与自动导向***的精度。此 外,将基于导向路径的导向作用与基于障碍物分布的排斥作用相结合,精确控制安检车辆行驶路径。It can be understood that, based on the descriptions of the above embodiments, the guidance control scheme according to the embodiments of the present disclosure uses a multi-line laser as a scanning device to enhance the detection accuracy of obstacles, reference objects, etc. in the environment, reduce the scope of scanning blind spots, and improve security inspection. Safety of vehicle operation. In addition, by calibrating multiple multi-line laser radars on the vehicle body and fusing point cloud data, it is convenient to obtain vehicle body contour information, vehicle body attitude information and surrounding environment information, and improve the accuracy of positioning and automatic guidance systems. In addition, the guiding effect based on the guiding path is combined with the repulsive effect based on the distribution of obstacles to precisely control the driving path of the security inspection vehicle.
图7示意性示出了根据本公开实施例的导向控制装置的框图。该导向控制装置可以应用于安检车辆,安检车辆可以包括车体、安检门和至少一个多线激光雷达。FIG. 7 schematically shows a block diagram of a steering control apparatus according to an embodiment of the present disclosure. The guidance control device can be applied to a security inspection vehicle, and the security inspection vehicle can include a vehicle body, a security inspection door and at least one multi-line laser radar.
如图7所示,该导向控制装置700可以包括:获取模块710、第一确定模块720、第二确定模块730和控制模块740。As shown in FIG. 7 , the guidance control apparatus 700 may include: an acquisition module 710 , a first determination module 720 , a second determination module 730 and a control module 740 .
获取模块710用于利用上述至少一个多线激光雷达获取安检车辆的环境点云数据。The acquiring module 710 is configured to acquire the environmental point cloud data of the security inspection vehicle by using the above at least one multi-line lidar.
第一确定模块720用于基于环境点云数据,确定位于安检车辆的外部环境中的多个基准物的位置信息。The first determining module 720 is configured to determine, based on the environmental point cloud data, position information of multiple reference objects located in the external environment of the security inspection vehicle.
第二确定模块730用于基于多个基准物的位置信息,确定引导路径。The second determining module 730 is configured to determine the guiding path based on the position information of the plurality of reference objects.
控制模块740用于基于引导路径,对所述车体进行导向控制。其中,当安检车辆处于安检状态时,经过导向控制的车体带动安检门相对于位于外部环境中的被检查对象运动,以使被检查对象穿过安检门。The control module 740 is used for guiding and controlling the vehicle body based on the guiding path. Wherein, when the security inspection vehicle is in the security inspection state, the vehicle body under the guidance control drives the security inspection door to move relative to the inspected object located in the external environment, so that the inspected object passes through the security inspection door.
需要说明的是,装置部分实施例中各模块/单元/子单元等的实施方式、解决的技术问题、实现的功能、以及达到的技术效果分别与方法部分实施例中各对应的步骤的实施方式、解决的技术问题、实现的功能、以及达到的技术效果相同或类似,在此不再赘述。It should be noted that the implementations of each module/unit/subunit, etc., the technical problems solved, the functions realized, and the technical effects achieved in some embodiments of the apparatus are respectively the implementations of the corresponding steps in the embodiments of the method part. , the technical problem solved, the function realized, and the technical effect achieved are the same or similar, and will not be repeated here.
图8示意性示出了根据本公开的实施例的适于实现上文描述的方法的安检车辆的示例结构图。图8示出的安检车辆仅仅是一个示例,不应对本公开实施例的结构、功能和使用范围带来任何限制。FIG. 8 schematically shows an example structural diagram of a security inspection vehicle suitable for implementing the above-described method according to an embodiment of the present disclosure. The security inspection vehicle shown in FIG. 8 is only an example, and should not impose any limitations on the structure, function and scope of use of the embodiments of the present disclosure.
如图8所示,安检车辆800包括处理器810和计算机可读存储介质820、车体830、安检门840、至少一个多线激光雷达850。该安检车辆800可以执行根据本公开实施例的方法。As shown in FIG. 8 , the security inspection vehicle 800 includes a processor 810 , a computer-readable storage medium 820 , a vehicle body 830 , a security inspection door 840 , and at least one multi-line lidar 850 . The security inspection vehicle 800 may execute the method according to the embodiment of the present disclosure.
根据本公开实施例,当上述至少一个多线激光雷达850包括多个多线激光雷达时,多个多线激光雷达中的至少两个多线激光雷达分散分布于车体外侧,以使该至少两个多线激光雷达的扫描范围覆盖车体周边360°。According to the embodiment of the present disclosure, when the above-mentioned at least one multi-line lidar 850 includes a plurality of multi-line lidars, at least two of the plurality of multi-line lidars are distributed outside the vehicle body, so that the at least two multi-line lidars are distributed outside the vehicle body. The scanning range of the two multi-line lidars covers 360° around the vehicle body.
根据本公开实施例,多个多线激光雷达850中除所述至少两个多线激光雷达之外的至少一个多线激光雷达位于安检门的内侧。According to an embodiment of the present disclosure, at least one of the multiple multi-line laser radars 850 other than the at least two multi-line laser radars is located inside the security gate.
具体地,处理器810例如可以包括通用微处理器、指令集处理器和/或相关芯片组和/或专用微处理器(例如,专用集成电路(ASIC)),等等。处理器810还可以包括用于缓存用途的板载存储器。处理器810可以是用于执行根据本公开实施例的方法流程的不同动作的单一处理单元或者是多个处理单元。Specifically, the processor 810 may include, for example, a general-purpose microprocessor, an instruction set processor and/or a related chipset, and/or a special-purpose microprocessor (eg, an application specific integrated circuit (ASIC)), and the like. The processor 810 may also include onboard memory for caching purposes. The processor 810 may be a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.
计算机可读存储介质820,例如可以是非易失性的计算机可读存储介质,具体示例包括但不限于:磁存储装置,如磁带或硬盘(HDD);光存储装置,如光盘(CD-ROM);存储器,如随机存取存储器(RAM)或闪存;等等。The computer-readable storage medium 820 can be, for example, a non-volatile computer-readable storage medium, and specific examples include but are not limited to: magnetic storage devices, such as magnetic tapes or hard disks (HDDs); optical storage devices, such as compact disks (CD-ROMs) ; memory, such as random access memory (RAM) or flash memory; etc.
计算机可读存储介质820可以包括计算机程序821,该计算机程序821可以包括代码/计算机可执行指令,其在由处理器810执行时使得处理器810执行根据本公开实施例的方法或其任何变形。The computer-readable storage medium 820 may include a computer program 821, which may include code/computer-executable instructions that, when executed by the processor 810, cause the processor 810 to perform methods according to embodiments of the present disclosure or any variation thereof.
计算机程序821可被配置为具有例如包括计算机程序模块的计算机程序代码。例如,在示例实施例中,计算机程序821中的代码可以包括一个或多个程序模块,例如包括821A、模块821B、......。应当注意,模块的划分方式和个数并不是固定的,本领域技术人员可以根据实际情况使用合适的程序模块或程序模块组合,当这些程序模块组合被处理器810执行时,使得处理器810可以执行根据本公开实施例的方法或其任何变形。The computer program 821 may be configured with computer program code comprising, for example, computer program modules. For example, in an example embodiment, the code in computer program 821 may include one or more program modules, including, for example, 821A, module 821B, . . . It should be noted that the division method and number of modules are not fixed, and those skilled in the art can use appropriate program modules or combination of program modules according to the actual situation. When these combination of program modules are executed by the processor 810, the processor 810 can A method according to an embodiment of the present disclosure or any variation thereof is performed.
根据本公开的实施例,获取模块710、第一确定模块720、第二确定模块730和控制模块740中的至少一个可以实现为参考图8描述的计算机程序模块,其在被处理器810执行时,可以实现上文所述的方法。According to an embodiment of the present disclosure, at least one of the acquisition module 710 , the first determination module 720 , the second determination module 730 , and the control module 740 may be implemented as the computer program modules described with reference to FIG. 8 , which when executed by the processor 810 , the method described above can be implemented.
本公开还提供了一种计算机可读存储介质,该计算机可读存储介质可以是上述实施例中描述的设备/装置/***中所包含的;也可以是单独存在,而未装配入该设备/装置/***中。上述计算机可读存储介质承载有一个或者多个程序,当上述一个或者多个程序被执行时,实现根据本公开实施例的方法。The present disclosure also provides a computer-readable storage medium. The computer-readable storage medium may be included in the device/apparatus/system described in the above embodiments; it may also exist alone without being assembled into the device/system. device/system. The above-mentioned computer-readable storage medium carries one or more programs, and when the above-mentioned one or more programs are executed, implement the method according to the embodiment of the present disclosure.
根据本公开的实施例,计算机可读存储介质可以是非易失性的计算机可读存储介质,例如可以包括但不限于:便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器 件、磁存储器件、或者上述的任意合适的组合。在本公开中,计算机可读存储介质可以是任何包含或存储程序的有形介质,该程序可以被指令执行***、装置或者器件使用或者与其结合使用。According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, such as, but not limited to, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM) , erasable programmable read only memory (EPROM or flash memory), portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. In this disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
附图中的流程图和框图,图示了按照本公开各种实施例的***、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上,流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分,上述模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意,在有些作为替换的实现中,方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如,两个接连地表示的方框实际上可以基本并行地执行,它们有时也可以按相反的顺序执行,这依所涉及的功能而定。也要注意的是,框图或流程图中的每个方框、以及框图或流程图中的方框的组合,可以用执行规定的功能或操作的专用的基于硬件的***来实现,或者可以用专用硬件与计算机指令的组合来实现。The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more functions for implementing the specified logical function(s) executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams or flowchart illustrations, and combinations of blocks in the block diagrams or flowchart illustrations, can be implemented in special purpose hardware-based systems that perform the specified functions or operations, or can be implemented using A combination of dedicated hardware and computer instructions is implemented.
尽管已经参照本公开的特定示例性实施例示出并描述了本公开,但是本领域技术人员应该理解,在不背离所附权利要求及其等同物限定的本公开的精神和范围的情况下,可以对本公开进行形式和细节上的多种改变。因此,本公开的范围不应该限于上述实施例,而是应该不仅由所附权利要求来进行确定,还由所附权利要求的等同物来进行限定。Although the present disclosure has been shown and described with reference to specific exemplary embodiments of the present disclosure, those skilled in the art will appreciate that, without departing from the spirit and scope of the present disclosure as defined by the appended claims and their equivalents, Various changes in form and detail have been made in the present disclosure. Therefore, the scope of the present disclosure should not be limited to the above-described embodiments, but should be determined not only by the appended claims, but also by their equivalents.