技术领域technical field
本发明涉及汽车电子技术领域，特别是涉及一种航迹推演的校正方法、终端和存储介质。The invention relates to the technical field of automotive electronics, in particular to a correction method, a terminal and a storage medium for track deduction.
背景技术Background technique
在现有技术中，“自动代客泊车”(Auto Valet Parking)成为自动驾驶领域的热门技术之一，同样也将是自动驾驶量产道路上的一个重要里程碑。作为一套完整的自动无人驾驶汽车系统，AVP系统以低速驾驶汽车或将汽车停在有限的区域内，如停车场或周围道路。此外，作为泊车辅助的一种功能扩展，也会是最早商业化的全自动驾驶功能之一。Among the existing technologies, "Auto Valet Parking" (Auto Valet Parking) has become one of the hot technologies in the field of autonomous driving, and it will also be an important milestone on the road to mass production of autonomous driving. As a complete autonomous driverless car system, the AVP system drives the car at a low speed or parks the car in a limited area, such as a parking lot or surrounding roads. In addition, as a function extension of parking assistance, it will also be one of the first commercialized fully automatic driving functions.
由于在泊车过程中，车辆进行路径规划和定位时依赖的信号是航迹推演(DR)，由于各种不可控的因素，DR信号存在较为明显的累积误差，无法满足控制系统的精度要求，最终导致泊车结束后，无法让车辆到达预定的位置并满足期望的姿态。During the parking process, the signal that the vehicle relies on for path planning and positioning is track deduction (DR). Due to various uncontrollable factors, the DR signal has obvious cumulative errors, which cannot meet the accuracy requirements of the control system. Finally, after the parking is over, the vehicle cannot reach the predetermined position and meet the desired attitude.
现有技术中，如公开号DE102015116220A1的用于检测机动车辆错误的机动车辆的至少半自动操纵的方法，计算装置，驾驶员辅助系统和机动车辆的方法，该文献涉及一种采用接触式测量误差的方案，即发动机扭矩信号来检测障碍物的距离来发现里程计误差的方法，这里的障碍物一般指路沿或限位器，车轮装上去，并且花比较大力气开不过去，因此扭矩增大。通过检测到这样的障碍物，来确定目前车辆的接触位置已经和地图上的障碍物有接触(有偏差的话，就会提前或者滞后接触)，从而发现误差。A method for at least semi-automatic maneuvering of a motor vehicle, a computing device, a driver assistance system and a method for a motor vehicle for detection of motor vehicle errors, such as the publication number DE102015116220A1, which relates to a method of using tactile measurement errors Solution, that is, the method of using the engine torque signal to detect the distance of the obstacle to find the odometer error. The obstacle here generally refers to the road edge or limiter, the wheel is installed, and it takes a lot of effort to drive it, so the torque increases . By detecting such an obstacle, it is determined that the current contact position of the vehicle has been in contact with the obstacle on the map (if there is a deviation, the contact will be advanced or delayed), so as to find the error.
如公开号DE102016106978A1的用于操作机动车辆的驾驶员辅助系统的方法，计算装置，驾驶员辅助系统和机动车辆，该文献主要公开了一项以图像为基础的非接触式测量里程计误差的方案，但是该方案中图像需要识别出明显的目标物作为参考。例如，需要在图像中找出车辆，车牌，墙面标识，地面标识等，可以被认为是目标级的参考物。但是这种依靠目标级参考物来识别里程计误差的方式，再车辆实时感知无法感知到目标级参考物或者实际场景中没有目标级参考物的情况下，即功能无法实现。A method for operating a driver assistance system of a motor vehicle, a computing device, a driver assistance system and a motor vehicle, such as the publication number DE102016106978A1, which mainly discloses an image-based non-contact method for measuring odometer errors , but in this scheme, the image needs to identify an obvious target as a reference. For example, it is necessary to find vehicles, license plates, wall signs, ground signs, etc. in the image, which can be considered as target-level references. However, this method of relying on target-level reference objects to identify odometer errors cannot be realized when the real-time perception of the vehicle cannot perceive the target-level reference objects or there is no target-level reference object in the actual scene.
如公开号DE102015112313A1的用于用于具有位置校正，驾驶员辅助系统和机动车辆的机动车辆的至少半自动操纵的方法，该文献主要公开一项以超声波传感器探测数据为基础的里程计误差感知方法，需要车辆在遇到立体物时才能给出偏差信号。且超声波传感器探测物体精度差，仅仅输出距离和速度信号，对于障碍物的位姿和形状无法掌握。作为里程计误差的参照物不是最好的选择。A method for at least semi-automatic maneuvering of a motor vehicle with position correction, driver assistance system and motor vehicle, such as the publication number DE102015112313A1, which mainly discloses an odometer error perception method based on ultrasonic sensor detection data, It is necessary for the vehicle to give a deviation signal when it encounters a three-dimensional object. Moreover, the ultrasonic sensor has poor accuracy in detecting objects, and only outputs distance and speed signals, and cannot grasp the pose and shape of obstacles. It is not the best choice as a reference object for odometer error.
发明内容Contents of the invention
为了解决上述的以及其他潜在的技术问题，本发明提供了一种航迹推演的校正方法、终端和存储介质，需要引入图像信号来实时观测目标车位，并且将观测的结果与DR推测出目标车位的位置进行比对，给出DR的误差。控制系统可以调整相关执行参数或重新规划泊车入位的路径。In order to solve the above and other potential technical problems, the present invention provides a correction method, terminal and storage medium for track derivation, which need to introduce image signals to observe the target parking space in real time, and infer the target parking space from the observation results and DR Comparing the position of , the error of DR is given. The control system can adjust relevant execution parameters or re-plan the parking path.
一种航迹推演的校正方法，包括以下步骤：A correction method for track deduction, comprising the following steps:
S01：根据车辆起始点和目标点位置获得车辆航迹推演结果；S01: Obtain the vehicle track deduction result according to the position of the vehicle starting point and target point;
S02：将包括但不限于车辆实时感知数据、目标点位置表述、历史航迹推演结果输入航迹推演纠偏系统；S02: Input including but not limited to vehicle real-time perception data, target point position representation, and historical track deduction results into the track deduction correction system;
S03：航迹推演纠偏系统先识别目标点位置的追踪目标，再依据追踪目标位置度量里程计偏差，获得里程计和地图之间的坐标转换矩阵，纠正航迹推演偏差。S03: The track deduction correction system first identifies the tracking target at the target point position, and then measures the odometer deviation based on the tracking target position to obtain the coordinate transformation matrix between the odometer and the map, and correct the track deduction deviation.
进一步地，所述步骤S01中的车辆航迹推演可用于定位导航和方向控制，除了对车辆姿进行估计，还可以从航迹推演中获得移动机器人前进速度和转向角速度。Further, the vehicle track deduction in the step S01 can be used for positioning navigation and direction control. In addition to estimating the vehicle attitude, the forward speed and steering angular velocity of the mobile robot can also be obtained from the track deduction.
进一步地，所述步骤S02中所述的车辆实时感知数据包括视觉感知数据、超声波感知数据和毫米波感知数据。Further, the real-time vehicle sensing data in step S02 includes visual sensing data, ultrasonic sensing data and millimeter wave sensing data.
进一步地，所述步骤S02中所述的车辆实时感知数据仅包含视觉感知数据，所述视觉感知数据为包含车辆的俯视图像。Further, the real-time perception data of the vehicle in the step S02 only includes visual perception data, and the visual perception data is a bird's-eye view image including the vehicle.
进一步地，所述步骤S02中所述的俯视图像，高位俯览环视图像，即TopView环视图：Further, the bird's-eye view image described in step S02 is a high-level bird's-eye view image, that is, a TopView ring view:
由于车位线是喷涂于地面的一种人工标识，AVM图像以俯视的方式将车身周围地面景象进行拼接，较好的保留了地面标识的几何表现。Since the parking space line is a kind of artificial mark sprayed on the ground, the AVM image splices the ground scene around the car body in a top-down manner, which better preserves the geometric performance of the ground mark.
进一步地，所述俯览环视图像的输入形式为：ros message，环视图像参数定义如下：Further, the input form of the bird's-eye view image is: ros message, and the parameters of the surround-view image are defined as follows:
Header headerHeader header
uint64indexuint64index
ImgRect blindAreaImgRect blindArea
ImgRect carPosImgRect carPos
int32phyHeightint32phyHeight
int32phyFrontint32phyFront
sensor_msgs/Image avmsensor_msgs/Image avm
相关成员说明：Description of relevant members:
header：主要包含时间戳信息header: mainly contains timestamp information
index：帧序号index: frame number
blindArea：中心盲区在图像中占据的区域blindArea: the area occupied by the central blind area in the image
avm：VYUY格式的彩色图片avm: color image in VYUY format
进一步地，所述俯览环视图像的获取方式：订阅zdada系统的TOPIC_TRACK_AVM_SRC。Further, the acquisition method of the bird's-eye view image: subscribe to the TOPIC_TRACK_AVM_SRC of the zdada system.
进一步地，所述俯览环视图像的输入要求包括下列条件中一种或几种：Further, the input requirements for the bird's-eye view image include one or more of the following conditions:
(1)观测范围：车头前方3m，车位后方3m，车身侧面的可是范围可以自动推算出。依据现有zadas系统提供的环视图片清晰度，能够在车辆后轴中心距离车位3m的范围内给出校正信号。(1) Observation range: 3m in front of the front of the car, 3m behind the parking space, and the range on the side of the vehicle body can be calculated automatically. According to the clarity of the surround view picture provided by the existing Zadas system, a correction signal can be given within 3m from the center of the rear axle of the vehicle to the parking space.
(2)图像拼接角度：45°。在此参数设置之下，生成的环视图可以在拼接处有较好的融合效果，不容易出现摄像头之间特别明显的错位感；因此在泊车过车中可以较好地满足车辆与车位之间呈现不同观测角度时观测的需求。(2) Image stitching angle: 45°. Under this parameter setting, the generated surround view can have a better fusion effect at the splicing point, and it is not easy to have a particularly obvious sense of dislocation between the cameras; therefore, it can better meet the needs of the vehicle and the parking space when parking and passing. Observation requirements when presenting different observation angles.
(3)图片尺寸：高600像素，宽480像素，宽高尺寸比例为1。按照此前设定的观测范围，假设车辆长度5m。每一个像素代表的坐标轴向距离为2.16cm。如果检测精度在3个像素以内，就可以保证输出结果的分辨精度在5cm以内。(3) Image size: 600 pixels high, 480 pixels wide, and the ratio of width to height is 1. According to the previously set observation range, it is assumed that the vehicle length is 5m. Each pixel represents a coordinate axial distance of 2.16 cm. If the detection accuracy is within 3 pixels, the resolution accuracy of the output result can be guaranteed to be within 5cm.
(4)发送频率：2～3Hz。根据车辆控制系统的要求，每秒钟得到2～3次校正即可满足要求，所有的处理流程在CPU上的耗时不超过250ms。(4) Sending frequency: 2~3Hz. According to the requirements of the vehicle control system, 2 to 3 corrections per second can meet the requirements, and the time consumption of all processing procedures on the CPU does not exceed 250ms.
进一步地，所述步骤S02中目标点位置表述用于自俯览环视图像中分割与本次泊车过程相关的信息，即缩小目标点位置的检测范围。Further, the expression of the position of the target point in the step S02 is used to segment information related to the current parking process from the bird's-eye view image, that is, to narrow the detection range of the position of the target point.
进一步地，所述步骤S02中目标点位置的输入形式为ros message，其数据包表达定义如下：Further, the input form of the target point position in the step S02 is ros message, and its data packet expression is defined as follows:
Header headerHeader header
SlotVertex slotSlotVertex slot
SlotVertex boundrySlotVertex boundary
int32typeint32type
int32valid_typeint32valid_type
int32validint32valid
int32idint32id
相关成员说明：Description of relevant members:
header：主要包含时间戳信息header: mainly contains timestamp information
slot：包含停车位4个顶点在zadas坐标系下的物理坐标slot: contains the physical coordinates of the 4 vertices of the parking space in the zadas coordinate system
type：车位类型。type: parking space type.
进一步地，所述步骤S02中目标点位置的获取方式：订阅zdada系统的TOPIC_APA_TARGET。Further, the method of acquiring the position of the target point in the step S02: subscribe to TOPIC_APA_TARGET of the zdada system.
进一步地，所述步骤S02中目标点位置的输入要求：在某一确定的坐标系下，发送构成一个车位的4个顶点的物理坐标位置，该信号只需要在泊车开始阶段，车辆静止时，发送一次即可。Further, the input requirement of the target point position in the step S02: in a certain coordinate system, send the physical coordinate positions of the 4 vertices that constitute a parking space, the signal only needs to be , send it once.
进一步地，所述步骤S02中输入航迹推演纠偏系统的还包括泊车状态信号，泊车状态信号不是系统基础服务，是根据需求启动的，在行车过程中并不需求提供此模块的输出，避免不必要的系统负担。例如，在泊车过程中，如果车辆俯览环视图中在车辆路径规划范围内突然出现障碍物或者根据其他感知设备例如超声波雷达或者毫米波雷达感知到障碍物而必须立即停止时，将此信号输入至航迹推演模块。Further, in the step S02, the input to the track derivation correction system also includes a parking status signal. The parking status signal is not a basic service of the system, but is activated according to requirements, and the output of this module does not need to be provided during the driving process. Avoid unnecessary system burden. For example, in the process of parking, if an obstacle suddenly appears in the vehicle's path planning range in the top view of the vehicle or it must be stopped immediately according to other sensing devices such as ultrasonic radar or millimeter wave radar. Input to the trajectory derivation module.
进一步地，所述步骤S02中的泊车状态信号的输入形式：ros message，泊车状态信号的数据包表达定义如下Further, the input form of the parking state signal in the step S02 is: ros message, and the data packet expression of the parking state signal is defined as follows
int32apaStageint32apaStage
相关信号含义说明：Explanation of the meaning of related signals:
APA_STATUS_PI_GUIDANCE：开始泊入APA_STATUS_PI_GUIDANCE: start to park in
APA_STATUS_PO_GUIDANCE：开始泊出APA_STATUS_PO_GUIDANCE: start to park out
APA_STATUS_SUSPEND：功能挂起APA_STATUS_SUSPEND: function is suspended
APA_STATUS_PI_SLOT_SEARCHING：正在搜寻车位APA_STATUS_PI_SLOT_SEARCHING: Searching for a parking space
APA_STATUS_PI_SLOT_CONFIRMED：目标车位已确认APA_STATUS_PI_SLOT_CONFIRMED: The target parking space has been confirmed
APA_STATUS_STANDBY：等待开始泊车APA_STATUS_STANDBY: Waiting to start parking
进一步地，所述步骤S02中的泊车状态信号的获取方式：订阅ZADAS系统的TOPIC_APA_STAGE。Further, the way of acquiring the parking state signal in the step S02 is: subscribe to TOPIC_APA_STAGE of the ZADAS system.
进一步地，所述步骤S02中的泊车状态信号的输入要求：无特殊要求，监听即可。Further, the input requirement of the parking state signal in the step S02: no special requirement, just monitor.
进一步地，所述步骤S02中输入航迹推演纠偏系统的还包括车辆档位信号，因为在整个泊车过程中并不是所有的行驶阶段都是泊入行为，因此需要在倒车模式下车辆档位信号应当给航迹推演纠偏系统提供校正输出。Further, the input to the track derivation correction system in the step S02 also includes the vehicle gear position signal, because not all driving stages in the entire parking process are parking behaviors, so the vehicle gear position needs to be changed in the reverse mode. The signal should provide a correction output to the trajectory correction system.
进一步地，所述步骤S02中输入航迹推演纠偏系统的还包括车辆档位信号的输入形式：car_live_info，所述车辆档位信号数据包的定义如下：GEAR_STATUS_RFurther, the input form of the track deduction correction system in the step S02 also includes the input form of the vehicle gear signal: car_live_info, and the definition of the vehicle gear signal data packet is as follows: GEAR_STATUS_R
进一步地，所述车辆档位信号获取方式：调用get_car_gear()。Further, the acquisition method of the vehicle gear position signal: calling get_car_gear().
进一步地，所述步骤S03中航迹推演纠偏系统先识别目标点位置的追踪目标，其追踪目标为车位线。Further, in the step S03, the track derivation correction system first identifies the tracking target at the target point, and the tracking target is the parking space line.
进一步地，所述步骤S03中里程计和地图之间的坐标转换矩阵，地图坐标代表了客观现实中存在的一些标识物的位置，里程计航迹推演坐标表达了依据车辆行驶轨迹推测的车辆位置，而车辆实时视觉感知数据中的俯览环视图像中观测到的信息来源于数据库链接baselink，存在于地图中，图像得到的观测，相当于是从地图产生的；从局部的角度来看，数据库链接baselink的观测是与地图一致的，里程计和地图之间的坐标转换矩阵就是从航迹推演变换回map，因此也代表了需要纠正的偏差，如果衡量图像检测到的目标点位置信息与航迹推演推测的车位信息间存在的误差，就可以校正航迹推演已形成的误差。Further, in the coordinate transformation matrix between the odometer and the map in the step S03, the map coordinates represent the positions of some markers existing in the objective reality, and the odometer track derivation coordinates express the estimated vehicle position based on the vehicle trajectory , while the information observed in the top view image in the vehicle's real-time visual perception data comes from the database link baselink, which exists in the map, and the observation obtained from the image is equivalent to being generated from the map; from a local point of view, the database link The baselink observation is consistent with the map. The coordinate transformation matrix between the odometer and the map is transformed from the track derivation back to the map, so it also represents the deviation that needs to be corrected. If the position information of the target point detected by the image is compared with the track The errors existing in the deduced parking space information can correct the errors formed by the track deduction.
进一步地，所述里程计到地图之间的坐标转换矩阵的输出方式：ZADAS系统的广播TOPIC_TF_MAP_ODOM_CONF。Further, the output method of the coordinate transformation matrix between the odometer and the map: broadcast TOPIC_TF_MAP_ODOM_CONF of the ZADAS system.
进一步地，所述步骤S03还包括对程计到地图之间的坐标转换矩阵校正的信号评价机制，为了能够让使用者了解信号质量，以此来决定是否接受本次校正信号，在发出转换矩阵的同时给出信号质量评价指标。Further, the step S03 also includes a signal evaluation mechanism for the correction of the coordinate transformation matrix between the odometer and the map. In order to allow the user to understand the signal quality and decide whether to accept the correction signal this time, after sending out the transformation matrix At the same time, the signal quality evaluation index is given.
进一步地，所述步骤S03还包括对程计到地图之间的坐标转换矩阵校正的信号质量评价指标包括至少三类，即包含平行度，直线证据累积数量，直线证据分布方差。Further, the step S03 also includes at least three types of signal quality evaluation indicators corrected for the coordinate transformation matrix between the odometer and the map, including parallelism, the cumulative number of straight-line evidence, and the distribution variance of the straight-line evidence.
(1)平行度-parallelism(1) Parallelism-parallelism
当两条直线都检测出的情况下，给出一个0～1的浮点数，越接近与1，平行度越好，检测的可信赖度越高When both straight lines are detected, a floating-point number from 0 to 1 is given. The closer to 1, the better the parallelism and the higher the reliability of the detection.
(2)直线证据累积数量-leftDispersion，rightDispersion(2) Cumulative quantity of linear evidence - leftDispersion, rightDispersion
表明了在搜集了多少数据后，给出了这条直线信息，左右两条校准线各有一个此项指标(3)直线证据分布方差-leftEvidence，rightEvidenceIndicates how much data has been collected, and the straight line information is given, and the left and right calibration lines each have an indicator of this item (3) The variance of the straight line evidence distribution-leftEvidence, rightEvidence
表明了搜集到的直线证据的离散程度。Indicates the degree of dispersion of the collected linear evidence.
进一步地，所述步骤S03还包括对程计到地图之间的坐标转换矩阵校正的信号质量评价指标的情况下，所述里程计到地图之间的坐标转换矩阵的数据包表达定义如下：Further, the step S03 also includes that in the case of correcting the signal quality evaluation index for the coordinate transformation matrix between the odometer and the map, the data package expression of the coordinate transformation matrix between the odometer and the map is defined as follows:
Header headerHeader header
float64leftDispersionfloat64leftDispersion
float64rightDispersionfloat64rightDispersion
float64parallelismfloat64parallelism
int32leftEvidenceint32leftEvidence
int32rightEvidenceint32rightEvidence
geometry_msgs/TransformStamped transgeometry_msgs/TransformStamped trans
成员说明：Member Description:
header：主要包含时间戳信息header: mainly contains timestamp information
leftDispersion：左侧校正线累积证据方差leftDispersion: cumulative evidence variance of the left correction line
rightDispersion：右侧校正线累积证据方差rightDispersion: cumulative evidence variance of the right correction line
parallelism：两条校正线平行度parallelism: Parallelism of two correction lines
leftEvidence：左侧校正线累积证据度量leftEvidence: left correction line cumulative evidence metric
rightEvidence：右侧校正线累积证据度量。rightEvidence: The right correction line cumulative evidence metric.
进一步地，所述步骤S03中的航迹推演纠偏系统先识别目标点位置的追踪目标，再依据追踪目标位置度量里程计偏差，获得里程计和地图之间的坐标转换矩阵，纠正航迹推演偏差，并输出航迹推演位置变换信号，在泊车过程中，使用航迹推演位置变换信号可以实时更新目标车位的位置，并实时了解目标车位在图像以及物理坐标系中的位置，以便根据实时位置制定相应的路径规划策略。Further, the track deduction correction system in the step S03 first identifies the tracking target at the target point position, and then measures the odometer deviation according to the tracking target position to obtain the coordinate transformation matrix between the odometer and the map, and correct the track deduction deviation , and output the track derivation position transformation signal. During the parking process, the position of the target parking space can be updated in real time by using the track deduction position transformation signal, and the position of the target parking space in the image and physical coordinate system can be known in real time, so that the real-time position Formulate corresponding path planning strategies.
进一步地，所述步骤S03中航迹推演位置变换信号的输入形式：ros message，航迹推演位置变换信号数据包表达定义如下：tf2_msgs::TFMessage messageFurther, the input form of the track derivation position change signal in the step S03 is: ros message, and the expression of the track deduction position change signal data packet is defined as follows: tf2_msgs::TFMessage message
相关成员说明：Description of relevant members:
message：3×3的位姿转换矩阵。message: 3×3 pose transformation matrix.
进一步地，所述步骤S03中航迹推演位置变换信号的获取方式：订阅zdada系统的TOPIC_TF_ODOM_BASELINK。Further, the acquisition method of the track derivation position transformation signal in the step S03: subscribe to the TOPIC_TF_ODOM_BASELINK of the zdada system.
进一步地，所述步骤S03中航迹推演位置变换信号的输入要求：无特殊要求，监听即可。Further, the input requirements of the track derivation position transformation signal in the step S03: no special requirements, just monitor.
如上所述，本发明的具有以下有益效果：As mentioned above, the present invention has the following beneficial effects:
需要引入图像信号来实时观测目标车位，并且将观测的结果与DR推测出目标车位的位置进行比对，给出DR的误差。控制系统可以调整相关执行参数或重新规划泊车入位的路径。It is necessary to introduce image signals to observe the target parking space in real time, and compare the observed result with the position of the target parking space estimated by DR to give the error of DR. The control system can adjust relevant execution parameters or re-plan the parking path.
本发明的特点是：The features of the present invention are:
(1)非接触式测量方法(使用图像)；(1) Non-contact measurement method (using images);
(2)这套系统中可以不依赖于地图，仅依赖于已经识别出的车位框，而无需地图来全面覆盖场景中的内容(柱子，道路)；在有地图的环境也可以使用，自主泊车中没有地图，代客泊车中有地图。(2) This system does not depend on the map, but only on the recognized parking space frame, without the map to fully cover the content in the scene (pillars, roads); it can also be used in an environment with a map, autonomous parking There is no map in the car, there is a map in the valet.
在自主泊车中目标车位来源于已经识别到的车位。代客泊车中可以来源于地图上已经确定的目标车位(需要先让车辆开到车位附近，这套系统才起作用)。In autonomous parking, the target parking space is derived from the already recognized parking spaces. The valet parking can come from the target parking space already determined on the map (you need to drive the vehicle to the vicinity of the parking space before this system works).
(3)参考的特征是地面标识线(车位框的边线)，并不要求特别明确的目标物；(3) The reference feature is the ground marking line (the sideline of the parking space frame), and does not require a particularly clear target;
(4)给出的偏差可以非常准确的描述车辆的横向偏差和纵向偏差。横向偏差可以理解为，车有没有停歪，有没有太靠近某一侧边线。纵向偏差可以理解为，车停的太靠车位里面还是车头出来点。(4) The given deviation can describe the lateral deviation and longitudinal deviation of the vehicle very accurately. The lateral deviation can be understood as whether the car is parked crookedly or not, and whether it is too close to a certain side line. The longitudinal deviation can be understood as that the car is parked too close to the inside of the parking space or the front of the car is a little bit out.
附图说明Description of drawings
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings that need to be used in the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those skilled in the art, other drawings can also be obtained based on these drawings without creative effort.
图1显示为本发明的流程框图。Fig. 1 shows the flow chart of the present invention.
图2显示为本发明另一实施例的流程框图。Fig. 2 is a flowchart of another embodiment of the present invention.
图3显示为本发明另一实施例的流程框图。Fig. 3 is a flowchart of another embodiment of the present invention.
图4显示为本发明另一实施例的流程框图。Fig. 4 is a block diagram showing another embodiment of the present invention.
图5显示为本发明另一实施例的流程框图。FIG. 5 is a block diagram showing another embodiment of the present invention.
图6显示为本发明另一实施例的流程框图。FIG. 6 is a block diagram showing another embodiment of the present invention.
具体实施方式Detailed ways
以下通过特定的具体实例说明本发明的实施方式，本领域技术人员可由本说明书所揭露的内容轻易地了解本发明的其他优点与功效。本发明还可以通过另外不同的具体实施方式加以实施或应用，本说明书中的各项细节也可以基于不同观点与应用，在没有背离本发明的精神下进行各种修饰或改变。需说明的是，在不冲突的情况下，以下实施例及实施例中的特征可以相互组合。Embodiments of the present invention are described below through specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various modifications or changes can be made to the details in this specification based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, in the case of no conflict, the following embodiments and features in the embodiments can be combined with each other.
须知，本说明书所附图式所绘示的结构、比例、大小等，均仅用以配合说明书所揭示的内容，以供熟悉此技术的人士了解与阅读，并非用以限定本发明可实施的限定条件，故不具技术上的实质意义，任何结构的修饰、比例关系的改变或大小的调整，在不影响本发明所能产生的功效及所能达成的目的下，均应仍落在本发明所揭示的技术内容得能涵盖的范围内。同时，本说明书中所引用的如“上”、“下”、“左”、“右”、“中间”及“一”等的用语，亦仅为便于叙述的明了，而非用以限定本发明可实施的范围，其相对关系的改变或调整，在无实质变更技术内容下，当亦视为本发明可实施的范畴。It should be noted that the structures, proportions, sizes, etc. shown in the drawings attached to this specification are only used to match the content disclosed in the specification, for those who are familiar with this technology to understand and read, and are not used to limit the implementation of the present invention. Limiting conditions, so there is no technical substantive meaning, any modification of structure, change of proportional relationship or adjustment of size, without affecting the effect and purpose of the present invention, should still fall within the scope of the present invention. The disclosed technical content must be within the scope covered. At the same time, terms such as "upper", "lower", "left", "right", "middle" and "one" quoted in this specification are only for the convenience of description and are not used to limit this specification. The practicable scope of the invention and the change or adjustment of its relative relationship shall also be regarded as the practicable scope of the present invention without any substantial change in the technical content.
参见图1～图6，See Figures 1 to 6,
一种航迹推演的校正方法，包括以下步骤：A correction method for track deduction, comprising the following steps:
S01：根据车辆起始点和目标点位置获得车辆航迹推演结果；S01: Obtain the vehicle track deduction result according to the position of the vehicle starting point and target point;
S02：将包括但不限于车辆实时感知数据、目标点位置表述、历史航迹推演结果输入航迹推演纠偏系统；S02: Input including but not limited to vehicle real-time perception data, target point position representation, and historical track deduction results into the track deduction correction system;
S03：航迹推演纠偏系统先识别目标点位置的追踪目标，再依据追踪目标位置度量里程计偏差，获得里程计和地图之间的坐标转换矩阵，纠正航迹推演偏差。S03: The track deduction correction system first identifies the tracking target at the position of the target point, and then measures the odometer deviation according to the tracking target position, obtains the coordinate transformation matrix between the odometer and the map, and corrects the track deduction deviation.
进一步地，所述步骤S01中的车辆航迹推演可用于定位导航和方向控制，除了对车辆姿进行估计，还可以从航迹推演中获得移动机器人前进速度和转向角速度。Further, the vehicle track deduction in the step S01 can be used for positioning navigation and direction control. In addition to estimating the vehicle attitude, the forward speed and steering angular velocity of the mobile robot can also be obtained from the track deduction.
进一步地，所述步骤S02中所述的车辆实时感知数据包括视觉感知数据、超声波感知数据和毫米波感知数据。Further, the real-time vehicle sensing data in step S02 includes visual sensing data, ultrasonic sensing data and millimeter wave sensing data.
进一步地，所述步骤S02中所述的车辆实时感知数据仅包含视觉感知数据，所述视觉感知数据为包含车辆的俯视图像。Further, the real-time perception data of the vehicle in the step S02 only includes visual perception data, and the visual perception data is a bird's-eye view image including the vehicle.
进一步地，所述步骤S02中所述的俯视图像，高位俯览环视图像，即TopView环视图：Further, the bird's-eye view image described in step S02 is a high-level bird's-eye view image, that is, a TopView ring view:
由于车位线是喷涂于地面的一种人工标识，AVM图像以俯视的方式将车身周围地面景象进行拼接，较好的保留了地面标识的几何表现。Since the parking space line is a kind of artificial mark sprayed on the ground, the AVM image splices the ground scene around the car body in a top-down manner, which better preserves the geometric performance of the ground mark.
进一步地，所述俯览环视图像的输入形式为：ros message，环视图像参数定义如下：Further, the input form of the bird's-eye view image is: ros message, and the parameters of the surround-view image are defined as follows:
Header headerHeader header
uint64indexuint64index
ImgRect blindAreaImgRect blindArea
ImgRect carPosImgRect carPos
int32phyHeightint32phyHeight
int32phyFrontint32phyFront
sensor_msgs/Image avmsensor_msgs/Image avm
相关成员说明：Description of relevant members:
header：主要包含时间戳信息header: mainly contains timestamp information
index：帧序号index: frame number
blindArea：中心盲区在图像中占据的区域blindArea: the area occupied by the central blind area in the image
avm：VYUY格式的彩色图片avm: color image in VYUY format
进一步地，所述俯览环视图像的获取方式：订阅zdada系统的TOPIC_TRACK_AVM_SRC。Further, the acquisition method of the bird's-eye view image: subscribe to the TOPIC_TRACK_AVM_SRC of the zdada system.
进一步地，所述俯览环视图像的输入要求包括下列条件中一种或几种：Further, the input requirements for the bird's-eye view image include one or more of the following conditions:
(1)观测范围：车头前方3m，车位后方3m，车身侧面的可是范围可以自动推算出。依据现有zadas系统提供的环视图片清晰度，能够在车辆后轴中心距离车位3m的范围内给出校正信号。(1) Observation range: 3m in front of the front of the car, 3m behind the parking space, and the range on the side of the vehicle body can be calculated automatically. According to the clarity of the surround view picture provided by the existing Zadas system, a correction signal can be given within 3m from the center of the rear axle of the vehicle to the parking space.
(2)图像拼接角度：45°。在此参数设置之下，生成的环视图可以在拼接处有较好的融合效果，不容易出现摄像头之间特别明显的错位感；因此在泊车过车中可以较好地满足车辆与车位之间呈现不同观测角度时观测的需求。(2) Image stitching angle: 45°. Under this parameter setting, the generated surround view can have a better fusion effect at the splicing point, and it is not easy to have a particularly obvious sense of dislocation between the cameras; therefore, it can better meet the needs of the vehicle and the parking space when parking and passing. Observation requirements when presenting different observation angles.
(3)图片尺寸：高600像素，宽480像素，宽高尺寸比例为1。按照此前设定的观测范围，假设车辆长度5m。每一个像素代表的坐标轴向距离为2.16cm。如果检测精度在3个像素以内，就可以保证输出结果的分辨精度在5cm以内。(3) Image size: 600 pixels high, 480 pixels wide, and the ratio of width to height is 1. According to the previously set observation range, it is assumed that the vehicle length is 5m. Each pixel represents a coordinate axial distance of 2.16 cm. If the detection accuracy is within 3 pixels, the resolution accuracy of the output result can be guaranteed to be within 5cm.
(4)发送频率：2～3Hz。根据车辆控制系统的要求，每秒钟得到2～3次校正即可满足要求，所有的处理流程在CPU上的耗时不超过250ms。(4) Sending frequency: 2~3Hz. According to the requirements of the vehicle control system, 2 to 3 corrections per second can meet the requirements, and the time consumption of all processing procedures on the CPU does not exceed 250ms.
进一步地，所述步骤S02中目标点位置表述用于自俯览环视图像中分割与本次泊车过程相关的信息，即缩小目标点位置的检测范围。Further, the expression of the position of the target point in the step S02 is used to segment information related to the current parking process from the bird's-eye view image, that is, to narrow the detection range of the position of the target point.
进一步地，所述步骤S02中目标点位置的输入形式为ros message，其数据包表达定义如下：Further, the input form of the target point position in the step S02 is ros message, and its data packet expression is defined as follows:
Header headerHeader header
SlotVertex slotSlotVertex slot
SlotVertex boundrySlotVertex boundary
int32typeint32type
int32valid_typeint32valid_type
int32validint32valid
int32idint32id
相关成员说明：Description of relevant members:
header：主要包含时间戳信息header: mainly contains timestamp information
slot：包含停车位4个顶点在zadas坐标系下的物理坐标slot: contains the physical coordinates of the 4 vertices of the parking space in the zadas coordinate system
type：车位类型。type: parking space type.
进一步地，所述步骤S02中目标点位置的获取方式：订阅zdada系统的TOPIC_APA_TARGET。Further, the method of acquiring the position of the target point in the step S02: subscribe to TOPIC_APA_TARGET of the zdada system.
进一步地，所述步骤S02中目标点位置的输入要求：在某一确定的坐标系下，发送构成一个车位的4个顶点的物理坐标位置，该信号只需要在泊车开始阶段，车辆静止时，发送一次即可。Further, the input requirement of the target point position in the step S02: in a certain coordinate system, send the physical coordinate positions of the 4 vertices that constitute a parking space, the signal only needs to be , send it once.
进一步地，所述步骤S02中输入航迹推演纠偏系统的还包括泊车状态信号，泊车状态信号不是系统基础服务，是根据需求启动的，在行车过程中并不需求提供此模块的输出，避免不必要的系统负担。例如，在泊车过程中，如果车辆俯览环视图中在车辆路径规划范围内突然出现障碍物或者根据其他感知设备例如超声波雷达或者毫米波雷达感知到障碍物而必须立即停止时，将此信号输入至航迹推演模块。Further, in the step S02, the input to the track derivation correction system also includes a parking status signal. The parking status signal is not a basic service of the system, but is activated according to requirements, and the output of this module does not need to be provided during the driving process. Avoid unnecessary system burden. For example, in the process of parking, if an obstacle suddenly appears in the vehicle's path planning range in the top view of the vehicle or it must be stopped immediately according to other sensing devices such as ultrasonic radar or millimeter wave radar. Input to the trajectory derivation module.
进一步地，所述步骤S02中的泊车状态信号的输入形式：ros message，泊车状态信号的数据包表达定义如下Further, the input form of the parking state signal in the step S02 is: ros message, and the data packet expression of the parking state signal is defined as follows
int32apaStageint32apaStage
相关信号含义说明：Explanation of the meaning of related signals:
APA_STATUS_PI_GUIDANCE：开始泊入APA_STATUS_PI_GUIDANCE: start to park in
APA_STATUS_PO_GUIDANCE：开始泊出APA_STATUS_PO_GUIDANCE: start to park out
APA_STATUS_SUSPEND：功能挂起APA_STATUS_SUSPEND: function is suspended
APA_STATUS_PI_SLOT_SEARCHING：正在搜寻车位APA_STATUS_PI_SLOT_SEARCHING: Searching for a parking space
APA_STATUS_PI_SLOT_CONFIRMED：目标车位已确认APA_STATUS_PI_SLOT_CONFIRMED: The target parking space has been confirmed
APA_STATUS_STANDBY：等待开始泊车APA_STATUS_STANDBY: Waiting to start parking
进一步地，所述步骤S02中的泊车状态信号的获取方式：订阅ZADAS系统的TOPIC_APA_STAGE。Further, the way of acquiring the parking state signal in the step S02 is: subscribe to TOPIC_APA_STAGE of the ZADAS system.
进一步地，所述步骤S02中的泊车状态信号的输入要求：无特殊要求，监听即可。Further, the input requirement of the parking state signal in the step S02: no special requirement, just monitor.
进一步地，所述步骤S02中输入航迹推演纠偏系统的还包括车辆档位信号，因为在整个泊车过程中并不是所有的行驶阶段都是泊入行为，因此需要在倒车模式下车辆档位信号应当给航迹推演纠偏系统提供校正输出。Further, the input to the track derivation correction system in the step S02 also includes the vehicle gear position signal, because not all driving stages in the entire parking process are parking behaviors, so the vehicle gear position needs to be changed in the reverse mode. The signal should provide a correction output to the trajectory correction system.
进一步地，所述步骤S02中输入航迹推演纠偏系统的还包括车辆档位信号的输入形式：car_live_info，所述车辆档位信号数据包的定义如下：GEAR_STATUS_RFurther, the input form of the track deduction correction system in the step S02 also includes the input form of the vehicle gear signal: car_live_info, and the definition of the vehicle gear signal data packet is as follows: GEAR_STATUS_R
进一步地，所述车辆档位信号获取方式：调用get_car_gear()。Further, the acquisition method of the vehicle gear position signal: calling get_car_gear().
进一步地，所述步骤S03中航迹推演纠偏系统先识别目标点位置的追踪目标，其追踪目标为车位线。Further, in the step S03, the track derivation correction system first identifies the tracking target at the target point, and the tracking target is the parking space line.
进一步地，所述步骤S03中里程计和地图之间的坐标转换矩阵，地图坐标代表了客观现实中存在的一些标识物的位置，里程计航迹推演坐标表达了依据车辆行驶轨迹推测的车辆位置，而车辆实时视觉感知数据中的俯览环视图像中观测到的信息来源于数据库链接baselink，存在于地图中，图像得到的观测，相当于是从地图产生的；从局部的角度来看，数据库链接baselink的观测是与地图一致的，里程计和地图之间的坐标转换矩阵就是从航迹推演变换回map，因此也代表了需要纠正的偏差，如果衡量图像检测到的目标点位置信息与航迹推演推测的车位信息间存在的误差，就可以校正航迹推演已形成的误差。Further, in the coordinate transformation matrix between the odometer and the map in the step S03, the map coordinates represent the positions of some markers existing in the objective reality, and the odometer track derivation coordinates express the estimated vehicle position based on the vehicle trajectory , while the information observed in the top view image in the vehicle's real-time visual perception data comes from the database link baselink, which exists in the map, and the observation obtained from the image is equivalent to being generated from the map; from a local point of view, the database link The baselink observation is consistent with the map. The coordinate transformation matrix between the odometer and the map is transformed from the track derivation back to the map, so it also represents the deviation that needs to be corrected. If the position information of the target point detected by the image is compared with the track The errors existing in the deduced parking space information can correct the errors formed by the track deduction.
进一步地，所述里程计到地图之间的坐标转换矩阵的输出方式：ZADAS系统的广播TOPIC_TF_MAP_ODOM_CONF。Further, the output method of the coordinate transformation matrix between the odometer and the map: broadcast TOPIC_TF_MAP_ODOM_CONF of the ZADAS system.
进一步地，所述步骤S03还包括对程计到地图之间的坐标转换矩阵校正的信号评价机制，为了能够让使用者了解信号质量，以此来决定是否接受本次校正信号，在发出转换矩阵的同时给出信号质量评价指标。Further, the step S03 also includes a signal evaluation mechanism for the correction of the coordinate transformation matrix between the odometer and the map. In order to allow the user to understand the signal quality and decide whether to accept the correction signal this time, after sending out the transformation matrix At the same time, the signal quality evaluation index is given.
进一步地，所述步骤S03还包括对程计到地图之间的坐标转换矩阵校正的信号质量评价指标包括至少三类，即包含平行度，直线证据累积数量，直线证据分布方差。Further, the step S03 also includes at least three types of signal quality evaluation indicators corrected for the coordinate transformation matrix between the odometer and the map, including parallelism, the cumulative number of straight-line evidence, and the distribution variance of the straight-line evidence.
(1)平行度-parallelism(1) Parallelism-parallelism
当两条直线都检测出的情况下，给出一个0～1的浮点数，越接近与1，平行度越好，检测的可信赖度越高When both straight lines are detected, a floating-point number from 0 to 1 is given. The closer to 1, the better the parallelism and the higher the reliability of the detection.
(2)直线证据累积数量-leftDispersion，rightDispersion(2) Cumulative quantity of linear evidence - leftDispersion, rightDispersion
表明了在搜集了多少数据后，给出了这条直线信息，左右两条校准线各有一个此项指标(3)直线证据分布方差-leftEvidence，rightEvidenceIndicates how much data has been collected, and the straight line information is given, and the left and right calibration lines each have an indicator of this item (3) The variance of the straight line evidence distribution-leftEvidence, rightEvidence
表明了搜集到的直线证据的离散程度。Indicates the degree of dispersion of the collected linear evidence.
进一步地，所述步骤S03还包括对程计到地图之间的坐标转换矩阵校正的信号质量评价指标的情况下，所述里程计到地图之间的坐标转换矩阵的数据包表达定义如下：Further, the step S03 also includes that in the case of correcting the signal quality evaluation index for the coordinate transformation matrix between the odometer and the map, the data package expression of the coordinate transformation matrix between the odometer and the map is defined as follows:
Header headerHeader header
float64leftDispersionfloat64leftDispersion
float64rightDispersionfloat64rightDispersion
float64parallelismfloat64parallelism
int32leftEvidenceint32leftEvidence
int32rightEvidenceint32rightEvidence
geometry_msgs/TransformStamped transgeometry_msgs/TransformStamped trans
成员说明：Member Description:
header：主要包含时间戳信息header: mainly contains timestamp information
leftDispersion：左侧校正线累积证据方差leftDispersion: cumulative evidence variance of the left correction line
rightDispersion：右侧校正线累积证据方差rightDispersion: cumulative evidence variance of the right correction line
parallelism：两条校正线平行度parallelism: Parallelism of two correction lines
leftEvidence：左侧校正线累积证据度量leftEvidence: left correction line cumulative evidence metric
rightEvidence：右侧校正线累积证据度量。rightEvidence: The right correction line cumulative evidence metric.
进一步地，所述步骤S03中的航迹推演纠偏系统先识别目标点位置的追踪目标，再依据追踪目标位置度量里程计偏差，获得里程计和地图之间的坐标转换矩阵，纠正航迹推演偏差，并输出航迹推演位置变换信号，在泊车过程中，使用航迹推演位置变换信号可以实时更新目标车位的位置，并实时了解目标车位在图像以及物理坐标系中的位置，以便根据实时位置制定相应的路径规划策略。Further, the track deduction correction system in the step S03 first identifies the tracking target at the target point position, and then measures the odometer deviation according to the tracking target position to obtain the coordinate transformation matrix between the odometer and the map, and correct the track deduction deviation , and output the track derivation position transformation signal. During the parking process, the position of the target parking space can be updated in real time by using the track deduction position transformation signal, and the position of the target parking space in the image and physical coordinate system can be known in real time, so that the real-time position Formulate corresponding path planning strategies.
进一步地，所述步骤S03中航迹推演位置变换信号的输入形式：ros message，航迹推演位置变换信号数据包表达定义如下：tf2_msgs::TFMessage messageFurther, the input form of the track derivation position change signal in the step S03 is: ros message, and the expression of the track deduction position change signal data packet is defined as follows: tf2_msgs::TFMessage message
相关成员说明：Description of relevant members:
message：3×3的位姿转换矩阵。message: 3×3 pose transformation matrix.
进一步地，所述步骤S03中航迹推演位置变换信号的获取方式：订阅zdada系统的TOPIC_TF_ODOM_BASELINK。Further, the acquisition method of the track derivation position transformation signal in the step S03: subscribe to the TOPIC_TF_ODOM_BASELINK of the zdada system.
进一步地，所述步骤S03中航迹推演位置变换信号的输入要求：无特殊要求，监听即可。Further, the input requirements of the track derivation position transformation signal in the step S03: no special requirements, just monitor.
一种移动终端，其可以是车载终端或手机移动终端，其执行上述航迹推演的校正方法或自车载终端航迹推演的校正方法获得航迹推演结果以更新车辆定位的手机移动终端。A mobile terminal, which may be a vehicle-mounted terminal or a mobile phone mobile terminal, which implements the above-mentioned correction method for track deduction or a mobile terminal for updating vehicle positioning by obtaining the result of track deduction from the correction method for vehicle-mounted terminal track deduction.
一种计算机存储介质，其是依照上述航迹推演的校正方法所编写的计算机程序。A computer storage medium, which is a computer program written according to the correction method of the above-mentioned flight path derivation.
作为优选实施例，本实施例还提供一种终端设备，如可以执行程序的智能手机、平板电脑、笔记本电脑、台式计算机、机架式云端、刀片式云端、塔式云端或机柜式云端(包括独立的云端，或者多个云端所组成的云端集群)等。本实施例的终端设备至少包括但不限于：可通过系统总线相互通信连接的存储器、处理器。需要指出的是，具有组件存储器、处理器的终端设备，但是应理解的是，并不要求实施所有示出的组件，可以替代的航迹推演的校正方法实施更多或者更少的组件。As a preferred embodiment, this embodiment also provides a terminal device, such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack cloud, a blade cloud, a tower cloud or a cabinet cloud (including independent cloud, or a cloud cluster composed of multiple clouds), etc. The terminal device in this embodiment at least includes but is not limited to: a memory and a processor that can be communicatively connected to each other through a system bus. It should be pointed out that the terminal device has components memory, processor, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented in alternative dead-route correction methods.
作为优选实施例，存储器(即可读存储介质)包括闪存、硬盘、多媒体卡、卡型存储器(例如，SD或DX存储器等)、随机访问存储器(RAM)、静态随机访问存储器(SRAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、可编程只读存储器(PROM)、磁性存储器、磁盘、光盘等。在一些实施例中，存储器可以是计算机设备的内部存储单元，例如该计算机设备的硬盘或内存。在另一些实施例中，存储器也可以是计算机设备的外部存储设备，例如该计算机设备上配备的插接式硬盘，智能存储卡(Smart Media Card,SMC)，安全数字(SecureDigital,SD)卡，闪存卡(Flash Card)等。当然，存储器还可以既包括计算机设备的内部存储单元也包括其外部存储设备。本实施例中，存储器通常用于存储安装于计算机设备的操作系统和各类应用软件，例如实施例中的航迹推演的校正程序代码等。此外，存储器还可以用于暂时地存储已经输出或者将要输出的各类数据。As a preferred embodiment, the memory (ie, readable storage medium) includes flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), Read Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Programmable Read Only Memory (PROM), Magnetic Memory, Magnetic Disk, Optical Disk, etc. In some embodiments, the memory may be an internal storage unit of the computer device, such as a hard disk or internal memory of the computer device. In other embodiments, the memory may also be an external storage device of the computer device, such as a plug-in hard disk equipped on the computer device, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, Flash Card (Flash Card), etc. Of course, the storage may also include both the internal storage unit of the computer device and its external storage device. In this embodiment, the memory is usually used to store the operating system and various application software installed in the computer equipment, such as the correction program code of the track deduction in the embodiment. In addition, the memory can also be used to temporarily store various types of data that have been output or will be output.
本实施例还提供一种计算机可读存储介质，如闪存、硬盘、多媒体卡、卡型存储器(例如，SD或DX存储器等)、随机访问存储器(RAM)、静态随机访问存储器(SRAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、可编程只读存储器(PROM)、磁性存储器、磁盘、光盘、云端、App应用商城等等，其上存储有计算机程序，程序被处理器执行时实现相应功能。本实施例的计算机可读存储介质用于航迹推演的校正程序，被处理器执行时实现航迹推演的校正程序实施例中的航迹推演的校正方法。This embodiment also provides a computer-readable storage medium, such as flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), only Read memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, cloud, App application store, etc., on which computer programs are stored, The corresponding functions are realized when the program is executed by the processor. The computer-readable storage medium of this embodiment is used for the correction program of the track deduction, and implements the correction method of the track deduction in the correction program embodiment of the track deduction when executed by the processor.
上述实施例仅例示性说明本发明的原理及其功效，而非用于限制本发明。任何熟悉此技术的人士皆可在不违背本发明的精神及范畴下，对上述实施例进行修饰或改变。因此，举凡所属技术领域中包括通常知识者在未脱离本发明所揭示的精神与技术思想下所完成的一切等效修饰或改变，仍应由本发明的权利要求所涵盖。The above-mentioned embodiments only illustrate the principles and effects of the present invention, but are not intended to limit the present invention. Anyone skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or changes made by those skilled in the art without departing from the spirit and technical ideas disclosed in the present invention should still be covered by the claims of the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910680100.6ACN110555801B (en) | 2019-07-26 | 2019-07-26 | A correction method, terminal and storage medium for track deduction |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910680100.6ACN110555801B (en) | 2019-07-26 | 2019-07-26 | A correction method, terminal and storage medium for track deduction |
| Publication Number | Publication Date |
|---|---|
| CN110555801Atrue CN110555801A (en) | 2019-12-10 |
| CN110555801B CN110555801B (en) | 2024-08-16 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910680100.6AActiveCN110555801B (en) | 2019-07-26 | 2019-07-26 | A correction method, terminal and storage medium for track deduction |
| Country | Link |
|---|---|
| CN (1) | CN110555801B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112987029A (en)* | 2021-02-09 | 2021-06-18 | 上海振华重工(集团)股份有限公司 | Positioning method, system, equipment and medium suitable for driving equipment |
| CN113340313A (en)* | 2020-02-18 | 2021-09-03 | 北京四维图新科技股份有限公司 | Navigation map parameter determination method and device |
| CN114248761A (en)* | 2021-12-10 | 2022-03-29 | 重庆长安汽车股份有限公司 | Target track discretization method, parking path tracking error optimization method and system |
| CN114274948A (en)* | 2021-12-15 | 2022-04-05 | 武汉光庭信息技术股份有限公司 | Automatic parking method and device based on 360-degree panorama |
| CN114419943A (en)* | 2021-12-29 | 2022-04-29 | 宜昌测试技术研究所 | A multi-AUV semi-offline tactical deduction system |
| CN114705198A (en)* | 2022-04-06 | 2022-07-05 | 智道网联科技(北京)有限公司 | Vehicle positioning method, apparatus, electronic device, and computer-readable storage medium |
| CN115953328A (en)* | 2023-03-13 | 2023-04-11 | 天津所托瑞安汽车科技有限公司 | Target correction method and system and electronic equipment |
| CN118968812A (en)* | 2024-10-11 | 2024-11-15 | 松立控股集团股份有限公司 | Automatic replenishment method for abnormal parking orders based on Lagrange interpolation |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102147262A (en)* | 2011-01-11 | 2011-08-10 | 北京理工大学 | Method for correcting navigation deviation and navigation display adopting same |
| CN104360366A (en)* | 2014-11-05 | 2015-02-18 | 中国科学院嘉兴微电子与系统工程中心 | Dead reckoning and GPS (global positioning system) combined positioning method |
| CN106412826A (en)* | 2016-09-07 | 2017-02-15 | 清华大学 | Indoor positioning method and positioning device based on multi-source information fusion |
| CN106767894A (en)* | 2015-11-20 | 2017-05-31 | 北方信息控制集团有限公司 | A kind of Big Dipper/odometer combination scaling method for inertial navigation |
| WO2017178232A1 (en)* | 2016-04-15 | 2017-10-19 | Valeo Schalter Und Sensoren Gmbh | Method for operating a driver assistance system of a motor vehicle, computing device, driver assistance system, and motor vehicle |
| CN107389088A (en)* | 2017-05-27 | 2017-11-24 | 纵目科技（上海）股份有限公司 | Error correcting method, device, medium and the equipment of vehicle-mounted inertial navigation |
| CN108492619A (en)* | 2018-04-17 | 2018-09-04 | 济南浪潮高新科技投资发展有限公司 | A kind of intelligent parking system and method |
| CN108871336A (en)* | 2018-06-20 | 2018-11-23 | 湘潭大学 | A kind of vehicle location estimating system and method |
| CN109029417A (en)* | 2018-05-21 | 2018-12-18 | 南京航空航天大学 | Unmanned plane SLAM method based on mixing visual odometry and multiple dimensioned map |
| CN109085840A (en)* | 2018-09-21 | 2018-12-25 | 大连维德智能视觉技术创新中心有限公司 | Vehicle navigation control system and control method based on binocular vision |
| CN109131317A (en)* | 2018-07-23 | 2019-01-04 | 同济大学 | Automatic vertical parking system and method based on multisection type planning and machine learning |
| KR101941654B1 (en)* | 2018-09-28 | 2019-01-24 | (주)신한항업 | Image editing system for gps coordinate on digital map searching position and link information |
| CN109556617A (en)* | 2018-11-09 | 2019-04-02 | 同济大学 | A kind of map elements extracting method of automatic Jian Tu robot |
| CN109631896A (en)* | 2018-07-23 | 2019-04-16 | 同济大学 | A kind of parking lot autonomous parking localization method based on vehicle vision and motion information |
| CN109710724A (en)* | 2019-03-27 | 2019-05-03 | 深兰人工智能芯片研究院（江苏）有限公司 | A kind of method and apparatus of building point cloud map |
| KR20190057710A (en)* | 2017-11-20 | 2019-05-29 | 현대오트론 주식회사 | Autonomous parking assistance system using lidar sensor and indoor posiontioning method thereof |
| CN109945858A (en)* | 2019-03-20 | 2019-06-28 | 浙江零跑科技有限公司 | A multi-sensor fusion localization method for low-speed parking driving scenarios |
| CN110017850A (en)* | 2019-04-19 | 2019-07-16 | 小狗电器互联网科技（北京）股份有限公司 | A kind of gyroscopic drift estimation method, device and positioning system |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102147262A (en)* | 2011-01-11 | 2011-08-10 | 北京理工大学 | Method for correcting navigation deviation and navigation display adopting same |
| CN104360366A (en)* | 2014-11-05 | 2015-02-18 | 中国科学院嘉兴微电子与系统工程中心 | Dead reckoning and GPS (global positioning system) combined positioning method |
| CN106767894A (en)* | 2015-11-20 | 2017-05-31 | 北方信息控制集团有限公司 | A kind of Big Dipper/odometer combination scaling method for inertial navigation |
| WO2017178232A1 (en)* | 2016-04-15 | 2017-10-19 | Valeo Schalter Und Sensoren Gmbh | Method for operating a driver assistance system of a motor vehicle, computing device, driver assistance system, and motor vehicle |
| CN106412826A (en)* | 2016-09-07 | 2017-02-15 | 清华大学 | Indoor positioning method and positioning device based on multi-source information fusion |
| CN107389088A (en)* | 2017-05-27 | 2017-11-24 | 纵目科技（上海）股份有限公司 | Error correcting method, device, medium and the equipment of vehicle-mounted inertial navigation |
| KR20190057710A (en)* | 2017-11-20 | 2019-05-29 | 현대오트론 주식회사 | Autonomous parking assistance system using lidar sensor and indoor posiontioning method thereof |
| CN108492619A (en)* | 2018-04-17 | 2018-09-04 | 济南浪潮高新科技投资发展有限公司 | A kind of intelligent parking system and method |
| CN109029417A (en)* | 2018-05-21 | 2018-12-18 | 南京航空航天大学 | Unmanned plane SLAM method based on mixing visual odometry and multiple dimensioned map |
| CN108871336A (en)* | 2018-06-20 | 2018-11-23 | 湘潭大学 | A kind of vehicle location estimating system and method |
| CN109131317A (en)* | 2018-07-23 | 2019-01-04 | 同济大学 | Automatic vertical parking system and method based on multisection type planning and machine learning |
| CN109631896A (en)* | 2018-07-23 | 2019-04-16 | 同济大学 | A kind of parking lot autonomous parking localization method based on vehicle vision and motion information |
| CN109085840A (en)* | 2018-09-21 | 2018-12-25 | 大连维德智能视觉技术创新中心有限公司 | Vehicle navigation control system and control method based on binocular vision |
| KR101941654B1 (en)* | 2018-09-28 | 2019-01-24 | (주)신한항업 | Image editing system for gps coordinate on digital map searching position and link information |
| CN109556617A (en)* | 2018-11-09 | 2019-04-02 | 同济大学 | A kind of map elements extracting method of automatic Jian Tu robot |
| CN109945858A (en)* | 2019-03-20 | 2019-06-28 | 浙江零跑科技有限公司 | A multi-sensor fusion localization method for low-speed parking driving scenarios |
| CN109710724A (en)* | 2019-03-27 | 2019-05-03 | 深兰人工智能芯片研究院（江苏）有限公司 | A kind of method and apparatus of building point cloud map |
| CN110017850A (en)* | 2019-04-19 | 2019-07-16 | 小狗电器互联网科技（北京）股份有限公司 | A kind of gyroscopic drift estimation method, device and positioning system |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113340313A (en)* | 2020-02-18 | 2021-09-03 | 北京四维图新科技股份有限公司 | Navigation map parameter determination method and device |
| CN113340313B (en)* | 2020-02-18 | 2024-04-16 | 北京四维图新科技股份有限公司 | Method and device for determining navigation map parameters |
| CN112987029A (en)* | 2021-02-09 | 2021-06-18 | 上海振华重工(集团)股份有限公司 | Positioning method, system, equipment and medium suitable for driving equipment |
| CN114248761A (en)* | 2021-12-10 | 2022-03-29 | 重庆长安汽车股份有限公司 | Target track discretization method, parking path tracking error optimization method and system |
| CN114248761B (en)* | 2021-12-10 | 2024-06-04 | 重庆长安汽车股份有限公司 | Target track discretization method, parking path tracking error optimization method and system |
| CN114274948A (en)* | 2021-12-15 | 2022-04-05 | 武汉光庭信息技术股份有限公司 | Automatic parking method and device based on 360-degree panorama |
| CN114419943A (en)* | 2021-12-29 | 2022-04-29 | 宜昌测试技术研究所 | A multi-AUV semi-offline tactical deduction system |
| CN114419943B (en)* | 2021-12-29 | 2024-05-10 | 宜昌测试技术研究所 | Multi-AUV semi-offline tactic deduction system |
| CN114705198A (en)* | 2022-04-06 | 2022-07-05 | 智道网联科技(北京)有限公司 | Vehicle positioning method, apparatus, electronic device, and computer-readable storage medium |
| CN115953328A (en)* | 2023-03-13 | 2023-04-11 | 天津所托瑞安汽车科技有限公司 | Target correction method and system and electronic equipment |
| CN118968812A (en)* | 2024-10-11 | 2024-11-15 | 松立控股集团股份有限公司 | Automatic replenishment method for abnormal parking orders based on Lagrange interpolation |
| CN118968812B (en)* | 2024-10-11 | 2025-02-07 | 松立控股集团股份有限公司 | Automatic replenishment method for abnormal parking orders based on Lagrange interpolation |
| Publication number | Publication date |
|---|---|
| CN110555801B (en) | 2024-08-16 |
| Publication | Publication Date | Title |
|---|---|---|
| CN110555801B (en) | A correction method, terminal and storage medium for track deduction | |
| CN109949439B (en) | Driving live-action information labeling method and device, electronic equipment and medium | |
| CN110869700B (en) | System and method for determining vehicle position | |
| US11125566B2 (en) | Method and apparatus for determining a vehicle ego-position | |
| CN108749813B (en) | Automatic parking system and parking method | |
| CN115235500B (en) | Pose correction method and device based on lane line constraints, full working condition static environment modeling method and device | |
| CN112884892B (en) | Unmanned mine car position information processing system and method based on road side device | |
| US20210149415A1 (en) | Method and system for localized travel lane perception | |
| CN110515376B (en) | Evaluation method, terminal and storage medium for track deduction correction | |
| CN112115857A (en) | Lane line identification method and device for intelligent automobile, electronic equipment and medium | |
| CN203480561U (en) | Driving state measurement system of non-contact unmanned vehicle | |
| US12347319B2 (en) | Platoon positioning system and method based on vehicle to vehicle communication and using relative pose information between vehicles in a platoon | |
| CN113459951A (en) | Vehicle exterior environment display method and device, vehicle, equipment and storage medium | |
| CN111881245B (en) | Method, device, equipment and storage medium for generating visibility dynamic map | |
| US20230098314A1 (en) | Localizing and updating a map using interpolated lane edge data | |
| WO2019220765A1 (en) | Self-position estimation device | |
| CN115331482A (en) | Vehicle early warning prompting method and device, base station and storage medium | |
| CN110083158B (en) | Method and equipment for determining local planning path | |
| CN108725319A (en) | A kind of image-type reversing guidance method | |
| CN117848357A (en) | Map construction method, vehicle-mounted device, vehicle and computer program product | |
| WO2020258222A1 (en) | Method and system for identifying object | |
| US20230065761A1 (en) | Remote driver support method, remote driver support system, and storage medium | |
| CN117168471A (en) | Vehicle positioning judgment method and device, vehicle-mounted terminal and vehicle | |
| CN115923783A (en) | Automatic vehicle driving obstacle avoidance method and system based on high-precision map lane lines | |
| CN116310068A (en) | HUD display method and system based on AR technology and readable storage medium |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | Denomination of invention:A correction method, terminal, and storage medium for trajectory deduction Granted publication date:20240816 Pledgee:China Construction Bank Corporation Shanghai Zhangjiang Branch Pledgor:ZONGMU TECHNOLOGY (SHANGHAI) Co.,Ltd. Registration number:Y2025980002018 |