公开(公告)号：US20160209211A1

公开(公告)日：2016-07-21

申请号：US14598894

申请日：2015-01-16

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Xiaofeng Frank Song ,  Xian Zhang ,  Shuqing Zeng

IPC: G01B21/24

CPC classification number: G01B21/24 ,  G01S7/4026 ,  G01S7/4972 ,  G01S13/931 ,  G01S17/936 ,  G01S2007/403 ,  G01S2013/9367 ,  G01S2013/9375 ,  G01S2013/9378 ,  G01S2013/9385

Abstract: A vehicle system and method that can determine object sensor misalignment while a host vehicle is being driven, and can do so within a single sensor cycle through the use of stationary and moving target objects and does not require multiple sensors with overlapping fields of view. In an exemplary embodiment where the host vehicle is traveling in a generally straight line, one or more object misalignment angle(s) αo between an object axis and a sensor axis are calculated and used to determine the actual sensor misalignment angle α.

Abstract translation: 一种车辆系统和方法，其可以在主车辆被驱动时确定物体传感器未对准，并且可以通过使用固定和移动的目标物体在单个传感器周期内进行，并且不需要具有重叠视场的多个传感器。 在本车辆以大致直线行进的示例性实施例中，计算物体轴和传感器轴之间的一个或多个物体未对准角αo，并用于确定实际的传感器未对准角α。

公开(公告)号：US20160064806A1

公开(公告)日：2016-03-03

申请号：US14473547

申请日：2014-08-29

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Kevin Geary ,  Joseph S. Colburn ,  Daniel J. Gregoire ,  Hooman Kazemi ,  Shuqing Zeng

IPC: H01Q1/32 ,  H01Q9/04 ,  H01Q19/02 ,  G01S7/03 ,  G01S13/93

CPC classification number: H01Q1/3233 ,  G01S7/03 ,  G01S13/931 ,  G01S2013/9371 ,  G01S2013/9375 ,  G01S2013/9378 ,  G01S2013/9392 ,  G01S2013/9396 ,  H01Q1/40 ,  H01Q21/065 ,  H01Q21/20

Abstract: A flexible, printable antenna for automotive radar. The antenna can be printed onto a thin, flexible substrate, and thus can be bent to conform to a vehicle body surface with compound curvature. The antenna can be mounted to the interior of a body surface such as a bumper fascia, where it cannot be seen but can transmit radar signals afield. The antenna can also be mounted to and blended into the exterior of an inconspicuous body surface, or can be made transparent and mounted to the interior or exterior of a glass surface. The antenna includes an artificial impedance surface which is tailored based on the three-dimensional shape of the surface to which the antenna is mounted and the desired radar wave pattern. The antenna can be used for automotive collision avoidance applications using 22-29 GHz or 76-81 GHz radar, and has a large aperture to support high angular resolution of radar data.

Abstract translation: 用于汽车雷达的灵活可打印天线。 天线可以印刷在薄的柔性基底上，因此可以弯曲以符合具有复合曲率的车身表面。 天线可以安装在诸如保险杠面板之类的身体表面的内部，其中它不能被看到，但是可以在远的地方传输雷达信号。 天线也可以安装到并且混合到不显眼的身体表面的外部，或者可以被制成透明的并且安装到玻璃表面的内部或外部。 天线包括基于安装天线的表面的三维形状和期望的雷达波形图案来裁剪的人造阻抗表面。 该天线可用于使用22-29 GHz或76-81 GHz雷达的汽车防撞应用，并具有大孔径以支持雷达数据的高角度分辨率。

公开(公告)号：US09199643B1

公开(公告)日：2015-12-01

申请号：US14497099

申请日：2014-09-25

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Shuqing Zeng

IPC: G06F17/10 ,  B60W30/095

CPC classification number: B60W40/10 ,  B60W2420/52 ,  B60W2550/10

Abstract: A method for determining an actual trajectory of a vehicle using object detection data and vehicle dynamics data. An object detection system identifies point objects and extended objects in proximity to the vehicle, where the point objects are less than a meter in length and width. An updated vehicle pose is calculated which optimally transposes the point objects in the scan data to a target list of previously-identified point objects. The updated vehicle pose is further refined by iteratively calculating a pose which optimally transposes the extended objects in the scan data to a target model of previously-identified extended objects, where the iteration is used to simultaneously determine a probability coefficient relating the scan data to the target model. The updated vehicle pose is used to identify the actual trajectory of the vehicle, which is compared to a planned path in a collision avoidance system.

Abstract translation: 一种使用物体检测数据和车辆动力学数据来确定车辆的实际轨迹的方法。 物体检测系统识别车辆附近的点对象和扩展对象，其中点对象的长度和宽度小于一米。 计算更新的车辆姿态，其将扫描数据中的点对象最佳地转换到先前识别的点对象的目标列表。 通过迭代地计算最佳地将扫描数据中的扩展对象转移到先前识别的扩展对象的目标模型的姿态来进一步改进更新的车辆姿势，其中迭代用于同时确定将扫描数据与 目标模型。 更新的车辆姿态用于识别车辆的实际轨迹，其与避碰系统中的计划路径进行比较。

公开(公告)号：US09129211B2

公开(公告)日：2015-09-08

申请号：US13789379

申请日：2013-03-07

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Shuqing Zeng

IPC: G06F17/50 ,  G06N7/00 ,  G01S17/66 ,  G01S17/93

CPC classification number: G06N7/005 ,  G01S7/4808 ,  G01S17/023 ,  G01S17/66 ,  G01S17/87 ,  G01S17/936 ,  G06F17/5009

Abstract: A system and method for fusing the outputs from multiple LiDAR sensors on a vehicle. The method includes providing object files for objects detected by the sensors at a previous sample time, where the object files identify the position, orientation and velocity of the detected objects. The method also includes receiving a plurality of scan returns from objects detected in the field-of-view of the sensors at a current sample time and constructing a point cloud from the scan returns. The method then segments the scan points in the point cloud into predicted clusters, where each cluster initially identifies an object detected by the sensors. The method matches the predicted clusters with predicted object models generated from objects being tracked during the previous sample time. The method creates new object models, deletes dying object models and updates the object files based on the object models for the current sample time.

Abstract translation: 用于将来自车辆上的多个LiDAR传感器的输出进行融合的系统和方法。 该方法包括在先前的采样时间提供由传感器检测到的物体的目标文件，其中目标文件识别被检测物体的位置，取向和速度。 该方法还包括在当前采样时间从传感器的视场中检测到的物体接收多个扫描返回，并从扫描返回构建点云。 然后，该方法将点云中的扫描点分割成预测的簇，其中每个簇最初识别由传感器检测到的对象。 该方法将预测的聚类与在之前的采样时间内跟踪的对象产生的预测对象模型进行匹配。 该方法创建新的对象模型，删除垂死对象模型，并根据当前采样时间的对象模型更新对象文件。