摘要：【中文】根据一个实施方式，系统基于ADV的地图和路线信息确定第一轨迹(例如，参考线路)。该系统确定第一轨迹的预定长度的最大曲率。该系统基于最大曲率确定采样衰减比。该系统为第一轨迹生成一个或多个采样点集合，其中，每个采样点集合包括以基于采样衰减比的横向距离分开的一个或多个采样点。该系统基于采样点集合为ADV生成第二轨迹以控制ADV，其中，第二轨迹基于第一轨迹的最大曲率移动到第一轨迹的左侧或右侧。 【EN】According to one embodiment, the system determines a first trajectory (e.g., a reference line) based on the map of the ADV and the route information. The system determines a maximum curvature of a predetermined length of the first trajectory. The system determines a sample attenuation ratio based on the maximum curvature. The system generates one or more sets of sampling points for the first trajectory, wherein each set of sampling points includes one or more sampling points separated by a lateral distance based on a sampling attenuation ratio. The system generates a second trajectory for the ADV based on the set of sampling points to control the ADV, wherein the second trajectory moves to the left or right of the first trajectory based on the maximum curvature of the first trajectory.

摘要：【中文】在一个实施方式中，接收一组LIDAR图像，该组LIDAR图像表示由自动驾驶车辆(ADV)的LIDAR装置在不同时间点采集的LIDAR点云数据。使用配置有参数集的坐标转换器将每个LIDAR图像从局部坐标系(例如，LIDAR坐标空间)变换或转化成全局坐标系(例如，GPS坐标空间)。基于经变换的LIDAR图像生成第一LIDAR反射图，例如，通过将经变换的LIDAR图像合并在一起。基于第一LIDAR反射图与作为参考LIDAR反射图的第二LIDAR反射图之间的差异，通过调整坐标转换器的一个或多个参数来优化坐标转换器。然后，可以利用经优化的坐标转换器来实时处理用于自动驾驶的LIDAR数据。 【EN】In one embodiment, a set of LIDAR images representing LIDAR point cloud data acquired by a LIDAR device of an autonomous vehicle (ADV) at different points in time is received. Each LIDAR image is transformed or translated from a local coordinate system (e.g., LIDAR coordinate space) to a global coordinate system (e.g., GPS coordinate space) using a coordinate converter configured with a set of parameters. A first LIDAR reflectometer is generated based on the transformed LIDAR images, e.g., by merging the transformed LIDAR images together. The coordinate converter is optimized by adjusting one or more parameters of the coordinate converter based on a difference between the first LIDAR reflectometry and the second LIDAR reflectometry as a reference LIDAR reflectometry. The LIDAR data for autonomous driving may then be processed in real time using the optimized coordinate converter.

摘要：【中文】在一个实施方式中，接收表示由ADV的LIDAR装置在不同时间点捕获的LIDAR点云数据的一组LIDAR图像。对于LIDAR图像中的每个，利用感知方法来确定LIDAR图像中捕获的障碍物在局部坐标系中的位置。使用坐标转换器(例如，LIDAR到GPS坐标转换逻辑或函数)将LIDAR图像从局部坐标系变换至全局坐标系。通过调整坐标转换器的一个或多个参数，基于变换后的LIDAR图像来优化坐标转换器，并且迭代地执行上述操作以获得一组最佳参数。然后，可利用优化后的坐标转换器在自动驾驶期间实时处理后续的LIDAR图像。 【EN】In one embodiment, a set of LIDAR images representing LIDAR point cloud data captured by a LIDAR device of an ADV at different points in time is received. For each of the LIDAR images, a perception method is utilized to determine the location of an obstacle captured in the LIDAR image in the local coordinate system. The LIDAR image is transformed from the local coordinate system to the global coordinate system using a coordinate converter (e.g., a LIDAR to GPS coordinate conversion logic or function). The coordinate converter is optimized based on the transformed LIDAR image by adjusting one or more parameters of the coordinate converter, and iteratively performing the above operations to obtain an optimal set of parameters. Subsequent LIDAR images may then be processed in real time during autonomous driving using the optimized coordinate converter.

摘要：【中文】公开了一种用于操作自动驾驶车辆(ADV)的方法。响应于驱动自动驾驶车辆从ADV的当前速度达到目标加速度的请求，基于目标加速度和ADV的当前速度在所选择的命令校准表中执行查找操作。在命令校准表中执行查找操作以定位与当前速度和目标加速度匹配的条目。每个命令校准表包括多个条目，其中每个条目将特定速度和发出的特定控制命令映射到响应于控制命令从车辆获得的特定加速度。从所选择的命令校准表的匹配条目获得控制命令。获得的控制命令被发送给ADV以控制ADV，而不必实时计算相同的命令。 【EN】A method for operating an autonomous vehicle (ADV) is disclosed. In response to a request to drive the autonomous vehicle from the current speed of the ADV to the target acceleration, a lookup operation is performed in the selected commanded calibration table based on the target acceleration and the current speed of the ADV. A lookup operation is performed in the command calibration table to locate an entry that matches the current velocity and the target acceleration. Each command calibration table includes a plurality of entries, where each entry maps a particular speed and a particular control command issued to a particular acceleration obtained from the vehicle in response to the control command. The control command is obtained from the matching entry of the selected command calibration table. The obtained control commands are sent to the ADV to control the ADV without having to calculate the same commands in real time.

摘要：【中文】本申请为用于L2自动驾驶的基于预定校准表的车辆油门/制动辅助系统。在一个实施方式中，响应于源自ADV的驾驶员的第一控制命令，ADV的响应于第一控制命令的预期加速度根据ADV在标准驾驶环境(例如，干燥的道路、平坦的路面、正常的轮胎压力、零负载)下的当前速度来确定。基于ADV在该时间点处的当前驾驶环境来选择命令校准表中的一个。在所选择的命令校准表中执行查找操作，以基于ADV的当前速度和预期加速度获取第二控制命令。然后，将第二控制命令发给ADV以控制ADV。结果，ADV在当前驾驶环境下达到与ADV在标准驾驶环境中驾驶时的加速度相同的加速度。 【EN】The present application is a vehicle throttle/brake assist system based on a predetermined calibration table for L2 autopilot. In one embodiment, in response to a first control command originating from a driver of the ADV, an expected acceleration of the ADV in response to the first control command is determined as a function of a current speed of the ADV under standard driving conditions (e.g., dry road, flat road, normal tire pressure, zero load). One of the command calibration tables is selected based on the current driving environment of the ADV at the point in time. A lookup operation is performed in the selected command calibration table to obtain a second control command based on the current velocity and the expected acceleration of the ADV. Then, a second control command is issued to the ADV to control the ADV. As a result, the ADV reaches the same acceleration in the current driving environment as the ADV would have if driven in the standard driving environment.

摘要：【中文】在一个实施方式中，当自动驾驶车辆(ADV)在各种驾驶环境中驾驶时，响应于各种控制命令在不同时间点处从ADV测量并收集第一驾驶统计数据集。基于第一驾驶统计数据集，在每个负载校准表中执行搜索以找到具有相似驾驶统计数据的负载校准表。选择负载校准表中的包括与第一驾驶统计数据集最相似的第二驾驶统计数据集的一个。基于所选择的负载校准表，通过例如将与所选的负载校准表相关的负载指定为ADV的当前负载来确定ADV的当前负载。ADV的负载可以用作生成ADV的后续控制命令的因子。 【EN】In one embodiment, a first set of driving statistics is measured and collected from an autonomous vehicle (ADV) at different points in time in response to various control commands while the ADV is driving in various driving environments. Based on the first set of driving statistics, a search is performed in each load calibration table to find load calibration tables with similar driving statistics. One of the load calibration tables is selected that includes a second set of driving statistics that is most similar to the first set of driving statistics. Based on the selected load calibration table, a current load of the ADV is determined by, for example, designating the load associated with the selected load calibration table as the current load of the ADV. The load of the ADV may be used as a factor in generating subsequent control commands for the ADV.

摘要：【中文】根据本公开的实施例，提供了一种用于控制车辆的方法、装置、设备和存储介质，涉及自动驾驶领域。该方法包括：响应于确定车辆从当前位置不能够前行通过目标区域，基于目标区域的边界确定车辆能够通过目标区域的至少一部分的预期通行轨迹；基于预期通行轨迹，确定在车辆后方的至少一个候选后退位置；确定车辆从当前位置到至少一个候选后退位置的至少一个候选后退轨迹；以及基于至少一个候选后退轨迹，确定目标后退轨迹。基于这样的方式，可以使得车辆能够通过前行规划无法通过的区域。 【EN】According to an embodiment of the disclosure, a method, an apparatus, a device and a storage medium for controlling a vehicle are provided, which relate to the field of automatic driving. The method comprises the following steps: in response to determining that the vehicle is unable to proceed from the current location through the target area, determining an expected transit trajectory for the vehicle to pass through at least a portion of the target area based on a boundary of the target area; determining at least one candidate retreat position behind the vehicle based on the expected passing track; determining at least one candidate back-off trajectory for the vehicle from the current location to at least one candidate back-off location; and determining a target retreat trajectory based on the at least one candidate retreat trajectory. In this way, the vehicle may be enabled to pass through areas that are not available for forward planning.

摘要：【中文】本申请公开了一种内侧髌骨韧带的解剖止点定位方法，包括以下步骤：采用手法定位方式确定参考止点，在该参考止点处固定金属止点标记；采用手法定位方式确定参考中点，在该参考中点处固定金属中点标记；携带该金属止点标记以及金属中点标记由CT透视获得患膝的第一透视图以及第二透视图；对该第一透视图以及第二透视图进行复合，确定滑车轨迹及其转动中心，设置该转动中心为图像矫正点；基于测量标尺测得该图像矫正点与参考止点图像和参考中点图像的距离和角度数值；根据该距离和角度数值，在患膝体表参照该参考止点标记作为手术入路点的修正止点。借助本申请的方法可为患者提供定制的手术入路，减少术后并发症的发生率以及缩短手术时间。 【EN】The application discloses a method for positioning an anatomical insertion point of a medial patellar ligament, which comprises the following steps: determining a reference dead point by adopting a manual positioning mode, and fixing a metal dead point mark at the reference dead point; determining a reference midpoint by adopting a manual positioning mode, and fixing a metal midpoint mark at the reference midpoint; carrying the metal dead point mark and the metal midpoint mark to obtain a first perspective view and a second perspective view of the affected knee through CT fluoroscopy; compounding the first perspective view and the second perspective view, determining a track of the pulley and a rotation center of the pulley, and setting the rotation center as an image correction point; measuring the distance and angle values between the image correction point and the reference dead point image and the reference midpoint image based on the measuring scale; and according to the distance and angle values, the reference stop mark is referred to as a correction stop of the surgical access point on the surface of the affected knee. With the methods of the present application, customized surgical access can be provided to the patient, reducing the incidence of postoperative complications and shortening the surgical time.

摘要：【中文】本发明公开了一种发生器及冷凝系统，发生器、精馏器、冷凝器、蒸发器、吸收器及储液罐依次连接形成回路，出气腔与精馏器通过提升管连通，加热腔与储液罐之间设置有输液管。发生器包括加热腔及出气腔，出气腔连接有提升管，出气腔的宽度沿出气方向逐渐缩小。从加热腔蒸发的氨气进入出气腔中，并沿着出气腔进入精馏器，流动的过程中通道逐渐缩窄，使流速加快，促进氨气进入精馏器同时对部分有倒流趋向的氨气进行阻碍的作用，极大地减小倒流，提高制冷效率。 【EN】The invention discloses a generator and a condensing system, wherein the generator, a rectifier, a condenser, an evaporator, an absorber and a liquid storage tank are sequentially connected to form a loop, an air outlet cavity is communicated with the rectifier through a lifting pipe, and a liquid conveying pipe is arranged between a heating cavity and the liquid storage tank. The generator comprises a heating cavity and an air outlet cavity, the air outlet cavity is connected with a lifting pipe, and the width of the air outlet cavity is gradually reduced along the air outlet direction. The ammonia from heating chamber evaporation gets into in the air outlet cavity to get into the rectifier along the air outlet cavity, the in-process passageway that flows narrows down gradually, makes the velocity of flow accelerate, promotes the ammonia and gets into the rectifier and carry out the effect that hinders to the ammonia that the part has the refluence trend simultaneously, greatly reduces the refluence, improves refrigeration efficiency.

摘要：【中文】本申请实施例公开了车辆控制参数的标定方法、装置、车载控制器和无人车，所述方法的一实施例包括：响应于达到预设的更新条件，执行标定步骤；标定步骤包括：获取当前偏移数据集合，当前偏移数据集合中的当前偏移数据在包含当前时刻的时段内确定；确定用于表征当前偏移数据集合的数值特征的当前偏移数据参考值；基于当前偏移数据参考值和历史偏移数据参考值之间的偏差，对车辆控制参数进行偏移校正。该实现方式实现了基于车辆偏移的变化对车辆参数的自主标定，使得车辆能够更精准地跟随相应的控制指标。 【EN】The embodiment of the application discloses a method and a device for calibrating vehicle control parameters, a vehicle-mounted controller and an unmanned vehicle, wherein one embodiment of the method comprises the following steps: executing a calibration step in response to reaching a preset updating condition; the calibration step comprises: acquiring a current offset data set, wherein the current offset data in the current offset data set is determined in a time period containing the current moment; determining a current offset data reference value for characterizing a numerical feature of a current offset data set; offset correction is performed on the vehicle control parameter based on a deviation between the current offset data reference value and the historical offset data reference value. The implementation mode realizes the autonomous calibration of the vehicle parameters based on the change of the vehicle deviation, so that the vehicle can follow the corresponding control indexes more accurately.