WO2023109501A1 - 一种基于定位技术的列车主动障碍物检测方法及装置 - Google Patents

一种基于定位技术的列车主动障碍物检测方法及装置 Download PDF

Info

Publication number
WO2023109501A1
WO2023109501A1 PCT/CN2022/134991 CN2022134991W WO2023109501A1 WO 2023109501 A1 WO2023109501 A1 WO 2023109501A1 CN 2022134991 W CN2022134991 W CN 2022134991W WO 2023109501 A1 WO2023109501 A1 WO 2023109501A1
Authority
WO
WIPO (PCT)
Prior art keywords
positioning
obstacle
train
module
track
Prior art date
Application number
PCT/CN2022/134991
Other languages
English (en)
French (fr)
Inventor
崔洪州
蒋耀东
韩海亮
阳扬
李云
Original Assignee
卡斯柯信号有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 卡斯柯信号有限公司 filed Critical 卡斯柯信号有限公司
Publication of WO2023109501A1 publication Critical patent/WO2023109501A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/86—Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
    • G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
    • G06T7/85—Stereo camera calibration
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10028—Range image; Depth image; 3D point clouds
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30244—Camera pose

Definitions

  • the invention relates to a train signal control system, in particular to a method and device for actively detecting train obstacles based on positioning technology.
  • the passive obstacle detection device used by the vehicle relies on the contact rod to touch the obstacle to drive the relevant sensor, and then performs subsequent induction processing, which has the disadvantages of short working distance and no early warning time.
  • the intelligent driving system With the development of unmanned driving technology in rail transit, the intelligent driving system provides more and more perfect functions, and the driver will eventually be replaced.
  • the unmanned driving system of GOA4 level there is no driver on duty on the train, and it has even been dismantled. cab. Therefore, it is necessary to develop a new obstacle detection technology to replace the driver's lookout, realize environmental awareness, remote warning, issue an alarm before the train encounters an obstacle, and take appropriate measures.
  • the intelligent obstacle detection method includes two steps, one is the identification of the track area, and the other is the detection of obstacles.
  • the obstacle warning distance is related to the identification distance of the track area and the detection distance of obstacles. The minimum value of the two determines the farthest warning distance. Therefore, improving the identification distance of the track area is of great significance for increasing the early warning distance.
  • the object of the present invention is to provide a method and device for actively detecting train obstacles based on positioning technology in order to overcome the above-mentioned defects in the prior art.
  • a kind of train active obstacle detection method based on positioning technology comprises the following steps:
  • Step S1 electronic map collection
  • Step S2 initial parameter calibration
  • Step S3 video camera parameter calibration
  • Step S4 train obstacle detection
  • Step S5 the obstacle recognition result is output.
  • step S1 electronic map collection is as follows: different collection methods are adopted according to different positioning technologies.
  • the train needs to run along all the tracks at least once to ensure that the characteristics of all track areas are recorded and an electronic map of the line is generated.
  • the step S2 the initial parameter calibration is specifically:
  • the coordinate system of the lidar and the coordinate system of the electronic map are registered, so that the line track coincides with the actual track in the coordinate system of the lidar.
  • the initial parameters include two sets of parameters of displacement XYZ and rotation YPR.
  • the conversion relationship between the two-dimensional coordinates of the image used by the video camera, the three-dimensional coordinates of the real world and the laser radar coordinate system is calculated through the calibration of the video camera parameters.
  • the train obstacle detection is specifically:
  • Step S401 the laser radar acquires the point cloud data in front, the camera acquires the image data in front, and enters into the computing host;
  • Step S402 the positioning module outputs the current position, finds the corresponding position in the map through electronic map matching, and obtains the coordinates and attitude data of the positioning point according to the corresponding position;
  • Step S403 according to the coordinates and driving direction of the positioning point, query the information of the track area ahead of the point, obtain the data of the track area ahead, and form a three-dimensional track area;
  • Step S404 converting the track area into the coordinate system of the laser radar, delineating the track area in the laser point cloud, and detecting whether there is an obstacle in the track area through the point cloud processing algorithm;
  • Step S405 project the track area into the video image coordinate system according to the calibration parameters of the video camera, draw the track area in the image, and use the video recognition algorithm to detect whether there is an obstacle in the track area
  • step S406 the obstacle information output by the laser radar and the obstacle information output by the video recognition are fused, and finally confirmed obstacle information is output and sent to the interface module.
  • step S402 if the positioning module can output the posture data, its own posture data can be used.
  • the video recognition module can directly run the track area identification algorithm to identify the track area information by itself, and then run the video recognition algorithm to detect whether there is an obstacle in the track area.
  • the obstacle information output in step S406 includes obstacle type, obstacle size, obstacle distance, obstacle orientation, and obstacle collision probability.
  • the interface module in step S5 makes a corresponding response according to the obstacle identification information, wherein the response includes sound and light alarm, whistle, conventional braking, emergency braking, log recording, remote message sending .
  • the method specifically includes for the processing of multiple strands:
  • a device for the active obstacle detection method for trains based on positioning technology including a positioning module, a laser radar detection module, a video recognition module, a computing host and an interface module;
  • the computing host is respectively connected with the positioning module, the laser radar detection module, the video recognition module and the interface module.
  • the positioning module is used to obtain the real-time position of the train, and one or more combinations are selected for the positioning technology, and the positioning technology includes satellite navigation positioning, and mapping positioning based on laser radar SLAM technology , Video-based VSLAM mapping positioning, inertial navigation equipment-based reckoning positioning, and combined positioning based on wheel speed sensors, beacon transponders, and Doppler speed sensors.
  • the positioning technology includes satellite navigation positioning, and mapping positioning based on laser radar SLAM technology , Video-based VSLAM mapping positioning, inertial navigation equipment-based reckoning positioning, and combined positioning based on wheel speed sensors, beacon transponders, and Doppler speed sensors.
  • the lidar detection module is installed in front of the vehicle to obtain a three-dimensional scanning point cloud in front of the vehicle to determine the size, orientation and distance of obstacles.
  • the video recognition module is installed in front of the vehicle to obtain color image information in front of the vehicle and transmit it to the computing host; the video recognition module can automatically adjust exposure parameters according to changes in light intensity to ensure clear images image.
  • the computing host is used to process the received positioning data, laser radar data and video image data, and output obstacle detection results to the interface module.
  • the interface module is used to receive the obstacle detection result of the computing host, and perform corresponding operations such as sound and light alarm, whistle, and output braking according to the settings.
  • an electronic device including a memory and a processor, the memory stores a computer program, and the processor implements the method when executing the program.
  • a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the method is implemented.
  • the present invention has the following advantages:
  • the present invention establishes the conversion relationship from the track coordinate system to the sensor coordinate system, and converts the electronic map information of the track area into the corresponding detector coordinate system.
  • the sensor coordinate system can also be converted into the track coordinate system.
  • the present invention uses a satellite navigation positioning receiver to realize the positioning and attitude measurement of the train, and then record the running track of the train to form an electronic track map.
  • the track area identification distance provided by the present invention can be flexibly set by software, exceeding the distance provided by the video track area identification algorithm.
  • the track area is a track area in three-dimensional space, and the width and height of the track area can be adjusted conveniently.
  • the present invention can be used to correctly identify the track area in the case of multiple tracks in the station, and reduce false alarms from trains and personnel on adjacent tracks.
  • the present invention provides a train active obstacle detection scheme, which can detect obstacles in front of the train and give an early warning.
  • the present invention adopts the combined detection method of video + laser radar, which is suitable for various scenes such as day and night, can improve the detection rate of obstacles, and reduce the situation of missed and false positives.
  • Fig. 1 is the structural block diagram of device of the present invention
  • Fig. 2 is a schematic diagram of the internal processing logic module of the computing host of the present invention.
  • Fig. 3 is a schematic diagram of coordinate system transformation of the present invention.
  • Fig. 4 is a schematic diagram of a turnout in a station according to the present invention.
  • the present invention provides an example, which can detect obstacles in front of trains in the existing rail transit field by using positioning technology, laser radar technology and video recognition technology.
  • the track where the train is located can be determined through precise positioning, and the turnout in front of the train can be judged through video recognition or route information, and then intelligently judge whether there is an obstacle in the track that the train is about to walk in front of, to avoid other obstacles. Obstacles such as vehicles or people in the lane generate false alarms.
  • the present invention is based on the train active obstacle detection method of positioning technology, and the specific process is as follows:
  • Step S1 electronic map collection
  • the positioning module uses a satellite navigation positioning receiver, which can output the current position of the train and the orientation of the train with high frequency and precision.
  • the train runs continuously on the track for a period of time, records the output data of the satellite receiver, and obtains the track of the train, that is, the geometric feature description of the track.
  • the track of the train that is, the geometric feature description of the track.
  • Step S2 initial parameter calibration
  • the boundary of the track area in front of the train can be transformed into the lidar or camera coordinate system.
  • the camera internal reference calibration method is used to obtain the projection parameters of the camera lens.
  • the objects in the common field of view are used for calibration, and the coordinates of the same point in the camera and radar coordinate systems are respectively recorded, and the transformation matrix is reversed.
  • several sets of corresponding coordinates can be collected, and a set of initial values can be assumed first, and the optimal solution can be obtained through an iterative optimization algorithm. Get the radar-to-camera conversion parameters.
  • Step S4 obstacle detection
  • the obstacle detection module includes a computing host, which is one or more hosts with powerful computing capabilities.
  • the interior can be divided into several programs according to different processing contents, including positioning programs, video processing programs, laser radar processing programs, and fusion logic processing programs. , external communication programs, etc.
  • it also stores data such as electronic map data, calibration and calibration parameters, as shown in Figure 2.
  • the positioning module When the train is running on the track, the positioning module outputs the positioning information. After being processed by the computing host, it generates the information of the front track area, and sends it to the laser radar processing program and the video recognition processing program to convert the coordinates of the track area from the ground coordinate system to In the sensor coordinate system, as shown in Figure 3, the two programs respectively detect whether there are obstacles in the front track area, and output the results to the fusion logic processing program, and determine whether there are obstacles according to the set fusion logic , and then output to the interface module.
  • Step S5 obstacle recognition result output
  • the detection result is output to the interface module (in Figure 1, module 5, interface module), and the interface module determines the output mode, such as sound and light alarm, whistle, conventional braking, emergency braking, logging, Remote messaging, etc.
  • the interface module determines the output mode, such as sound and light alarm, whistle, conventional braking, emergency braking, logging, Remote messaging, etc.
  • the sound and light alarm and log function are selected, a flashing icon will appear on the screen, and a prompt sound will be played at the same time to remind the driver that there are obstacles ahead.
  • the image information and obstacle information of this alarm will be recorded for post-event analysis. .
  • Step S6 the processing of multiple strands
  • Run the intelligent turnout recognition program through the video recognition program identify the opening direction of the switch (1) in the image, then switch the track to the No. 2 track, and then recognize the (2) switch, and switch the track to the No. 3 track.
  • the identification program sends the identified results back to the positioning program, and the positioning program outputs the correct track area information (the track shown by the dotted line in Figure 4).
  • the present invention converts the electronic map coordinate system of the track area into the sensor coordinate system. It can be known from mathematical derivation that the sensor coordinate system can also be converted into the track area coordinate system. This transformation is also a simple formula transformation and does not Constitute new innovation points, also within the protection scope of the present invention.
  • the device for the train active obstacle detection method based on positioning technology includes a positioning module 1, a laser radar detection module 2, a video recognition module 3, a computing host 4 and an interface module 5; the computing The host 4 is connected to the positioning module 1 , the laser radar detection module 2 , the video recognition module 3 and the interface module 5 respectively.
  • the positioning module 1 is used to obtain the real-time position of the train, including satellite navigation positioning, mapping positioning based on laser radar SLAM technology, video-based VSLAM mapping positioning, and reckoning positioning based on inertial navigation equipment , based on the combined positioning of wheel speed sensors, beacon transponders, and Doppler speed sensors.
  • the lidar detection module 2 is installed in front of the vehicle, and is used to obtain the three-dimensional scanning point cloud in front of the vehicle, and determine the size, orientation and distance of obstacles.
  • the video recognition module 3 is installed in front of the vehicle to obtain color image information in front of the vehicle and transmit it to the computing host; the video recognition module 3 can automatically adjust exposure parameters according to changes in light intensity to ensure clear images.
  • the computing host 4 is used to process the received positioning data, laser radar data and video image data, and output obstacle detection results to the interface module.
  • the interface module 5 is used to receive the obstacle detection result of the computing host, and perform corresponding operations such as sound and light alarm, whistle, and output braking according to the settings.
  • the electronic device of the present invention includes a central processing unit (CPU), which can execute various Appropriate action and handling.
  • CPU central processing unit
  • RAM various programs and data necessary for device operation can also be stored.
  • the CPU, ROM, and RAM are connected to each other through a bus.
  • I/O Input/output
  • I/O interface Multiple components in the device are connected to the I/O interface, including: input units, such as keyboards, mice, etc.; output units, such as various types of displays, speakers, etc.; storage units, such as magnetic disks, optical discs, etc.; and communication units, Such as network card, modem, wireless communication transceiver, etc.
  • the communication unit allows the device to exchange information/data with other devices over a computer network such as the Internet and/or various telecommunication networks.
  • the processing unit executes various methods and processes described above, such as methods S1-S6.
  • the methods S1-S6 may be implemented as computer software programs tangibly embodied in a machine-readable medium, such as a storage unit.
  • part or all of the computer program may be loaded and/or installed on the device via a ROM and/or a communication unit.
  • the CPU may be configured in any other appropriate way (for example, by means of firmware) to execute the methods S1-S6.
  • exemplary types of hardware logic components include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Product (ASSP), System on a Chip (SOC), Complex Programmable Logic Devices (CPLDs) and more.
  • FPGA Field Programmable Gate Array
  • ASIC Application Specific Integrated Circuit
  • ASSP Application Specific Standard Product
  • SOC System on a Chip
  • CPLDs Complex Programmable Logic Devices
  • Program codes for implementing the methods of the present invention may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special purpose computer, or other programmable data processing devices, so that the program codes, when executed by the processor or controller, make the functions/functions specified in the flow diagrams and/or block diagrams Action is implemented.
  • the program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device.
  • a machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • a machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing.
  • machine-readable storage media would include one or more wire-based electrical connections, portable computer discs, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any combination of the above.
  • RAM random access memory
  • ROM read only memory
  • EPROM or flash memory erasable programmable read only memory
  • CD-ROM compact disk read-only memory
  • magnetic storage devices or any combination of the above.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Electromagnetism (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computer Graphics (AREA)
  • Geometry (AREA)
  • Software Systems (AREA)
  • Optical Radar Systems And Details Thereof (AREA)
  • Traffic Control Systems (AREA)
  • Train Traffic Observation, Control, And Security (AREA)

Abstract

一种基于定位技术的列车主动障碍物检测方法及装置。该方法包括：步骤S1，电子地图采集；步骤S2，初始参数校准；步骤S3，视频相机参数标定；步骤S4，列车障碍物检测；步骤S5，障碍物识别结果输出。该装置包括定位模块（1）、激光雷达探测模块（2）、视频识别模块（3）、运算主机（4）和接口模块（5）；运算主机（4）分别与定位模块（1）、激光雷达探测模块（2）、视频识别模块（3）和接口模块（5）连接。该方法和装置具有能够提高障碍物的检测率，降低漏报、误报的情况等优点。

Description

一种基于定位技术的列车主动障碍物检测方法及装置 技术领域
本发明涉及列车信号控制***，尤其是涉及一种基于定位技术的列车主动障碍物检测方法及装置。
背景技术
轨道交通领域中，随着列车运行速度越来越快，运行频率越来越高，列车前方障碍物检测变得更加重要。传统的列车操纵方式，对列车前方出现的障碍物，主要依靠司机瞭望目视发现，存在容易走神疏忽，疲惫导致注意力下降等问题。
目前，车辆使用的被动式障碍物检测装置，是依靠接触杆触及到障碍物带动相关传感器，再进行后续的感应处理，存在作用距离短，无预警时间等缺点。随着轨道交通无人驾驶技术的发展，智能驾驶***提供越来越完善的功能，司机终将被取代，在GOA4级的无人驾驶***中，已经没有司机在列车上值守，甚至已经拆除了驾驶室。因此，需要发展新的障碍物探测技术，用于替代司机的瞭望，实现环境感知，远程预警，在列车碰到障碍物之前发出告警，并采取适当的措施。
随着汽车无人驾驶技术的发展，出现了越来越多的障碍物检测方法，如视频识别方法，激光雷达建模方法，毫米波雷达及超声雷达探测方法，以及它们的组合使用。汽车无人驾驶技术同轨道交通无人驾驶技术还有很多区别，最明显的就是汽车是在路面上行驶、会存在超车现象，因此轨迹是不确定的。而轨道交通没有平整的路面，列车在专有的轨道上行驶，轨迹及姿态是重复的。利用好这些特点，可以极大地简化轨道交通领域的感知探测技术。在轨道交通领域，智能障碍物检测方法包括两步，一是轨行区的识别，二是障碍物的探测，只有障碍物在轨行区限界内部才会危及行车安全，才需要报警。障碍物预警距离与轨行区的识别距离和障碍物的探测距离有关，这两者最小的值决定了最远预警距离，因此提高轨行区的识别距离对于提高预警距离有重要意义。
因此如何来充分利用定位技术、激光雷达技术、视频识别技术对现有轨道交通领域内的列车前方障碍物进行高精度探测，成为需要解决的技术问题。
发明内容
本发明的目的就是为了克服上述现有技术存在的缺陷而提供一种基于定位技术的列车主动障碍物检测方法及装置。
本发明的目的可以通过以下技术方案来实现：
根据本发明的第一方面，提供了一种基于定位技术的列车主动障碍物检测方法，该方法包括以下步骤：
步骤S1，电子地图采集；
步骤S2，初始参数校准；
步骤S3，视频相机参数标定；
步骤S4，列车障碍物检测；
步骤S5，障碍物识别结果输出。
作为优选的技术方案，所述的步骤S1，电子地图采集为：根据定位技术的不同，采用不同的采集方法。
作为优选的技术方案，所述的根据定位技术的不同，采用不同的采集方法具体为：
101)对于点式定位技术，采用列车在轨道上行驶采集，或者根据已有的轨道线路数据文件进行转换；
102)对于采用SLAM定位技术，需要列车沿着所有轨道运行至少一遍，以保证记录所有轨行区的特征，并且生成线路电子地图。
作为优选的技术方案，所述的步骤S2，初始参数校准具体为：
通过初始参数校准，将激光雷达的坐标系和电子地图的坐标系进行配准，使得线路轨迹在激光雷达的坐标系中与实际轨道重合。
作为优选的技术方案，所述的初始参数包括位移XYZ和旋转YPR两组参数。
作为优选的技术方案，所述的步骤S3中通过视频相机参数标定，将视频相机使用图像的二维坐标、现实世界的三维坐标和激光雷达坐标系之间的转换关系计算出来。
作为优选的技术方案，所述的步骤S4，列车障碍物检测具体为：
步骤S401，激光雷达获取前方点云数据，摄像机获取前方图像数据，进入运算主机；
步骤S402，定位模块输出当前位置，通过电子地图匹配找到地图中的对应位置， 根据对应位置获取定位点的坐标及姿态数据；
步骤S403，根据定位点的坐标和行驶方向，查询该点前方的轨行区信息，获取前方轨行区的数据，并形成三维的轨行区；
步骤S404，将轨行区转换到激光雷达的坐标系中，在激光点云中描绘出轨行区，通过点云处理算法来检测轨行区内是否有障碍物；
步骤S405，将轨行区根据视频相机标定参数，投影到视频图像坐标系中，在图像中描绘出轨行区，通过视频识别算法来检测轨行区内是否有障碍物
步骤S406，将激光雷达输出的障碍物信息和视频识别输出的障碍物信息进行融合，输出最终确认的障碍物信息，并且发送给接口模块。
作为优选的技术方案，所述的步骤S402中，若定位模块能够输出姿态数据，则可使用本身的姿态数据。
作为优选的技术方案，所述的步骤S405中，视频识别模块可直接运行轨行区识别算法，自行识别出轨行区信息，然后运行视频识别算法，检测轨行区内是否有障碍物。
作为优选的技术方案，所述的步骤S406中输出的障碍物信息包括障碍物类型、障碍物大小、障碍物距离、障碍物方位、障碍物碰撞的概率。
作为优选的技术方案，所述的步骤S5中的接口模块根据障碍物识别信息做出相应的反应，其中反应包括声光报警、鸣笛、常规制动、紧急制动、日志记录、远程消息发送。
作为优选的技术方案，该方法对于多股道的处理具体包括：
(a)从地面联锁***中获取前方进路信息，从中分析出道岔的开向，进而确定即将行走的股道，将轨行区延长到该股道上去；
(b)使用视频识别的方法，确定道岔的开向，选择对应的股道；视频相机能够根据道岔缺口位置识别出道岔是处于定位还是反位，进而通知视频识别模块和激光雷达检测模块，选择对应的股道；如果有多个道岔，则依次识别，选择股道。
根据本发明的第二方面，提供了一种用于所述基于定位技术的列车主动障碍物检测方法的装置，包括定位模块、激光雷达探测模块、视频识别模块、运算主机和接口模块；所述运算主机分别与定位模块、激光雷达探测模块、视频识别模块和接口模块连接。
作为优选的技术方案，所述的定位模块用于获取列车的实时位置，采用的定位技术选择一种或多种组合，所述的定位技术包括卫星导航定位，基于激光雷达SLAM技术的建图定位，基于视频的VSLAM建图定位，基于惯导设备的推算定位，基于轮速传感器、信标应答器、多普勒速度传感器的组合定位。
作为优选的技术方案，所述的激光雷达探测模块安装于车辆前方，用于获取车辆前方的三维扫描点云，确定障碍物的大小、方位和距离。
作为优选的技术方案，所述的视频识别模块安装于车辆前方，用于获取车辆前方的彩色图像信息，并传输给运算主机；视频识别模块能够根据光照强度变化自动调整曝光参数，确保获取清晰的图像。
作为优选的技术方案，所述的运算主机用于对接收到的定位数据、激光雷达数据和视频图像数据进行处理，并且输出障碍物检测结果给接口模块。
作为优选的技术方案，所述的接口模块用于接收运算主机的障碍物检测结果，并且根据设置进行声光报警、鸣笛、输出制动的相应操作。
根据本发明的第三方面，提供了一种电子设备，包括存储器和处理器，所述存储器上存储有计算机程序，所述处理器执行所述程序时实现所述的方法。
根据本发明的第四方面，提供了一种计算机可读存储介质，其上存储有计算机程序，所述程序被处理器执行时实现所述的方法。
与现有技术相比，本发明具有以下优点：
1、本发明建立轨道坐标系到传感器坐标系的转换关系，把轨行区电子地图信息转换到相应的探测器坐标系中，当然也可以将传感器坐标系转换到轨道坐标系中。
2、本发明用卫星导航定位接收机实现列车的定位和姿态测量，进而记录列车的运行轨迹，形成电子轨道地图。
3、本发明提供的轨行区识别距离可由软件灵活设定，超过视频轨行区识别算法提供的距离。轨行区为三维空间内的轨行区，可以方便调整轨行区宽度及高度。
4、本发明可用于解决站场内多股道的情况下，正确识别轨行区，降低相邻股道列车、人员等的误报。
5、本发明提供了一种列车主动障碍物检测方案，能够对列车前方的障碍物进行检测，提前预警。
6、本发明采用了视频+激光雷达的组合探测方式，适应白天和黑夜等各种场景， 能够提高障碍物的检测率，降低漏报、误报的情况。
附图说明
图1为本发明装置的结构框图；
图2为本发明运算主机内部处理逻辑模块示意图；
图3为本发明坐标系转换示意图；
图4为本发明站场内道岔示意图。
具体实施方式
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明的一部分实施例，而不是全部实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例，都应属于本发明保护的范围。
本发明提供了一个实例，能够利用定位技术、激光雷达技术、视频识别技术对现有轨道交通领域内的列车前方障碍物进行探测。对于多股道的站场内，能够通过精确定位确定列车所处股道，通过视频识别或者进路信息判断列车前方道岔，进而智能判断列车前方即将行走的股道是否存在障碍物，避免因为其它股道内的车或者人员等障碍物产生误报。
本发明基于定位技术的列车主动障碍物检测方法，具体过程如下：
步骤S1，电子地图采集
实例中定位模块采用卫星导航定位接收机，其能够以较高的频率、精度输出列车当前所在的位置及列车的方位。列车在轨道上连续运行一段时间，记录卫星接收机的输出数据，得到列车的轨迹，即轨道的几何特征描述。列车在多次经过同一个道岔，但是道岔状态不同时，可获得多个股道的轨迹，最终获取全站场的股道信息。
步骤S2，初始参数校准
安装完成后，测出卫星天线到激光雷达的距离，天线到摄像机的距离，以及方位等参数，即位移XYZ和旋转YPR。得到这些参数后，即可将列车前方的轨行区限界转换到激光雷达或者摄像机坐标系中。
步骤S3，视频相机标定
采用相机内参标定方法，获取相机镜头的投影参数，相关标定方法网上有公开的参考资料。相机与雷达的标定，采用共视野的物体进行标定，分别记录相机和雷达坐标系中相同点的坐标，反求变换矩阵。实际使用过程中，可以多采集几组对应坐标，先假设一组初始值，通过迭代优化算法求解最优解。获得雷达到相机的转换参数。
步骤S4，障碍物检测
障碍物检测模块包含运算主机，是一台或多台运算能力强大的主机，内部按照处理内容不同，可以划分为几个程序，包括定位程序、视频处理程序、激光雷达处理程序、融合逻辑处理程序，外部通信程序等，此外还存储电子地图数据，校准及标定参数等数据，见图2。
列车行走在轨道上时，定位模块输出定位信息，经运算主机处理后，产生前方轨行区信息，并且送给激光雷达处理程序和视频识别处理程序，将轨行区坐标由地面坐标系转换到传感器坐标系中，如图3所示，然后由两个程序分别检测前方轨行区内是否有障碍物，并且将结果输出给融合逻辑处理程序，根据设定的融合逻辑，确定是否有障碍物，然后输出给接口模块。
运算主机内有外部通信程序，用于获取联锁***给出的进路信息，并且送给定位处理程序，以确定在站场区域，碰到道岔时，选择哪条股道作为轨行区。
步骤S5，障碍物识别结果输出
检测到障碍物后，检测结果输出到接口模块(图1中，模块5，接口模块)，由接口模块确定输出方式，比如声光告警、鸣笛、常规制动、紧急制动、日志记录、远程消息发送等。本实例选择声光告警，及日志功能，则会在屏幕上出现闪烁图标，同时播放提示声音，提醒司机前方有障碍物，同时会记录本次报警的图像信息及障碍物信息，用于事后分析。
步骤S6，多股道的处理
列车行经多股道的区域时，需要根据道岔信息确定列车行进的线路，如图4所示。列车前进方向上有(1)号和(2)号道岔，此时1号股道和2号股道上已经有车厢停放，占用了股道，列车计划行走的是3号股道，定位程序需要知道这些信息并且生成正确的轨行区信息(图中虚线所示的股道)。有两种方式可以获得道岔信息：1通过外部通信程序，从联锁***或其相关***中获取进路信息，进而得知道岔信息及道岔开向；2通过视频识别程序，运行智能道岔识别程序，在图像中识别出道岔(1)的 开向，然后将股道切换到2号股道，然后再识别到(2)号道岔，将股道切换到3号股道。识别识别程序将识别出来的结果反送给定位程序，由定位程序输出正确的轨行区信息(图4中虚线所示股道)。
本实例仅用于说明列车主动障碍物检测方法及***的可行性，并不代表***一定是按照此实例实施，在此基础上的简单增减模块，如增加或减少摄像机的模块，增加或减少激光雷达的模块，均应视为本发明的一种实现方式。此外定位技术的组合和更换也在本发明的允许范围之内，如更换各式各类卫星接收机，更换惯性导航设备，更换或增加各式各类位移传感器、速度传感器、角度传感器、角速度传感器、加速度传感器等。
本发明将轨行区的电子地图坐标系转换到传感器坐标系中，由数学推导可知，亦可以将传感器坐标系转换到轨行区坐标系中，此种变换也是简单的公式形式变换，并不构成新的创新要点，也在本发明的保护范围之内。
以上是关于方法实施例的介绍，以下通过装置实施例，对本发明所述方案进行进一步说明。
如图1所示，用于所述基于定位技术的列车主动障碍物检测方法的装置，包括定位模块1、激光雷达探测模块2、视频识别模块3、运算主机4和接口模块5；所述运算主机4分别与定位模块1、激光雷达探测模块2、视频识别模块3和接口模块5连接。
作为优选的技术方案，所述的定位模块1用于获取列车的实时位置，包括卫星导航定位，基于激光雷达SLAM技术的建图定位，基于视频的VSLAM建图定位，基于惯导设备的推算定位，基于轮速传感器、信标应答器、多普勒速度传感器的组合定位。
所述的激光雷达探测模块2安装于车辆前方，用于获取车辆前方的三维扫描点云，确定障碍物的大小、方位和距离。
所述的视频识别模块3安装于车辆前方，用于获取车辆前方的彩色图像信息，并传输给运算主机；视频识别模块3能够根据光照强度变化自动调整曝光参数，确保获取清晰的图像。
所述的运算主机4用于对接收到的定位数据、激光雷达数据和视频图像数据进行处理，并且输出障碍物检测结果给接口模块。
所述的接口模块5用于接收运算主机的障碍物检测结果，并且根据设置进行声光报警、鸣笛、输出制动的相应操作。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，所述描述的模块的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
本发明电子设备包括中央处理单元(CPU)，其可以根据存储在只读存储器(ROM)中的计算机程序指令或者从存储单元加载到随机访问存储器(RAM)中的计算机程序指令，来执行各种适当的动作和处理。在RAM中，还可以存储设备操作所需的各种程序和数据。CPU、ROM以及RAM通过总线彼此相连。输入/输出(I/O)接口也连接至总线。
设备中的多个部件连接至I/O接口，包括：输入单元，例如键盘、鼠标等；输出单元，例如各种类型的显示器、扬声器等；存储单元，例如磁盘、光盘等；以及通信单元，例如网卡、调制解调器、无线通信收发机等。通信单元允许设备通过诸如因特网的计算机网络和/或各种电信网络与其他设备交换信息/数据。
处理单元执行上文所描述的各个方法和处理，例如方法S1～S6。例如，在一些实施例中，方法S1～S6可被实现为计算机软件程序，其被有形地包含于机器可读介质，例如存储单元。在一些实施例中，计算机程序的部分或者全部可以经由ROM和/或通信单元而被载入和/或安装到设备上。当计算机程序加载到RAM并由CPU执行时，可以执行上文描述的方法S1～S6的一个或多个步骤。备选地，在其他实施例中，CPU可以通过其他任何适当的方式(例如，借助于固件)而被配置为执行方法S1～S6。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如，非限制性地，可以使用的示范类型的硬件逻辑部件包括：现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、芯片上***的***(SOC)、复杂可编程逻辑设备(CPLD)等等。
用于实施本发明的方法的程序代码可以采用一个或多个编程语言的任何组合来编写。这些程序代码可以提供给通用计算机、专用计算机或其他可编程数据处理装置的处理器或控制器，使得程序代码当由处理器或控制器执行时使流程图和/或框图中所规定的功能/操作被实施。程序代码可以完全在机器上执行、部分地在机器上执行，作为独立软件包部分地在机器上执行且部分地在远程机器上执行或完全在远程机器或服务器上执行。
在本发明的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行***、装置或设备使用或与指令执行***、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体***、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合形式组合。
以上所述，仅为本发明的具体实施方式，但本发明的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，可轻易想到各种等效的修改或替换，这些修改或替换都应涵盖在本发明的保护范围之内。因此，本发明的保护范围应以权利要求的保护范围为准。

Claims (20)

  1. 一种基于定位技术的列车主动障碍物检测方法，其特征在于，该方法包括以下步骤：
    步骤S1，电子地图采集；
    步骤S2，初始参数校准；
    步骤S3，视频相机参数标定；
    步骤S4，列车障碍物检测；
    步骤S5，障碍物识别结果输出。
  2. 根据权利要求1所述的一种基于定位技术的列车主动障碍物检测方法，其特征在于，所述的步骤S1，电子地图采集为：根据定位技术的不同，采用不同的采集方法。
  3. 根据权利要求2所述的一种基于定位技术的列车主动障碍物检测方法，其特征在于，所述的根据定位技术的不同，采用不同的采集方法具体为：
    101)对于点式定位技术，采用列车在轨道上行驶采集，或者根据已有的轨道线路数据文件进行转换；
    102)对于采用SLAM定位技术，需要列车沿着所有轨道运行至少一遍，以保证记录所有轨行区的特征，并且生成线路电子地图。
  4. 根据权利要求1所述的一种基于定位技术的列车主动障碍物检测方法，其特征在于，所述的步骤S2，初始参数校准具体为：
    通过初始参数校准，将激光雷达的坐标系和电子地图的坐标系进行配准，使得线路轨迹在激光雷达的坐标系中与实际轨道重合。
  5. 根据权利要求1或4所述的一种基于定位技术的列车主动障碍物检测方法，其特征在于，所述的初始参数包括位移XYZ和旋转YPR两组参数。
  6. 根据权利要求1所述的一种基于定位技术的列车主动障碍物检测方法，其特征在于，所述的步骤S3中通过视频相机参数标定，将视频相机使用图像的二维坐标、现实世界的三维坐标和激光雷达坐标系之间的转换关系计算出来。
  7. 根据权利要求1所述的一种基于定位技术的列车主动障碍物检测方法，其特征在于，所述的步骤S4，列车障碍物检测具体为：
    步骤S401，激光雷达获取前方点云数据，摄像机获取前方图像数据，进入运算 主机；
    步骤S402，定位模块输出当前位置，通过电子地图匹配找到地图中的对应位置，根据对应位置获取定位点的坐标及姿态数据；
    步骤S403，根据定位点的坐标和行驶方向，查询该点前方的轨行区信息，获取前方轨行区的数据，并形成三维的轨行区；
    步骤S404，将轨行区转换到激光雷达的坐标系中，在激光点云中描绘出轨行区，通过点云处理算法来检测轨行区内是否有障碍物；
    步骤S405，将轨行区根据视频相机标定参数，投影到视频图像坐标系中，在图像中描绘出轨行区，通过视频识别算法来检测轨行区内是否有障碍物
    步骤S406，将激光雷达输出的障碍物信息和视频识别输出的障碍物信息进行融合，输出最终确认的障碍物信息，并且发送给接口模块。
  8. 根据权利要求7所述的一种基于定位技术的列车主动障碍物检测方法，其特征在于，所述的步骤S402中，若定位模块能够输出姿态数据，则可使用本身的姿态数据。
  9. 根据权利要求7所述的一种基于定位技术的列车主动障碍物检测方法，其特征在于，所述的步骤S405中，视频识别模块可直接运行轨行区识别算法，自行识别出轨行区信息，然后运行视频识别算法，检测轨行区内是否有障碍物。
  10. 根据权利要求7所述的一种基于定位技术的列车主动障碍物检测方法，其特征在于，所述的步骤S406中输出的障碍物信息包括障碍物类型、障碍物大小、障碍物距离、障碍物方位、障碍物碰撞的概率。
  11. 根据权利要求7所述的一种基于定位技术的列车主动障碍物检测方法，其特征在于，所述的步骤S5中的接口模块根据障碍物识别信息做出相应的反应，其中反应包括声光报警、鸣笛、常规制动、紧急制动、日志记录、远程消息发送。
  12. 根据权利要求1所述的一种基于定位技术的列车主动障碍物检测方法，其特征在于，该方法对于多股道的处理具体包括：
    (a)从地面联锁***中获取前方进路信息，从中分析出道岔的开向，进而确定即将行走的股道，将轨行区延长到该股道上去；
    (b)使用视频识别的方法，确定道岔的开向，选择对应的股道；视频相机能够根据道岔缺口位置识别出道岔是处于定位还是反位，进而通知视频识别模块和激光雷 达检测模块，选择对应的股道；如果有多个道岔，则依次识别，选择股道。
  13. 一种用于权利要求1所述基于定位技术的列车主动障碍物检测方法的装置，其特征在于，包括定位模块(1)、激光雷达探测模块(2)、视频识别模块(3)、运算主机(4)和接口模块(5)；所述运算主机(4)分别与定位模块(1)、激光雷达探测模块(2)、视频识别模块(3)和接口模块(5)连接。
  14. 根据权利要求13所述的装置，其特征在于，所述的定位模块(1)用于获取列车的实时位置，采用的定位技术选择一种或多种组合，所述的定位技术包括卫星导航定位，基于激光雷达SLAM技术的建图定位，基于视频的VSLAM建图定位，基于惯导设备的推算定位，基于轮速传感器、信标应答器、多普勒速度传感器的组合定位。
  15. 根据权利要求13所述的装置，其特征在于，所述的激光雷达探测模块(2)安装于车辆前方，用于获取车辆前方的三维扫描点云，确定障碍物的大小、方位和距离。
  16. 根据权利要求13所述的装置，其特征在于，所述的视频识别模块(3)安装于车辆前方，用于获取车辆前方的彩色图像信息，并传输给运算主机；视频识别模块(3)能够根据光照强度变化自动调整曝光参数，确保获取清晰的图像。
  17. 根据权利要求13所述的装置，其特征在于，所述的运算主机(4)用于对接收到的定位数据、激光雷达数据和视频图像数据进行处理，并且输出障碍物检测结果给接口模块。
  18. 根据权利要求13所述的装置，其特征在于，所述的接口模块(5)用于接收运算主机的障碍物检测结果，并且根据设置进行声光报警、鸣笛、输出制动的相应操作。
  19. 一种电子设备，包括存储器和处理器，所述存储器上存储有计算机程序，其特征在于，所述处理器执行所述程序时实现如权利要求1～12中任一项所述的方法。
  20. 一种计算机可读存储介质，其上存储有计算机程序，其特征在于，所述程序被处理器执行时实现如权利要求1～12中任一项所述的方法。
PCT/CN2022/134991 2021-12-14 2022-11-29 一种基于定位技术的列车主动障碍物检测方法及装置 WO2023109501A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111529867.2A CN114397672A (zh) 2021-12-14 2021-12-14 一种基于定位技术的列车主动障碍物检测方法及装置
CN202111529867.2 2021-12-14

Publications (1)

Publication Number Publication Date
WO2023109501A1 true WO2023109501A1 (zh) 2023-06-22

Family

ID=81226827

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/134991 WO2023109501A1 (zh) 2021-12-14 2022-11-29 一种基于定位技术的列车主动障碍物检测方法及装置

Country Status (2)

Country Link
CN (1) CN114397672A (zh)
WO (1) WO2023109501A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116605268A (zh) * 2023-07-19 2023-08-18 成都交控轨道科技有限公司 一种车地协同感知移动授权计算方法

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114397672A (zh) * 2021-12-14 2022-04-26 卡斯柯信号有限公司 一种基于定位技术的列车主动障碍物检测方法及装置

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106627670A (zh) * 2016-12-19 2017-05-10 交控科技股份有限公司 一种基于激光检测的列车防护***及方法
WO2018104454A2 (de) * 2016-12-07 2018-06-14 Siemens Aktiengesellschaft Verfahren, vorrichtung und bahnfahrzeug, insbesondere schienenfahrzeug, zur hinderniserkennung im bahnverkehr, insbesondere im schienenverkehr
CN108482427A (zh) * 2018-02-22 2018-09-04 中车长春轨道客车股份有限公司 一种非接触式轨道车辆障碍物检测***和安全控制方法
CN109298415A (zh) * 2018-11-20 2019-02-01 中车株洲电力机车有限公司 一种轨道和道路障碍物检测方法
CN109977748A (zh) * 2019-01-10 2019-07-05 浙江众合科技股份有限公司 一种多融合技术的列车障碍物检测方法
CN112977541A (zh) * 2021-03-17 2021-06-18 上海电气泰雷兹交通自动化***有限公司 一种基于多技术融合的列车防护预警***
CN113568002A (zh) * 2021-06-24 2021-10-29 中车南京浦镇车辆有限公司 基于激光和图像数据融合的轨道交通主动障碍物检测装置
CN114397672A (zh) * 2021-12-14 2022-04-26 卡斯柯信号有限公司 一种基于定位技术的列车主动障碍物检测方法及装置

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018104454A2 (de) * 2016-12-07 2018-06-14 Siemens Aktiengesellschaft Verfahren, vorrichtung und bahnfahrzeug, insbesondere schienenfahrzeug, zur hinderniserkennung im bahnverkehr, insbesondere im schienenverkehr
CN106627670A (zh) * 2016-12-19 2017-05-10 交控科技股份有限公司 一种基于激光检测的列车防护***及方法
CN108482427A (zh) * 2018-02-22 2018-09-04 中车长春轨道客车股份有限公司 一种非接触式轨道车辆障碍物检测***和安全控制方法
CN109298415A (zh) * 2018-11-20 2019-02-01 中车株洲电力机车有限公司 一种轨道和道路障碍物检测方法
CN109977748A (zh) * 2019-01-10 2019-07-05 浙江众合科技股份有限公司 一种多融合技术的列车障碍物检测方法
CN112977541A (zh) * 2021-03-17 2021-06-18 上海电气泰雷兹交通自动化***有限公司 一种基于多技术融合的列车防护预警***
CN113568002A (zh) * 2021-06-24 2021-10-29 中车南京浦镇车辆有限公司 基于激光和图像数据融合的轨道交通主动障碍物检测装置
CN114397672A (zh) * 2021-12-14 2022-04-26 卡斯柯信号有限公司 一种基于定位技术的列车主动障碍物检测方法及装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116605268A (zh) * 2023-07-19 2023-08-18 成都交控轨道科技有限公司 一种车地协同感知移动授权计算方法
CN116605268B (zh) * 2023-07-19 2023-10-31 成都交控轨道科技有限公司 一种车地协同感知移动授权计算方法

Also Published As

Publication number Publication date
CN114397672A (zh) 2022-04-26

Similar Documents

Publication Publication Date Title
US20210389768A1 (en) Trajectory Assistance for Autonomous Vehicles
WO2023109501A1 (zh) 一种基于定位技术的列车主动障碍物检测方法及装置
CN107161141B (zh) 无人驾驶汽车***及汽车
CN109927719B (zh) 一种基于障碍物轨迹预测的辅助驾驶方法和***
US20200276973A1 (en) Operation of a vehicle in the event of an emergency
Yu et al. A study on recent developments and issues with obstacle detection systems for automated vehicles
WO2020147485A1 (zh) 一种信息处理方法、***、设备和计算机存储介质
US8849494B1 (en) Data selection by an autonomous vehicle for trajectory modification
US8996224B1 (en) Detecting that an autonomous vehicle is in a stuck condition
CN214151498U (zh) 一种车辆控制***及车辆
JP2020045090A (ja) 車両の自動運転制御補助方法、車両の自動運転制御補助装置、機器、コンピュータ読み取り可能な記憶媒体及び車路連携システム
CN110471085B (zh) 一种轨道检测***
WO2020228393A1 (zh) 基于物联网的深度学习型智能驾驶环境感知***
CN109552366B (zh) 机车车载铁道障碍物智能探测报警***及其预警方法
US20220340130A1 (en) Information processing apparatus, information processing method, and program
WO2020259284A1 (zh) 一种障碍物检测方法及装置
US20200320864A1 (en) Vehicle detection systems
CN111094097A (zh) 用于为车辆提供远程辅助的方法和***
CN116337102A (zh) 基于数字孪生技术的无人驾驶环境感知与导航方法
AU2020428822A1 (en) Method, apparatus, server, and computer program for collision accident prevention
EP4222034A1 (en) Annotation and mapping for vehicle operation in low-confidence object detection conditions
EP4184480A2 (en) Driving control system and method of controlling the same using sensor fusion between vehicles
Li et al. Composition and application of current advanced driving assistance system: A review
JP2019049811A (ja) 車両制御装置、車両制御方法、およびプログラム
CN114084129A (zh) 一种基于融合的车辆自动驾驶控制方法及***

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22906251

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2022906251

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2022906251

Country of ref document: EP

Effective date: 20240515