WO2024109837A1 - 基于异构无人系统相互观测的同时定位与地图构建方法 - Google Patents

基于异构无人系统相互观测的同时定位与地图构建方法 Download PDF

Info

Publication number
WO2024109837A1
WO2024109837A1 PCT/CN2023/133428 CN2023133428W WO2024109837A1 WO 2024109837 A1 WO2024109837 A1 WO 2024109837A1 CN 2023133428 W CN2023133428 W CN 2023133428W WO 2024109837 A1 WO2024109837 A1 WO 2024109837A1
Authority
WO
WIPO (PCT)
Prior art keywords
robot
area
exploration
binocular camera
unmanned
Prior art date
Application number
PCT/CN2023/133428
Other languages
English (en)
French (fr)
Inventor
徐坤
冯时羽
沈启广
李慧云
蔡宇翔
马聪
Original Assignee
中国科学院深圳先进技术研究院
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 中国科学院深圳先进技术研究院 filed Critical 中国科学院深圳先进技术研究院
Publication of WO2024109837A1 publication Critical patent/WO2024109837A1/zh

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C22/00—Measuring distance traversed on the ground by vehicles, persons, animals or other moving solid bodies, e.g. using odometers, using pedometers
    • 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
    • G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
    • G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
    • G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
    • G01S19/42—Determining position
    • G01S19/43—Determining position using carrier phase measurements, e.g. kinematic positioning; using long or short baseline interferometry
    • G01S19/44—Carrier phase ambiguity resolution; Floating ambiguity; LAMBDA [Least-squares AMBiguity Decorrelation Adjustment] method
    • 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
    • G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
    • G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
    • G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
    • G01S19/42—Determining position
    • G01S19/48—Determining position by combining or switching between position solutions derived from the satellite radio beacon positioning system and position solutions derived from a further system

Definitions

  • the present disclosure relates to intelligent transportation, and in particular to a simultaneous positioning and map building method based on mutual observation of heterogeneous unmanned systems.
  • the utility model discloses an air-ground collaborative operation system, including: an unmanned vehicle, which builds a three-dimensional map of the target scene by moving on the ground, and locates its own position in the map coordinate system of the three-dimensional map in real time; a drone, which is used to operate the operation target; a data collector, which is used to obtain a first relative position between the drone and the unmanned vehicle and a second relative position between the operation target and the unmanned vehicle; a data processor, which is connected to the unmanned vehicle, the drone and the data collector, and is used to obtain a first relative position between the unmanned vehicle and the unmanned vehicle and a second relative position between the operation target and the unmanned vehicle according to the unmanned vehicle.
  • the pose, the first relative pose and the second relative pose in the map coordinate system are used to obtain the third relative pose between the UAV and the operation target, and the third relative pose is sent to the UAV so that the UAV adjusts its pose to the preset operation range according to the third relative pose.
  • the air-ground collaborative operation system uses an unmanned vehicle to assist the UAV in accurately positioning itself in the target scene. Although this method can also achieve the effect of collaborative operation between unmanned vehicles and UAVs, it only places AprilTag markers on the unmanned vehicle to assist in the positioning of the UAV, without considering the use of mutual observation information between the unmanned vehicle and the UAV to achieve collaborative positioning, and does not make full use of effective information.
  • the utility model discloses an unmanned vehicle and unmanned aerial vehicle collaborative navigation device, including an unmanned aerial vehicle, a QGC ground station and an unmanned vehicle, wherein the unmanned aerial vehicle is equipped with a GPS positioning device, a lithium battery pack, a first wireless image transmission module, a binocular camera, a second wireless data transmission module, a support plate, a landing gear and a flight controller, wherein the flight controller includes a main controller, a first I/O controller, a first IMU inertial navigation module and a GPS module, wherein the QGC ground station is equipped with a first wireless data transmission module, wherein the unmanned vehicle is provided with an MC bottom-layer control module, an upper computer graphical interface display module, a speed controller, a steering controller, a second I/O controller and a second wireless image transmission module, wherein the MC bottom-layer control module is composed of
  • the utility model solves the problems of small recognition range, large delay and large influence of GPS signals of traditional navigation devices, and designs an unmanned vehicle and unmanned aerial vehicle collaborative navigation device, but the utility model relies on the GPS module to provide global positioning information, and cannot be used in scenes where GPS signals are missing, such as mine caves or high-rise canyons.
  • the system includes a ground station, an unmanned aerial vehicle, and an unmanned vehicle.
  • the unmanned aerial vehicle includes an overall physical structure, an onboard embedded computer, and an image sensor; the overall physical structure includes a frame, a quadcopter, and a motor; the onboard embedded computer includes a communication module and an embedded processor, and the image sensor includes a binocular camera and an RGB-D camera.
  • the unmanned vehicle includes an embedded processor, a lidar sensor, and a communication module.
  • the ground station includes a display control, a control control, and a communication control.
  • the method uses the control and mapping instructions output by the ground station to convert the 3D point cloud map constructed by the unmanned aerial vehicle into a real-time map.
  • the 2D plane grid map constructed by the drone and the unmanned aerial vehicle is fused through SLAM technology.
  • This invention collects environmental information through remote control, improves the safety of related operations, eliminates positioning errors caused by factors such as weak GPS signals, and improves the accuracy of map construction.
  • this method only uses the structural information in the scene for the fusion of unmanned aerial vehicle and drone maps, and does not use the mutual observation between drones and unmanned vehicles, so the information utilization is not sufficient.
  • map matching errors caused by the heterogeneous perspectives of drones and unmanned vehicles are prone to occur, resulting in serious drift of the entire positioning system.
  • CN111707988A discloses a Chinese invention patent for an unmanned vehicle positioning system and positioning method based on an unmanned vehicle-mounted UWB base station, as shown in Figure 4.
  • the invention discloses an unmanned vehicle positioning system and positioning method based on an unmanned vehicle-mounted UWB base station, including four UWB anchor nodes on the unmanned vehicle, a positioning calculation module and a UWB tag of a drone, and establishes an unmanned vehicle-mounted coordinate system.
  • the four UWB anchor nodes on the unmanned vehicle respectively obtain the distance information of the UWB tag of the drone in real time, and calculate the position of the drone in the unmanned vehicle-mounted coordinate system based on the three-dimensional space Euclidean distance calculation method, so as to provide position information for maintaining the formation.
  • this method requires the installation of UWB signal transceiver modules on the drone and the unmanned vehicle, which increases the hardware cost and limits the application scenarios of the method.
  • the system consists of omnidirectional sensors including stereo fisheye cameras and ultra-wideband (UWB) sensors and algorithms including fisheye visual inertial odometry (VIO) to achieve multi-UAV map-based positioning and visual object detectors.
  • Graph-based optimization and forward propagation work as the back end of Omni-Swarm to fuse the measurement results of the front end.
  • the proposed decentralized state estimation method for the swarm system achieves centimeter-level relative state estimation accuracy while ensuring global consistency.
  • this method uses the information of mutual observation between drones in positioning, the The method does not have autonomy, that is, it cannot distinguish between the positioning results of drones in good perception conditions and drones in poor perception conditions.
  • the positioning result drift of a certain drone in the cluster causes the positioning instability of the entire cluster.
  • the main problem that the present invention solves is at least how to achieve accurate positioning through observation of the environment and each other between the drone and the unmanned vehicle when an unmanned vehicle and a drone jointly perform tasks (such as inspection, cargo transportation, and survey) within the same space-time range, without relying on external information such as GNSS and RTK, and only using airborne/vehicle-mounted sensing equipment, so that the collaborative positioning accuracy of the unmanned vehicle and drone is better than the positioning accuracy of a single machine, thereby providing positioning information for performing further high-precision operations.
  • tasks such as inspection, cargo transportation, and survey
  • the present invention proposes a method for simultaneous positioning and mapping based on mutual observation of heterogeneous unmanned systems, the method comprising the following steps:
  • the critical area is an area where the first robot or the second robot can keep itself in a stationary state relative to the environment
  • the exploration area is an area where a map needs to be established.
  • the first robot and the second robot are robots in a broad sense, which can be drones, unmanned vehicles, handheld devices or other portable devices.
  • the first robot and the second robot cooperate to locate and build a map, so as to solve the problem that when it is impossible to use external information for positioning or there is a serious deviation in positioning and it is necessary to obtain the environmental conditions of a certain area, such as tunnels, mines, unmanned areas, etc., by obtaining the relative positions of each other in real time to avoid the positioning drift and positioning tracking of a single robot due to the visual odometer. Lost.
  • the method switches roles until the task of sensing the degraded area is completed. Specifically, it also includes the following steps:
  • step S400 If there is still an exploration area, make the second robot stationary in the critical area for the first robot, make the first robot the second robot, enter a new exploration area, and return to step S200.
  • an implementation method of generating a safe area is as follows:
  • the dense point cloud is converted into an occupancy grid map Mocp , which has three types of voxels, namely known obstacle voxels V obstacle , known safe area voxels V safe , and unknown voxels V unknow ;
  • the first set distance is used to ensure the positioning accuracy between the first robot and the second robot.
  • S300 adopts a graph-structure-based exploration path planning method to perform path planning.
  • the method uses an optical flow method to make the first robot stationary in the critical area.
  • the first robot has a first identifier
  • the second robot has a second identifier.
  • the first identifier and/or the second identifier are used to determine the relative position between the first robot and the second robot.
  • the relative position between the first robot and the second robot is estimated as follows:
  • Texp-odom is the pose estimation value of the second robot obtained by its own binocular camera.
  • the dynamic weight balancing factor is estimated using the following formula:
  • d max is the maximum relative position between the first robot and the second robot
  • N Fast is the number of Fast feature points within the current field of view of the binocular camera of the second robot
  • d is the distance between the first robot and the second robot.
  • the present invention provides a computer-readable storage medium, characterized in that: a computer program capable of being loaded by a processor and executing any one of the methods of claims 1 to 8 is stored therein.
  • the present invention proposes a simultaneous positioning and map construction device based on mutual observation of heterogeneous unmanned systems, the device comprising a first robot, a second robot, and a map construction module; the first robot is configured to be stationary in a critical area, and a first binocular camera is configured on the first robot; the second robot is configured to be movable in an exploration area, and a second binocular camera is configured on the second robot; the map construction module is configured to use a safe area generation unit and a path planning unit to complete the map construction of the exploration area; the safe area generation unit is configured to: establish an occupancy grid map based on the depth images of the first binocular camera and the second binocular camera, detect obstacles in the exploration area, and generate a safe area; the path planning unit is configured to: perform path planning in the safe area, and adjust the path based on the real-time field of view of the second binocular camera in the exploration area and the relative position between the second robot and the first robot until the second robot moves to a new critical
  • FIG1 is a block diagram of the air-ground collaborative operation system mentioned in the background technology
  • FIG2 is a schematic diagram of the structure of the unmanned vehicle and unmanned aerial vehicle collaborative navigation device mentioned in the background technology
  • FIG3 is a block diagram of the overall structure of the multi-dimensional air-ground collaborative mapping system based on vision and laser SLAM technology mentioned in the background technology;
  • FIG4 is a schematic diagram of the positioning principle of the unmanned vehicle positioning system and positioning method based on the UWB base station on the unmanned vehicle mentioned in the background technology;
  • FIG5 is a schematic diagram of positioning a drone cluster using mutual observation between multiple drones and UWB distance measurement as mentioned in the background technology
  • FIG6 is a schematic diagram of a camera structure according to an embodiment of the present invention.
  • FIG. 7 is a schematic diagram of a method for simultaneously positioning and mapping an unmanned vehicle and an unmanned aerial vehicle by observing each other according to an embodiment of the present invention
  • FIG8 is a schematic diagram of an application scenario of a method for simultaneous positioning and map building of an unmanned vehicle and an unmanned aerial vehicle observing each other according to an embodiment of the present invention
  • FIG. 9 is a schematic diagram of a method flow chart in one embodiment of the present invention.
  • the first robot is a drone and the second robot is an unmanned vehicle.
  • the drone and the unmanned vehicle jointly perform tasks (such as inspection, cargo transportation, and survey) within the same space-time range.
  • the drone and the unmanned vehicle are equipped with a binocular camera, a fisheye camera, and multiple AprilTag QR code markers, as shown in FIG6 .
  • the binocular camera is used to perceive the surrounding environment to achieve positioning, mapping, and obstacle avoidance
  • the fisheye camera is used for mutual observation between the drone and the unmanned vehicle
  • the AprilTag QR code marker is used as an identifier on the drone or the unmanned vehicle to determine the relative position between the drone and the unmanned vehicle.
  • the unmanned vehicle can carry the drone and travel, relying only on its own binocular camera to perform positioning, mapping and obstacle avoidance.
  • the unmanned vehicle and the drone can simultaneously observe each other and perform positioning and mapping.
  • the method architecture is shown in Figure 7.
  • an unmanned vehicle and a drone start from a starting point and pass through an area with degraded perception conditions.
  • the drone and the unmanned vehicle collaborate to locate and build a map of the area with degraded perception conditions through mutual observation, which can avoid the positioning drift and tracking loss of the visual odometer when a single machine passes through the degraded perception area.
  • the drone and the unmanned vehicle are always in a condition where they can observe each other, and the two sides take turns to serve as each other's reference until the task of passing through the degraded perception area is completed.
  • steps S101 to S401 are shown in steps S101 to S401 below, as shown in FIG. 9 :
  • robot is used to refer to drones or unmanned vehicles, and the robots in the cluster are classified according to the perception environment they are in.
  • the robots in the critical area are defined as reference robots, and the robots that need to enter the perception degradation area for exploration are defined as exploration robots.
  • the initial role assignment is random, that is, drones and unmanned vehicles may both serve as exploration robots and reference robots.
  • the exploration area is the area where a map needs to be established.
  • the exploration robot in order to perceive the degraded area, the exploration robot can perform robust positioning by fusing the AprilTag posted by the mutual observation of the reference robot and the results of its own visual odometer.
  • the critical position is the area where the first robot or the second robot can keep itself in a stationary state relative to the environment.
  • the critical position is the position where the perception condition can meet the requirement that the robot ensures itself to be stationary based on the optical flow method. Whether a certain location meets the critical position requirement can be measured by the texture richness within the field of view of the binocular camera. In one implementation, if a certain robot If the number of Fast feature points extracted within the robot's field of view exceeds a certain threshold value T Fast , then the location is suitable as a critical position.
  • the Fast feature point extraction method is: traverse all pixel points, and the only criterion for judging whether the current pixel point is a feature point is to draw a circle with a radius of 3 pixels with the current pixel point as the center (there are 16 points on the circle), and count the number of points whose pixel values of these 16 points are significantly different from the pixel value of the center of the circle. If there are more than 9 points with a large difference, the pixel point at the center of the circle is considered to be a feature point.
  • the binocular cameras of drones and unmanned vehicles use the binocular ranging principle to build a dense point cloud of the surrounding environment, and convert the dense point cloud into an occupancy grid map Mocp with a voxel side length of d ocp , which has three types of voxels: known obstacle voxels V obstacle , known safe area voxels V safe , and unknown voxels V unknow .
  • the voxels representing obstacles in Mocp increase dynamically.
  • the occupancy grid maps they generate have their own independent coordinates, which are recorded as Mocp -UAV and Mocp-UGV .
  • the initial position of Mocp-UGV is the position of Mocp
  • the position transformation of Mocp-UAV and Mocp-UGV relative to Mocp at time t is determined by mutual positioning between the UAV and the unmanned vehicle using AprilTag.
  • d max is the maximum relative position of the reference robot and the exploration robot. The purpose of setting d max is to prevent the reference robot and the exploration robot from being too far away, which will cause the AprilTag positioning accuracy to decrease.
  • one implementation method is to use a graph-based exploration path planning method to plan an exploration path for the exploration robot.
  • a graph-based exploration path planning method After integrating the dense point clouds of the exploration robot and the reference robot into the global map to form an occupancy grid map, obstacle voxels and unknown voxels are determined, and a safe area is delineated within a certain range.
  • a series of nodes in the space are obtained by random sampling within the safe area with a density not higher than a certain density.
  • the nodes are connected according to the threshold to form a graph structure, and the Dijkstra shortest path algorithm is used for local trajectory planning. Specifically:
  • the location with the largest exploration gain in A safe in step S200 is the end point P gain-max of the local path planning.
  • the Dijkstra shortest path algorithm is executed in the graph structure, with the starting point being the current position of the exploration robot and the end point being the end point P gain-max determined in the safe area.
  • the passed nodes are interpolated to obtain the path Traj, and the interpolation method can be, for example, cubic B-spline, Newton interpolation, etc.
  • observation results of the reference robot, the observation results of the exploration robot, and the results of the exploration robot's visual odometry are linearly fused according to the distance between the two robots and the environmental perception conditions within the exploration robot's field of view to obtain the constructed map.
  • step S401 If there is still an exploration area, make the exploration robot a reference robot and keep it stationary in the critical area, make the reference robot an exploration robot, enter a new exploration area, and return to step S201.
  • the reference robot When the exploration robot is performing the exploration task, the reference robot remains stationary at a critical position, that is, the perception conditions at this position can meet the requirement of ensuring that it is stationary.
  • the exploration robot determines its own position by observing the reference robot and combining the observations of itself sent by the reference robot until the exploration robot reaches the next critical position, changes the robot role and continues the above steps.
  • the proportional-integral-derivative (PID) method is used to control Control the exploration robot to track the trajectory.
  • the reference robot is in a critical position, and based on the optical flow method, it ensures that its position is stationary at point Pref . At this time, the position and posture of the reference robot is Tref .
  • the exploration robot obtains its relative pose estimation relative to the reference robot by observing the AprilTag of the reference robot
  • the reference robot observes the exploration robot to estimate its own position relative to the exploration robot
  • the exploration robot obtains its own pose estimation Texp-odom based on the visual odometer according to its own binocular camera.
  • d max is the maximum distance between the two robots.
  • the exploration robot After the exploration robot reaches the focus of the local path planning, it is determined whether the location is a critical position. If so, the exploration robot and the reference robot are exchanged, and the process returns to step S201 until the task is completed and the environment perception friendly area is reached. If not, the exploration robot retreats along the original path until it reaches a point that is a critical position, and the exploration robot and the reference robot are exchanged, and the process returns to step S201 until all the areas that need to be mapped are mapped.
  • the above implementation methods only rely on the binocular cameras and fisheye cameras carried by drones and unmanned vehicles to achieve mutual observation and positioning in harsh perception environments.
  • Previous methods for solving the problem of robust positioning of multiple robots in perception-degraded environments mostly rely on increasing the redundancy of sensors or relying on external positioning signals.
  • UWB ultra-wideband
  • the station sends a pseudo-GPS satellite signal to achieve positioning in a tunnel environment.
  • the number of binocular cameras configured on the drone or unmanned vehicle in the above-mentioned implementation mode can be changed, and the number of drones or unmanned vehicles can also be changed, which can be further improved into multi-machine positioning and map construction.
  • the above implementation method can be used to manually assist in the positioning and map construction of unknown areas.
  • the corresponding pose estimation becomes a position estimation.

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Automation & Control Theory (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

一种基于异构无人系统相互观测的同时定位与地图构建方法。所述方法的一种实施方式是用于解决无人车和无人机在同一时空范围内联合执行任务(如巡检、运送货物、勘察)时，在不依赖于GNSS和RTK等外部信息，仅使用机载/车载感知设备的条件下，通过无人机与无人车之间对环境和彼此的观测来实现准确定位，使得无人车和无人机协作的定位精度优于单机定位精度，为执行进一步的高精度的操作提供定位信息。

Description

基于异构无人系统相互观测的同时定位与地图构建方法 技术领域
本公开涉及智能交通，尤其涉及一种基于异构无人系统相互观测的同时定位与地图构建方法。
背景技术
准确的环境感知与自身状态估计是无人系统自主执行各种高层次任务的重要基础。在光照正常、纹理丰富、结构特征明显的一般场景下，现有的同时定位与地图构建(simultaneous localization and mapping,SLAM)方法已经取得了非常稳定的性能表现，如在经典的室内数据集上，SLAM最高定位精度已经可以达到厘米级。然而，在感知退化环境下(如隧道、矿洞、狭长走廊等)进行机器人的同时定位与地图构建仍然是一个具有挑战性的问题。主要表现在：(1)与开阔空间之间存在遮挡，导致无人系统无法接收到GPS或RTK等外部定位信号；(2)高度相似性的结构增加了里程计错误匹配的概率，进而容易引起错误的回环检测，一旦将错误的回环引入地图优化，将会为全局地图带来严重的破坏；(3)较大的空间规模使里程计的累计误差随运行时间明显增加，即使采用回环修正的方法对精度的提升也非常有限。
为了实现在复杂环境下不依赖外部信息的精确定位，将无人机与无人车协同，发挥二者各自优势来解决环境感知条件退化与自身运动导致的定位丢失问题是一种有效的方案。
(1)公开号CN210377164U公布一项中国实用新型专利—一种空地协同作业系统，如图1所示。该实用新型公开了一种空地协同作业系统，包括：无人车，通过在地面上的移动构建目标场景的三维地图，并实时定位自身在三维地图的地图坐标系下的位姿；无人机，用于对作业目标进行作业；数据采集器，用于获取无人机与无人车的第一相对位姿以及作业目标与无人车的第二相对位姿；数据处理器，与无人车、无人机以及数据采集器均相连，用于根据无人车 在地图坐标系下的位姿、第一相对位姿以及第二相对位姿，得到无人机与作业目标的第三相对位姿，并将第三相对位姿发送至无人机，以使无人机根据第三相对位姿调整位姿至预设作业范围内。该空地协同作业系统通过无人车协助无人机在目标场景中精确定位。该方法虽然同样可以达到无人车与无人机协同作业的效果，但是该方法仅在无人车上安放AprilTag标记，用于辅助无人机的定位，而没有考虑使用无人车和无人机相互的观测信息实现协同定位，对有效信息的利用不够充分。
(2)公开号CN217716438U公布一项中国实用新型专利一种无人车、无人机协同导航装置，如图2所示。该实用新型公开了一种无人车、无人机协同导航装置，包括无人机、QGC地面站和无人车，所述无人机安装有GPS定位装置、锂电池组、第一无线图传模块、双目相机、第二无线数传模块、支撑板、起落架和飞行控制器，所述飞行控制器包括主控制器、第一I/O控制器、第一IMU惯性导航模块和GPS模块，所述QGC地面站安装有第一无线数传模块，所述无人车设置有MC底层控制模块、上位机图形界面显示模块、速度控制器、转向控制器、第二I/O控制器和第二无线图传模块，所述MC底层控制模块由车载控制器和第二IMU惯性导航模块组成。该实用新型解决了传统导航装置识别范围小、延时较大、受GPS信号影响较大的问题，设计了一种无人车、无人机协同导航装置但该实用新型依赖GPS模块提供全局定位信息，在矿坑洞穴或高楼峡谷等GPS信号缺失的场景中无法使用。
(3)公开号CN114923477A公布一项中国发明专利基于视觉与激光SLAM技术的多维度空地协同建图系统和方法，如图3所示。该系统包括地面站、无人机和无人车。无人机包括整体物理架构、机载嵌入式电脑和图像传感器；整体物理架构包括机架、四旋翼和电机；机载嵌入式电脑包括通信模块与嵌入式处理器，图像传感器包括双目相机与RGB-D相机。无人车包括嵌入式处理器、激光雷达传感器和通信模块。地面站包括显示控件、控制控件和通信控件。所述方法利用地面站输出控制和建图指令，将无人机构建的3D点云地 图和无人机构建的2D平面栅格地图通过SLAM技术进行融合。该发明通过远程控制采集环境信息，提高了相关作业的安全性，消除了GPS信号弱等因素造成的定位误差，提高了建图的精准度，但该方法在无人测和无人机的地图融合上仅使用场景中的结构信息，没有使用到无人机与无人车之间的相互观测，信息利用不够充分。且在感知退化环境下，容易出现由于无人机和无人车异构视角引起的地图匹配错误，导致整个定位系统出现严重飘移。
(4)公开号CN111707988A公布一项中国发明专利基于无人车车载UWB基站的无人器定位系统及定位方法，如图4所示。该发明公开了基于无人车车载UWB基站的无人器定位系统及定位方法，包括无人车车载的4个UWB锚节点、定位计算模块和无人机UWB标签，建立无人车车载坐标系，在无人机无人车编队运动过程中，无人车车载4个UWB锚节点分别实时获取无人机UWB标签的距离信息，依据三维空间欧氏距离计算方法，计算无人机在无人车车载坐标系中的位置，为编队队形的保持提供位置信息，但该方法需要在无人机和无人车上安装UWB信号收发模块，提升了硬件成本，限制了方法的应用场景。
(5)论文《Omni-Swarm:A Decentralized Omnidirectional Visual–Inertial–UWB State Estimation System for Aerial Swarms》使用多无人机之间的相互观测和UWB距离测量来进行无人机集群的定位，如图5所示。该文提出了一种用于航空群的分散式全向视觉惯性UWB状态估计系统Omni-Swarm。为了解决可观测性、复杂的初始化、精度不足和缺乏全局一致性的问题，引入了一个全向感知系统作为全向群的前端，该系统由包括立体鱼眼相机和超宽带(UWB)传感器在内的全向传感器和包括鱼眼视觉惯性里程计(VIO)在内的算法组成，以实现基于多无人机地图的定位和视觉对象检测器。基于图的优化和正向传播作为Omni-Swarm的后端工作，以融合前端的测量结果。根据实验结果，所提出的群系统分散状态估计方法在保证全局一致性的同时，达到了厘米级的相对状态估计精度。该方法虽然在定位中用到了无人机之间相互观测的信息，但该 方法不具备自主性，即无法区别对待处于感知条件良好的无人机与处于感知条件恶劣的无人机的定位结果，存在集群中某一无人机定位结果漂移引起整个集群定位不稳定的缺点。
发明内容
针对上述现有技术，本发明主要解决的问题至少是无人车和无人机在同一时空范围内联合执行任务(如巡检、运送货物、勘察)时，在不依赖于GNSS和RTK等外部信息，仅使用机载/车载感知设备的条件下，如何通过无人机与无人车之间对环境和彼此的观测来实现准确定位，使得无人车和无人机协作的定位精度优于单机定位精度，为执行进一步的高精度的操作提供定位信息。
为了解决上述技术问题，本发明的技术方案如下。
第一方面，本发明提出了一种基于异构无人系统相互观测的同时定位与地图构建方法，所述方法包括下述步骤：
S100、使第一机器人静止于临界区域，使第二机器人位于探索区域，第一机器人具有第一双目相机，第二机器人具有第二双目相机；
S200、基于第一双目相机、第二双目相机两者的深度图像，建立占据栅格地图，检测探索区域的障碍物，并生成安全区域；
S300、在安全区域内进行路径规划，基于探索区域中第二双目相机的实时视野以及第二机器人与第一机器人之间的相对位置，调整路径，直至第二机器人移动至新的临界区域，完成探索区域的地图构建；
所述临界区域为第一机器人或第二机器人能够使自身相对所在环境处于静止状态的区域，所述探索区域为需要建立地图的区域。
在上述技术方案中，第一机器人、第二机器人是广义的机器人，可以是无人机、无人车、手持设备或其它随身便携设备。通过第一机器人和第二机器人协作定位以构建地图，以解决在无法利用外部信息进行定位或定位发生严重偏差而又需要获取某一区域的环境状况时，比如隧道、矿坑、无人区域等，通过实时获取彼此的相对位置避免单个机器人因视觉里程计的定位飘移与定位跟踪 丢失。
作为上述技术方案的进一步改进，所述方法通过角色互换，直至完成通过感知退化区域的任务。具体地，还包括下述步骤：
S400、若还存在探索区域，则使第二机器人为第一机器人静止于临界区域，使第一机器人为第二机器人，进入新的探索区域，返回步骤S200。
在上述技术方案中，一种生成安全区域的实施方式如下：
基于第一双目相机和第二双目相机，建立周围环境的稠密点云；
将稠密点云转化为占据栅格地图Mocp，占据栅格地图Mocp具有三类体素，分别为已知障碍物体素Vobstacle、已知安全区域体素Vsafe、未知体素Vunknow；
在Mocp中，以第一机器人为圆心，在第一设定距离内，将所有空白的区域中与障碍物体素距离不超过第二设定距离的已知安全区域体素作为安全区域；
所述第一设定距离用于保证第一机器人和第二机器人距离之间的定位精度。
在上述技术方案中，所述S300采用基于图结构的探索路径规划方法进行路径规划。
在上述技术方案中，所述方法采用光流法使第一机器人静止于临界区域。
在上述技术方案中，第一机器人具有第一标识，第二机器人具有第二标识，第一标识和/或第二标识用于确定第一机器人与第二机器人之间的相对位置。
在上述技术方案中，所述第一机器人和第二机器人之间的相对位置，估算如下：
式中：
为动态权重平衡因子；为第二机器人基于第一标识得到的自身相对第一机器人的相对位姿估计，为第一机器人基于第二标识得到的自身相对第一机器人的相对位姿估计，Texp-odom为第二机器人根据自身双目相机得到的关于自身位姿估计值。
在上述技术方案中，所述动态权重平衡因子采用下式估算：
式中：dmax为第一机器人和第二机器人之间的最大相对位置，NFast为第二机器人的双目相机当前视野范围内Fast特征点数量，d为第一机器人、第二机器人之间距离。
第二方面，本发明提出了一种计算机可读存储介质，其特征在于：存储有能够被处理器加载并执行如权利要求1至8中任一种方法的计算机程序。
第三方面，本发明提出了一种基于异构无人系统相互观测的同时定位与地图构建装置，所述装置包括第一机器人、第二机器人、地图构建模块；所述第一机器人，被配置位于临界区域静止，在第一机器人上配置第一双目相机，所述第二机器人，被配置位于探索区域能够移动，在第二机器人上配置第二双目相机；所述地图构建模块，被配置利用生成安全区域单元、路径规划单元，以完成探索区域的地图构建；所述生成安全区域单元，被配置用于：基于第一双目相机、第二双目相机两者的深度图像，建立占据栅格地图，检测探索区域的障碍物，并生成安全区域；所述路径规划单元，被配置用于：在安全区域内进行路径规划，基于探索区域中第二双目相机的实时视野以及第二机器人与第一机器人之间的相对位置，调整路径，直至第二机器人移动至新的临界区域；所述临界区域为第一机器人或第二机器人能够使自身相对所在环境处于静止状态的区域，所述探索区域为需要建立地图的区域。
附图说明
为了更清楚地说明本申请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申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1、背景技术中提及的空地协同作业系统的结构框图；
图2、背景技术中提及的无人车、无人机协同导航装置结构示意图；
图3、背景技术中提及的基于视觉与激光SLAM技术的多维度空地协同建图系统的总体结构框图；
图4、背景技术中提及的基于无人车车载UWB基站的无人器定位系统及定位方法的定位原理示意图；
图5、背景技术中提及的使用多无人机之间的相互观测和UWB距离测量来进行无人机集群的定位示意图；
图6、本发明一种实施方式下的相机结构示意图；
图7、本发明一种实施方式下的无人车与无人机相互观测的同时定位与地图构建方法架构示意图；
图8、本发明一种实施方式下的无人车与无人机相互观测的同时定位与地图构建方法应用场景示意图；
图9、本发明一种实施方式下的方法流程示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。
在一种实施方式中，第一机器人为无人机，第二机器人为无人车。无人机、无人车在同一时空范围内联合执行任务(如巡检、运送货物、勘察)。无人机和无人车都配备一个双目相机、一个鱼眼相机和多个AprilTag二维码标记，如图6所示。其中：双目相机用于感知周围环境以实现定位建图及避障，鱼眼相机用于无人机与无人车之间的相互观测，AprilTag二维码标记作为无人机或无人车上的标识，用于确定无人机和无人车之间的相对位置。
在感知条件良好的环境下，无人车可以搭载无人机行驶，仅依靠自身的双目相机执行定位建图和避障；当环境感知条件退化时，执行无人车与无人机相互观测的同时定位与地图构建方法，方法架构如图7所示。
其中，感知条件的退化主要表现在：
(1)与开阔空间之间存在遮挡，导致无人系统无法接收到GPS或RTK等外部定位信号；
(2)高度相似性的结构增加了里程计错误匹配的概率，进而容易引起错误的回环检测，一旦将错误的回环引入地图优化，将会为全局地图带来严重的破坏；
(3)较大的空间规模使里程计的累计误差随运行时间明显增加，即使采用回环修正的方法对精度的提升也非常有限。
参见图8所示的场景，一辆无人车与一架无人机从起点出发，经过一片感知条件退化的区域。无人机、无人车通过彼此的观测来协作定位与构建感知条件退化区域的地图，可避免在单机在经过感知退化区域时视觉里程计的定位飘移与跟踪丢失问题。在这个过程中，无人机与无人车时刻处于可相互观测的条件，双方交替作为彼此的参照，直到完成通过感知退化区域的任务。
基于图7的方法架构，具体步骤见下文步骤S101～S401，如图9所示：
S101、使参照机器人静止于临界区域，使探索机器人位于探索区域。
在这里，使用机器人来代指无人机或无人车，并依据所处的感知环境将集群中的机器人分类，规定位于临界区域的机器人为参照机器人，需要进入感知退化区域进行探索的机器人为探索机器人。初始角色分配随机进行。即无人机和无人车都有可能作为探索机器人和参照机器人。
探索区域为需要建立地图的区域，在当前实施方式中，为感知退化区域，探索机器人可通过融合与参照机器人的相互观测张贴的AprilTag与自身视觉里程计的结果来进行鲁棒定位。
临界位置，为第一机器人或第二机器人能够使自身相对所在环境处于静止状态的区域。在当前实施方式中，临界位置为该位置的感知条件能够满足机器人基于光流法确保自身处于静止的要求。可通过双目相机视野内的纹理丰富程度来度量某一地点是否满足临界位置的要求。在一种实施方式中，如果某一机 器人视野内提取Fast特征点的数量超过某一阈值TFast，则该地点适合作为临界位置。Fast特征点提取方法为：遍历所有的像素点，判断当前像素点是不是特征点的唯一标准就是在以当前像素点为圆心以3像素为半径画个圆(圆上有16个点)，统计这16个点的像素值与圆心像素值相差比较大的点的个数。超过9个差异度很大的点那就认为圆心那个像素点是一个特征点。
S201、基于第一双目相机、第二双目相机两者的深度图像，建立占据栅格地图，检测探索区域的障碍物，并生成安全区域。
在这一步骤中，基于探索机器人和参照机器人双目相机的感知融合结果，检测待探索区域的障碍物，为探索机器人生成安全的探索区域。
具体地，无人机和无人车的双目相机通过双目测距原理建立周围环境的稠密点云，并将稠密点云转化为体素边长为docp的占据栅格地图Mocp，其中有三类体素，分别为已知障碍物体素Vobstacle、已知安全区域体素Vsafe、未知体素Vunknow。随着机器人在空间中移动执行任务，Mocp中代表障碍物的体素动态增加。
由于无人机和无人车各自携带一个双目相机，所以其产生的占据栅格图有各自独立的坐标，分别记为Mocp-UAV和Mocp-UGV。本实施方式中以Mocp-UGV初始位置为Mocp的位置，通过无人机与无人车之间使用AprilTag的相互定位来确定t时刻Mocp-UAV和Mocp-UGV相对于Mocp的位姿变换。
在Mocp中，以参照机器人为圆心，dmax距离内所有空白的区域中与障碍物体素距离不超过设定的安全区域距离dsafe的所有已知安全区域体素即为安全区域Asafe，机器人可在此区域内规划路径。dmax为参照机器人和探索机器人的最大相对位置，设定dmax的意义在于防止参照机器人和探索机器人距离过远导致的AprilTag定位精度下降。
S301、在安全区域内进行路径规划，基于探索区域中第二双目相机的实时视野以及参照机器人与探索机器人之间的相对位置，调整路径，直至探索机器人移动至新的临界区域，完成探索区域的地图构建。
在这一步骤中，一种实施方式是使用基于图结构的探索路径规划方法为探索机器人规划探索路径。在融合探索机器人和参照机器人的稠密点云到全局地图形成占据栅格地图后，确定障碍物体素和未知体素，在一定范围内划定安全区域，在安全区域内通过不高于某一密度的随机采样得到空间中一系列节点，按照阈值将节点连接形成图结构，使用迪杰斯特拉最短路径算法进行局部轨迹规划。具体地：
首先，确定局部路径规划的终点。定义某一地点的探索增益为该地点dgain邻域内的未知体素的数量。步骤S200中Asafe内探索增益最大的地点即为局部路径规划的终点Pgain-max。
其次，生成图结构。在安全区域内生成随机采样点，过滤掉该随机采样点与最近邻点距离小于dmin的点，并将距离小于dedge的点用无向边连接，最终在局部生成图结构。dmin、dedge为设定的超参数。
最终，在图结构中执行迪杰斯特拉最短路径算法，起点为探索机器人的当前位置，终点为安全区域内确定的终点Pgain-max，并将经过的节点进行插值得到路径Traj，插值方法比如三次B样条，牛顿插值等。
将参照机器人的观测结果、探索机器人的观测结果、探索机器人视觉里程计的结果根据两机器人的距离以及探索机器人视野内环境感知条件进行线性融合，以获得构建的地图。
S401、若还存在探索区域，则使探索机器人为参照机器人并静止于临界区域，使参照机器人为探索机器人，进入新的探索区域，返回步骤S201。
在探索机器人执行探索任务的过程中，参照机器人静止于临界位置，即该位置的感知条件可以满足确保自身处于静止的要求，探索机器人通过观测参照机器人并结合参照机器人发送的对自身的观测来确定自身位姿，直到探索机器人达到下一临界位置，转变机器人角色继续进行上述步骤。
具体过程如下：
首先，根据步骤3中得到的轨迹Traj，使用比例-积分-微分(PID)方法控 制探索机器人进行轨迹跟踪。
其次，在探索机器人执行轨迹跟踪的过程中，参照机器人处于临界位置，基于光流法确保自身位置静止于点Pref，此时参照机器人的位姿为Tref。
在探索机器人执行轨迹跟踪同时，两机器人相互观测对方的AprilTag，得到以下结果：探索机器人通过观测参照机器人AprilTag得到自身相对参照机器人的相对位姿估计参照机器人观测探索机器人得到的自身相对探索机器人的位姿估计探索机器人根据自身双目相机得到基于视觉里程计的自身位姿估计Texp-odom.
最终，探索机器人的位姿可以表示为：
其中，为动态权重平衡因子，其取值与两机器人之间距离d和探索机器人当前视野范围内Fast特征点数量NFast有关，具体表示为：
其中，dmax为两机器人之间的最大距离。
在探索机器人到达局部路径规划的重点后，判断该地点是否属于临界位置。若是，则由交换探索机器人与参照机器人身份，返回步骤S201，直到完成任务达到环境感知友好的区域。若否，则探索机器人沿原路径回退，直到到达某一属于临界位置的点，交换探索机器人与参照机器人身份，返回步骤S201，直至需要构建地图的区域全部建立起地图。
综上，上述实施方式仅仅依靠无人机和无人车搭载的双目相机和鱼眼相机实现感知恶劣环境下相互观测定位。以往解决感知退化环境下多机器人鲁棒定位问题的方法，大都依赖于增加传感器的冗余程度，或依赖外部定位信号。如，如通过增加主动光源实现弱光线环境下的同时定位与地图构建，通过增加有锚点的超宽带(Ultra-WideBand,UWB)定位实现矿坑下复杂环境的定位，通过基 站发送伪GPS卫星信号实现隧道环境下的定位。上述方法虽然提升了感知退化环境下机器人同时定位与地图构建的能力，但增加机器人携带传感器和辅助设备的数量和种类会增加整个无人系统的复杂性，无人机/无人车等移动平台的载荷和运算能力往往会受到限制，从而限制了其应用的范围。而本方法基于低成本的双目相机、鱼眼相机、AprilTag二维码标签即可实现感知恶劣环境下的同时定位与建图。在无人机与无人车的自主轨迹规划考虑到了对定位的影响。以往轨迹规划方法侧重于考虑最短距离或最短时间，而上述实施方式采用的轨迹规划方法，综合考虑了机器人在场景中的定位能力。可以最大限度保证基于视觉里程计的定位不丢失或飘移，为复杂环境下机器人执行多种任务提供了精确的未知信息环境信息。
需注意的是：上述实施方式中的无人机或无人车上配置的双目相机数目可改变，而无人机或无人车的数目也可以改变，进一步改进成多机定位与地图构建。
需要注意的是：上述实施方式中，当无人机或无人车为一种手持设备或便携设备时，上述实施方法可用于人工辅助进行未知区域的定位和地图的构建，在上述方法的使用中，相应的位姿估计变为一种位置估计。
通过以上的实施方式的描述，所属领域的技术人员可以清楚地了解到本公开可借助软件加必需的通用硬件的方式来实现，当然也可以通过专用硬件包括专用集成电路、专用CPU、专用存储器、专用元器件等来实现。一般情况下，凡由计算机程序完成的功能都可以很容易地用相应的硬件来实现，而且，用来实现同一功能的具体硬件结构也可以是多种多样的，例如模拟电路、数字电路或专用电路等。但是，对本公开而言更多情况下，软件程序实现是更佳的实施方式。
尽管以上结合附图对本发明的实施方案进行了描述，但本发明并不局限于上述的具体实施方案和应用领域，上述的具体实施方案仅仅是示意性的、指导性的，而不是限制性的。本领域的普通技术人员在本说明书的启示下和在不脱 离本发明权利要求所保护的范围的情况下，还可以做出很多种的形式，这些均属于本发明保护之列。

Claims (10)

  1. 基于异构无人系统相互观测的同时定位与地图构建方法，其特征在于，所述方法包括下述步骤：
    S100、使第一机器人静止于临界区域，使第二机器人位于探索区域，第一机器人具有第一双目相机，第二机器人具有第二双目相机；
    S200、基于第一双目相机、第二双目相机两者的深度图像，建立占据栅格地图，检测探索区域的障碍物，并生成安全区域；
    S300、在安全区域内进行路径规划，基于探索区域中第二双目相机的实时视野以及第二机器人与第一机器人之间的相对位置，调整路径，直至第二机器人移动至新的临界区域，完成探索区域的地图构建；
    所述临界区域为第一机器人或第二机器人能够使自身相对所在环境处于静止状态的区域，所述探索区域为需要建立地图的区域。
  2. 根据权利要求1所述的方法，其特征在于，所述方法还包括下述步骤：
    S400、若还存在探索区域，则使第二机器人为第一机器人静止于临界区域，使第一机器人为第二机器人，进入新的探索区域，返回步骤S200。
  3. 根据权利要求1所述的方法，其特征在于，所述S200包括：
    基于第一双目相机和第二双目相机，建立周围环境的稠密点云；
    将稠密点云转化为占据栅格地图Mocp，占据栅格地图Mocp具有三类体素，分别为已知障碍物体素Vobstacle、已知安全区域体素Vsafe、未知体素Vunknow；
    在Mocp中，以第一机器人为圆心，在第一设定距离内，将所有空白的区域中与障碍物体素距离不超过第二设定距离的已知安全区域体素作为安全区域；
    所述第一设定距离用于保证第一机器人和第二机器人距离之间的定位精度。
  4. 根据权利要求1所述的方法，其特征在于，所述S300采用基于图结构的探索路径规划方法进行路径规划。
  5. 根据权利要求1所述的方法，其特征在于，所述方法采用光流法使第一机器人静止于临界区域。
  6. 根据权利要求1所述的方法，其特征在于，第一机器人具有第一标识， 第二机器人具有第二标识，第一标识和/或第二标识用于确定第一机器人与第二机器人之间的相对位置。
  7. 根据权利要求6所述的方法，其特征在于，所述第一机器人和第二机器人之间的相对位置，估算如下：
    式中：
    为动态权重平衡因子；为第二机器人基于第一标识得到的自身相对第一机器人的相对位姿估计，为第一机器人基于第二标识得到的自身相对第一机器人的相对位姿估计，Texp-odom为第二机器人根据自身双目相机得到的关于自身位姿估计值。
  8. 根据权利要求7所述的方法，其特征在于，所述动态权重平衡因子采用下式估算：
    式中：dmax为第一机器人和第二机器人之间的最大相对位置，NFast为第二机器人的双目相机当前视野范围内Fast特征点数量，d为第一机器人、第二机器人之间距离。
  9. 一种计算机可读存储介质，其特征在于：存储有能够被处理器加载并执行如权利要求1至8中任一种方法的计算机程序。
  10. 基于异构无人系统相互观测的同时定位与地图构建装置，其特征在于：
    所述装置包括第一机器人、第二机器人、地图构建模块；
    所述第一机器人，被配置位于临界区域静止，在第一机器人上配置第一双目相机，所述第二机器人，被配置位于探索区域能够移动，在第二机器人上配置第二双目相机；
    所述地图构建模块，被配置利用生成安全区域单元、路径规划单元，以完成探索区域的地图构建；
    所述生成安全区域单元，被配置用于：基于第一双目相机、第二双目相机两者的深度图像，建立占据栅格地图，检测探索区域的障碍物，并生成安全区域；
    所述路径规划单元，被配置用于：在安全区域内进行路径规划，基于探索区域中第二双目相机的实时视野以及第二机器人与第一机器人之间的相对位置，调整路径，直至第二机器人移动至新的临界区域；
    所述临界区域为第一机器人或第二机器人能够使自身相对所在环境处于静止状态的区域，所述探索区域为需要建立地图的区域。
PCT/CN2023/133428 2022-11-25 2023-11-22 基于异构无人系统相互观测的同时定位与地图构建方法 WO2024109837A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211496423.8 2022-11-25
CN202211496423.8A CN115790571A (zh) 2022-11-25 2022-11-25 基于异构无人系统相互观测的同时定位与地图构建方法

Publications (1)

Publication Number Publication Date
WO2024109837A1 true WO2024109837A1 (zh) 2024-05-30

Family

ID=85441894

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/133428 WO2024109837A1 (zh) 2022-11-25 2023-11-22 基于异构无人系统相互观测的同时定位与地图构建方法

Country Status (2)

Country Link
CN (1) CN115790571A (zh)
WO (1) WO2024109837A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115790571A (zh) * 2022-11-25 2023-03-14 中国科学院深圳先进技术研究院 基于异构无人系统相互观测的同时定位与地图构建方法
CN117870652B (zh) * 2024-03-13 2024-05-14 北京航空航天大学 一种基于雷达、惯性、视觉融合的陆空在线协同定位方法
CN118010008B (zh) * 2024-04-08 2024-06-07 西北工业大学 基于双目slam和机间回环优化双无人机协同定位方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107808407A (zh) * 2017-10-16 2018-03-16 亿航智能设备（广州）有限公司 基于双目相机的无人机视觉slam方法、无人机及存储介质
US20210150755A1 (en) * 2019-11-14 2021-05-20 Samsung Electronics Co., Ltd. Device and method with simultaneous implementation of localization and mapping
CN114923477A (zh) * 2022-05-19 2022-08-19 南京航空航天大学 基于视觉与激光slam技术的多维度空地协同建图系统和方法
CN115164919A (zh) * 2022-09-07 2022-10-11 北京中科慧眼科技有限公司 基于双目相机的空间可行驶区域地图构建方法及装置
CN115790571A (zh) * 2022-11-25 2023-03-14 中国科学院深圳先进技术研究院 基于异构无人系统相互观测的同时定位与地图构建方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107808407A (zh) * 2017-10-16 2018-03-16 亿航智能设备（广州）有限公司 基于双目相机的无人机视觉slam方法、无人机及存储介质
US20210150755A1 (en) * 2019-11-14 2021-05-20 Samsung Electronics Co., Ltd. Device and method with simultaneous implementation of localization and mapping
CN114923477A (zh) * 2022-05-19 2022-08-19 南京航空航天大学 基于视觉与激光slam技术的多维度空地协同建图系统和方法
CN115164919A (zh) * 2022-09-07 2022-10-11 北京中科慧眼科技有限公司 基于双目相机的空间可行驶区域地图构建方法及装置
CN115790571A (zh) * 2022-11-25 2023-03-14 中国科学院深圳先进技术研究院 基于异构无人系统相互观测的同时定位与地图构建方法

Also Published As

Publication number Publication date
CN115790571A (zh) 2023-03-14

Similar Documents

Publication Publication Date Title
JP7263630B2 (ja) 無人航空機による３次元再構成の実行
WO2024109837A1 (zh) 基于异构无人系统相互观测的同时定位与地图构建方法
TWI827649B (zh) 用於ｖｓｌａｍ比例估計的設備、系統和方法
Mostegel et al. Active monocular localization: Towards autonomous monocular exploration for multirotor mavs
Saha et al. A real-time monocular vision-based frontal obstacle detection and avoidance for low cost UAVs in GPS denied environment
US10254767B1 (en) Determining position or orientation relative to a marker
JP7245084B2 (ja) 自動運転システム
US11754415B2 (en) Sensor localization from external source data
Javanmardi et al. Autonomous vehicle self-localization based on multilayer 2D vector map and multi-channel LiDAR
CN112034479A (zh) 一种应用于煤矿井下智能巡检无人机的定位方法及系统
US20210263533A1 (en) Mobile object and method for controlling mobile object
Celik et al. Mono-vision corner SLAM for indoor navigation
US12019453B2 (en) Multi-sensor-fusion-based autonomous mobile robot indoor and outdoor positioning method and robot
US11561553B1 (en) System and method of providing a multi-modal localization for an object
KR20200063363A (ko) 로봇 자율주행 시스템 및 방법
KR20240035530A (ko) 모바일 플랫폼을 탐색하기 위한 장치, 시스템 및 방법
US20220334594A1 (en) Information processing system, information processing apparatus, and information processing program
Wang et al. A vision-aided navigation system by ground-aerial vehicle cooperation for UAV in GNSS-denied environments
Zhou et al. Localization for unmanned vehicle
CN113777615B (zh) 室内机器人的定位方法、系统及清洁机器人
US12025983B2 (en) Indicating a scan target for an unmanned aerial vehicle
CN114675670B (zh) 一种基于相对定位的无人机自主穿越框型障碍物方法
Zhang et al. RGBD Navigation: A 2D navigation framework for visual SLAM with pose compensation
JP2023173688A (ja) 移動体、事前地図生成方法、位置推定システム、位置推定方法、事前地図生成方法、およびプログラム
Harris et al. Practical issues in automatic 3D reconstruction and navigation applications using man-portable or vehicle-mounted sensors