CN115311349A - Vehicle automatic driving auxiliary positioning fusion method and domain control system thereof - Google Patents
Vehicle automatic driving auxiliary positioning fusion method and domain control system thereof Download PDFInfo
- Publication number
- CN115311349A CN115311349A CN202210939943.5A CN202210939943A CN115311349A CN 115311349 A CN115311349 A CN 115311349A CN 202210939943 A CN202210939943 A CN 202210939943A CN 115311349 A CN115311349 A CN 115311349A
- Authority
- CN
- China
- Prior art keywords
- result
- vehicle
- factor
- ndt
- point cloud
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a vehicle automatic driving auxiliary positioning fusion method and a domain control system thereof, wherein the method comprises the following steps: acquiring various positioning related data of a vehicle; preprocessing the various positioning related data to obtain a GNSS factor, an IMU pre-integration factor and a preprocessing result; sequentially carrying out first NDT point cloud registration and pose calculation on the preprocessing result to obtain a pose calculation result; carrying out NDT map registration by using the pose calculation result to obtain an NDT map registration result and a laser odometer factor; constructing a sliding window map according to the NDT map registration result; performing second NDT point cloud registration on the sliding window map to obtain a second NDT point cloud registration result; performing closed-loop detection on the second NDT point cloud registration result to generate a closed-loop detection factor; performing constraint factor fusion and factor graph optimization on the four factors to obtain an optimization result; and generating a motion track of the vehicle according to the optimization result and the pose calculation result.
Description
Technical Field
The invention relates to the technical field of automatic driving, in particular to a vehicle automatic driving auxiliary positioning fusion method and a domain control system thereof.
Background
With the popularization of the automatic driving technology and the complexity of the environment perception requirement of the vehicle, the automatic driving domain controller is an important carrier for realizing the automatic driving function and bears the module computational power and performance requirements of environment perception fusion, decision planning, chassis control and the like. In terms of functions, the current automatic driving area controller mainly supports various environment sensing sensors, does not integrate high-precision inertial navigation, satellite navigation and 4G RTK (Real-time kinematic/carrier phase difference technology), is not high enough in integration degree, needs additional power lines for the sensors, and is still complex in system wiring harness. In the aspect of algorithms, synchronous positioning and map building (SLAM) algorithms are also researched more and more, some algorithms need to establish clear matching relations among feature points, and the clear feature matching is most prone to errors.
Disclosure of Invention
The invention aims to provide an automatic driving assistance positioning fusion method for a vehicle and a domain control system thereof, so as to improve the real-time performance and accuracy of positioning data communication.
The technical scheme for solving the technical problems is as follows:
the invention provides a vehicle automatic driving auxiliary positioning fusion method, which comprises the following steps:
s1: acquiring various positioning related data of a vehicle;
s2: preprocessing the various positioning related data to obtain a GNSS factor, an IMU pre-integration factor and a preprocessing result;
s3: performing first NDT point cloud registration on the preprocessing result to obtain a first point cloud registration result;
s4: performing pose calculation on the first point cloud registration result to obtain a pose calculation result;
s5: carrying out NDT map registration by using the pose calculation result to obtain an NDT map registration result and a laser odometer factor;
s6: constructing a sliding window map according to the NDT map registration result;
s7: performing second NDT point cloud registration on the sliding window map to obtain a second NDT point cloud registration result;
s8: performing closed-loop detection on the second NDT point cloud registration result to generate a closed-loop detection factor;
s9: performing constraint factor fusion on the GNSS factor, the IMU pre-integration factor, the laser odometer factor and the closed-loop detection factor to obtain a fusion result;
s10: performing factor graph optimization on the fusion result to obtain an optimization result;
s11: and generating a motion track of the vehicle according to the optimization result and the pose calculation result.
Optionally, in step S1, the plurality of positioning-related data of the vehicle includes: absolute pose, angular velocity, acceleration, and laser point cloud.
Optionally, in the step S2, the preprocessing operation includes coordinate transformation, pre-integration and distortion removal, and the step S2 includes:
s201: carrying out coordinate transformation on the absolute pose to obtain an initial pose and a GNSS factor;
s202: pre-integrating the angular velocity and the acceleration by utilizing an IMU pre-integration model to obtain a pre-integration result and an IMU factor;
s203: performing motion estimation on the pre-integration result to obtain a motion estimation result;
s204: carrying out distortion removal on the laser point cloud and the pre-integration result to obtain a distortion removal result;
s205: performing feature calculation on the distortion removal result to obtain a feature calculation result;
s206: and outputting the initial pose, the motion estimation result and the feature calculation result as the preprocessing result.
Optionally, in step S202, the IMU pre-integration model includes:
wherein v is t+Δt Representing the speed, P, of the vehicle at time t + Deltat t+Δt Indicating the position of the vehicle at time t + deltat,representing the rotation of the vehicle at time t + Δ t, v t Representing the speed of the vehicle at time t, g w Which represents the gravitational acceleration of the vehicle in the world coordinate system, deltat represents a period of time,a rotation matrix representing the inertial system to the world coordinate system,represents the raw measured acceleration of the IMU at the time and represents the deviation of the acceleration that varies slowly with time,a white gaussian noise representing the acceleration,representing the IMU's raw measured angular velocity at a time Indicates the deviation of the angular velocity over time,gaussian white noise representing angular velocity.
Optionally, in step S6, the sliding window is a fixed-size window that is set on the time axis and slides over time, and only the variables in the window are optimized each time, and the remaining variables are rimmed.
Alternatively, the step S8 includes:
s81: classifying the appearance of each grid by using the characteristic value attribute of each grid in the second NDT point cloud registration result to obtain a classification result;
s82: constructing a similarity function between two frames according to the classification result;
s83: carrying out coarse closed loop detection by using the similar function to obtain a coarse closed loop detection result;
s84: if the detection result of the coarse closed loop meets a preset threshold, the step S85 is executed;
s85: and performing accurate closed-loop detection by using the sum of the distances from the mean value of each grid to the origin of coordinates to obtain an accurate closed-loop detection result, wherein the accurate closed-loop detection result comprises the closed-loop detection factor.
Optionally, in the step S9, in the process of adding the laser odometry factor, only the current frame associated with the current state of the vehicle is added as the constraint factor in the map, and the laser scanning frame between two frames will not be optimized.
The invention also provides a vehicle automatic driving domain control system using the vehicle automatic driving auxiliary positioning fusion method, which comprises the following steps:
a positioning-related data acquisition module for acquiring a plurality of positioning-related data of a vehicle;
an autonomous driving processor for performing a series of processes on the plurality of positioning-related data of the vehicle to generate a motion profile of the vehicle.
Optionally, the positioning-related data acquisition module comprises a GNSS + RTK unit for acquiring an absolute pose of the vehicle, an IMU unit and a sensor unit; the IMU unit is used for acquiring the angular speed and the acceleration of the vehicle, and the sensor unit is used for acquiring the laser point cloud of the vehicle.
The invention has the following beneficial effects:
the invention integrates the IMU, the GNSS and the 4G RTK real-time differential system in the automatic driving area controller, reduces the external line connection, improves the real-time performance of positioning data communication and achieves the aim of reducing the technical cost. The data fusion algorithm based on factor graph optimization represents the relationship between different nodes more intuitively, when the state quantity needs to be added, the factor graph can directly add factors on the basis of the original graph, and similarly, if the reliability of the measured value is low or the signal is lost, the factors only need to be simply reduced on the basis of the original graph, special programming or model modification is not needed, and the calculation quantity when the SLAM problem is processed is greatly reduced.
Drawings
FIG. 1 is a flow chart of a vehicle automatic driving assistance positioning fusion method according to the present invention;
FIG. 2 is a block diagram of the vehicle autopilot assistance positioning fusion of the present invention;
FIG. 3 is a diagram illustrating the process of factor graph optimization according to the present invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
The invention provides a vehicle automatic driving auxiliary positioning fusion method, which comprises the following steps of:
s1: acquiring various positioning related data of a vehicle;
in the invention, the various positioning related data of the vehicle at least comprise absolute pose, angular velocity, acceleration and laser point cloud.
The absolute pose is acquired through a GNSS + RTK unit, and the angular velocity and the acceleration are acquired through an IMU unit; the laser point cloud is acquired by a sensor unit.
The GNSS + RTK unit is compatible with various galaxy systems and various frequency bands, more satellites are searched, the stability is better, the RTK high-precision positioning is supported, and the precision can reach centimeter level.
The IMU unit can output 3-axis acceleration and 3-axis angular velocity, accurately output the motion state of the vehicle, and input the acceleration and angular velocity information into the automatic driving processor for information fusion calculation for SLAM positioning. The vehicle can deduce the self pose by knowing the rotation angle and the acceleration information in the driving process, the accuracy of the measurement values of the angular velocity and the acceleration of the IMU is highest in the rotation angle and the acceleration, and the vehicle can provide information output with higher frequency. The IMU acts on the factor graph to provide good pose and make complementary constraints with the laser odometer factor.
Specifically, the GNSS + RTK unit selects an INS-YI100C differential GPS unit.
Specifically, the IMU unit adopts a BW-127 inertial measurement unit of north micro sensing.
S2: preprocessing the various positioning related data to obtain a GNSS factor, an IMU pre-integration factor and a preprocessing result;
referring to fig. 2, the preprocessing operation includes coordinate transformation, pre-integration, and distortion removal, and thus, the step S2 includes:
s201: carrying out coordinate transformation on the absolute pose to obtain an initial pose and a GNSS factor;
since the drift of the lidar odometer and the odometer increases very slowly, no GNSS factors have to be added in real time after the GNSS factors are generated. The invention adds GNSS factors at the initial position and loop detection, and in other operating conditions only when the estimated position covariance is greater than the received GNSS position covariance.
S202: pre-integrating the angular velocity and the acceleration by utilizing an IMU pre-integration model to obtain a pre-integration result and an IMU factor;
the IMU pre-integration model comprises:
wherein v is t+Δt Representing the speed, P, of the vehicle at time t + Deltat t+Δt Representing the position of the vehicle at time t + deltat,representing the rotation of the vehicle at time t + Δ t, v t Representing the speed of the vehicle at time t, g w Which represents the gravitational acceleration of the vehicle in the world coordinate system, deltat represents a period of time,a rotation matrix representing the inertial system to the world coordinate system,represents the raw measured acceleration of the IMU at the time and represents the deviation of the acceleration that varies slowly with time,a white gaussian noise that represents the acceleration of the vehicle,representing the IMU's raw measured angular velocity at a time Indicates the deviation of the angular velocity over time,gaussian white noise representing angular velocity.
S203: performing motion estimation on the pre-integration result to obtain a motion estimation result;
s204: carrying out distortion removal on the laser point cloud and the pre-integration result to obtain a distortion removal result;
s205: performing feature calculation on the distortion removal result to obtain a feature calculation result;
s206: and outputting the initial pose, the motion estimation result and the feature calculation result as the preprocessing result.
S3: performing first NDT point cloud registration on the preprocessing result to obtain a first point cloud registration result;
s4: carrying out pose calculation on the first point cloud registration result to obtain a pose calculation result;
s5: carrying out NDT map registration by using the pose calculation result to obtain an NDT map registration result and a laser odometer factor;
the laser odometry factor, like the IMU pre-integration factor, plays a crucial role in motion estimation. Compared with a GNSS factor, the laser odometer factor has obvious advantages in the estimation of the pose accuracy, and is not influenced by the obstruction of the obstacles in the environment. For the addition of the laser odometry factors, in order to ensure the real-time performance of the algorithm, in the process of adding the laser odometry factors, only the current frame associated with the current state of the vehicle is added as a constraint factor in the image, and the laser scanning frame between the two frames is not subjected to optimization calculation, so that the calculation efficiency is greatly improved. Meanwhile, the method helps to maintain a relatively sparse factor graph and is suitable for real-time nonlinear optimization.
S6: constructing a sliding window map according to the NDT map registration result;
the sliding window is a fixed window which is arranged on a time axis and slides along with time, only the variable in the window is optimized each time, and the rest variables are marginalized, and because all the variables are linearized again during optimization iteration, the linearization accumulated error is small, and the precision is ensured; meanwhile, the window size is fixed, the number of optimized variables is basically unchanged, and the real-time performance can be met.
S7: performing second NDT point cloud registration on the sliding window map to obtain a second NDT point cloud registration result;
s8: performing closed-loop detection on the second NDT point cloud registration result to generate a closed-loop detection factor;
after the closed loop condition matures, a closed loop detection factor is added, which in fact has the benefit of optimization of rotation and pitch angle. In the actual map building process, the point cloud map added with the loop factors has good performance in the scene of large map rotation and height change.
S9: performing constraint factor fusion on the GNSS factor, the IMU pre-integration factor, the laser odometer factor and the closed-loop detection factor to obtain a fusion result;
s10: optimizing the factor graph of the fusion result to obtain an optimized result;
the method combining the factor graph optimization and the sliding window is widely applied to various fusion positioning and mapping systems due to good real-time performance and robustness, so that the invention takes a Normal distribution transformation (Normal distribution Transform) point cloud matching algorithm which is characterized by sliding window matching as a core, and establishes a factor graph optimization SLAM framework based on multi-sensor fusion by taking factor graph optimization as a multi-sensor fusion means.
FIG. 3 is a schematic diagram of a factor graph optimization system. In the factor graph optimization, the precise GNSS positioning information, the IMU pre-integration information and the loop detection information are fused with the laser odometer factor to serve as the correction factor, so that the accumulated error can be greatly eliminated in the process of constructing the map in a complex large scene, and the high-precision SLAM map construction is realized. The GNSS provides absolute pose information including the initial pose of the SLAM positioning system, and the method has the advantage of improving the repositioning capacity of the unmanned vehicle.
S11: and generating a motion track of the vehicle according to the optimization result and the pose calculation result.
Alternatively, the step S8 includes:
s81: classifying the appearance of each grid by using the characteristic value attribute of each grid in the second NDT point cloud registration result to obtain a classification result;
s82: constructing a similarity function between two frames according to the classification result;
s83: performing coarse closed loop detection by using the similar function to obtain a coarse closed loop detection result;
s84: if the detection result of the coarse closed loop meets a preset threshold, the step S85 is executed;
s85: and performing accurate closed-loop detection by using the sum of the distances from the mean value of each grid to the origin of coordinates to obtain an accurate closed-loop detection result, wherein the accurate closed-loop detection result comprises the closed-loop detection factor.
Optionally, in the step S9, in the process of adding the laser odometry factor, only the current frame associated with the current state of the vehicle is added as the constraint factor in the map, and the laser scanning frame between two frames will not be subjected to the optimization calculation.
The invention also provides a vehicle automatic driving domain control system using the vehicle automatic driving auxiliary positioning fusion method, which comprises the following steps:
a positioning-related data acquisition module for acquiring a plurality of positioning-related data of a vehicle;
an autonomous driving processor for performing a series of processes on the plurality of positioning-related data of the vehicle to generate a motion profile of the vehicle.
Optionally, the positioning-related data acquisition module comprises a GNSS + RTK unit for acquiring an absolute pose of the vehicle, an IMU unit and a sensor unit; the IMU unit is used for acquiring the angular speed and the acceleration of the vehicle, and the sensor unit is used for acquiring the laser point cloud of the vehicle.
In particular, in practical applications, the autopilot domain controller may include an autopilot processor, a microprocessor, a GNSS + RTK positioning module, an IMU module, as well as autopilot sensors, a drive-by-wire chassis, other external devices, and the like.
As a specific embodiment, the autopilot processor of the present invention employs an embedded intelligent system Xavier chip including an autopilot system developed by NVIDIA, and the chip performance includes: eight core CPU based on ARMv8 ISA, deep Learning Accelerator (DLA): 5TOPS (FP 16) |10TOPS (INT 8), volta GPU:512CUDA cores (INT 8) |1.3TFLOPS (FP 32), vision processor: 1.6TOPS, stereo and Optical Flow Engine (SOFE): 6TOPS, image Signal Processor (ISP): 1.5Giga Pixels/s, video encoder: 1.2GPix/s, video decoder: 1.8GPix/s.
The microcontroller adopts an English flying TC297 series chip, comprises a three-core TriCore architecture with 300MHz working frequency, a 728KB +8MB capacity and an RAM with ECC (error correction coding) protection, is designed based on an ISO26262 standard, and supports the requirement of ASIL-D maximum security level. And the hardware core security architecture design is realized by matching with a basic chip.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (9)
1. A vehicle automatic driving auxiliary positioning fusion method is characterized by comprising the following steps:
s1: acquiring various positioning related data of a vehicle;
s2: preprocessing the various positioning related data to obtain a GNSS factor, an IMU pre-integration factor and a preprocessing result;
s3: performing first NDT point cloud registration on the preprocessing result to obtain a first point cloud registration result;
s4: performing pose calculation on the first point cloud registration result to obtain a pose calculation result;
s5: carrying out NDT map registration by using the pose calculation result to obtain an NDT map registration result and a laser odometer factor;
s6: constructing a sliding window map according to the NDT map registration result;
s7: performing second NDT point cloud registration on the sliding window map to obtain a second NDT point cloud registration result;
s8: performing closed-loop detection on the second NDT point cloud registration result to generate a closed-loop detection factor;
s9: performing constraint factor fusion on the GNSS factor, the IMU pre-integration factor, the laser odometer factor and the closed-loop detection factor to obtain a fusion result;
s10: optimizing the factor graph of the fusion result to obtain an optimized result;
s11: and generating a motion track of the vehicle according to the optimization result and the pose calculation result.
2. The vehicle automatic driving assistance positioning fusion method according to claim 1, wherein in the step S1, the plurality of positioning related data of the vehicle comprises: absolute pose, angular velocity, acceleration, and laser point cloud.
3. The vehicle automatic driving assistance positioning fusion method according to claim 2, wherein in the step S2, the preprocessing operation includes coordinate transformation, pre-integration and distortion removal, and the step S2 includes:
s201: carrying out coordinate transformation on the absolute pose to obtain an initial pose and a GNSS factor;
s202: pre-integrating the angular velocity and the acceleration by utilizing an IMU pre-integration model to obtain a pre-integration result and an IMU factor;
s203: performing motion estimation on the pre-integration result to obtain a motion estimation result;
s204: carrying out distortion removal on the laser point cloud and the pre-integration result to obtain a distortion removal result;
s205: performing feature calculation on the distortion removal result to obtain a feature calculation result;
s206: and outputting the initial pose, the motion estimation result and the feature calculation result as the preprocessing result.
4. The vehicle autopilot-assisted positioning fusion method of claim 3 wherein in step S202, the IMU pre-integration model comprises:
wherein v is t+Δt Representing the speed, P, of the vehicle at time t + Deltat t+Δt Representing the position of the vehicle at time t + deltat,representing the rotation of the vehicle at time t + Δ t, v t Representing the speed of the vehicle at time t, g w Representing the gravitational acceleration of the vehicle in the world coordinate system, at represents a period of time,a rotation matrix representing the inertial system to the world coordinate system,represents the raw measured acceleration of the IMU at the time and represents the deviation of the acceleration that varies slowly with time,a white gaussian noise that represents the acceleration of the vehicle,representing the IMU's raw measured angular velocity at a time Indicates the deviation of the angular velocity over time,gaussian white noise representing angular velocity.
5. The method for fusing automatic driving assistance positions of vehicles according to claim 1, wherein in step S6, the sliding window is a fixed-size window that is set on a time axis and slides along with time, only the variables in the window are optimized each time, and the remaining variables are rimmed.
6. The vehicle automatic driving assistance positioning fusion method according to claim 1, wherein the step S8 comprises:
s81: classifying the appearance of each grid by using the characteristic value attribute of each grid in the second NDT point cloud registration result to obtain a classification result;
s82: constructing a similarity function between two frames according to the classification result;
s83: carrying out coarse closed loop detection by using the similar function to obtain a coarse closed loop detection result;
s84: if the detection result of the coarse closed loop meets a preset threshold, the step S85 is carried out;
s85: and performing accurate closed-loop detection by using the sum of the distances from the mean value of each grid to the origin of coordinates to obtain an accurate closed-loop detection result, wherein the accurate closed-loop detection result comprises the closed-loop detection factor.
7. The fusion method for positioning assistance in automatic driving of vehicle according to any one of claims 1-6, wherein in step S9, during the process of adding the laser odometry factor, only the current frame associated with the current state of the vehicle is added as a constraint factor in the graph, and the laser scanning frame between two frames will not be optimized.
8. A vehicle automatic driving domain control system using the vehicle automatic driving assistance positioning fusion method according to any one of claims 1 to 7, characterized in that the vehicle automatic driving domain control system comprises:
a positioning-related data acquisition module for acquiring a plurality of positioning-related data of a vehicle;
an autonomous driving processor for performing a series of processes on the plurality of positioning-related data of the vehicle to generate a motion profile of the vehicle.
9. The vehicle autopilot-assisted positioning fusion method of claim 5 wherein the positioning-related data acquisition module comprises a GNSS + RTK unit for acquiring the absolute pose of the vehicle, an IMU unit and a sensor unit; the IMU unit is used for acquiring the angular speed and the acceleration of the vehicle, and the sensor unit is used for acquiring the laser point cloud of the vehicle.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210939943.5A CN115311349A (en) | 2022-08-05 | 2022-08-05 | Vehicle automatic driving auxiliary positioning fusion method and domain control system thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210939943.5A CN115311349A (en) | 2022-08-05 | 2022-08-05 | Vehicle automatic driving auxiliary positioning fusion method and domain control system thereof |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115311349A true CN115311349A (en) | 2022-11-08 |
Family
ID=83861158
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210939943.5A Pending CN115311349A (en) | 2022-08-05 | 2022-08-05 | Vehicle automatic driving auxiliary positioning fusion method and domain control system thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115311349A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115601433A (en) * | 2022-12-12 | 2023-01-13 | 安徽蔚来智驾科技有限公司(Cn) | Loop detection method, computer device, computer-readable storage medium and vehicle |
CN117671013A (en) * | 2024-02-01 | 2024-03-08 | 安徽蔚来智驾科技有限公司 | Point cloud positioning method, intelligent device and computer readable storage medium |
-
2022
- 2022-08-05 CN CN202210939943.5A patent/CN115311349A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115601433A (en) * | 2022-12-12 | 2023-01-13 | 安徽蔚来智驾科技有限公司(Cn) | Loop detection method, computer device, computer-readable storage medium and vehicle |
CN117671013A (en) * | 2024-02-01 | 2024-03-08 | 安徽蔚来智驾科技有限公司 | Point cloud positioning method, intelligent device and computer readable storage medium |
CN117671013B (en) * | 2024-02-01 | 2024-04-26 | 安徽蔚来智驾科技有限公司 | Point cloud positioning method, intelligent device and computer readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109945858B (en) | Multi-sensing fusion positioning method for low-speed parking driving scene | |
CN113945206B (en) | Positioning method and device based on multi-sensor fusion | |
CN109341706B (en) | Method for manufacturing multi-feature fusion map for unmanned vehicle | |
CN109061703B (en) | Method, apparatus, device and computer-readable storage medium for positioning | |
CN109696663B (en) | Vehicle-mounted three-dimensional laser radar calibration method and system | |
CN109709801B (en) | Indoor unmanned aerial vehicle positioning system and method based on laser radar | |
CN115311349A (en) | Vehicle automatic driving auxiliary positioning fusion method and domain control system thereof | |
KR20220053513A (en) | Image data automatic labeling method and device | |
CN112639502A (en) | Robot pose estimation | |
CN111272165A (en) | Intelligent vehicle positioning method based on characteristic point calibration | |
CN112462372B (en) | Vehicle positioning method and device | |
CN113865580A (en) | Map construction method and device, electronic equipment and computer readable storage medium | |
CN111461048B (en) | Vision-based parking lot drivable area detection and local map construction method | |
CN108827339B (en) | High-efficient vision odometer based on inertia is supplementary | |
CN113920198B (en) | Coarse-to-fine multi-sensor fusion positioning method based on semantic edge alignment | |
CN112378397B (en) | Unmanned aerial vehicle target tracking method and device and unmanned aerial vehicle | |
CN112596071A (en) | Unmanned aerial vehicle autonomous positioning method and device and unmanned aerial vehicle | |
CN113933818A (en) | Method, device, storage medium and program product for calibrating laser radar external parameter | |
CN112379681A (en) | Unmanned aerial vehicle obstacle avoidance flight method and device and unmanned aerial vehicle | |
Li et al. | Robust localization for intelligent vehicles based on compressed road scene map in urban environments | |
CN114323033A (en) | Positioning method and device based on lane lines and feature points and automatic driving vehicle | |
CN116359905A (en) | Pose map SLAM (selective level mapping) calculation method and system based on 4D millimeter wave radar | |
CN114915913A (en) | UWB-IMU combined indoor positioning method based on sliding window factor graph | |
CN112380933B (en) | Unmanned aerial vehicle target recognition method and device and unmanned aerial vehicle | |
CN116608873A (en) | Multi-sensor fusion positioning mapping method for automatic driving vehicle |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |