CN110906941B - Automatic driving map construction method and system for long-distance tunnel - Google Patents
Automatic driving map construction method and system for long-distance tunnel Download PDFInfo
- Publication number
- CN110906941B CN110906941B CN201911218787.8A CN201911218787A CN110906941B CN 110906941 B CN110906941 B CN 110906941B CN 201911218787 A CN201911218787 A CN 201911218787A CN 110906941 B CN110906941 B CN 110906941B
- Authority
- CN
- China
- Prior art keywords
- track
- odometer
- information
- gps
- pose
- 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.)
- Active
Links
Images
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
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
- G01C21/30—Map- or contour-matching
- G01C21/32—Structuring or formatting of map data
-
- 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
- G01S19/45—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement
-
- 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
Abstract
The invention discloses a construction method and a system of an automatic driving map for a long-distance tunnel, wherein the construction method comprises the following steps: step S1: collecting initial GPS pose information of a tunnel and vehicle wheel speed information; step S2: processing the initial GPS pose information and the vehicle wheel speed information to obtain an odometer track; step S3: establishing a track adjustment model, and optimizing the odometer track through the track adjustment model to obtain an optimal odometer track; step S4: and constructing an automatic driving map according to the optimal odometer track.
Description
Technical Field
The present invention relates to a map construction method and system, and more particularly, to a method and system for constructing an autopilot map for a long-distance tunnel.
Background
In automotive autopilot, the construction of high-precision maps is a very critical ring in the overall autopilot system. Accurate and consistent high-precision maps can help other modules of the overall autopilot system obtain accurate pose information and provide more local environmental information. In a long-distance tunnel scene, an automobile cannot obtain an accurate GPS positioning signal, so that a GPS track obtained directly is difficult to be directly used for constructing a high-precision map required by a system.
In the prior art, more sensor information is generally introduced to assist in constructing a more accurate vehicle motion track, but for a long-distance tunnel, due to an error accumulation effect, an odometer mode scheme cannot theoretically obtain an accurate and consistent tunnel motion track, if more sensor data is introduced into an optimization problem, the problems of large memory consumption, even incapacity of accommodating, incapacity of guaranteeing reliability of an optimization result and the like are possibly encountered, such as in Chinese patent publication numbers CN109991636a and CN109443348A, visual characteristic information is introduced to solve map construction under a poor scene of a GPS signal, but due to extremely high similarity of visual information in the tunnel, a correct optimization track cannot be guaranteed by using a closed-loop optimization mode.
There is therefore an urgent need to develop a method and system for constructing an autopilot map for long-distance tunnels that overcomes the above-mentioned drawbacks.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a method for constructing an automatic driving map for a long-distance tunnel, which comprises the following steps:
step S1: collecting initial GPS pose information of a tunnel and vehicle wheel speed information;
step S2: processing the initial GPS pose information and the vehicle wheel speed information to obtain an odometer track;
step S3: establishing a track adjustment model, and optimizing the odometer track through the track adjustment model to obtain an optimal odometer track;
step S4: and constructing an automatic driving map according to the optimal odometer track.
In the above construction method, in the step S1, the GPS pose information and the vehicle wheel speed information of each section before and after entering the tunnel scene are collected.
The above construction method, wherein the step S2 includes:
step S21: starting the odometer at time t 0 Setting the GPS pose information of the odometer track as a coordinate origin of the odometer track;
step S22: according to the starting time t 0 The GPS pose information of each moment is obtained through calculation;
step S23: and integrating the GPS pose information according to all moments to obtain the odometer track.
The above construction method, wherein the step S3 includes:
step S31: establishing an optimized loss function, wherein the optimized loss function L is as follows:
L(T)＝L prior (T)+L odom (T)，
wherein T is the pose track to be optimized, L prior To a priori lose terms, L odom Loss of relative pose;
step S32: and adjusting the attitude track by using the initial parameters of the loss function L of the odometer track by using a nonlinear optimization method so as to obtain the optimal odometer track.
In the above construction method, in the step S4, the autopilot map is obtained through point cloud extraction, point cloud alignment, and regional point cloud map generation according to the optimal odometer track.
The invention also provides a system for constructing an automatic driving map for a long-distance tunnel, which comprises:
the information acquisition unit acquires initial GPS pose information of the tunnel and vehicle wheel speed information;
the odometer track obtaining unit is used for processing the initial GPS pose information and the vehicle wheel speed information to obtain an odometer track;
the optimizing unit is used for establishing a track adjusting model and optimizing the odometer track through the track adjusting model to obtain an optimal odometer track;
and the map construction unit is used for constructing an automatic driving map according to the optimal odometer track.
The construction system comprises an information acquisition unit, wherein the information acquisition unit acquires GPS pose information and vehicle wheel speed information of each section before and after entering a tunnel scene.
The above construction system, wherein the odometer trajectory obtaining unit includes:
the origin setting module is used for setting the starting time t of the odometer 0 Setting the GPS pose information of the odometer track as a coordinate origin of the odometer track;
the calculation module is used for calculating the time t according to the starting time t 0 The GPS pose information of each moment is obtained through calculation;
and the integration module is used for integrating and obtaining the odometer track according to the GPS pose information at all moments.
The above construction system, wherein the optimizing unit includes:
the optimizing loss function establishing module is used for establishing an optimizing loss function, wherein the optimizing loss function L is as follows:
L(T)＝L prior (T)+L odom (T)，
wherein T is the pose track to be optimized, L prior To a priori lose terms, L odom Loss of relative pose;
and the adjusting module is used for adjusting the gesture track by using a nonlinear optimization method according to the initial parameters of the loss function L of the odometer track so as to obtain the optimal odometer track.
The map construction unit obtains the automatic driving map through point cloud extraction, point cloud alignment and regional point cloud map generation according to the optimal odometer track.
The invention aims at the prior art and has the following effects: the construction method and the system are simple and effective, are suitable for correcting long-distance GPS tracks, only use initial GPS pose information and wheel speed information as all inputs, and can ensure that a continuous and consistent high-precision map which is enough to be used by the whole automatic driving system is obtained.
Drawings
FIG. 1 is a flow chart of a construction method of the present invention;
FIG. 2 is a partial flow chart of step S2 in FIG. 1;
FIG. 3 is a partial flow chart of step S3 in FIG. 1;
fig. 4 is a schematic diagram of the construction system.
Wherein, the reference numerals:
Odometer trajectory acquisition unit 12
Optimization unit 13
The optimized loss function creation module 131
Detailed Description
The detailed description and technical descriptions of the present invention will now be further described with reference to a preferred embodiment, but should not be construed as limiting the practice of the invention.
It is generally considered that the GPS pose signal is completely unavailable in the tunnel scene, but according to research and observation, it is found that the pose information output by the GPS in the tunnel can be used to obtain a smoother odometer track, and based on the observation, we propose a method for constructing an autopilot map for a long-distance tunnel.
Referring to fig. 1-3, fig. 1 is a flowchart of a construction method according to the present invention; FIG. 2 is a partial flow chart of step S2 in FIG. 1; fig. 3 is a substep flow chart of step S3 in fig. 1. As shown in fig. 1 to 3, the construction method of the present invention comprises the steps of:
step S1: and acquiring initial GPS pose information of the tunnel and vehicle wheel speed information.
Specifically, a vehicle with a GPS device is provided with a tunnel scene once, and accurate initial GPS pose information and vehicle wheel speed information of a section of GPS signals before and after entering and exiting the tunnel scene are acquired through the GPS device, wherein the GPS pose information comprises position information and orientation information.
Step S2: and processing the initial GPS pose information and the vehicle wheel speed information to obtain the odometer track.
The step S2 includes:
step S21: starting the odometer at time t 0 The GPS pose information of the meter is set as the origin of coordinates of the odometer track;
step S22: according to the starting time t 0 The GPS pose information of each moment is obtained through calculation;
step S23: and integrating and obtaining the odometer track according to the GPS pose information at all moments.
Specifically, the odometer start time t 0 Is of the initial pose P 0 Setting the coordinate origin of the odometer track as the pose of the odometer track at the time tiThe information is P i Then at time t i+1 Lower odometer pose P i+1 Then go through the GPS pose G i The resulting vehicle is oriented in a direction vector D in the world coordinate system i Binding t i Time of day vehicle wheel speed information s i The method comprises the following steps: p (P) i+1 ＝P i +D i *s i The GPS pose information of each moment is obtained by calculation, and the odometer track is obtained by integration according to the GPS pose information of all the moments.
Step S3: and establishing a track adjustment model, and optimizing the odometer track through the track adjustment model to obtain an optimal odometer track.
The step S3 includes:
step S31: establishing an optimized loss function, wherein the optimized loss function L is as follows:
L(T)＝L prior (T)+L odom (T)，
wherein T is the pose track to be optimized, L prior To a priori lose terms, L odom Loss of relative pose.
Specifically, the GPS pose variance threshold is set to be xi t Construct the optimized loss function L (T) =l prior +L odom T represents the pose locus to be optimized, where L prior Representing a priori loss terms provided by GPS, L prior ＝L position +L orientation From the position a priori L position ＝(T(x,y,z)-T wheel (x,y,z)) 2 And gesture a priori L orientation ＝(T(roll,pitch,yaw)-T wheel (roll,pitch,yaw)) 2 Composition, where T (x, y, z) is cartesian coordinate information of the pose T, and T (roll, pitch, yaw) is three direction angle information of the pose T.
It should be noted that the position priori constraint L position Only at this moment is the pose variance ζ of the GPS track>ξ t Only then is the loss function L added; l (L) odom For the loss of relative pose, the relative pose between two adjacent time points is constrained, for two time points t i And t i+1 Between, L odom (t i ，t i+1 )＝((ΔT (i,i+1) )-(ΔT wheel(i,i+1) )) 2 Wherein DeltaT (i,i+1) ＝T i -T i+1 。
It is worth noting that the method and the device automatically judge whether the GPS position is introduced as the prior position constraint according to the GPS variance information xi, ensure that the tunnel entrance and exit positions have accurate GPS signals as the constraint, and enable the optimized track to be consistent with the original GPS position at the position with good GPS signals.
Step S32: and adjusting the attitude track by using the initial parameters of the loss function L of the odometer track by using a nonlinear optimization method so as to obtain the optimal odometer track.
It should be noted that the present invention can obtain a high-precision map of a continuous autopilot long-distance tunnel under the condition of using only GPS pose information and wheel speed information, and L is added in the constructed loss function L odom The existence of the loss term can ensure the smooth and continuous whole track after optimization.
Specifically, the trajectory T is measured in mileage wheel As an initial parameter of the loss function L, adjusting the attitude track T by using a nonlinear optimization method to minimize the loss function L and finally obtaining the optimal odometer track T corrected 。
Step S4: and constructing an automatic driving map according to the optimal odometer track.
Specifically, in step S4, an autopilot map is obtained according to the optimal odometer trajectory through point cloud extraction, point cloud alignment, and regional point cloud map generation, and the autopilot map is shown in fig. 5.
According to the invention, the inaccurate and discontinuous GPS track in the tunnel is quickly corrected, so that the corrected GPS track is used for constructing the high-precision automatic driving map.
Referring to fig. 4, fig. 4 is a schematic structural diagram of the construction system of the present invention. As shown in fig. 4, the system for constructing an autopilot map for a long-distance tunnel of the present invention includes:
an information acquisition unit 11 for acquiring initial GPS pose information of a tunnel and wheel speed information of a vehicle;
an odometer trajectory obtaining unit 12 that obtains an odometer trajectory by processing the initial GPS pose information and the vehicle wheel speed information;
the optimizing unit 13 is used for establishing a track adjusting model, and optimizing the odometer track through the track adjusting model to obtain an optimal odometer track; and
the map construction unit 14 constructs an automatic driving map based on the optimal odometer trajectory.
The information acquisition unit 11 acquires the GPS pose information and the vehicle wheel speed information of each section before and after entering a tunnel scene.
Further, the odometer trajectory obtaining unit 12 includes:
the origin setting module 121 sets the starting time t of the odometer 0 Setting the GPS pose information of the odometer track as a coordinate origin of the odometer track;
the calculation module 122, according to the start time t 0 The GPS pose information of each moment is obtained through calculation;
and an integration module 123 for integrating and obtaining the odometer track according to the GPS pose information at all times.
Still further, the optimizing unit 13 includes:
the optimization loss function building module 131 builds an optimization loss function, where the optimization loss function L is:
L(T)＝L prior (T)+L odom (T)，
wherein T is the pose track to be optimized, L prior To a priori lose terms, L odom Loss of relative pose; the method comprises the steps of carrying out a first treatment on the surface of the
The adjustment module 132 adjusts the gesture track with the initial parameters of the loss function L of the odometer track, using a nonlinear optimization method, so as to obtain the optimal odometer track.
Still further, the map construction unit 14 obtains the automatic driving map through point cloud extraction, point cloud alignment, and regional point cloud map generation according to the optimal odometer trajectory.
The invention has the following effects:
1) The method is simple and effective and is suitable for correcting long-distance GPS tracks;
2) Only using the initial GPS pose information and wheel speed information as all inputs can ensure a continuous consistent high-precision map that is sufficient for use by the entire autopilot system.
The foregoing is merely illustrative of the preferred embodiments of the present invention and is not intended to limit the scope of the invention, since various modifications and variations can be made in the light of the above teachings by those skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (8)
1. A method of constructing an autopilot map for a long-distance tunnel, comprising:
step S1: collecting initial GPS pose information of a tunnel and vehicle wheel speed information;
step S2: processing the initial GPS pose information and the vehicle wheel speed information to obtain an odometer track;
step S3: establishing a track adjustment model, and optimizing the odometer track through the track adjustment model to obtain an optimal odometer track;
wherein, in the step S3, the method includes:
step S31: establishing an optimized loss function, wherein the optimized loss function L is as follows:
L(T)＝L prior (T)+L odom (T)，
wherein T is the pose track to be optimized; l (L) prior Representing a priori loss terms provided by GPS, L prior ＝L position +L orientation From the position a priori L position ＝(T(x,y,z)-T wheel (x,y,z)) 2 And gesture a priori L orientation ＝(T(roll,pitch,yaw)-T wheel (roll,pitch,yaw)) 2 Composition, where T (x, y, z) is Cartesian coordinate information of pose T, T (roll, pit)ch, yaw) is three direction angle information of the posture T; l (L) odom For the loss of relative pose, the relative pose between two adjacent time points is constrained, for two time points t i And t i+1 Between, L odom (t i ，t i+1 )＝((ΔT (i,i+1) )-(ΔT wheel(i,i+1) )) 2 Wherein DeltaT (i,i+1) ＝T i -T i+1 ；
Step S32: taking the odometer track as an initial parameter of the loss function L, and adjusting the gesture track by using a nonlinear optimization method to obtain the optimal odometer track;
step S4: and constructing an automatic driving map according to the optimal odometer track.
2. The method according to claim 1, wherein the GPS pose information and the vehicle wheel speed information of each section before and after entering the tunnel scene are collected in the step S1.
3. The construction method according to claim 1, wherein the step S2 comprises:
step S21: starting the odometer at time t 0 Setting the GPS pose information of the odometer track as a coordinate origin of the odometer track;
step S22: according to the starting time t 0 The GPS pose information of each moment is obtained through calculation;
step S23: and integrating the GPS pose information according to all moments to obtain the odometer track.
4. The method according to claim 1, wherein the autopilot map is obtained in step S4 from the optimal odometer trajectory by point cloud extraction, point cloud alignment, and regional point cloud map generation.
5. A system for constructing an autopilot map for a long-distance tunnel, comprising:
the information acquisition unit acquires initial GPS pose information of the tunnel and vehicle wheel speed information;
the odometer track obtaining unit is used for processing the initial GPS pose information and the vehicle wheel speed information to obtain an odometer track;
the optimizing unit is used for establishing a track adjusting model and optimizing the odometer track through the track adjusting model to obtain an optimal odometer track;
the map construction unit is used for constructing an automatic driving map according to the optimal odometer track;
the optimizing unit includes:
the optimizing loss function establishing module is used for establishing an optimizing loss function, wherein the optimizing loss function L is as follows:
L(T)＝L prior (T)+L odom (T)，
wherein T is the pose track to be optimized, L prior To a priori lose terms, L odom For relative pose loss, T is the pose track to be optimized; l (L) prior Representing a priori loss terms provided by GPS, L prior ＝L position +L orientation From the position a priori L position ＝(T(x,y,z)-T wheel (x,y,z)) 2 And gesture a priori L orientation ＝(T(roll,pitch,yaw)-T wheel (roll,pitch,yaw)) 2 Composition, wherein T (x, y, z) is Cartesian coordinate information of a gesture T, and T (roll, pitch, yaw) is three direction angle information of the gesture T; l (L) odom For the loss of relative pose, the relative pose between two adjacent time points is constrained, for two time points t i And t i+1 Between, L odom (t i ，t i+1 )＝((ΔT (i,i+1) )-(ΔT wheel(i,i+1) )) 2 Wherein DeltaT (i,i+1) ＝T i -T i+1 ；
And the adjusting module is used for adjusting the gesture track by using a nonlinear optimization method according to the initial parameters of the loss function L of the odometer track so as to obtain the optimal odometer track.
6. The construction system according to claim 5, wherein the information acquisition unit acquires the GPS pose information and the vehicle wheel speed information of each of a section before and after entering a tunnel scene.
7. The building system according to claim 5, wherein the odometer trajectory obtaining unit includes:
the origin setting module is used for setting the starting time t of the odometer 0 Setting the GPS pose information of the odometer track as a coordinate origin of the odometer track;
the calculation module is used for calculating the time t according to the starting time t 0 The GPS pose information of each moment is obtained through calculation;
and the integration module is used for integrating and obtaining the odometer track according to the GPS pose information at all moments.
8. The building system of claim 5, wherein the map building unit obtains the autopilot map from the optimal odometer trajectory through point cloud extraction, point cloud alignment, and regional point cloud map generation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911218787.8A CN110906941B (en) | 2019-12-03 | 2019-12-03 | Automatic driving map construction method and system for long-distance tunnel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911218787.8A CN110906941B (en) | 2019-12-03 | 2019-12-03 | Automatic driving map construction method and system for long-distance tunnel |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110906941A CN110906941A (en) | 2020-03-24 |
| CN110906941B true CN110906941B (en) | 2023-06-23 |
Family
ID=69821455
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911218787.8A Active CN110906941B (en) | 2019-12-03 | 2019-12-03 | Automatic driving map construction method and system for long-distance tunnel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110906941B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111552757B (en) * | 2020-04-30 | 2022-04-01 | 上海商汤临港智能科技有限公司 | Method, device and equipment for generating electronic map and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107219542A (en) * | 2017-04-14 | 2017-09-29 | 北京克路德人工智能科技有限公司 | GNSS/ODO-based robot double-wheel differential positioning method |
| CN108693549A (en) * | 2018-03-28 | 2018-10-23 | 东风商用车有限公司 | A kind of vehicle-mounted real-time positioning system and method |
| CN109507677A (en) * | 2018-11-05 | 2019-03-22 | 浙江工业大学 | A kind of SLAM method of combination GPS and radar odometer |
| CN110274589A (en) * | 2018-03-15 | 2019-09-24 | 高德信息技术有限公司 | A kind of localization method and device |
| CN110415266A (en) * | 2019-07-19 | 2019-11-05 | 东南大学 | A method of it is driven safely based on this vehicle surrounding vehicles trajectory predictions |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6675074B2 (en) * | 2001-08-21 | 2004-01-06 | Robert Bosch Gmbh | Method and system for vehicle trajectory estimation |
| US10739773B2 (en) * | 2017-09-28 | 2020-08-11 | Nec Corporation | Generative adversarial inverse trajectory optimization for probabilistic vehicle forecasting |
-
2019
- 2019-12-03 CN CN201911218787.8A patent/CN110906941B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107219542A (en) * | 2017-04-14 | 2017-09-29 | 北京克路德人工智能科技有限公司 | GNSS/ODO-based robot double-wheel differential positioning method |
| CN110274589A (en) * | 2018-03-15 | 2019-09-24 | 高德信息技术有限公司 | A kind of localization method and device |
| CN108693549A (en) * | 2018-03-28 | 2018-10-23 | 东风商用车有限公司 | A kind of vehicle-mounted real-time positioning system and method |
| CN109507677A (en) * | 2018-11-05 | 2019-03-22 | 浙江工业大学 | A kind of SLAM method of combination GPS and radar odometer |
| CN110415266A (en) * | 2019-07-19 | 2019-11-05 | 东南大学 | A method of it is driven safely based on this vehicle surrounding vehicles trajectory predictions |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110906941A (en) | 2020-03-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113945206B (en) | Positioning method and device based on multi-sensor fusion | |
| CN107246868B (en) | Collaborative navigation positioning system and navigation positioning method | |
| US11802769B2 (en) | Lane line positioning method and apparatus, and storage medium thereof | |
| CN109946732B (en) | Unmanned vehicle positioning method based on multi-sensor data fusion | |
| CN101846734B (en) | Agricultural machinery navigation and position method and system and agricultural machinery industrial personal computer | |
| CN109934920A (en) | High-precision three-dimensional point cloud map constructing method based on low-cost equipment | |
| CN105716617B (en) | The system and method for driving locus is drawn based on vehicle data | |
| CN111065043B (en) | System and method for fusion positioning of vehicles in tunnel based on vehicle-road communication | |
| CN107728175A (en) | The automatic driving vehicle navigation and positioning accuracy antidote merged based on GNSS and VO | |
| CN111339802B (en) | Method and device for generating real-time relative map, electronic equipment and storage medium | |
| CN104118430B (en) | A kind of Parallel parking system based on sliding formwork Active Disturbance Rejection Control and method of parking | |
| CN113819914A (en) | Map construction method and device | |
| CN112683281B (en) | Automatic driving vehicle joint positioning method based on vehicle kinematics | |
| CN110361008B (en) | Positioning method and device for automatic parking of underground garage | |
| CN105865461A (en) | Automobile positioning system and method based on multi-sensor fusion algorithm | |
| WO2021147391A1 (en) | Map generation method and device based on fusion of vio and satellite navigation system | |
| CN108974054B (en) | Seamless train positioning method and system | |
| CN105387858B (en) | A kind of yacht intelligent guidance system and working method | |
| CN112945230B (en) | Vehicle driving state identification method and device, computer equipment and storage medium | |
| CN112433531A (en) | Trajectory tracking method and device for automatic driving vehicle and computer equipment | |
| CN103712598A (en) | Attitude determination system and method of small unmanned aerial vehicle | |
| CN107600073A (en) | A kind of vehicle centroid side drift angle estimating system and method based on Multi-source Information Fusion | |
| WO2023087802A1 (en) | Automatic driving positioning method and system, testing method, device, and storage medium | |
| CN114779791A (en) | Wave glider position keeping method and system | |
| CN111619589B (en) | Automatic driving control method for complex environment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |