CN111750855B - Intelligent vibratory roller of independent operation of vision leading - Google Patents
Intelligent vibratory roller of independent operation of vision leading Download PDFInfo
- Publication number
- CN111750855B CN111750855B CN202010769305.4A CN202010769305A CN111750855B CN 111750855 B CN111750855 B CN 111750855B CN 202010769305 A CN202010769305 A CN 202010769305A CN 111750855 B CN111750855 B CN 111750855B
- Authority
- CN
- China
- Prior art keywords
- information
- camera
- roller
- road roller
- road
- 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
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
- G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
- G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
- G01C21/165—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments
-
- E—FIXED CONSTRUCTIONS
- E01—CONSTRUCTION OF ROADS, RAILWAYS, OR BRIDGES
- E01C—CONSTRUCTION OF, OR SURFACES FOR, ROADS, SPORTS GROUNDS, OR THE LIKE; MACHINES OR AUXILIARY TOOLS FOR CONSTRUCTION OR REPAIR
- E01C19/00—Machines, tools or auxiliary devices for preparing or distributing paving materials, for working the placed materials, or for forming, consolidating, or finishing the paving
- E01C19/22—Machines, tools or auxiliary devices for preparing or distributing paving materials, for working the placed materials, or for forming, consolidating, or finishing the paving for consolidating or finishing laid-down unset materials
- E01C19/23—Rollers therefor; Such rollers usable also for compacting soil
- E01C19/28—Vibrated rollers or rollers subjected to impacts, e.g. hammering blows
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/02—Picture taking arrangements specially adapted for photogrammetry or photographic surveying, e.g. controlling overlapping of pictures
-
- 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
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0219—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory ensuring the processing of the whole working surface
Abstract
The invention discloses a vision-dominated autonomous operation intelligent vibratory roller, which comprises an inertial navigation unit, a vibration unit and a vibration unit, wherein the inertial navigation unit is used for acquiring pose information of the roller; the camera is used for acquiring the compaction edge image information of the lane to be rolled; the GNSS mobile station is used for acquiring the position information of the road roller; and the computing platform is used for performing feature extraction and feature matching, front-end visual odometer optimization and rear-end optimization on two adjacent frames of compacted edge images according to the information of the compacted edge images acquired by the camera, estimating the pose information of the camera, performing Kalman filtering fusion on the estimated pose information of the camera and the pose information of the road roller acquired by the inertial navigation unit to obtain the visual positioning information of the camera, performing loop detection according to the position information of the road roller acquired by the GNSS mobile station, and performing positioning compensation on the visual positioning information of the camera. The method can accurately position in areas with poor GNSS signals, such as tunnels and shelters from obstacles, and realize high-precision navigation construction of the road roller.
Description
Technical Field
The invention belongs to the technical field of road rollers, and particularly relates to a vision-dominated intelligent vibratory roller for autonomous operation.
Background
With the progress and development of society, the requirements of people on the road construction quality are gradually improved, so that higher requirements are provided for compaction machinery for controlling the road construction quality, and the vibratory roller is taken as one of typical machines of the compaction machinery and widely applied to the construction of infrastructures such as highways, water conservancy projects, railways, aviation airports, ports and large-scale fields. At present, the road roller is basically operated manually, and the compaction quality cannot be guaranteed. The main reason is that: the amplitude is randomly switched by an operator, the rolling times are reduced, the rolling speed is accelerated, and the road roller can not work according to the preset compaction process strictly; when the road roller is used for changing the road and rolling, the compaction overlapping width is mainly determined by the driving experience of an operator, and the dependence on a skilled operator is increased. Meanwhile, in some dangerous working scenes, the danger coefficient of operators is increased, safety accidents are easy to occur, and casualties are caused.
At present, research achievements in autonomous operation road rollers and intelligent road rollers exist, related unmanned road roller products appear and related patents are reported, but the overall framework of the unmanned road roller products is largely the same as or different from that of the unmanned road roller products, and the navigation and positioning of the road rollers only depend on a GNSS mode. However, the positioning mode cannot accurately position in a tunnel and an area shielded by a large obstacle, and the positioning error can reach more than 30cm, so that the working scene of the road roller adopting the positioning mode is severely limited, the maximum advantage of the autonomous working road roller cannot be exerted, and the road construction unit does not adopt the autonomous working road roller adopting the positioning mode to carry out road construction at the present stage.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides the vision-dominated autonomous operation intelligent vibratory roller, which can realize unmanned driving of the roller, reduce manual misoperation, get rid of dependence on skilled manipulators, work in dangerous working scenes, reduce the danger coefficient of operators, avoid safety accidents and casualties, accurately position in tunnels, areas with poor GNSS signals, such as large-scale barrier sheltering and the like, and realize high-precision navigation construction of the roller.
In order to solve the technical problems, the invention is realized by the following technical scheme:
the utility model provides a vision-dominated independently-operated intelligent vibratory roller, includes the roller body, be provided with vision orientation module and machine control module on the roller body, the vision orientation module includes:
the inertial navigation unit is used for acquiring pose information of the road roller;
the camera is used for acquiring the compaction edge image information of the lane to be rolled;
the GNSS mobile station is used for collecting the position information of the road roller under the combined action with a GNSS base station outside the construction area;
the computing platform is used for performing feature extraction, feature matching and front-end visual odometer optimization on two adjacent frames of the compacted edge images according to the compacted edge image information acquired by the camera, estimating to obtain pose information of the camera, performing Kalman filtering fusion on the estimated pose information of the camera and the pose information of the road roller acquired by the inertial navigation unit, performing rear-end optimization on the fused pose information to obtain visual positioning information of the camera, performing loop detection according to the position information of the road roller acquired by the GNSS flow station and a GNSS base station in a construction area, and performing positioning compensation on the visual positioning information of the camera to obtain real-time path information of the road roller; the computing platform is further used for comparing the real-time path information of the road roller with preset rolling path information to obtain a comparison result;
the machine control module includes:
and the vehicle-mounted controller is used for receiving the comparison result of the computing platform and controlling the road roller to move along a preset rolling path according to the comparison result.
Furthermore, the road roller is also matched with a remote planning module, the remote planning module comprises a user management module, and an expert system and a compaction big data system are arranged in the user management module and used for planning road roller diameter information and operation parameter information of the road roller by self.
Further, the remote planning module further comprises a remote planning unit, and the remote planning unit is used for presetting construction area information and operation parameter information.
Furthermore, a speed sensor and a corner sensor are further arranged on the road roller body, the speed sensor is used for acquiring moving speed information of the road roller, and the corner sensor is used for acquiring deflection angle information of a front frame of the road roller; the vehicle-mounted controller is used for comparing the moving speed information and the deflection angle information of the road roller with preset operation parameter information and controlling the road roller to operate according to the preset moving speed and the deflection angle.
Further, the remote planning module further comprises a planning end communication module, the visual positioning module further comprises a vehicle-mounted end communication module, and the planning end communication module and the vehicle-mounted end communication module establish real-time communication.
The vehicle-mounted controller is used for acquiring obstacle image information in a lane to be rolled, the computing platform is further used for constructing an octree map according to the obstacle image information acquired by the camera and pose information of the camera estimated by the computing platform, the octree map contains information about whether three-dimensional points in the lane to be rolled are occupied, and if the three-dimensional points are occupied and the distance between the road roller and the three-dimensional points is smaller than a preset safety distance, the vehicle-mounted controller controls the road roller to stop.
Further, the computing platform and the vehicle-mounted controller are communicated through a CAN bus.
Further, the camera is mounted on the top of the cab of the road roller body.
Further, the camera is an RGB-D camera.
Compared with the prior art, the invention has at least the following beneficial effects: the vision-dominated autonomous operation intelligent vibratory roller provided by the invention is positioned by means of vision, and the camera shoots and collects the compaction edge image information of a lane to be rolled for feature matching between subsequent images and resolving the motion of the camera in adjacent time, so that the positioning of the roller applying the vision is realized. The accuracy of visual positioning can be directly influenced by the quality of the feature matching, but as the construction site of the road roller belongs to an unstructured scene, too much feature information cannot be extracted by a camera for feature point matching, so that lane compaction edge features are extracted for subsequent feature point matching, and the matching accuracy and efficiency can be effectively improved. The GNSS acts as an absolute positioning sensor providing the absolute position of the camera for subsequent loop detection steps. Through the real-time position provided by the GNSS, whether the road roller reaches the position or not can be judged in time, and the elimination of the accumulated error of the visual odometer is facilitated. The method can realize unmanned driving of the road roller, reduce manual misoperation, get rid of dependence on skilled operators, work in dangerous working scenes, reduce the danger coefficient of operators, avoid safety accidents and casualties, accurately position in tunnels, areas with poor GNSS signals and shielded by large obstacles and the like, and realize high-precision navigation construction of the road roller. According to the invention, by presetting compaction parameters, the construction quality can be effectively ensured, and the flatness of compaction is improved. The invention has the advantages of reasonable scheme, simple structure, lower cost and easy realization.
Further, the conventional scheme usually adopts a laser radar or a millimeter wave radar to detect and avoid obstacles, and although the effect is good, the cost of one vibratory roller is increased by about 5 thousands. According to the invention, the obstacle avoidance scheme of the camera is adopted, so that the additional sensor is not added, the cost is reduced, and the cost performance is improved; and the visual sensor (camera) can provide more appearance image information of objects compared with the radar sensor, and can provide convenience for subsequent object identification, thereby establishing an obstacle avoidance scheme in a more targeted manner. The point cloud data obtained by the camera cannot represent information about whether an obstacle exists, and therefore cannot be directly used for obstacle avoidance. The invention uses the point cloud data to construct an octree map which contains important information as to whether the three-dimensional point is occupied, if the point is occupied, it indicates that there is an obstacle, and the road roller must be stopped when running in front of the point cloud data. After the barrier is completely removed, the road roller can be restarted to complete the rest work.
Furthermore, the camera is installed at the top of the cab of the road roller body, and the collected visual angle is good.
Further, the camera is an RGB-D camera because the visual localization requires depth information for each feature point. The RGB-D camera can realize real-time depth measurement, and can effectively shorten the time required by visual positioning.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a system architecture diagram of the present invention;
fig. 2 is a diagram of the entire road roller of the invention:
FIG. 3 is a diagram of a visual SLAM framework for a vibratory roller according to the invention;
FIG. 4 is a schematic diagram of the back-end optimization procedure of the present invention.
In the figure: 1-a road roller body; 2-vehicle-mounted terminal communication module; 3-a computing platform; 4-an onboard controller; 5-a hinged shaft; 6-an inertial navigation unit; 7-a speed sensor; 8-rotation angle sensors; 9-a camera; 10-GNSS rover station; 11-GNSS base stations.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As a preferred embodiment of the present invention, with reference to fig. 1, 2, 3 and 4, a vision-dominated autonomous-operation intelligent vibratory roller includes a roller body 1, where the roller body 1 is provided with a vision positioning module and a machine control module, and as shown in fig. 1, the vision positioning module includes a vehicle-mounted terminal communication module 2, a computing platform 3, an inertial navigation unit 6, a camera 9 and a GNSS rover station 10.
As shown in fig. 2, the vehicle-mounted communication module 2 is disposed in the cab and is used for transmitting information with the communication module of the remote planning module. Two cameras 9 are arranged on the top of a cab of the road roller, the front camera and the rear camera are respectively used for collecting the compaction edge image information of a lane to be rolled, and the collected image data is used as the input of a front-end visual odometer and is also used as the basis for judging whether obstacles exist before and after. The inertial navigation unit 6 is mounted on a front frame of the road roller and is used for acquiring pose information of the road roller so as to compensate the estimated camera pose. The GNSS mobile station 10 is mounted on a front frame of the road roller and is used for collecting position information of the road roller under the combined action of the GNSS base station 11 arranged outside a construction area.
The computing platform 3 is arranged in the cab, and is combined with the graph shown in fig. 3, the computing platform 3 is used for performing feature extraction, feature matching and front-end visual odometer optimization on two adjacent frames of compacted edge images according to the information of the compacted edge images acquired by the camera 9, estimating the pose information of the camera 9, performing kalman filtering fusion on the estimated pose information of the camera 9 and the pose information of the road roller acquired by the inertial navigation unit 6, performing rear-end optimization on the fused pose information to obtain the visual positioning information of the camera 9, performing loop detection according to the position information of the road roller acquired by the GNSS rover station 10 and the GNSS base station 11 in the construction area, performing positioning compensation on the visual positioning information of the camera 9, and obtaining the real-time path information of the road roller; the computing platform 3 is further configured to compare the real-time path information of the road roller with preset rolling path information to obtain a comparison result.
As shown in fig. 1 and fig. 3, the system further includes a visual obstacle avoidance module, and the sensor used in the visual obstacle avoidance module is the same as the visual positioning module, and is also a camera 9. The camera 9 is further used for acquiring obstacle image information in a lane to be rolled, the computing platform 3 is further used for constructing an octree map according to the obstacle image information acquired by the camera 9 and pose information of the camera 9 estimated by the computing platform 3, the octree map contains information about whether three-dimensional points in the lane to be rolled are occupied, and if the three-dimensional points are occupied and the distance between the road roller and the three-dimensional points is smaller than a preset safety distance, the vehicle-mounted controller 4 controls the road roller to stop. Specifically, as shown in fig. 3, when the road roller rolls, a GNSS positioning data is introduced to perform a loop detection process, and whether a current point has arrived is determined, so as to eliminate an accumulated error of state estimation, and build an octree map that can be used for obstacle avoidance.
As shown in fig. 1, the machine control module includes an on-board controller 4, a speed sensor 7, and a rotation angle sensor 8. As shown in fig. 2, the onboard controller 4 is disposed in the cab, and is configured to receive the comparison result of the computing platform 3, and control the road roller to move along a preset rolling path according to the comparison result, and the onboard controller 4 performs signal transmission communication with the computing platform 3 through the CAN bus, receives a control instruction issued by the computing platform 3, and controls the speed, the steering, the amplitude, and the frequency of the road roller. The speed sensor 7 is arranged on the rotating shaft and used for collecting moving speed information of the road roller, and the corner sensor 8 is arranged on the articulated shaft 5 of the front frame and the rear frame and used for collecting deflection angle information of the front frame of the road roller; and the vehicle-mounted controller 4 is used for comparing the moving speed information and the deflection angle information of the road roller with preset operation parameter information and controlling the road roller to operate according to the preset moving speed and the deflection angle.
As shown in fig. 1, the road roller is further provided with a remote planning module, the remote planning module comprises a user management module, a remote planning unit and a planning terminal communication module, an expert system and a compaction big data system are arranged in the user management module, the rolling track and the compaction operation parameters of the road roller can be planned automatically according to the construction map and the characteristics of the rolled paving material, and the information of the path and the operation parameters is transmitted to a computing platform of the visual navigation positioning module. The remote planning unit is used for presetting construction area information and operation parameter information. The planning end communication module establishes real-time communication with the vehicle-mounted end communication module 2.
In conclusion, the computing platform 3 processes the data transmitted from the camera 9 and the inertial navigation unit 6 in real time to obtain real-time position data of the road roller, compares the real-time position data with the path planned by the user, and sends a control instruction to the machine control module to ensure that the actual construction path and the planned path have no large error.
In this embodiment, the camera 9 is an RGB-D camera, which may be a monocular camera or a binocular camera, and the RGB-D camera may implement real-time depth measurement, but the monocular camera has a triangulation process to resolve the depth, so the RGB-D camera may be selected to effectively shorten the time required for visual positioning, and meanwhile, under the condition of insufficient illumination such as a tunnel and at night, the effect of the monocular and binocular cameras depending on the optical imaging principle may become worse, so the selection of the RGB-D camera as the sensor for visual positioning is the best choice.
As one embodiment of the invention, the construction area and the operation parameters are sent to the user management module before construction, and the user management module determines the rolling planned path by comparing the built-in expert system with the rolling rules and sends the rolling planned path to the computing platform through the communication module. The GNSS mobile station and the vehicle-mounted end communication module are respectively connected with a computing platform board card, the computing platform board card compares the planned path with the position of the real-time road roller, and the walking speed and the steering angle adjusting value are calculated in real time and are issued to the vehicle-mounted controller. And the road roller automatically performs rolling operation according to the compaction track planning in a construction area according to the control instruction, and controls a steering system, a forward and backward system and a safety system in real time. Preferably, millimeter wave radars are further arranged at the front end and the rear end of the road roller respectively.
As shown in fig. 3, the front-end visual odometer: and performing edge detection and feature extraction on the compacted edge image, then performing feature matching between adjacent frames, and performing Kalman filtering fusion on the estimated camera pose and pose information measured and calculated by the inertial navigation unit, thereby obtaining accurate camera motion and an approximate spatial position of an observed landmark point.
And (3) rear-end optimization: and constructing a rear-end optimization problem by using a g2o library by adopting a graph optimization method, modeling a cost function, performing Schur element elimination, and performing global optimization on the camera pose and the spatial position of the landmark points.
Loop detection: whether the road roller reaches the coordinate point is judged through GNSS positioning data so as to eliminate accumulated errors of state estimation, improve the accuracy of self positioning and map building of the road roller and ensure the global consistency of the track of the road roller and the map.
Establishing a graph: the construction site of the road roller is unstructured, and the road roller cannot be well adapted to the situation of the site through a network map. Therefore, the high-precision map is constructed by reading the depth information of RGB-D to splice the point cloud map and is used for path planning and navigation of the road roller.
As shown in fig. 4, a specific process of performing a back-end optimization algorithm using graph optimization. Firstly, declaring an g2o graph optimizer, then configuring an optimization solver and a gradient descent method, simultaneously inputting the set g2o node and the set g2o side into the solver, starting iteration, and outputting optimized pose information when a cost function is not reduced or converged any more.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (8)
1. The utility model provides a vision-dominated independently-operated intelligent vibratory roller which is characterized in that, includes roller body (1), be provided with vision orientation module and machine control module on roller body (1), the vision orientation module includes:
the inertial navigation unit (6) is used for acquiring pose information of the road roller;
the camera (9) is used for acquiring compaction edge image information of the lane to be rolled;
the GNSS mobile station (10) is used for collecting the position information of the road roller under the combined action with a GNSS base station (11) outside a construction area;
the computing platform (3) is used for performing feature extraction, feature matching and front-end visual odometer optimization on two adjacent frames of the compacted edge images according to the information of the compacted edge images acquired by the camera (9), estimating pose information of the camera (9), performing Kalman filtering fusion on the estimated pose information of the camera (9) and the pose information of the road roller acquired by the inertial navigation unit (6), performing rear-end optimization on the fused pose information to obtain visual positioning information of the camera (9), performing loop detection according to the position information of the road roller acquired by the GNSS mobile station (10) and a GNSS base station (11) in a construction area, and performing positioning compensation on the visual positioning information of the camera (9) to obtain real-time path information of the road roller; the computing platform (3) is also used for comparing the real-time path information of the road roller with preset rolling path information to obtain a comparison result;
the machine control module includes:
the vehicle-mounted controller (4) is used for receiving the comparison result of the computing platform (3) and controlling the road roller to move along a preset rolling path according to the comparison result;
the vehicle-mounted road roller parking system comprises a camera (9), a computing platform (3) and an on-board controller (4), wherein the camera (9) is further used for acquiring obstacle image information in a lane to be rolled, the computing platform (3) is further used for constructing an octree map according to the obstacle image information acquired by the camera (9) and pose information of the camera (9) estimated by the computing platform (3), the octree map comprises information whether three-dimensional points in the lane to be rolled are occupied, and if the three-dimensional points are occupied and the distance from the road roller to the three-dimensional points is smaller than a preset safety distance, the vehicle-mounted controller (4) controls the road roller to park.
2. The intelligent vibratory roller of claim 1 with autonomous operation based on visual guidance, further comprising a remote planning module comprising a customer management module having an expert system and a compaction data system built therein for self-planning roller road diameter information and operational parameter information.
3. The visually dominated, autonomous operation, intelligent vibratory roller of claim 2, wherein the remote planning module further comprises a remote planning unit, the remote planning unit configured to preset construction area information and operation parameter information.
4. A vision-dominated intelligent vibratory roller as claimed in claim 2 or 3, wherein the roller body (1) is further provided with a speed sensor (7) and a rotation angle sensor (8), the speed sensor (7) is used for acquiring moving speed information of the roller, and the rotation angle sensor (8) is used for acquiring deflection angle information of a front frame of the roller; and the vehicle-mounted controller (4) is used for comparing the moving speed information and the deflection angle information of the road roller with preset operation parameter information and controlling the road roller to operate according to the preset moving speed and the deflection angle.
5. A visual dominated, autonomous working intelligent vibratory roller according to claim 2, wherein the remote planning module further comprises a planning end communication module, the visual positioning module further comprises a vehicle end communication module (2), and the planning end communication module establishes real time communication with the vehicle end communication module (2).
6. A visually dominated, autonomous working intelligent vibratory roller according to claim 1, characterized in that the computing platform (3) and the onboard controllers (4) communicate via a CAN bus.
7. A visually dominated, autonomous working, intelligent vibratory roller as claimed in claim 1, wherein the camera (9) is mounted on top of a cab of the roller body (1).
8. A visually dominated, autonomous working, intelligent vibratory roller according to claim 1, characterized in that the camera (9) is an RGB-D camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010769305.4A CN111750855B (en) | 2020-08-03 | 2020-08-03 | Intelligent vibratory roller of independent operation of vision leading |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010769305.4A CN111750855B (en) | 2020-08-03 | 2020-08-03 | Intelligent vibratory roller of independent operation of vision leading |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111750855A CN111750855A (en) | 2020-10-09 |
| CN111750855B true CN111750855B (en) | 2022-02-15 |
Family
ID=72712957
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010769305.4A Active CN111750855B (en) | 2020-08-03 | 2020-08-03 | Intelligent vibratory roller of independent operation of vision leading |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111750855B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115096329B (en) * | 2022-08-25 | 2022-11-08 | 燚璞锐科技(江苏)有限公司 | Visual navigation control system and method for engineering road roller |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103292804A (en) * | 2013-05-27 | 2013-09-11 | 浙江大学 | Monocular natural vision landmark assisted mobile robot positioning method |
| CN109799830A (en) * | 2019-03-06 | 2019-05-24 | 山东交通学院 | Impact road roller automatic driving control system and method |
| CN110331639A (en) * | 2019-07-08 | 2019-10-15 | 长安大学 | One kind can AUTONOMOUS TASK intelligent roller system |
| CN110361027A (en) * | 2019-06-25 | 2019-10-22 | 马鞍山天邦开物智能商务管理有限公司 | Robot path planning method based on single line laser radar Yu binocular camera data fusion |
| CN111121767A (en) * | 2019-12-18 | 2020-05-08 | 南京理工大学 | GPS-fused robot vision inertial navigation combined positioning method |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN205581306U (en) * | 2016-01-18 | 2016-09-14 | 湖南致同工程科技有限公司 | A data acquisition facility for writing down road roller rolls orbit |
| US10371530B2 (en) * | 2017-01-04 | 2019-08-06 | Qualcomm Incorporated | Systems and methods for using a global positioning system velocity in visual-inertial odometry |
| CN109341694A (en) * | 2018-11-12 | 2019-02-15 | 哈尔滨理工大学 | A kind of autonomous positioning air navigation aid of mobile sniffing robot |
-
2020
- 2020-08-03 CN CN202010769305.4A patent/CN111750855B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103292804A (en) * | 2013-05-27 | 2013-09-11 | 浙江大学 | Monocular natural vision landmark assisted mobile robot positioning method |
| CN109799830A (en) * | 2019-03-06 | 2019-05-24 | 山东交通学院 | Impact road roller automatic driving control system and method |
| CN110361027A (en) * | 2019-06-25 | 2019-10-22 | 马鞍山天邦开物智能商务管理有限公司 | Robot path planning method based on single line laser radar Yu binocular camera data fusion |
| CN110331639A (en) * | 2019-07-08 | 2019-10-15 | 长安大学 | One kind can AUTONOMOUS TASK intelligent roller system |
| CN111121767A (en) * | 2019-12-18 | 2020-05-08 | 南京理工大学 | GPS-fused robot vision inertial navigation combined positioning method |
Non-Patent Citations (1)
| Title |
|---|
| 基于BIM和北斗卫星定位的路基连续压实信息系统研究;梁策 等;《铁道建筑》;20170731(第7期);第104-107页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111750855A (en) | 2020-10-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111986506B (en) | Mechanical parking space parking method based on multi-vision system | |
| US11560160B2 (en) | Information processing apparatus | |
| US9896810B2 (en) | Method for controlling a self-propelled construction machine to account for identified objects in a working direction | |
| US10509412B2 (en) | Movable body control system | |
| CN114812581B (en) | Cross-country environment navigation method based on multi-sensor fusion | |
| CN108888187A (en) | A kind of sweeping robot based on depth camera | |
| CN105946853A (en) | Long-distance automatic parking system and method based on multi-sensor fusion | |
| CN111531549A (en) | Robot system and positioning navigation method | |
| US20190073762A1 (en) | Site scanning using a work machine with a camera | |
| CN112518739A (en) | Intelligent self-navigation method for reconnaissance of tracked chassis robot | |
| CN108873914A (en) | A kind of robot autonomous navigation system and method based on depth image data | |
| CN110562248A (en) | automatic parking system and automatic parking method based on unmanned aerial vehicle | |
| CN111168669B (en) | Robot control method, robot, and readable storage medium | |
| JP7252801B2 (en) | Autonomous vehicle traffic control system | |
| CN101308023A (en) | Navigation apparatus and method based on heterogeneous visual sense sensor system | |
| KR20170037197A (en) | Foldable frame for mobile mapping system with multi sensor module | |
| CN113071518B (en) | Automatic unmanned driving method, minibus, electronic equipment and storage medium | |
| CN111750855B (en) | Intelligent vibratory roller of independent operation of vision leading | |
| CN112492522A (en) | Control method for autonomous parking of vehicle | |
| CN111157008B (en) | Local autonomous navigation system and method based on multidimensional environment information perception | |
| CN109835343B (en) | Vehicle control device, vehicle control method, and storage medium | |
| CN114937258B (en) | Control method for mowing robot, and computer storage medium | |
| JP2019206318A (en) | Monitoring device | |
| CN114581603A (en) | Unmanned aerial vehicle modeling method and device | |
| JP6742479B1 (en) | Map generating device, map generating method and program |
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 |