CN112581613A - Grid map generation method and system, electronic device and storage medium - Google Patents
Grid map generation method and system, electronic device and storage medium Download PDFInfo
- Publication number
- CN112581613A CN112581613A CN202011445128.0A CN202011445128A CN112581613A CN 112581613 A CN112581613 A CN 112581613A CN 202011445128 A CN202011445128 A CN 202011445128A CN 112581613 A CN112581613 A CN 112581613A
- Authority
- CN
- China
- Prior art keywords
- point
- radar
- grid map
- hit
- probability
- 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
- 238000000034 method Methods 0.000 title claims abstract description 81
- 238000012545 processing Methods 0.000 claims abstract description 43
- 230000008569 process Effects 0.000 claims abstract description 14
- 230000004044 response Effects 0.000 claims description 34
- 230000009466 transformation Effects 0.000 claims description 16
- 230000000007 visual effect Effects 0.000 claims description 13
- 238000001514 detection method Methods 0.000 claims description 8
- 238000012790 confirmation Methods 0.000 claims description 7
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 238000010276 construction Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 11
- 238000004590 computer program Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 230000007423 decrease Effects 0.000 description 6
- 230000033001 locomotion Effects 0.000 description 5
- 238000013507 mapping Methods 0.000 description 5
- 238000005457 optimization Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000000717 retained effect Effects 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000004807 localization Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004984 smart glass Substances 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/05—Geographic models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10044—Radar image
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Graphics (AREA)
- Remote Sensing (AREA)
- Traffic Control Systems (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention provides a method and a system for generating a grid map, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring track data and point cloud data of a millimeter wave radar; initializing a grid map based on SLAM trajectory data; multiplying the point cloud data of the millimeter wave radar of the current frame with the corresponding SLAM track data to obtain track data of the current frame, and converting the track data of the current frame to a world coordinate system; acquiring the position of a radar hit point in an initialized grid map; marking the radar hit point, adjusting the probability value of the radar hit point, and updating the grid map based on the adjusted probability value; responding to the uncompleted processing of the point cloud data of the millimeter wave radars of all frames, and completing the processing of the point cloud data of the millimeter wave radars of all other frames based on the processing process of the current frame; a grid map is saved based on probability values of radar hits in each frame. The invention constructs the grid map through the millimeter wave radar, so that the cost of map construction and positioning is greatly reduced.
Description
Technical Field
The invention belongs to the technical field of maps, particularly relates to the technical field of grid maps, and particularly relates to a grid map generation method and system, electronic equipment and a storage medium.
Background
The electronic map is a map in a digital form generated by using a computing technology, and can be widely used in scenes such as inquiry, positioning, navigation and the like. The electronic map is generally divided into a common navigation map and a high-precision map, wherein the common navigation map is a user-oriented map and provides a visual interface for a user to inquire and display; and a high-precision map is a kind of machine-oriented map data that can be used for, for example, automatic driving, robot navigation, positioning, and the like. Ordinary navigation maps are usually obtained by satellite mapping, and their accuracy is usually not high (e.g. errors can reach several meters or even several tens of meters). A high-precision map is high-precision map data that is not only high in precision but also includes other information that can be used for precise navigation and positioning, such as lane line information, object height information, road shape information, and the like.
A grid map is a commonly used form of high-precision electronic map that divides the environment into a series of grids, where each grid is marked with a value that indicates that the grid is occupied. That is, a grid map is a product of digitally rasterizing a real environment to identify obstacles in the environment by whether the grid is occupied or not. Due to the demand for navigation and positioning of autonomous vehicles and robots, occupancy grid maps are widely used in navigation and positioning scenes of unmanned vehicles and intelligent robots.
The sensor for generating the grid map is a laser radar (single line or multiple lines), and the grid map is constructed while generating a track. The laser light is considered to be occupied when it encounters an obstacle, i.e., returns, the grid passing from the origin to the occupied point is considered to be unoccupied, and the remaining points are considered to be unknown areas. At present, a laser radar is adopted to generate a grid map, and the characteristics of high precision, low noise, long distance and more points of the laser radar are benefited, but the price of the current method for constructing the map by adopting the laser radar is expensive.
Disclosure of Invention
In view of the above-mentioned shortcomings of the prior art, it is an object of the present invention to provide a method, system, electronic device and storage medium for generating a grid map, which provides a low-cost way of generating a grid map.
To achieve the above and other related objects, an embodiment of the present invention provides a method for generating a grid map, including: acquiring track data and point cloud data of a millimeter wave radar; initializing a grid map based on the trajectory data; multiplying the point cloud data of the millimeter wave radar of the current frame with the corresponding track data to transform to a world coordinate system; acquiring the position of the radar hit point in the grid map based on the point in the world coordinate system obtained by transformation; respectively adjusting probability values of the radar hit points and unoccupied points, and updating the grid map based on the adjusted probability values; detecting whether the processing of the point cloud data of the millimeter wave radars of all frames is finished or not, responding to the fact that the processing of the point cloud data of the millimeter wave radars of all frames is not finished, and finishing the processing of the point cloud data of the millimeter wave radars of all other frames based on the processing process of the current frame; and saving the grid map based on the probability value of the radar hit points in each frame.
In an embodiment of the present application, in step S1, point cloud data of the millimeter wave radar satisfying the predetermined distance range is obtained.
In an embodiment of the present application, in step S5, the implementation manner of adjusting the probability value of the radar hit point includes: detecting whether the radar hit point is a first hit; in response to the radar hit point being a first hit, marking the radar hit point and increasing a probability value of the radar hit point; in response to the radar hit point not being the first hit, increasing a probability value for the radar hit point.
In an embodiment of the present application, in step S5, the implementation of adjusting the probability value of the unoccupied point includes: confirming that points except the radar hitting point on a connecting line between the radar hitting point and the position of the vehicle body are unoccupied points; confirming whether the unoccupied point is marked; in response to the unoccupied point being marked, keeping the probability value for that point unchanged; in response to the unoccupied point not being marked, decreasing the probability value for the point.
In an embodiment of the present application, in step S7, an implementation manner of saving the grid map based on the probability value of the radar hit point in each frame includes: confirming whether the probability value of the radar hit point is greater than a probability threshold value; responding to the probability value of the radar hit point being larger than the probability threshold value, confirming that the radar hit point is an occupied point and marking the occupied point as a first numerical value; confirming whether the probability value of the radar hit point is equal to the initial value of a grid map; responding to the probability value of the radar hit point being equal to the initial value of the grid map, confirming that the radar hit point is an unknown point and marking as a second numerical value; and in response to the probability value of the radar hit point being less than or equal to the probability threshold value or in response to the probability value of the radar hit point not being equal to the initial value of the grid map, confirming that the radar hit point is an unoccupied point and marking the unoccupied point as a third numerical value.
In an embodiment of the present application, in step S1, the trajectory data is acquired based on visual SLAM data, laser SLAM data, vehicle body data, or millimeter wave radar data.
The embodiment of the present invention further provides a grid map generation system, including: the data acquisition module is used for acquiring track data and point cloud data of the millimeter wave radar; an initialization module for initializing a grid map based on the trajectory data; the coordinate transformation module is used for multiplying the point cloud data of the millimeter wave radar of the current frame with the corresponding track data to transform to a world coordinate system; a hit point position acquisition module, configured to acquire, based on a point in the world coordinate system obtained through the transformation, a position of a radar hit point in the grid map; the probability updating module is used for respectively adjusting the probability values of the radar hit points and the unoccupied points and updating the grid map based on the adjusted probability values; the traversal detection module is used for detecting whether the processing of the point cloud data of the millimeter wave radars of all frames is finished or not, and the coordinate transformation module, the hit point position acquisition module and the probability updating module respond to the processing of the point cloud data of the millimeter wave radars which are not formed into all frames and continue to finish the processing of the point cloud data of the millimeter wave radars of all other frames; and the map storage module is used for storing the grid map based on the probability value of the radar hit point in each frame.
In an embodiment of the application, the data acquisition module acquires point cloud data of the millimeter wave radar satisfying a preset distance range.
In an embodiment of the present application, the probability updating module includes: the first hit detection unit is used for detecting whether the radar hit point is a first hit; and the probability increasing unit is used for responding to the fact that the radar hit point is the first hit, marking the radar hit point, increasing the probability value of the radar hit point, and responding to the fact that the radar hit point is not the first hit, and increasing the probability value of the radar hit point.
In an embodiment of the present application, the probability updating module further includes: a line point confirmation unit configured to confirm that points other than the radar hit point on a line between the radar hit point and the vehicle body position are unoccupied points; a marking confirmation unit configured to confirm whether the unoccupied dot is marked; and the probability adjusting unit is used for responding to the fact that the unoccupied point is marked, keeping the probability value of the point unchanged, responding to the fact that the unoccupied point is not marked, and reducing the probability value of the point.
In an embodiment of the present application, the map saving module includes: an occupation point confirming unit, configured to confirm whether a probability value of the radar hit point is greater than a probability threshold, and in response to that the probability value of the radar hit point is greater than the probability threshold, confirm that the radar hit point is an occupation point and mark the occupation point as a first numerical value; an unknown point confirming unit, configured to confirm whether a probability value of the radar hit point is equal to an initial value of the grid map, and in response to that the probability value of the radar hit point is equal to the initial value of the grid map, confirm that the radar hit point is an unknown point and mark the unknown point as a second numerical value; and the unoccupied point confirming unit is used for confirming that the radar hit point is an unoccupied point and marking the unoccupied point as a third numerical value in response to that the probability value of the radar hit point is smaller than or equal to the probability threshold value or that the probability value of the radar hit point is not equal to the initial value of the grid map.
In an embodiment of the application, the trajectory data acquired by the data acquisition module is generated based on visual SLAM data, laser SLAM data, vehicle body data, or millimeter wave radar data.
Embodiments of the present invention also provide an electronic device, comprising a processor and a memory, the memory storing program instructions; the processor executes program instructions to implement the grid map generation method described above.
Embodiments of the present invention also provide a storage medium storing program instructions that, when executed, implement the method for generating a grid map as described above.
As described above, the method, system, electronic device, and storage medium for generating a grid map according to the present invention have the following advantageous effects:
1. the invention constructs the grid map through the millimeter wave radar, so that the cost of map construction and positioning is greatly reduced.
2. The method for adjusting the probability value of the hit point can avoid that effective information can be brushed away by subsequent noise points, so that the constructed map can reflect the information of the real environment.
3. When the grid map is stored, whether the grid map is an occupied grid or not is confirmed through the probability value, a small number of hit points can be filtered, and multiple hit points can be reserved, so that part of noise points are effectively filtered.
Drawings
Fig. 1 is a flow chart illustrating a method for generating a grid map according to the present invention.
Fig. 2 is a diagram showing an example in which a millimeter wave radar transmits one frame of data in the method of generating a grid map according to the present invention.
Fig. 3 is a schematic diagram illustrating initialization of a grid map based on SLAM trajectory data in the grid map generation method according to the present invention.
Fig. 4 is a flowchart illustrating a method for adjusting probability values of radar hit points in the method for generating a grid map according to the present invention.
Fig. 5 is a schematic flow chart showing the adjustment of the point between the origin and the radar hit point in the method for generating a grid map according to the present invention.
Fig. 6 is a schematic flow chart illustrating a process of saving a map in the method for generating a grid map according to the present invention.
Fig. 7 is a schematic view showing a grid map constructed in the grid map generation method of the present invention.
Fig. 8 is a schematic diagram illustrating the overall implementation of the grid map generation method according to the present invention.
Fig. 9 is a schematic structural diagram of the system for generating the grid map of the present invention.
FIG. 10 is a schematic diagram of the principle structure of the probability updating module in the grid map generation system according to the present invention.
Fig. 11 is a schematic diagram showing the principle structure of the probability updating module included in the grid map generating system according to the present invention.
Fig. 12 is a schematic structural diagram of a map saving module in the grid map generation system according to the present invention.
Fig. 13 is a schematic structural diagram of an electronic device in an embodiment of the present application.
Description of the element reference numerals
100 grid map generation system
110 data acquisition module
120 initialization module
130 coordinate transformation module
140 hit position acquisition module
150 probability update module
151 first hit detection unit
152 probability increasing unit
153 connection point confirming unit
154 mark confirmation unit
155 probability adjusting unit
160 traversal detection module
170 map saving module
171 occupancy point confirmation unit
172 unknown point confirming unit
173 unoccupied dot confirmation cell
10 electronic device
101 processor
102 memory
S1-S7
S510 to S580 steps
S710 to S750
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
The embodiment aims to provide a grid map generation method, a grid map generation system, an electronic device and a storage medium, which are used for providing a low-cost grid map generation mode.
The principles and embodiments of the method, system, electronic device and storage medium for generating a grid map according to the present invention will be described in detail below, so that those skilled in the art can understand the method, system, electronic device and storage medium for generating a grid map without creative work.
Example 1
As shown in fig. 1, the present embodiment provides a method for generating a grid map, including:
step S1: acquiring track data and point cloud data of a millimeter wave radar;
step S2: initializing a grid map based on the trajectory data;
step S3: multiplying the point cloud data of the millimeter wave radar of the current frame with the corresponding track data to transform to a world coordinate system;
step S4: acquiring the position of the radar hit point in the grid map based on the point in the world coordinate system obtained by transformation;
step S5: respectively adjusting probability values of the radar hit points and unoccupied points, and updating the grid map based on the adjusted probability values;
step S6: detecting whether the processing of the point cloud data of the millimeter wave radars of all frames is finished or not, responding to the fact that the processing of the point cloud data of the millimeter wave radars of all frames is not finished, and finishing the processing of the point cloud data of the millimeter wave radars of all other frames based on the processing process of the current frame;
step S7: and saving the grid map based on the probability value of the radar hit points in each frame.
The following describes steps S1 to S7 of the method for generating a grid map according to the present embodiment in detail.
Step S1: and acquiring track data and point cloud data of the millimeter wave radar.
In step S1, the trajectory data is acquired based on, but not limited to, visual SLAM data, laser SLAM data, vehicle body data, or millimeter wave radar data.
For example, the trajectory data is acquired based on visual SLAM data.
SLAM (simultaneous localization and mapping) is considered as a key for realizing a true fully-autonomous mobile localization key map and mainly comprises a front-end preprocessing part and a rear-end optimization part, wherein the front-end preprocessing part is used for analyzing and integrating various sensor data to provide an initial estimation map and position information, the rear-end optimization part is used for describing initial estimation and probability constraint by using a map model, and the initial estimation part is optimized by using an optimization method to realize higher-precision mapping and positioning SLAM track data.
Wherein the process of generating trajectory data based on the visual SLAM data comprises:
1) when any vehicle is in a map building mode, the motion posture of the vehicle and the vehicle periphery image are obtained, and landmark information is extracted from the vehicle periphery image.
2) And generating a landmark map and a vehicle running track according to the motion attitude of the vehicle and the landmark information based on the SLAM algorithm.
The SLAM algorithm used in this embodiment includes, but is not limited to, the EXF family, particle filter FastSLAM, graph optimization, etc.
Most vision-based SLAM techniques select landmark information like SIFT, FAST. But these landmark information is subject to large environmental changes. The time invariance is not good. It cannot be stored in the map. In the embodiment, when the map is constructed by using the SLAM algorithm, the selected landmark information includes, but is not limited to, a fixed point of a parking space, a pillar edge, a projection of the parking space on the ground, and the like.
In addition, in this embodiment, other methods for acquiring the trajectory data in the prior art may be adopted, and the method is not limited to the above-described process for generating the trajectory data based on the visual SLAM data.
Since the noise ratio of the millimeter wave radar is large, the point cloud data of the millimeter wave radar is filtered. Specifically, in the present embodiment, in the point cloud data of the millimeter wave radar, the point cloud data of the millimeter wave radar satisfying a preset distance range is obtained, wherein the preset distance range is, but not limited to, 10 meters to 30 meters, for example, the point cloud data of the millimeter wave radar within 20 meters near the vehicle is retained.
In this embodiment, the echo point cloud data of the target is obtained by the millimeter wave radar. Fig. 2 is a diagram showing an example in which a millimeter wave radar transmits one frame of data in the method of generating a grid map according to the present invention. The point cloud data is the result of distance measurement, speed measurement and angle measurement and constant false alarm rate detection performed on the data cube received by the millimeter wave radar, and includes but is not limited to the number of traces, the distance of each trace, the Doppler (velocity) information of each trace and the angle parameter of each trace.
Those skilled in the art may also adopt other methods for acquiring the track data and the point cloud data of the millimeter wave radar in the prior art according to actual needs, and details of this embodiment are not described in detail.
Step S2: initializing a grid map based on the trajectory data.
Fig. 3 is a schematic diagram illustrating initialization of a grid map based on SLAM trajectory data in the present embodiment. Specifically, in the present embodiment, a vehicle travelable region is detected and a grid map is generated based on a vehicle travel track and the detected travelable region.
In this embodiment, the road surface form drivable region is sensed, and the local grid map is generated according to the movement posture of the vehicle and by combining the landmark information. And storing the attribute of the area covered by each grid in the grid map. For example, 1 represents a road surface and 0 represents a non-road surface. The method comprises the steps of sensing a road surface form drivable area of a drivable road surface, mapping the road surface form drivable area to a grid map, carrying out road surface segmentation through semantics, and mapping the road surface form drivable area to the grid map. In the present embodiment, the road surface configuration, i.e., the travel area, includes, but is not limited to, a straight road surface, an entrance road surface, and an intersection road surface.
And initializing the grid map, namely calculating the size of the generated grid map so as to avoid the situation of border crossing in the map building process. In general, the smaller the size of each grid, the higher its accuracy and the higher the resolution. That is, the higher the number of grids therein, the higher the resolution of the spatial grid for the same spatial grid. Initializing the grid map sets each grid to a predetermined size (e.g., 0.125 meters or other size).
Step S3: and multiplying the point cloud data of the millimeter wave radar of the current frame with the corresponding track data to transform to a world coordinate system.
The present embodiment registers the millimeter wave radar as the grid map using the trajectory data.
The world coordinate system is an absolute coordinate system of the system, and the coordinates of all points on the picture before the user coordinate system is not established are determined by the origin of the coordinate system.
Specifically, in this embodiment, the world coordinate system is the position of the first frame of the visual track, and the process of multiplying the point cloud data of the millimeter wave radar of the current frame by the corresponding track data to transform to the world coordinate system is as follows:
let Pi be a point of the current frame and Twc be the transformation (rotation R + translation t) of the current frame to the world coordinate system, then the transformation to the world coordinate system Pw ═ Twc ═ Pi ═ R ═ Pi + t.
Step S4: and acquiring the position of the radar hit point in the grid map based on the point in the world coordinate system obtained by transformation.
Step S5: and respectively adjusting the probability values of the radar hit points and the unoccupied points, and updating the grid map based on the adjusted probability values.
Fig. 4 is a flowchart illustrating a method for adjusting probability values of radar hit points in the method for generating a grid map according to the present invention. Specifically, as shown in fig. 4, in the present embodiment, in step S5, the implementation manner of adjusting the probability value of the radar hit point includes:
step S510: and detecting whether the radar hit point is the first hit, if so, continuing to execute the step S520, and if not, continuing to execute the step S530.
Step S520: in response to the radar hit point being the first hit, the radar hit point is marked and a probability value for the radar hit point is increased.
Step S530: in response to the radar hit point not being the first hit, increasing a probability value for the radar hit point.
In other words, in this embodiment, according to the obtained point of the world coordinate system, the vehicle body position is first obtained, the position of the grid map where the radar hit point is located is obtained through calculation, and if the radar hit point is hit for the first time, the radar hit point is marked as the hit point, and the probability value is increased; if the radar hit point is not hit for the first time, the probability value is directly increased.
In this embodiment, the probability value is increased as follows:
the increase in probability value is expressed in the form of a variation of a logarithmic function, and assuming that the probability of a certain grid is p, the variation of the probability value of the grid (radar hit point) is log (p/(1-p)). log odd ═ log (p/(1-p)), where log odd is the log of the probability log change value and p is the initial probability of the grid. Assuming that the real-time probability value of log odd of the current grid is map _ odd, the update when it is hit is map _ odd + log _ occ, where log _ occ is a preset added fixed value.
Fig. 5 is a schematic flow chart showing the adjustment of the point between the origin and the radar hit point in the method for generating a grid map according to the present invention. As shown in fig. 5, in the present embodiment, in step S5, the implementation manner of adjusting the probability value of the unoccupied point includes:
step S540: confirming that points except the radar hitting point on a connecting line between the radar hitting point and the vehicle body position are unoccupied points;
step S550: confirming whether the unoccupied point is marked; if yes, continue to step S570, otherwise continue to step S580;
step S560: in response to the unoccupied point being marked, keeping the probability value for that point unchanged;
step S570: in response to the unoccupied point not being marked, decreasing the probability value for the point.
Firstly, acquiring a vehicle body position, then forming a connecting line by the radar hitting point and the vehicle body position, wherein points (not including the radar hitting point (hit point)) on the connecting line are unoccupied points, and if the unoccupied points are marked, the probability value of the unoccupied points is unchanged; if the unoccupied point is not marked, its probability value decreases.
In this embodiment, the probability value is reduced as follows:
the probability value reduction is represented by a variation value of a logarithmic function, and assuming that the probability of a certain grid is p, the probability value of the grid (radar hit point) reduction is log (p/(1-p)). log odd ═ log (p/(1-p)), where log odd is the log of the probability log change value and p is the initial probability of the grid. Assuming that the real-time probability value of log odd of the current grid is map _ odd, it is updated as map _ odd-log _ free when the ray passes through (is unoccupied), where log _ free c is a preset reduced fixed value.
In this embodiment, noise still has an influence after filtering the point cloud data of the millimeter wave radar, which may cause that effective information may be brushed away by subsequent noise points, so that the grid map may not reflect information of the real environment, so the above probability strategy is adopted when constructing the grid map in this embodiment: once a point is hit, it is marked and the probability value is calculated, and if a line passes through it, its probability value will not decrease, and after hitting again, the probability value will still increase. Therefore, the method for adjusting the probability value of the radar hit point in the embodiment can avoid that effective information can be brushed away by subsequent noise points, so that the constructed map can reflect the information of the real environment.
Step S6: and detecting whether the processing of the point cloud data of the millimeter wave radars of all frames is finished or not, responding to the fact that the processing of the point cloud data of the millimeter wave radars of all frames is not finished, and finishing the processing of the point cloud data of the millimeter wave radars of all other frames based on the processing process of the current frame.
If the millimeter wave radar of all frames is traversed, the step S7 is carried out, and the map is stored; if the traversal is not completed, the step S3 is returned to continue processing the next frame of trace data.
After each frame of track data is processed, the grid map is updated after the probability value of the radar hit point is adjusted, and the grid map is updated after the probability value of the point between the origin and the radar hit point is adjusted.
Step S7: and saving the grid map based on the probability value of the radar hit points in each frame.
Fig. 6 is a schematic flow chart illustrating a process of saving a map in the method for generating a grid map according to the present invention. As shown in fig. 6, in the present embodiment, in step S7, an implementation manner of saving the grid map based on the probability value of the radar hit point in each frame includes:
step S710: determining whether a probability value of the radar hit point is greater than a probability threshold.
Step S720: and in response to the probability value of the radar hit point being larger than the probability threshold value, confirming that the radar hit point is an occupied point and marking the radar hit point as a first numerical value.
Wherein the first value is a reference number, such as but not limited to 100.
Step S730: and confirming whether the probability value of the radar hit point is equal to the initial value of the grid map.
Step S740: and in response to the probability value of the radar hit point being equal to the initial value of the grid map, confirming that the radar hit point is an unknown point and marking the radar hit point as a second numerical value.
Wherein the second value is a reference number different from the first value, such as but not limited to-1.
It should be noted that step S710 and step S720 may be executed first, and then step S730 and step S740 may be executed continuously, or step S730 and step S740 may be executed first, and then step S710 and step S720 may be executed continuously.
Step S750: and in response to the probability value of the radar hit point being less than or equal to the probability threshold value or in response to the probability value of the radar hit point not being equal to the initial value of the grid map, confirming that the radar hit point is an unoccupied point and marking the unoccupied point as a third numerical value.
Wherein the third value is a reference number different from the first value and the second value, such as but not limited to 0.
For example, when saving a grid map, points greater than a certain probability threshold are occupied points, labeled 100; marking the point which is equal to the initial value of the map as an unknown point as-1; the remaining dots are unoccupied dots, labeled 0. A schematic diagram of the grid map construction constructed in the present embodiment is shown in fig. 7.
It should be noted that, in the present embodiment, the log odd of the change of the probability that the update occupied (radar hit point) and the unoccupied point are updates increases or decreases, for example, the update occupied point is updated by a fixed preset increase value log _ occ, and the unoccupied point is updated by a preset fixed decrease value log _ free.
Assuming that the real-time probability value of log odd for the current grid is map _ odd, then the update when it is hit is map _ odd + log _ occ, and the update when it is passed (unoccupied) by a ray is map _ odd-log _ free. When a grid has been marked as occupied, no more unoccupied updates are made.
When the map is saved, the log odd value of the existing data is converted into a probability value to be saved. Assuming that the value of log odd of a certain grid of the current map is m, its probability value p is exp (m)/(1+ exp (m)).
Therefore, in the method for generating the grid map of the embodiment, when the grid map is stored, whether the grid map is an occupied grid or not is determined through the probability value, a small number of hit points are filtered, multiple hit points are reserved, and part of noise points are effectively filtered.
In order to make those skilled in the art further understand the implementation process of the method for generating a grid map in this embodiment, the following further describes the implementation process of the method for generating a grid map in this embodiment.
As shown in fig. 8, track data and point cloud data of the millimeter wave radar are respectively obtained, a grid map is initialized based on the track data, and the point cloud data of the millimeter wave radar of the current frame and the corresponding track data are multiplied to be transformed to a world coordinate system.
Aiming at the radar hit point, calculating the position of the grid map where the radar hit point is located according to the obtained points of the world coordinate system, if the radar hit point is hit for the first time, marking the radar hit point as the hit point, and increasing the probability value of the radar hit point; if the radar hit point is not hit for the first time, the probability value is directly increased. The grid map is then updated.
Aiming at a point between an origin and a radar hitting point, forming a connecting line between the radar hitting point and the position of the vehicle body, wherein a point (not including the radar hitting point (hit point)) on the connecting line is an unoccupied point, and if the unoccupied point is marked, the probability value of the unoccupied point is unchanged; if the unoccupied point is not marked, its probability value decreases. The grid map is then updated.
By means of the method for adjusting the probability value of the radar hit point, effective information can be prevented from being brushed away by subsequent noise points, and the constructed map can reflect information of a real environment.
Detecting whether the millimeter wave radar traversal of all frames is completed or not, and if so, entering a stored map; and if the traversal is not completed, returning to continue processing the next frame of track data.
When the map is stored, points larger than a certain probability threshold are confirmed as occupied points and marked as 100; confirming a point equal to the initial value of the map as an unknown point, and marking the unknown point as-1; the remaining dots are identified as unoccupied dots, labeled 0. Whether the grid is occupied or not is confirmed through the probability value, a small number of hit points can be filtered, the hit points for multiple times can be reserved, and partial noise points are effectively filtered.
Example 2
As shown in fig. 9, the present embodiment provides a system 100 for generating a grid map, where the system 100 for generating a grid map includes: the map data processing system comprises a data acquisition module 110, an initialization module 120, a coordinate transformation module 130, a hit point position acquisition module 140, a probability updating module 150, a traversal detection module 160 and a map saving module 170.
In this embodiment, the data obtaining module 110 is used to obtain the track data and the point cloud data of the millimeter wave radar.
The trajectory data acquired by the data acquisition module 110 is generated based on, but not limited to, visual SLAM data, laser SLAM data, vehicle body data, or millimeter wave radar data.
For example, the trajectory data acquired in the data acquisition module 110 is generated based on visual SLAM data.
Wherein the process of generating trajectory data based on the visual SLAM data comprises:
1) when any vehicle is in a map building mode, the motion posture of the vehicle and the vehicle periphery image are obtained, and landmark information is extracted from the vehicle periphery image.
2) And generating a landmark map and a vehicle running track according to the motion attitude of the vehicle and the landmark information based on the SLAM algorithm.
The SLAM algorithm used in this embodiment includes, but is not limited to, the EXF family, particle filter FastSLAM, graph optimization, etc.
Most vision-based SLAM techniques select landmark information like SIFT, FAST. But these landmark information is subject to large environmental changes. The time invariance is not good. It cannot be stored in the map. In the embodiment, when the map is constructed by using the SLAM algorithm, the selected landmark information includes, but is not limited to, a fixed point of a parking space, a pillar edge, a projection of the parking space on the ground, and the like.
Since the noise ratio of the millimeter wave radar is large, the point cloud data of the millimeter wave radar is filtered. In the present embodiment, the data obtaining module 110 obtains the point cloud data of the millimeter wave radar satisfying the preset distance range. The preset distance range is, but not limited to, 10 meters to 30 meters, and for example, point cloud data of millimeter wave radar within 20 meters near the vehicle is retained.
In this embodiment, the initialization module 120 is configured to initialize the grid map based on the trajectory data.
In this embodiment, the initialization module 120 generates the grid map by detecting a vehicle travelable area and generating the grid map according to a vehicle travel track and the detected travelable area.
In this embodiment, the coordinate transformation module 130 is configured to multiply the point cloud data of the millimeter wave radar of the current frame with the corresponding trajectory data to transform to a world coordinate system.
In this embodiment, the hit point position obtaining module 140 is configured to obtain a position of the radar hit point in the grid map based on a point in the world coordinate system obtained through the transformation.
In this embodiment, the probability updating module 150 is configured to adjust the probability values of the radar hit point and the unoccupied point respectively, and update the grid map based on the adjusted probability values.
In this embodiment, as shown in fig. 10, the probability updating module 150 includes: a first hit detecting unit 151 and a probability increasing unit 152.
Wherein, the first hit detecting unit 151 is configured to detect whether the radar hit point is a first hit; the probability increasing unit 152 is configured to mark the radar hit point and increase the probability value of the radar hit point in response to the radar hit point being a first hit, and increase the probability value of the radar hit point in response to the radar hit point not being a first hit.
In the embodiment, the position of the grid map where the radar hit point is located is calculated according to the obtained points of the world coordinate system, and if the radar hit point is hit for the first time, the radar hit point is marked as the hit point, and the probability value of the radar hit point is increased; if the radar hit point is not hit for the first time, the probability value is directly increased.
In this embodiment, as shown in fig. 11, the probability updating module 150 further includes: a connection point confirming unit 153, a mark confirming unit 154, and a probability adjusting unit 155.
The connection point confirming unit 153 is configured to confirm that points on a connection line between the radar hit point and the vehicle body position, except for the radar hit point, are unoccupied points, and the probability updating module 150 further includes a vehicle body position unit configured to obtain the vehicle body position; the marking confirmation unit 154 is configured to confirm whether the unoccupied dot is marked; the probability adjusting unit 155 is configured to, in response to the unoccupied point being marked, keep the probability value of the point unchanged, and in response to the unoccupied point not being marked, reduce the probability value of the point.
The radar hitting point and the vehicle body position form a connecting line, a point on the line (not including the radar hitting point (hit point)) is an unoccupied point, and if the unoccupied point is marked, the probability value of the unoccupied point is unchanged; if the unoccupied point is not marked, its probability value decreases.
After each frame of track data is processed, the grid map is updated after the probability value of the radar hit point is adjusted, and the grid map is updated after the probability value of the point between the origin and the radar hit point is adjusted.
In this embodiment, the traversal detecting module 160 is configured to detect whether the processing of the point cloud data of the millimeter wave radars of all frames is completed, and the coordinate transforming module 130, the hit point position obtaining module 140, and the probability updating module 150 respond to the processing of the point cloud data of the millimeter wave radars of all frames, and continue to complete the processing of the point cloud data of the millimeter wave radars of all other frames.
In this embodiment, the map saving module 170 is configured to save the grid map based on the probability value of the radar hit point in each frame.
In this embodiment, as shown in fig. 12, the map saving module 170 includes: occupied point confirming section 171, unknown point confirming section 172, and unoccupied point confirming section 173.
In this embodiment, the occupancy point determination unit 171 is configured to determine whether the probability value of the radar hit point is greater than a probability threshold, and determine that the radar hit point is an occupancy point and is marked as a first numerical value in response to that the probability value of the radar hit point is greater than the probability threshold.
In this embodiment, the unknown point confirming unit 172 is configured to confirm whether the probability value of the radar hit point is equal to the initial value of the grid map, and in response to that the probability value of the radar hit point is equal to the initial value of the grid map, confirm that the radar hit point is an unknown point and mark the unknown point as a second value.
In this embodiment, the unoccupied point identification unit 173 is configured to identify the radar hit point as an unoccupied point and mark the unoccupied point as a third value in response to the probability value of the radar hit point being less than or equal to the probability threshold value or in response to the probability value of the radar hit point not being equal to the initial value of the grid map.
Therefore, when the grid map is stored, the system 100 for generating the grid map of this embodiment determines whether the grid map is an occupied grid or not through the probability value, a small number of hit points are filtered, multiple hit points are retained, and a part of noise points are effectively filtered.
The technical features of the specific implementation of the system 100 for generating a grid map in this embodiment are substantially the same as the method for generating a grid map in embodiment 1, and the technical contents that can be used in the embodiments are not repeated.
It should be noted that the division of the modules of the above apparatus is only a logical division, and the actual implementation may be wholly or partially integrated into one physical entity, or may be physically separated. And these modules can be realized in the form of software called by processing element; or may be implemented entirely in hardware; and part of the modules can be realized in the form of calling software by the processing element, and part of the modules can be realized in the form of hardware. For example, a module may be a processing element that is set up separately, or may be implemented by being integrated into a chip of an electronic terminal, or may be stored in a memory of the terminal in the form of program code, and the processing element of the terminal calls and executes the functions of the tracking calculation module. Other modules are implemented similarly. In addition, all or part of the modules can be integrated together or can be independently realized. The processing element described herein may be an integrated circuit having signal processing capabilities. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in the form of software.
For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), or one or more microprocessors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), among others. For another example, when one of the above modules is implemented in the form of a Processing element scheduler code, the Processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).
Example 3
As shown in fig. 13, the present embodiment further provides an electronic device 10, where the electronic device 10 includes a processor 101 and a memory 102. The electronic device 10 is a vehicle-mounted terminal, such as a vehicle-mounted device or a vehicle-mounted box, and the electronic device 10 may also be a mobile terminal disposed in a vehicle, such as a smart phone, a PAD, smart glasses, a smart band, and the like. The method for generating the grid map can be applied to various types of electronic devices 10100. The electronic device 10 may also be, for example, a computer that includes components such as memory, a memory controller, one or more processing units (CPUs), a peripheral interface, RF circuitry, audio circuitry, speakers, a microphone, an input/output (I/O) subsystem, a display screen, other output or control devices, and external ports; the computer includes but is not limited to personal computers such as desktop computers, notebook computers, smart televisions, and the like. In other embodiments, the electronic device 10 may also be a server, where the server may be arranged on one or more physical servers according to various factors such as functions, loads, and the like, or may be formed by a distributed or centralized server cluster, and this embodiment is not limited in this embodiment.
The memory 102 is connected to the processor 101 through a system bus and performs communication with the processor 101, the memory 102 is used for storing a computer program, the processor 101 is coupled to the display 1003 and the memory 1002, and the processor 101 is used for running the computer program, so that the electronic device 10100 performs the method for generating the grid map according to embodiment 1. The embodiment 1 has already described the generation method of the grid map in detail, and is not described again here.
In an actual implementation manner, the electronic device 10100 is, for example, an electronic device 10100 installed with an Android operating system or an iOS operating system, or an operating system such as Palm OS, Symbian, Black Berry OS, or Windows Phone.
In an exemplary embodiment, the electronic device 10100 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors, cameras, or other electronic components for performing the above grid map generating method.
It should be noted that the above-mentioned system bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The system bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 11, but this is not intended to represent only one bus or type of bus. The communication interface is used for realizing communication between the database access device and other devices (such as a client, a read-write library and a read-only library). The Memory may include a Random Access Memory (RAM), and may further include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory.
The Processor 101 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
Those of ordinary skill in the art will understand that: all or part of the steps for implementing the above method embodiments may be performed by hardware associated with a computer program. The aforementioned computer program may be stored in a computer readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Example 4
The present embodiment provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of generating a grid map. The above-mentioned generation method of the grid map has been described in detail, and is not described herein again.
Those of ordinary skill in the art will understand that: all or part of the steps for implementing the above method embodiments may be performed by hardware associated with a computer program. The aforementioned computer program may be stored in a computer readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
In conclusion, the grid map is constructed through the millimeter wave radar, so that the construction cost and the positioning cost are greatly reduced; the method for adjusting the probability value of the hit point can avoid that effective information can be brushed away by subsequent noise points, so that the constructed map can reflect the information of a real environment; when the grid map is stored, whether the grid map is an occupied grid or not is confirmed through the probability value, a small number of hit points can be filtered, and multiple hit points can be reserved, so that part of noise points are effectively filtered. Therefore, the invention effectively overcomes various defects in the prior art and has high industrial utilization value.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (14)
1. A grid map generation method is characterized in that: the method comprises the following steps:
step S1, acquiring track data and point cloud data of the millimeter wave radar;
step S2, initializing a grid map based on the track data;
step S3, multiplying the point cloud data of the millimeter wave radar of the current frame with the corresponding track data to transform to a world coordinate system;
step S4, acquiring the position of the radar hit point in the grid map based on the point in the world coordinate system obtained by transformation;
step S5, respectively adjusting the probability value of the radar hit point and the probability value of the unoccupied point, and updating the grid map based on the adjusted probability values;
step S6, detecting whether the processing of the point cloud data of the millimeter wave radar of all frames is finished or not, responding to the fact that the processing of the point cloud data of the millimeter wave radar of all frames is not finished, and finishing the processing of the point cloud data of the millimeter wave radar of all other frames based on the processing process of the current frame;
and step S7, saving the grid map based on the probability value of the radar hit point in each frame.
2. The method for generating a grid map according to claim 1, characterized in that: in step S1, point cloud data of the millimeter wave radar satisfying the preset distance range is obtained.
3. The method for generating a grid map according to claim 1, characterized in that: in step S5, the implementation of adjusting the probability value of the radar hit point includes:
detecting whether the radar hit point is a first hit;
in response to the radar hit point being a first hit, marking the radar hit point and increasing a probability value of the radar hit point;
in response to the radar hit point not being the first hit, increasing a probability value for the radar hit point.
4. The method for generating a grid map according to claim 1 or 3, characterized in that: in step S5, the implementation of adjusting the probability value of the unoccupied point includes:
confirming that points except the radar hitting point on a connecting line between the radar hitting point and the position of the vehicle body are unoccupied points;
confirming whether the unoccupied point is marked;
in response to the unoccupied point being marked, keeping the probability value for that point unchanged;
in response to the unoccupied point not being marked, decreasing the probability value for the point.
5. The method for generating a grid map according to claim 1, characterized in that: in step S7, an implementation of saving the grid map based on the probability value of the radar hit point in each frame includes:
confirming whether the probability value of the radar hit point is greater than a probability threshold value;
responding to the probability value of the radar hit point being larger than the probability threshold value, confirming that the radar hit point is an occupied point and marking the occupied point as a first numerical value;
confirming whether the probability value of the radar hit point is equal to the initial value of a grid map;
responding to the probability value of the radar hit point being equal to the initial value of the grid map, confirming that the radar hit point is an unknown point and marking as a second numerical value;
and in response to the probability value of the radar hit point being less than or equal to the probability threshold value or in response to the probability value of the radar hit point not being equal to the initial value of the grid map, confirming that the radar hit point is an unoccupied point and marking the unoccupied point as a third numerical value.
6. The method for generating a grid map according to claim 1, characterized in that: in step S1, the trajectory data is acquired based on the visual SLAM data, the laser SLAM data, the vehicle body data, or the millimeter wave radar data.
7. A grid map generation system, characterized by: the method comprises the following steps:
the data acquisition module is used for acquiring track data and point cloud data of the millimeter wave radar;
an initialization module for initializing a grid map based on the trajectory data;
the coordinate transformation module is used for multiplying the point cloud data of the millimeter wave radar of the current frame with the corresponding track data to transform to a world coordinate system;
a hit point position acquisition module, configured to acquire, based on a point in the world coordinate system obtained through the transformation, a position of a radar hit point in the grid map;
the probability updating module is used for respectively adjusting the probability values of the radar hit points and the unoccupied points and updating the grid map based on the adjusted probability values;
the traversal detection module is used for detecting whether the processing of the point cloud data of the millimeter wave radars of all frames is finished or not, and the coordinate transformation module, the hit point position acquisition module and the probability updating module respond to the processing of the point cloud data of the millimeter wave radars which are not formed into all frames and continue to finish the processing of the point cloud data of the millimeter wave radars of all other frames;
and the map storage module is used for storing the grid map based on the probability value of the radar hit point in each frame.
8. The grid map generation system of claim 7, wherein: the data acquisition module acquires point cloud data of the millimeter wave radar meeting a preset distance range.
9. The grid map generation system of claim 7, wherein: the probability updating module comprises:
the first hit detection unit is used for detecting whether the radar hit point is a first hit;
and the probability increasing unit is used for responding to the fact that the radar hit point is the first hit, marking the radar hit point, increasing the probability value of the radar hit point, and responding to the fact that the radar hit point is not the first hit, and increasing the probability value of the radar hit point.
10. The system for generating a grid map according to claim 7 or 9, characterized in that: the probability updating module further comprises:
a connecting line point confirming unit for confirming that points on a connecting line between the radar hitting point and the vehicle body position except the radar hitting point are unoccupied points;
a marking confirmation unit configured to confirm whether the unoccupied dot is marked;
and the probability adjusting unit is used for responding to the fact that the unoccupied point is marked, keeping the probability value of the point unchanged, responding to the fact that the unoccupied point is not marked, and reducing the probability value of the point.
11. The grid map generation system of claim 1, wherein: the map saving module comprises:
an occupation point confirming unit, configured to confirm whether a probability value of the radar hit point is greater than a probability threshold, and in response to that the probability value of the radar hit point is greater than the probability threshold, confirm that the radar hit point is an occupation point and mark the occupation point as a first numerical value;
an unknown point confirming unit, configured to confirm whether a probability value of the radar hit point is equal to an initial value of the grid map, and in response to that the probability value of the radar hit point is equal to the initial value of the grid map, confirm that the radar hit point is an unknown point and mark the unknown point as a second numerical value;
and the unoccupied point confirming unit is used for confirming that the radar hit point is an unoccupied point and marking the unoccupied point as a third numerical value in response to that the probability value of the radar hit point is smaller than or equal to the probability threshold value or that the probability value of the radar hit point is not equal to the initial value of the grid map.
12. The grid map generation system of claim 7, wherein: the trajectory data acquired in the data acquisition module is generated based on visual SLAM data, laser SLAM data, vehicle body data or millimeter wave radar data.
13. An electronic device, characterized in that: comprising a processor and a memory, said memory storing program instructions; the processor executes the program instructions to realize the grid map generation method of any one of claims 1 to 6.
14. A storage medium storing program instructions which, when executed, implement a method of generating a grid map according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011445128.0A CN112581613A (en) | 2020-12-08 | 2020-12-08 | Grid map generation method and system, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011445128.0A CN112581613A (en) | 2020-12-08 | 2020-12-08 | Grid map generation method and system, electronic device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112581613A true CN112581613A (en) | 2021-03-30 |
Family
ID=75131097
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011445128.0A Pending CN112581613A (en) | 2020-12-08 | 2020-12-08 | Grid map generation method and system, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112581613A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114577216A (en) * | 2022-03-31 | 2022-06-03 | 美智纵横科技有限责任公司 | Navigation map construction method and device, robot and storage medium |
| WO2022237821A1 (en) * | 2021-05-14 | 2022-11-17 | 阿波罗智能技术(北京)有限公司 | Method and device for generating traffic sign line map, and storage medium |
| CN115469330A (en) * | 2022-10-28 | 2022-12-13 | 深圳市云鼠科技开发有限公司 | Subgraph construction method and device, terminal device and storage medium |
| CN116088489B (en) * | 2021-11-05 | 2024-02-27 | 北京三快在线科技有限公司 | Grid map updating method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104699099A (en) * | 2009-08-31 | 2015-06-10 | Neato机器人技术公司 | Method and apparatus for simultaneous localization and mapping of mobile robot environment |
| CN107209515A (en) * | 2014-09-01 | 2017-09-26 | 法雷奥开关和传感器有限责任公司 | Positioning and map drawing device and method |
| CN110007670A (en) * | 2019-02-14 | 2019-07-12 | 四川阿泰因机器人智能装备有限公司 | Localization for Mobile Robot builds drawing method |
| CN110045376A (en) * | 2019-04-28 | 2019-07-23 | 森思泰克河北科技有限公司 | It can travel area obtaining method, computer readable storage medium and terminal device |
| CN110398964A (en) * | 2019-07-16 | 2019-11-01 | 浙江大学 | A kind of low energy loss robot complete coverage path planning method and system |
| CN110570449A (en) * | 2019-09-16 | 2019-12-13 | 电子科技大学 | positioning and mapping method based on millimeter wave radar and visual SLAM |
| CN111307166A (en) * | 2018-12-11 | 2020-06-19 | 北京图森智途科技有限公司 | Method, device and processing equipment for constructing occupied grid map |
-
2020
- 2020-12-08 CN CN202011445128.0A patent/CN112581613A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104699099A (en) * | 2009-08-31 | 2015-06-10 | Neato机器人技术公司 | Method and apparatus for simultaneous localization and mapping of mobile robot environment |
| CN107209515A (en) * | 2014-09-01 | 2017-09-26 | 法雷奥开关和传感器有限责任公司 | Positioning and map drawing device and method |
| CN111307166A (en) * | 2018-12-11 | 2020-06-19 | 北京图森智途科技有限公司 | Method, device and processing equipment for constructing occupied grid map |
| CN110007670A (en) * | 2019-02-14 | 2019-07-12 | 四川阿泰因机器人智能装备有限公司 | Localization for Mobile Robot builds drawing method |
| CN110045376A (en) * | 2019-04-28 | 2019-07-23 | 森思泰克河北科技有限公司 | It can travel area obtaining method, computer readable storage medium and terminal device |
| CN110398964A (en) * | 2019-07-16 | 2019-11-01 | 浙江大学 | A kind of low energy loss robot complete coverage path planning method and system |
| CN110570449A (en) * | 2019-09-16 | 2019-12-13 | 电子科技大学 | positioning and mapping method based on millimeter wave radar and visual SLAM |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022237821A1 (en) * | 2021-05-14 | 2022-11-17 | 阿波罗智能技术(北京)有限公司 | Method and device for generating traffic sign line map, and storage medium |
| CN116088489B (en) * | 2021-11-05 | 2024-02-27 | 北京三快在线科技有限公司 | Grid map updating method and device |
| CN114577216A (en) * | 2022-03-31 | 2022-06-03 | 美智纵横科技有限责任公司 | Navigation map construction method and device, robot and storage medium |
| CN115469330A (en) * | 2022-10-28 | 2022-12-13 | 深圳市云鼠科技开发有限公司 | Subgraph construction method and device, terminal device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112581613A (en) | Grid map generation method and system, electronic device and storage medium | |
| CN113158763B (en) | Three-dimensional target detection method based on multi-view feature fusion of 4D millimeter waves and laser point clouds | |
| CN109059902B (en) | Relative pose determination method, device, equipment and medium | |
| CN107341819B (en) | Target tracking method and storage medium | |
| CN111771141B (en) | LIDAR positioning for solution inference using 3D CNN network in autonomous vehicles | |
| CN111971574B (en) | Deep learning based feature extraction for LIDAR localization of autonomous vehicles | |
| CN111771135B (en) | LIDAR positioning using RNN and LSTM for time smoothing in autonomous vehicles | |
| Homm et al. | Efficient occupancy grid computation on the GPU with lidar and radar for road boundary detection | |
| US11045953B2 (en) | Relocalization method and robot using the same | |
| CN112513679B (en) | Target identification method and device | |
| CN109849930B (en) | Method and device for calculating speed of adjacent vehicle of automatic driving automobile | |
| JP7224682B1 (en) | 3D multiple object detection device and method for autonomous driving | |
| CN114111774B (en) | Vehicle positioning method, system, equipment and computer readable storage medium | |
| CN110969055A (en) | Method, apparatus, device and computer-readable storage medium for vehicle localization | |
| US20230206500A1 (en) | Method and apparatus for calibrating extrinsic parameter of a camera | |
| CN115079168B (en) | Mapping method, device and equipment based on fusion of laser radar and millimeter wave radar | |
| Li et al. | Robust localization for intelligent vehicles based on compressed road scene map in urban environments | |
| CN115346192A (en) | Data fusion method, system, equipment and medium based on multi-source sensor perception | |
| WO2023216555A1 (en) | Obstacle avoidance method and apparatus based on binocular vision, and robot and medium | |
| CN116466712A (en) | Autonomous cruising method and system based on CML-AVG laser radar trolley | |
| CN112835063B (en) | Method, device, equipment and storage medium for determining dynamic and static properties of object | |
| CN114061573A (en) | Ground unmanned vehicle formation positioning device and method | |
| CN115147612B (en) | Processing method for estimating vehicle size in real time based on accumulated point cloud | |
| Song et al. | Target detection based on 3d multi-component model and inverse projection transformation | |
| CN115527034A (en) | Vehicle end point cloud dynamic and static segmentation method, device and medium |
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 |