CN115151954A - Method and device for detecting a drivable region - Google Patents
Method and device for detecting a drivable region Download PDFInfo
- Publication number
- CN115151954A CN115151954A CN202080097562.6A CN202080097562A CN115151954A CN 115151954 A CN115151954 A CN 115151954A CN 202080097562 A CN202080097562 A CN 202080097562A CN 115151954 A CN115151954 A CN 115151954A
- Authority
- CN
- China
- Prior art keywords
- grid
- laser
- height
- ground
- map
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Optical Radar Systems And Details Thereof (AREA)
- Traffic Control Systems (AREA)
Abstract
The application discloses a method and a device for detecting a drivable area, which belong to the technical field of automatic driving, and comprise the following steps: and acquiring laser point cloud of a detectable area of the automatic driving platform. And generating a grid map corresponding to the laser point cloud. An initial ground grid is determined among the grids of the grid map. Based on the determined initial ground grid, a target ground grid is determined in the grid map. And taking the area corresponding to the determined initial ground grid and the target ground grid as a travelable area. The method can accurately detect the travelable area in severe weather.
Description
The present disclosure relates to the field of automatic driving technologies, and in particular, to a method and an apparatus for detecting a travelable region.
In autonomous driving, travelable region detection of a vehicle is one of key technologies in unmanned technology.
At present, the detection of the driving-capable area of the automatic driving vehicle can be realized by shooting an image of a certain area in front of the vehicle through a camera on the automatic driving vehicle, identifying the image through a machine learning model and a computer vision technology, judging a driving-capable road and obstacles influencing the driving of the vehicle, and identifying trees and other objects which do not influence the driving of the vehicle.
In the process of implementing the present application, the inventors found that the related art has at least the following problems:
the travelable area and the obstacle cannot be accurately identified by the images shot in the severe environments such as heavy fog and heavy rain, so the detection accuracy of the method is low in the severe environments such as heavy fog and heavy rain.
Disclosure of Invention
The embodiment of the application provides a method and a device for detecting a travelable area, so as to solve the problem of large travelable area detection error in the related art.
In a first aspect, the present application provides a method for detecting a travelable area, including:
acquiring laser point cloud of a detectable area of the automatic driving platform;
generating a grid map corresponding to the laser point cloud, wherein each laser point in the laser point cloud corresponds to a grid in the grid map;
determining an initial ground grid in each grid of the grid map;
determining a target ground grid in the grid map based on the initial ground grid;
and taking the determined area corresponding to the initial ground grid and the target ground grid as a travelable area.
According to the scheme shown in the embodiment of the application, the automatic traveling platform can be an automatic driving automobile, an intelligent robot and the like, and the grid map can be a polar coordinate grid or a rectangular coordinate grid. The autonomous traveling platform may be installed with a laser radar, which may be generally installed on the top or in the front of the autonomous traveling platform in order to effectively detect obstacles in the traveling direction. During the driving process of the automatic driving platform, the laser radar can emit laser lines to the detectable area of the surrounding environment of the automatic driving platform so as to scan the surrounding environment. The laser line can be reflected when contacting the ground, trees, obstacles, buildings and the like, and the laser radar can receive reflected echoes so as to obtain laser point clouds in the detectable area. A grid pattern is then generated such that each laser spot will be in a grid of the grid pattern. Then, an initial grid is determined among the grids of the grid map. Then, with the determined initial ground grids as reference, the target ground grid is determined in the grid map. And finally, taking the determined areas corresponding to the initial ground grid and the target ground grid as travelable areas. The method comprises the steps of firstly obtaining laser point clouds of an area, then rasterizing the laser point clouds, then determining an initial ground grid in a grid, and further continuously determining a target ground grid in the grid by taking the initial ground grid as a reference. Therefore, the method realizes the detection of the travelable area through the laser, can adapt to severe environment, and avoids the false detection possibly caused by the image recognition technology in severe weather.
In one possible implementation, before determining an initial ground grid in the grid of the grid map, the method further includes:
and for each grid in the grid map, layering the laser points in the grid to obtain at least one point layer.
According to the scheme shown in the embodiment of the application, for each grid including laser points, the laser points in the grid can be layered according to the preset travelable height and the height of the laser points in the grid, and a set of the laser points in each layer can be called a point layer. The layering principle is as follows: the minimum height difference of the laser points between different point layers is larger than the preset travelable height. Therefore, when the grid is detected subsequently, only the point layer with the minimum average height can be detected, all laser points in the grid do not need to be detected, and the detection speed is improved.
In one possible implementation, the determining an initial ground grid among the grids of the grid map includes:
determining an initial ground grid among the grids of the grid map based on the distance between the grids of the grid map and the automatic traveling platform and the height of the laser spot in a target point layer with the smallest average height of the laser spots in the grids of the grid map, wherein the target point layer belongs to the at least one point layer.
According to the scheme shown in the embodiment of the application, the initial ground grid can be determined in each grid in the grid map according to the distance between the grid and the automatic driving platform and the height of the laser point in the target point layer with the minimum average height of the grid.
In one possible implementation, the determining a target ground grid in the grid map based on the initial ground grid includes:
taking the initial ground grid as a reference grid, and taking the average height of the laser points in the target point layer with the minimum average height of the laser points in the initial ground grid as the reference ground height corresponding to the initial ground grid;
taking the grid with the reference grid meeting the preset proximity condition as a grid to be detected;
determining a target ground grid in the grid to be detected based on the reference ground height corresponding to the reference grid and the average height of the laser points in the target point layer with the minimum average height of the laser points in the grid to be detected;
and taking the determined target ground grid as a reference grid, taking the average height of the laser points in a target point layer with the minimum average height of the laser points in the target ground grid as the reference ground height corresponding to the target ground grid, and turning to execute the step of taking the grid of which the reference grid meets the preset proximity condition as the grid to be detected.
According to the scheme shown in the embodiment of the application, after the initial ground grid is determined, the initial ground grid can be used as a reference grid, the grid of which the initial ground grid meets the preset proximity condition is used as the grid to be detected, and whether the grid to be detected is the target ground grid or not is detected. And then, taking the detected target ground grid as a reference grid, taking the grid of which the target ground grid meets a preset proximity condition as a to-be-detected grid, continuously judging whether the to-be-detected grids are the target ground grids, and the like. Thus, in determining whether each grid is a ground grid, reference is made to its neighboring already determined ground grid, which is more accurate than merely the underlying grid itself.
In one possible implementation, the grid map is a polar grid map;
determining an initial ground grid in each grid based on the distance between the grid and the automatic driving platform and the average height of the laser points in the target point layer with the smallest average height of the laser points in the grid, including:
and respectively determining initial ground grids in radial grids of the polar coordinate grid graph from the grid with the minimum distance from the automatic driving platform along the radial direction based on the height of the laser points in the target point layer with the minimum average height of the laser points in the grids.
According to the scheme shown in the embodiment of the application, in the radial direction of each angle in the polar coordinate grid diagram, whether the grid is the initial ground grid or not is judged outwards in sequence from the grid which is closest to the automatic traveling platform and comprises the laser point until the initial ground grid in the radial direction is determined.
In one possible implementation, the generating a grid map corresponding to the laser point cloud includes:
the grid graph is a polar coordinate grid graph;
the grid of the reference grid satisfying the preset proximity condition is the grid including the laser spot next to the reference grid in the radial direction.
In one possible implementation, the grid map is a rectangular coordinate grid map;
determining an initial ground grid in each grid based on the distance between the grid and the automatic driving platform and the average height of the laser points in the target point layer with the smallest average height of the laser points in the grid, including:
and determining an initial ground grid based on the height of the laser point in the target point layer with the minimum average height of the laser points in the grids in a first preset range around the automatic driving platform in the rectangular coordinate grid map.
According to the scheme shown in the embodiment of the application, for the condition of rectangular coordinates, the initial ground grid can be determined in the first preset range around the automatic traveling platform. The first preset range is a range close to the automatic driving platform. For example, the first preset range may be a range set to 8m × 8m around the automated travel platform.
In one possible implementation, the grid map is a rectangular coordinate grid map;
and the grid of which the reference grid meets the preset proximity condition is the grid in a second preset range around the reference grid.
In the solution shown in the embodiment of the present application, the second preset range may be a grid in the neighborhood of 3*3 centered on the reference grid, for example, as shown in fig. 12, R22 is the reference grid, and the eight surrounding grids R11, R12, R13, R21, R23, R31, R32, and R33 are the second preset range.
In one possible implementation, the layering, for each grid in the grid map, laser points in the grid includes:
acquiring laser points in the grid one by one according to the sequence of the heights from small to large;
and if the absolute value of the difference between the height of the currently acquired laser point and the height of the previously acquired laser point is smaller than the preset travelable height, dividing the currently acquired laser point to the point layer where the previously acquired laser point is located, otherwise, dividing the currently acquired laser point to a newly built point layer.
According to the scheme shown in the embodiment of the application, the laser points in the grid are sequenced according to the heights. When the 1 st laser spot is acquired by starting from the laser spot with the minimum height one by one, a point layer is created, and the 1 st laser spot is divided into the created point layers. Continuously acquiring the laser points, and acquiring the height z of the ith laser point currently acquired i And the height z of the i-1 th laser spot acquired previously i-1 Making a comparison if z i And z i-1 And if the difference is smaller than the preset travelable height h, dividing the ith laser point into the point layer where the (i-1) th laser point is located, otherwise, newly building a point layer, and dividing the ith laser point into the newly built point layer. By this method, the minimum height difference of the laser spots between different spot layers can be made larger than the preset travelable height.
In a second aspect, there is provided an apparatus for travelable region detection, the apparatus comprising:
the acquisition module is used for acquiring laser point cloud of a detectable area of the automatic driving platform;
the generating module is used for generating a grid map corresponding to the laser point cloud, wherein each laser point in the laser point cloud corresponds to a grid in the grid map;
the determining module is used for determining an initial ground grid in each grid of the grid map, determining a target ground grid in the grid map based on the initial ground grid, and taking an area corresponding to the determined initial ground grid and the target ground grid as a travelable area.
In one possible implementation, the apparatus further includes:
and for each grid in the grid map, layering the laser points in the grid to obtain at least one point layer.
In a possible implementation manner, the determining module is configured to:
determining an initial ground grid among the grids of the grid map based on the distance between the grid in the grid map and the automatic traveling platform and the height of the laser point in a target point layer where the average height of the laser points in the grid map is the smallest, the target point layer belonging to the at least one point layer.
In one possible implementation manner, the determining module is configured to:
taking the initial ground grid as a reference grid, and taking the average height of the laser points in a target point layer with the minimum average height of the laser points in the initial ground grid as the reference ground height corresponding to the initial ground grid;
taking the grid with the reference grid meeting the preset proximity condition as a grid to be detected;
determining a target ground grid in the grid to be detected based on the reference ground height corresponding to the reference grid and the average height of the laser points in the target point layer with the minimum average height of the laser points in the grid to be detected;
and taking the determined target ground grid as a reference grid, taking the average height of the laser points in a target point layer with the minimum average height of the laser points in the target ground grid as the reference ground height corresponding to the target ground grid, and turning to execute the step of taking the grid of which the reference grid meets the preset proximity condition as the grid to be detected.
In one possible implementation, the grid map is a polar grid map;
determining an initial ground grid in each grid based on the distance between the grid and the automatic driving platform and the average height of the laser points in the target point layer with the smallest average height of the laser points in the grid, including:
and respectively determining initial ground grids in radial grids of the polar coordinate grid graph from the grid with the minimum distance from the automatic driving platform along the radial direction based on the height of the laser points in the target point layer with the minimum average height of the laser points in the grids.
In a possible implementation manner, the generating module is configured to:
the grid graph is a polar coordinate grid graph;
the grid of the reference grid satisfying the preset proximity condition is the grid including the laser spot next to the reference grid in the radial direction.
In one possible implementation, the grid map is a rectangular coordinate grid map;
the determining module is configured to:
and determining an initial ground grid based on the height of the laser point in the target point layer with the minimum average height of the laser points in the grids in a first preset range around the automatic driving platform in the rectangular coordinate grid map.
In one possible implementation, the grid map is a rectangular coordinate grid map;
and the grid of which the reference grid meets the preset proximity condition is the grid in a second preset range around the reference grid.
In one possible implementation, the layering module is configured to:
acquiring laser points in the grid one by one according to the sequence of the heights from small to large;
and if the absolute value of the difference between the height of the currently acquired laser point and the height of the previously acquired laser point is smaller than the preset travelable height, dividing the currently acquired laser point to the point layer where the previously acquired laser point is located, otherwise, dividing the currently acquired laser point to a newly built point layer.
In a third aspect, a decision controller is provided, which includes a processor and a memory;
the memory stores one or more programs configured to be executed by the processor for implementing the travelable region detection method of the first aspect described above.
In a fourth aspect, a computer-readable storage medium is provided, comprising computer-readable instructions, which, when run on a decision controller, cause the decision controller to perform the method of travelable area detection of the first aspect.
In a fifth aspect, there is provided a computer program product comprising instructions which, when run on a decision controller, cause the decision controller to perform the method of travelable area detection of the first aspect described above.
The technical scheme provided by the application at least comprises the following beneficial effects:
according to the method, the laser point cloud is firstly acquired, the acquired laser points are divided into grids, initial ground grids are determined in the grids, and then each initial ground grid is used as a reference to continuously determine the target ground grid. And finally, taking the determined areas corresponding to the initial ground grid and the target ground grid as travelable areas. In this way, since the travelable region is determined based on the laser point, the laser has better penetrability and is minimally affected by the environment, and the travelable region can be detected more accurately even in severe environments such as heavy fog and heavy rain.
Fig. 1 is a schematic structural diagram of a decision controller according to an embodiment of the present application;
fig. 2 is a flowchart of a method for detecting a travelable area according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a lidar coordinate system provided by an embodiment of the present application;
fig. 4 is a schematic diagram of a polar grid diagram provided in an embodiment of the present application;
FIG. 5 is a schematic diagram of a grid rectangular coordinate diagram provided by an embodiment of the present application;
FIG. 6 is a schematic diagram of a dot layer provided by an embodiment of the present application;
fig. 7 is a flowchart of a method for detecting a travelable area according to an embodiment of the present disclosure;
fig. 8 is a flowchart of a method for detecting a travelable area according to an embodiment of the present disclosure;
FIG. 9 is a schematic diagram of a rectangular grid map provided by an embodiment of the present application;
fig. 10 is a flowchart of a method for detecting a travelable area according to an embodiment of the present application;
fig. 11 is a flowchart of a method for detecting a travelable area according to an embodiment of the present disclosure;
FIG. 12 is a schematic diagram of a grid orthogonal coordinate diagram provided by an embodiment of the present application;
fig. 13 is a schematic structural diagram of a device for detecting a travelable region according to an embodiment of the present application.
To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
The embodiment of the application provides a method for detecting a drivable area, which can be applied to automatic driving platforms such as automatic driving automobiles and intelligent robots. The method can be realized by decision controllers of various automatic driving platforms. Sensing systems, such as lidar, may be deployed in various autonomous driving platforms. The decision controller judges the drivable area by acquiring the data acquired by the sensing system, so as to control the automatic driving platform to drive.
Fig. 1 is a schematic diagram of a decision controller 100 according to an embodiment of the present disclosure. In fig. 1, the decision controller may comprise a processor 101 and a memory 102. The processor 101 may be a Central Processing Unit (CPU). The processor 101 may refer to one processor or may include a plurality of processors. Memory 102 may include volatile memory, such as Random Access Memory (RAM); the memory may also include non-volatile memory, such as read-only memory (ROM), flash memory, etc.; the memory may also comprise a combination of memories of the kind described above. The memory 102 may refer to one memory or may include a plurality of memories. In one embodiment, the memory 102 stores computer readable instructions, which can be executed by the processor 101 to implement the method for detecting a travelable area provided by the embodiment of the present application.
The embodiment of the application provides a method for detecting a travelable area, and as shown in fig. 2, a processing flow of the method may include the following steps:
The automatic driving platform can be an automatic driving automobile, an intelligent robot and the like.
In practice, the autonomous platform may be equipped with a lidar, which may be typically mounted on top of or in front of the autonomous platform in order to effectively detect obstacles in the direction of travel. The lidar may be a multi-line lidar, a micro-electro-mechanical system (MEMS) lidar, an area array FLASH (FLASH) lidar, or the like.
During the driving process of the automatic driving platform, the laser radar can emit laser lines to the detectable area of the surrounding environment of the automatic driving platform so as to scan the surrounding environment. The laser line can be reflected when contacting the ground, trees, obstacles, buildings and the like, and the laser radar can receive reflected echoes so as to obtain laser point clouds in the detectable area. The following describes the acquisition of three-dimensional coordinates of each laser spot in the laser point cloud.
The reflected echo is processed to obtain the emission angle and the scanning distance d of the laser line corresponding to the echo, where the emission angle includes a horizontal angle α and a vertical angle β, and fig. 3 shows a schematic diagram of a laser spot in a lidar coordinate system. Therefore, the three-dimensional coordinates of the laser point of the laser line on the object in the laser radar coordinate system can be calculated as follows: (x, y, z), wherein:
x＝cosα·sinβ·d
y＝cosα·cosβ·d
z＝sinβ·d
and then, converting the three-dimensional coordinates of the laser point in the laser radar coordinate system into the coordinate system of the automatic traveling platform. When the automatic driving platform is an automatic driving vehicle, the coordinate system of the automatic driving platform can use the middle point of the rear axle of the automatic driving vehicle as the origin, the driving direction is the positive direction of a transverse (X) axis, the left side is the positive direction of a longitudinal (Y) axis, and the vertical direction is the positive direction of a vertical (Z) axis. Of course, the coordinate system of the autopilot platform may also be calibrated in other manners, which is not limited in the embodiment of the present application. The conversion method for converting the three-dimensional coordinate of the laser point in the laser radar coordinate system into the automatic traveling platform coordinate system can be as follows:
p '= R.P + T, wherein P' is the three-dimensional coordinate of the laser point under the coordinate system of the automatic driving platform, P is the three-dimensional coordinate of the laser point under the coordinate system of the automatic driving platform, R is a rotation matrix, T is a translation matrix, and R and T can be obtained by calibrating the coordinate system of the laser radar and the coordinate system of the automatic driving platform in advance. Here, the calibration may be implemented by using a plane segmentation matching algorithm estimated by a random sample consensus (RANSAC) model, or may be implemented by using other methods, which is not limited in the embodiment of the present application.
Here, it should be further noted that P 'is a three-dimensional coordinate of the laser point in the autopilot platform coordinate system, and a vertical coordinate of P' indicates a height of the laser point in the laser point autopilot platform coordinate system.
In a possible implementation, since the laser radar is usually installed on the top of the automatic traveling platform, some laser lines may be swept onto the automatic traveling platform, and laser points obtained by sweeping the laser lines onto the automatic traveling platform may be eliminated. The removing method can be as follows:
the bounding box of the automatic driving platform is established under the automatic driving platform, and the bounding box can be a minimum cuboid which completely encloses the automatic driving platform. And eliminating the laser points falling in the bounding box from the laser point cloud. Namely, the laser points with the horizontal coordinate, the vertical coordinate and the vertical coordinate all in the coordinate range of the bounding box are removed. In addition, since the objects above the automatic traveling platform do not influence the normal traveling of the automatic traveling platform, the laser points obtained by scanning the objects can be eliminated. In other words, the laser points within the coordinate range of the bounding box are eliminated in both the abscissa and the ordinate.
Each laser point in the laser point cloud corresponds to a grid in the grid map, and one grid may have no laser point or one or more laser points.
In implementation, first, the laser point cloud is reduced in dimension. That is, the laser point cloud is projected onto a two-dimensional plane of Z =0 in the above-mentioned automatic traveling platform coordinate system, and the height of each laser point is stored as the feature data of the laser point. Then, a grid map may be generated on the laser point cloud within the two-dimensional plane, dividing the laser points into each grid of each grid map. The grid map may be a polar grid map, a rectangular grid map, or the like, and the polar grid and the rectangular grid will be described below.
1. Grid diagram of polar coordinates
The polar coordinate grid graph can be generated for an area within a preset range around the automatic traveling platform, the original point of the coordinate system of the automatic traveling platform is used as the original point, a polar coordinate system is established, and the polar coordinate grid graph is divided under the polar coordinate according to a preset angle resolution and a preset radial resolution. For example, as shown in fig. 4, the polar grid pattern is a polar grid pattern generated with a radial resolution of 0.2m at an angle of 0.5 degrees and within a radial distance of 30 meters (m), a radial resolution of 0.5m at 30m to 60m, and a radial resolution of 1m at 60m or more in fig. 4. In fig. 4, grid a, grid B, and grid C are in the same radial direction in the polar grid diagram, where grid B is the next grid in the radial direction of grid a, and grid C is the next grid in the radial direction of grid B.
2. Rectangular coordinate grid diagram
Rectangular coordinate grid maps can be generated for areas within a preset range around the automatic traveling platform, and each grid in the rectangular coordinate grid maps has the same size and rectangle. For example, as shown in fig. 5, fig. 5 is a rectangular grid diagram generated for an area of 80m around the automatic traveling platform and 60m around the automatic traveling platform, and each grid in the grid diagram is a square with a side of 0.2m.
Wherein the distance between the grid and the autopilot platform may be the distance from the center to the autopilot platform.
In implementation, for each grid including laser points, the laser points in the grid may be layered according to a preset travelable height and the heights of the laser points in the grid, and a set of laser points of each layer may be referred to as a point layer. The layering principle is as follows: the minimum height difference of the laser points between different point layers is larger than the preset travelable height. There are many methods of layering based on this layering principle, and several methods are listed below.
The first method,
Laser spots are acquired one by one, when the 1 st laser spot is acquired, a spot layer is created, and the 1 st laser spot is divided into the created spot layers. Continuously acquiring laser points, and when an ith laser point is acquired, judging whether a target point layer exists in the existing point layer or not to meet the following conditions:
H-h＜z i < L-H, where H is the maximum height of the laser spot in any existing spot layer, L is the minimum height of the laser spot in that existing spot layer, and z i The height of the ith laser spot, h is the preset travelable height, and may be set to a value slightly greater than the height of the automated travel platform, for example, the height of the automated travel platform plus 0.1m.
If a target dotted layer satisfying the above condition is determined, the ith laser spot is classified into the target dotted layer. If a plurality of target existing point layers meeting the condition are determined to be point layers, the plurality of target existing point layers are combined, and the ith laser point is divided into the combined point layers.
The second method,
The laser spots in the grid are sorted by elevation. When the laser points with the minimum height are acquired one by one, and the 1 st laser point is acquired, a point layer is created, and the 1 st laser point is divided into the created point layers. Continuing to acquire the laser spot and acquiring the current laser spotHeight z of the ith laser spot of (1) i And the height z of the i-1 th laser spot acquired previously i-1 Making a comparison if z i And z i-1 And if the difference is smaller than the preset travelable height h, dividing the ith laser point into the point layer where the (i-1) th laser point is located, otherwise, newly building a point layer, and dividing the ith laser point into the newly built point layer.
After layering the laser points of the grid, an initial ground grid may be determined in each grid of the grid map based on the distance between the grid and the autonomous driving platform in the grid map and the height of the laser point in the target point layer where the average height of the laser points in the grid map is the smallest. The following describes a method for determining an initial ground grid in the case of a polar grid map and a rectangular grid map.
1. In the case of the polar grid diagram, as shown in fig. 7, the following processing is possible in this case.
And in the radial direction of each angle in the grid map, starting from the grid which is closest to the automatic driving platform and comprises the laser points, sequentially judging whether the grid is an initial ground grid or not outwards until the initial ground grid in the radial direction is determined. The determination method may be as follows.
701. And acquiring the grid with the minimum distance from the automatic traveling platform in each radial direction in the grid map as the grid to be detected.
702. And acquiring a target point layer with the minimum average height of the laser points in the grid to be detected.
703. And determining whether the heights of all the laser points in the target point layer are within a preset height range, and the maximum height difference of the laser points in the target point layer is smaller than a first height difference threshold value.
Wherein the preset height range may be [ h ] 0 -Δh，h 0 +Δh]，h 0 The height from the origin of the coordinate system of the automatic traveling platform to the ground can be called as the calibrated ground height and can be obtained through factory calibration. The preset height range may be set according to the following criteria: the ground which is fluctuated within a certain height range does not influence the running of the automatic running platform. For example, theThe height fluctuation range Δ h may be set to 0.2m. The first height difference threshold may be set according to: since obstacles are usually high and thus influence the traffic, for example 1m, the maximum height difference of the laser spot swept over the obstacle may reach about 1m, while for a ground meeting the road grade specification, the maximum height difference of the laser spot swept over the ground may be about 0.1m, and further, due to some error in the lidar ranging, the first height difference threshold may be set relatively large, for example, between 0.1m and 0.2m.
704. And if the heights of all the laser points in the target point layer are within the preset height range and the maximum height difference of the laser points in the target point layer is smaller than a first height difference threshold value, determining the grid to be detected as an initial ground grid, and determining the average height of the laser points in the target point layer as a reference ground height corresponding to the initial ground grid.
705. And if the laser point with the height not within the preset height range exists in the target point layer, or the maximum height difference of the laser point in the target point layer is not smaller than a first height difference threshold value, determining whether the absolute value of a first difference value between the minimum height of the laser point in the target point layer and the calibrated ground height is larger than the preset travelable height.
706. If the absolute value of the first difference is greater than the preset travelable height, the to-be-detected cell is determined as an overhead cell, and the cell including the laser spot next to the overhead cell in the radial direction is taken as the to-be-detected cell, and the process goes to execute step 702.
Due to the limitations of the scanning angle of the lidar, the following situations may occur: the ground around the running platform cannot be scanned by the laser radar, and a suspended object, such as a banner, is arranged above the ground which is not scanned by the laser radar, and the suspended object can be scanned by the laser radar.
Then there is only the laser spot of the flying object in the grid corresponding to this area. Because the suspended object is very high, the height of the corresponding laser point is much larger than the height of the calibrated ground, and the grid cannot meet the condition of the ground grid in the step 701. In step 706, by determining that the first difference between the minimum height of the laser point and the calibrated ground height is greater than the preset travelable height, it can be identified that the region corresponding to the grid has a suspended object, but the automatic traveling platform is passable. Then the grid may be determined to be a high altitude grid and not to be determined to be an obstacle.
707. And if the absolute value of the first difference is not less than the preset travelable height, determining the grid to be detected as the barrier grid.
Corresponding to the situation of 706, if the suspended object is a handrail, then in step 707, by determining that the first difference between the minimum height of the laser point and the calibrated ground height is smaller than the preset travelable height, it can be identified that there is a suspended object in the area corresponding to the grid, and the height between the suspended object and the ground is not enough for the automatic traveling platform to pass through. Then the grid may be determined as an obstacle grid.
2. In the case of the rectangular grid map, as shown in fig. 8, the following processing is possible in this case.
801. And determining the grids including the laser points in a first preset range around the automatic driving platform as the grids to be detected.
The first preset range is a range close to the automatic driving platform. For example, as shown in fig. 9, the first preset range may be a range set to 8m × 8m around the automated driving platform.
802. And acquiring a target point layer with the minimum average height of the laser points in the grid to be detected.
803. And determining whether the heights of all the laser points in the target point layer are within a preset height range, and the maximum height difference of the laser points in the target point layer is smaller than a first height difference threshold value.
804. And if the heights of the laser points in the target point layer are all within the preset height range and the maximum height difference of the laser points in the target point layer is smaller than a first height threshold value, determining the average height of the laser points in the target point layer as the reference ground height corresponding to the grid to be detected, determining the grid to be detected as the initial ground grid, and marking the grid to be detected as detected.
805. And if the laser point with the height not within the preset height range exists in the target point layer, or the maximum height difference of the laser point in the target point layer is not smaller than a first height difference threshold value, determining whether the absolute value of a first difference value between the minimum height of the laser point in the target point layer and the calibrated ground height is smaller than the preset travelable height.
806. And if the absolute value of the first difference is smaller than the preset travelable height, determining the grid to be detected as the barrier grid and marking the grid to be detected as detected.
And if the absolute value of the first difference is larger than the preset travelable height, not marking the grid to be detected as detected so as to carry out rechecking on the grid to be detected later.
By the method, the ground grids around the automatic traveling platform can be determined in the rectangular coordinate grid diagram and the polar coordinate grid diagram.
After the initial ground grid is determined, it may be determined whether a grid adjacent to the initial ground grid is a target ground grid, an overhead grid, or an obstacle grid, with the determined initial ground grid as a reference. Next, methods for determining whether a target land grid, an overhead grid, or an obstacle grid is used in the case of the polar grid map and the rectangular grid map will be described.
1. In the case of the polar grid diagram, as shown in fig. 10, the following processing is possible in this case.
1001. Determining the determined initial ground grid as a reference grid;
1002. the next grid in the radial direction of the reference grid, which includes the laser spot, is acquired as the grid to be detected.
1003. And acquiring a target point layer with the minimum average height of the laser points in the to-be-detected grid.
1004. And calculating the gradient of the target point layer relative to the reference grid based on the average height of the laser points in the target point layer and the reference ground height corresponding to the reference grid.
The gradient calculation method may be as follows:
s＝(z current -z last )/(r current -r last )
where s is the slope of the target point layer relative to the reference grid, z current Is the average height of the laser spot in the target spot layer, z last Reference ground height, r, for a reference grid current Distance r from center to origin of grid to be detected last Is the distance from the center of the reference grid to the origin.
1005. And determining whether the absolute value of the gradient is smaller than a preset gradient threshold value or not, and the maximum height difference of the laser point in the target point layer is smaller than a first height difference threshold value.
Wherein the preset gradient threshold value may be set between 0.1 and 0.15, such as 0.15, in consideration of the road gradient specification and the ranging error of the laser radar.
1006. And if the absolute value of the slope is smaller than a preset slope threshold value and the maximum height difference of the laser points in the target point layer is smaller than a first height difference threshold value, determining the grid to be detected as a target ground grid, determining the average height of the laser points in the target point layer as a reference ground height corresponding to the target ground grid, and determining the slope as a reference ground slope corresponding to the target ground grid. Determining the target ground grid as the reference grid proceeds to step 1002.
1007, if the slope is not less than the preset slope threshold, or the maximum height difference of the laser points in the target point layer is not less than the first height difference threshold, determining whether the slope is greater than zero.
1008. And if the gradient is larger than zero, determining the estimated ground height of the grid to be detected based on the reference ground height and the reference ground gradient corresponding to the reference grid.
The calculation method of the estimated ground height can be as follows:
z current ′＝z last +s last ×(r current -r last )
wherein z is current ' estimated ground height, z, of the grid to be inspected last Reference ground height, r, for a reference grid current Distance r from center to origin of grid to be detected last For the distance from the centre of the reference grid to the origin, s last Is the reference ground slope corresponding to the reference grid. It should be noted that if the reference grid is the ground grid closest to the autonomous driving platform, the reference ground slope may be set to 0.
1009. Determining whether an absolute value of a second difference between the estimated ground height and a minimum height of the laser spot in the target point layer is greater than a preset travelable height.
1010. And if the absolute value of a second difference between the estimated ground height and the minimum height of the laser point in the target point layer is greater than the preset drivable height, determining the grid to be detected as a high-altitude grid, determining the estimated ground height as a reference ground height corresponding to the high-altitude grid, and determining a reference ground slope corresponding to the reference grid as a reference ground slope corresponding to the high-altitude grid. The high-altitude grid is determined as the reference ground grid, and the process goes to step 1002.
Due to the limitations of the scanning angle of the lidar, the following situations may occur: on the ground, which is far from the autonomous platform, the lidar may not be able to scan, but the suspended objects on the ground may be scanned. In this case, the calculated slope is greater than 0, and if the suspended object is high enough not to affect the traffic, such as a swath, the absolute value of the second difference between the calculated estimated ground height and the minimum height of the laser spot in the target point layer is greater than the preset travelable height, and the grid can be determined to be a high altitude grid. In this case, the area corresponding to the grid actually has the ground, but is not scanned, and then, the estimated ground height may be used as the reference ground height corresponding to the high-altitude grid, and the high-altitude grid is used as a reference to determine which grid the next grid in the radial direction is.
1011. And if the absolute value of the second difference is smaller than the preset travelable height, determining the grid to be detected as the obstacle grid. If the obstacle grid is determined, the grids following the obstacle grid in the radial direction are not detected any more.
1012. And if the gradient is smaller than zero, determining the grid to be detected as an obstacle grid.
In the case that the slope is smaller than 0, it may be that the area corresponding to the grid to be detected is a downhill slope or a sunken ground, and the slope is too large or the sunken depth cannot pass through, then the grid to be detected may be determined as an obstacle grid.
2. In the case of the rectangular grid map, as shown in fig. 11, the following processing is possible in this case.
1101. And taking the determined initial ground grid as a reference grid.
1102. And determining grids which are not marked as detected in a second preset range around the reference grid as the grids to be detected.
The second predetermined range may be a grid of the 3*3 neighborhood centered on the reference grid. That is, for example, as shown in fig. 12, R22 is a reference grid, and the eight grids R11, R12, R13, R21, R23, R31, R32, and R33 around it are the second preset range.
1103. It is determined whether the grid to be detected includes a laser spot.
1104. And if the grid to be detected does not comprise the laser point, determining the reference ground height corresponding to the reference grid as the reference ground height corresponding to the grid to be detected, determining the grid to be detected as the ground grid, and marking the grid to be detected as the detected ground grid. Taking the target ground grid as the reference grid, go to step 1102.
1105. And if the grid to be detected comprises the laser points, acquiring a target point layer with the minimum average height of the laser points in the grid to be detected.
1106. It is determined whether an absolute value of a third difference between the average height of the laser spots in the target point layer and a reference ground height corresponding to the reference grid is less than a second height threshold, and a maximum height difference of the laser spots in the target point layer is less than the first height difference threshold.
1107. And if the absolute value of a third difference value between the average height of the laser points in the target point layer and the reference ground height corresponding to the reference grid is smaller than a second height threshold value, and the maximum height difference of the laser points in the target point layer is smaller than a first threshold value, determining the average height of the laser points in the target point layer as the reference ground height corresponding to the grid to be detected, determining the grid to be detected as the target ground grid, and marking the grid to be detected as the detected grid. Taking the target ground grid as the reference grid, go to step 1102.
1108. And if the absolute value of a third difference value between the average height of the laser points in the target point layer and the reference ground height corresponding to the reference grid is not less than a second height threshold value, or the maximum height difference of the laser points in the target point layer is not less than a first threshold value, determining whether the average height of the laser points in the target point layer is greater than the reference ground height corresponding to the reference grid.
1109. And if the average height of the laser points in the target point layer is greater than the reference ground height corresponding to the reference grid, determining whether the absolute value of a fourth difference between the minimum height of the laser points in the target point layer and the reference ground height corresponding to the reference grid is greater than the preset travelable height.
1110. And if the absolute value of the fourth difference is larger than the preset travelable height, determining the average height of the laser points in the target point layer as the reference ground height corresponding to the grid to be detected, determining the grid to be detected as a high-altitude grid, and marking the grid to be detected as a detected grid. Taking the determined high-altitude grid as a reference grid, and going to step 1102.
1111. And if the absolute value of the fourth difference is smaller than the preset travelable height, determining the grid to be detected as the obstacle grid and marking the grid to be detected as detected.
1112. And if the average height of the laser points in the target point layer is less than the reference ground height corresponding to the reference grid, determining the grid to be detected as an obstacle grid, and marking the grid to be detected as detected.
The target ground grid in the grid map can be detected by the method, and the high-altitude grid and the obstacle grid can be detected at the same time.
And step 205, taking the determined areas corresponding to the initial ground grid and the target ground grid as travelable areas.
In an implementation, in the case where the ground grid (the ground grid including the initial ground grid and the target ground grid), the high-altitude grid, and the obstacle grid are specified in the rectangular grid map, a region corresponding to the specified ground grid and the high-altitude grid may be directly used as a travelable region. In the case of determining the ground grid, the overhead grid and the obstacles in the polar grid map, they may first be transformed under the rectangular grid map. The conversion method can be as follows: and directly generating a direct coordinate grid map on the generated polar coordinate grid map, connecting the center of the obstacle grid in the polar coordinate grid map with the origin of the polar coordinate grid map, marking grids in the right-angle grid map through which the connection lines pass as travelable grids, and determining areas corresponding to the travelable grids as travelable areas.
Based on the same technical concept, the embodiment of the present application further provides a device for detecting a travelable region, as shown in fig. 13, the device includes:
an obtaining module 1310, configured to obtain a laser point cloud of a detectable area of the automatic traveling platform, which may specifically implement the obtaining function in step 201 and other implicit steps;
a generating module 1320, configured to generate a grid map corresponding to the laser point cloud, where each laser point in the laser point cloud corresponds to a grid in the grid map, and specifically, the generating function in step 202 above and other implicit steps may be implemented;
the determining module 1330 is configured to determine an initial ground grid in each grid of the grid map, determine a target ground grid in the grid map based on the initial ground grid, and use an area corresponding to the determined initial ground grid and the target ground grid as a travelable area, which may specifically implement the determining function in steps 202 to 205, and other implicit steps.
In one possible implementation, the apparatus further includes:
and for each grid in the grid map, layering the laser points in the grid to obtain at least one point layer.
In a possible implementation manner, the determining module 1330 is configured to:
determining an initial ground grid in each grid of the grid map based on the distance between the grid in the grid map and the automatic traveling platform and the height of the laser points in a target point layer with the minimum average height of the laser points in the grid map, wherein the target point layer belongs to the at least one point layer.
In a possible implementation manner, the determining module 1330 is configured to:
taking the initial ground grid as a reference grid, and taking the average height of the laser points in the target point layer with the minimum average height of the laser points in the initial ground grid as the reference ground height corresponding to the initial ground grid;
taking the grid with the reference grid meeting the preset proximity condition as a grid to be detected;
determining a target ground grid in the to-be-detected grid based on the reference ground height corresponding to the reference grid and the average height of the laser points in the target point layer with the minimum average height of the laser points in the to-be-detected grid;
and taking the determined target ground grid as a reference grid, taking the average height of the laser points in a target point layer with the minimum average height of the laser points in the target ground grid as the reference ground height corresponding to the target ground grid, and turning to execute the step of taking the grid of which the reference grid meets the preset proximity condition as the grid to be detected.
In one possible implementation, the grid map is a polar grid map;
determining an initial ground grid in each grid based on the distance between the grid and the automatic driving platform and the average height of the laser points in the target point layer with the smallest average height of the laser points in the grid, including:
and respectively determining an initial ground grid in each radial grid of the polar coordinate grid map, starting from the grid with the minimum distance from the automatic driving platform, and based on the height of the laser spot in the target point layer with the minimum average height of the laser spots in the grids in the radial direction.
In one possible implementation, the generating module 1320 is configured to:
the grid graph is a polar coordinate grid graph;
the grid of the reference grid satisfying the preset proximity condition is the grid including the laser spot next to the reference grid in the radial direction.
In one possible implementation, the grid map is a rectangular coordinate grid map;
the determining module 1330 is configured to:
and determining an initial ground grid based on the height of the laser point in the target point layer with the minimum average height of the laser points in the grids in a first preset range around the automatic driving platform in the rectangular coordinate grid map.
In one possible implementation, the grid map is a rectangular coordinate grid map;
and the grid of which the reference grid meets the preset proximity condition is the grid in a second preset range around the reference grid.
In one possible implementation, the layering module is configured to:
acquiring laser points in the grid one by one according to the sequence of the heights from small to large;
and if the absolute value of the difference between the height of the currently acquired laser point and the height of the previously acquired laser point is smaller than the preset travelable height, dividing the currently acquired laser point to the point layer where the previously acquired laser point is located, otherwise, dividing the currently acquired laser point to a newly built point layer.
It should be noted that the obtaining module 1310, the generating module 1320, and the determining module 1330 may be implemented by a processor, or a processor and a memory, or a processor executing program instructions in a memory.
It should be further noted that, in the device for detecting a travelable area according to the foregoing embodiment, only the division of the functional modules is illustrated in the description, and in practical applications, the functions may be distributed by different functional modules according to needs, that is, the internal structure of the decision controller may be divided into different functional modules to complete all or part of the functions described above. In addition, the travelable region detection apparatus provided in the above embodiment and the method embodiment for travelable region detection belong to the same concept, and the specific implementation process thereof is described in detail in the method embodiment, and is not described again here.
In the above embodiments, all or part of the implementation may be realized by software, hardware, firmware or any combination thereof, and when the implementation is realized by software, all or part of the implementation may be realized in the form of a computer program product. The computer program product comprises one or more computer program instructions which, when loaded and executed on a device, cause a process or function according to an embodiment of the application to be performed in whole or in part. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (e.g., coaxial cable, fiber optics, digital subscriber line) or wirelessly (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by the device or a data storage device, such as a server, a data center, etc., that is integrated into one or more available media. The usable medium may be a magnetic medium (such as a floppy Disk, a hard Disk, a magnetic tape, etc.), an optical medium (such as a Digital Video Disk (DVD), etc.), or a semiconductor medium (such as a solid state Disk, etc.).
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only one embodiment of the present application and should not be taken as limiting the present application, and any modifications, equivalents, improvements, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (20)
- A method of travelable region detection, the method comprising:acquiring laser point cloud of a detectable area of the automatic driving platform;generating a grid map corresponding to the laser point cloud, wherein each laser point in the laser point cloud corresponds to a grid in the grid map;determining an initial ground grid in each grid of the grid map;determining a target ground grid in the grid map based on the initial ground grid;and taking the determined area corresponding to the initial ground grid and the target ground grid as a travelable area.
- The method of any of claims 1, wherein prior to determining an initial ground grid in a grid of the grid map, the method further comprises:and for each grid in the grid map, layering the laser points in the grid to obtain at least one point layer.
- The method of claim 2, wherein determining an initial ground grid among the grids of the grid map comprises:determining an initial ground grid among the grids of the grid map based on the distance between the grids of the grid map and the automatic traveling platform and the height of the laser spot in a target point layer with the smallest average height of the laser spots in the grids of the grid map, wherein the target point layer belongs to the at least one point layer.
- The method of claim 2 or 3, wherein determining a target ground grid in the grid map based on the initial ground grid comprises:taking the initial ground grid as a reference grid, and taking the average height of the laser points in the target point layer with the minimum average height of the laser points in the initial ground grid as the reference ground height corresponding to the initial ground grid;taking the grid with the reference grid meeting the preset proximity condition as a grid to be detected;determining a target ground grid in the grid to be detected based on the reference ground height corresponding to the reference grid and the average height of the laser points in the target point layer with the minimum average height of the laser points in the grid to be detected;and taking the determined target ground grid as a reference grid, taking the average height of the laser points in a target point layer with the minimum average height of the laser points in the target ground grid as the reference ground height corresponding to the target ground grid, and turning to execute the step of taking the grid of which the reference grid meets the preset proximity condition as the grid to be detected.
- The method of claim 3, wherein the grid map is a polar grid map;determining an initial ground grid in each grid based on the distance between the grid and the automatic driving platform and the average height of the laser points in the target point layer with the smallest average height of the laser points in the grid, including:and respectively determining an initial ground grid in each radial grid of the polar coordinate grid map, starting from the grid with the minimum distance from the automatic driving platform, and based on the height of the laser spot in the target point layer with the minimum average height of the laser spots in the grids in the radial direction.
- The method of claim 4, the generating a grid map corresponding to the laser point cloud, comprising:the grid graph is a polar coordinate grid graph;the grid of the reference grid satisfying the preset proximity condition is the grid including the laser spot next to the reference grid in the radial direction.
- The method of claim 3, wherein the grid map is a rectangular grid map;determining an initial ground grid in each grid based on the distance between the grid and the automatic driving platform and the average height of the laser points in the target point layer with the smallest average height of the laser points in the grid, including:and determining an initial ground grid based on the height of the laser point in the target point layer with the minimum average height of the laser points in the grids in a first preset range around the automatic driving platform in the rectangular coordinate grid map.
- The method of claim 4, wherein the grid map is a rectangular grid map;and the grid of which the reference grid meets the preset proximity condition is the grid in a second preset range around the reference grid.
- The method of any of claims 2-8, wherein the layering laser points in the grid for each grid in the grid map comprises:acquiring laser points in the grid one by one according to the sequence of the heights from small to large;and if the absolute value of the difference between the height of the currently acquired laser point and the height of the previously acquired laser point is smaller than the preset travelable height, dividing the currently acquired laser point to the point layer where the previously acquired laser point is located, otherwise, dividing the currently acquired laser point to a newly built point layer.
- An apparatus for travelable area detection, the apparatus comprising:the acquisition module is used for acquiring laser point cloud of a detectable area of the automatic driving platform;the generating module is used for generating a grid map corresponding to the laser point cloud, wherein each laser point in the laser point cloud corresponds to a grid in the grid map;the determination module is used for determining an initial ground grid in each grid of the grid map, determining a target ground grid in the grid map based on the initial ground grid, and taking a region corresponding to the determined initial ground grid and the target ground grid as a travelable region.
- The apparatus of any one of claims 10, further comprising:and the layering module is used for layering the laser points in the grids to obtain at least one point layer for each grid in the grid map.
- The apparatus of claim 11, wherein the determining module is configured to:determining an initial ground grid among the grids of the grid map based on the distance between the grids of the grid map and the automatic traveling platform and the height of the laser spot in a target point layer with the smallest average height of the laser spots in the grids of the grid map, wherein the target point layer belongs to the at least one point layer.
- The apparatus of claim 11 or 12, wherein the determining module is configured to:taking the initial ground grid as a reference grid, and taking the average height of the laser points in the target point layer with the minimum average height of the laser points in the initial ground grid as the reference ground height corresponding to the initial ground grid;taking the grid with the reference grid meeting a preset proximity condition as a grid to be detected;determining a target ground grid in the grid to be detected based on the reference ground height corresponding to the reference grid and the average height of the laser points in the target point layer with the minimum average height of the laser points in the grid to be detected;and taking the determined target ground grid as a reference grid, taking the average height of the laser points in a target point layer with the minimum average height of the laser points in the target ground grid as the reference ground height corresponding to the target ground grid, and turning to execute the step of taking the grid of which the reference grid meets the preset proximity condition as the grid to be detected.
- The apparatus of claim 12, wherein the grid map is a polar grid map;the determining module is configured to:and respectively determining an initial ground grid in each radial grid of the polar coordinate grid map, starting from the grid with the minimum distance from the automatic driving platform, and based on the height of the laser spot in the target point layer with the minimum average height of the laser spots in the grids in the radial direction.
- The apparatus of claim 13, the generating a grid map corresponding to the laser point cloud, comprising:the grid graph is a polar coordinate grid graph;the grid of the reference grid satisfying the preset proximity condition is the grid including the laser spot next to the reference grid in the radial direction.
- The apparatus of claim 12, wherein the grid map is a rectangular grid map;the determining module is configured to:and determining an initial ground grid based on the height of the laser point in the target point layer with the minimum average height of the laser points in the grids in a first preset range around the automatic driving platform in the rectangular coordinate grid map.
- The apparatus of claim 13, wherein the grid map is a rectangular grid map;and the grid of which the reference grid meets the preset proximity condition is the grid in a second preset range around the reference grid.
- The apparatus of any one of claims 11-17, wherein the layering module is configured to:acquiring laser points in the grid one by one according to the sequence of the heights from small to large;and if the absolute value of the difference between the height of the currently acquired laser point and the height of the previously acquired laser point is smaller than the preset travelable height, dividing the currently acquired laser point to the point layer where the previously acquired laser point is located, otherwise, dividing the currently acquired laser point to a newly built point layer.
- A decision controller, comprising a processor and a memory;the memory stores one or more programs configured to be executed by the processor for implementing a method of travelable region detection as claimed in any of claims 1-9.
- A computer-readable storage medium comprising computer-readable instructions that, when run on a decision controller, cause the decision controller to perform the method of travelable area detection of any of claims 1-9.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2020/077336 WO2021168854A1 (en) | 2020-02-29 | 2020-02-29 | Method and apparatus for free space detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115151954A true CN115151954A (en) | 2022-10-04 |
Family
ID=77490541
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202080097562.6A Pending CN115151954A (en) | 2020-02-29 | 2020-02-29 | Method and device for detecting a drivable region |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115151954A (en) |
| WO (1) | WO2021168854A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116449335A (en) * | 2023-06-14 | 2023-07-18 | 上海木蚁机器人科技有限公司 | Method and device for detecting drivable area, electronic device and storage medium |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114359866A (en) * | 2021-12-31 | 2022-04-15 | 中国第一汽车股份有限公司 | Road boundary detection method and device based on laser radar |
| CN114387585B (en) * | 2022-03-22 | 2022-07-05 | 新石器慧通（北京）科技有限公司 | Obstacle detection method, detection device, and travel device |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105551082B (en) * | 2015-12-02 | 2018-09-07 | 百度在线网络技术（北京）有限公司 | A kind of pavement identification method and device based on laser point cloud |
| CN109238221B (en) * | 2017-07-10 | 2021-02-26 | 上海汽车集团股份有限公司 | Method and device for detecting surrounding environment of vehicle |
| JP7077013B2 (en) * | 2017-12-27 | 2022-05-30 | 株式会社トプコン | 3D information processing unit, device equipped with 3D information processing unit, unmanned aerial vehicle, notification device, moving object control method using 3D information processing unit, and program for moving object control processing |
| CN108873013B (en) * | 2018-06-27 | 2022-07-22 | 江苏大学 | Method for acquiring passable road area by adopting multi-line laser radar |
| CN109283936A (en) * | 2018-08-15 | 2019-01-29 | 广州极飞科技有限公司 | Mobile device control method, device and terminal |
| CN109255302A (en) * | 2018-08-15 | 2019-01-22 | 广州极飞科技有限公司 | Object recognition methods and terminal, mobile device control method and terminal |
| CN110320504B (en) * | 2019-07-29 | 2021-05-18 | 浙江大学 | Unstructured road detection method based on laser radar point cloud statistical geometric model |
| CN110569749B (en) * | 2019-08-22 | 2021-11-30 | 江苏徐工工程机械研究院有限公司 | Detection method and system for boundary line and travelable area of mine road |
-
2020
- 2020-02-29 WO PCT/CN2020/077336 patent/WO2021168854A1/en active Application Filing
- 2020-02-29 CN CN202080097562.6A patent/CN115151954A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116449335A (en) * | 2023-06-14 | 2023-07-18 | 上海木蚁机器人科技有限公司 | Method and device for detecting drivable area, electronic device and storage medium |
| CN116449335B (en) * | 2023-06-14 | 2023-09-01 | 上海木蚁机器人科技有限公司 | Method and device for detecting drivable area, electronic device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021168854A1 (en) | 2021-09-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022022694A1 (en) | Method and system for sensing automated driving environment | |
| CN109144097B (en) | Obstacle or ground recognition and flight control method, device, equipment and medium | |
| CN112665556B (en) | Generating a three-dimensional map of a scene using passive and active measurements | |
| US20200049511A1 (en) | Sensor fusion | |
| CN111192295B (en) | Target detection and tracking method, apparatus, and computer-readable storage medium | |
| CN110411366B (en) | Road water depth detection method and electronic equipment | |
| CN112781599B (en) | Method for determining the position of a vehicle | |
| Yoneda et al. | Urban road localization by using multiple layer map matching and line segment matching | |
| CN115151954A (en) | Method and device for detecting a drivable region | |
| CN112346463B (en) | Unmanned vehicle path planning method based on speed sampling | |
| CN112464812B (en) | Vehicle-based concave obstacle detection method | |
| CN110674705A (en) | Small-sized obstacle detection method and device based on multi-line laser radar | |
| US10444398B2 (en) | Method of processing 3D sensor data to provide terrain segmentation | |
| EP4180835A1 (en) | Calibration of sensors in autonomous vehicle applications | |
| US11780436B2 (en) | On-board sensor system | |
| CN114821526A (en) | Obstacle three-dimensional frame detection method based on 4D millimeter wave radar point cloud | |
| CN110824495B (en) | Laser radar-based drosophila visual inspired three-dimensional moving target detection method | |
| CN110554409B (en) | Concave obstacle detection method and system | |
| CN110865394A (en) | Target classification system based on laser radar data and data processing method thereof | |
| CN110893845A (en) | Method and apparatus for diagonal lane detection | |
| CN113376643A (en) | Distance detection method and device and electronic equipment | |
| CN114217641B (en) | Unmanned aerial vehicle power transmission and transformation equipment inspection method and system in non-structural environment | |
| Kolu et al. | A mapping method tolerant to calibration and localization errors based on tilting 2D laser scanner | |
| CN114089376A (en) | Single laser radar-based negative obstacle detection method | |
| CN110907949A (en) | Method and system for detecting automatic driving travelable area and vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |