CN114675292A - Location status detection method, device, equipment, storage medium and program product - Google Patents
Location status detection method, device, equipment, storage medium and program product Download PDFInfo
- Publication number
- CN114675292A CN114675292A CN202210302797.5A CN202210302797A CN114675292A CN 114675292 A CN114675292 A CN 114675292A CN 202210302797 A CN202210302797 A CN 202210302797A CN 114675292 A CN114675292 A CN 114675292A
- Authority
- CN
- China
- Prior art keywords
- library
- grid
- determining
- area
- robot
- 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
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V8/00—Prospecting or detecting by optical means
- G01V8/10—Detecting, e.g. by using light barriers
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V8/00—Prospecting or detecting by optical means
- G01V8/10—Detecting, e.g. by using light barriers
- G01V8/20—Detecting, e.g. by using light barriers using multiple transmitters or receivers
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geophysics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Electromagnetism (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The embodiment of the invention provides a method and a device for detecting a library bit state, electronic equipment, a storage medium and a computer program product. Scanning and detecting the library area by using a laser radar installed on the robot to obtain current laser point cloud data, and determining the hit point and the non-hit point in the library area by using the current pose data, the laser radar installation position and the current laser point cloud data of the robot, so as to determine the state of at least one of the plurality of library positions in the library area. After the storage position detection method provided by the embodiment of the invention is adopted to determine the storage position state, the detection result can be sent to the robot scheduling server for the robot scheduling server to carry out storage position taking and unloading planning, robot path planning, obstacle avoidance planning and the like, so that the problems that the robot is in the following states are greatly improved: the efficiency, intelligence and reliability of cargo handling under the application scenes such as warehouse logistics and the like.
Description
Technical Field
The embodiment of the invention relates to the technical field of information processing, in particular to a method and a device for detecting a library bit state, electronic equipment, a storage medium and a computer program product.
Background
At present, various mobile robots are widely applied to the intelligent automation industry and play a very important role, and particularly in the logistics storage industry, the mobile robots play an important role.
When the robot carries goods under the storehouse district scene of disposing a large amount of concentrated storehouse positions, consider to improve the robot and get goods, unload and handling efficiency, maximize storehouse position utilization ratio, and then increase the demands such as intelligence, security and reliability of robot goods transport. It is necessary to know whether the status of the various positions is available before the robot performs the cargo handling task. However, there is no feasible method for detecting the state of the library bit.
Therefore, there is a need for a method for detecting the status of each bay to determine whether the status of each bay is available before the robot performs a cargo handling task.
Disclosure of Invention
The embodiment of the invention provides a position state detection method, a position state detection device, electronic equipment, a storage medium and a computer program product, which are used for determining whether the state of each position is available before a robot executes a cargo carrying task.
The first aspect of the embodiments of the present invention provides a method for detecting a library bit state, where the method includes:
acquiring a configuration file of a library area consisting of a plurality of library positions, and determining a detection area according to the configuration file of the library area;
acquiring current pose data of the robot and current laser point cloud data obtained by detecting the detection area by a laser radar installed on the robot;
determining a hit point of the detection area according to the current pose data, the installation position of the laser radar and the current laser point cloud data;
and determining the state of at least one of the plurality of bin positions according to the hit point.
Optionally, after determining the detection area according to the configuration file of the library area, the method further includes:
performing grid division on the detection area according to a preset grid size to obtain a plurality of grids;
determining initial hit probability and initial miss probability of each grid in the detection area according to a preset value;
determining a hit point in a detection area according to the current pose data, the installation position of the laser radar and the current laser point cloud data, and the method comprises the following steps:
determining whether each grid in the detection area contains a hit point and a miss point according to the current pose data, the installation position of the laser radar and the current laser point cloud data, and further determining the actual hit probability and the actual miss probability of each grid in the detection area;
determining the current hit probability and the current miss probability of each grid in the detection area according to the initial hit probability and the initial miss probability of each grid in the detection area and the actual hit probability and the actual miss probability of each grid in the detection area;
determining a state of at least one of the plurality of bin locations according to the hit point and the hit point, including:
and determining the state of each bin according to the current hit probability and the current miss probability of each grid contained in each bin in the plurality of bins.
Optionally, acquiring current pose data of the robot includes:
obtaining movement data of the robot, the movement data including: moving speed, angular velocity;
under the condition that the moving speed of the robot is greater than a preset speed threshold, determining the current pose data of the robot when laser point cloud is received according to the moving speed, the angular speed and the time difference of the robot and the latest pose data of the robot; and the time difference is the time difference between the timestamp of the laser point cloud when being received and the timestamp of the latest pose data.
Optionally, obtaining a configuration file of a library area composed of a plurality of library locations, and determining a detection area according to the configuration file of the library area, includes:
analyzing the configuration file of the library area, and determining the center coordinates of each library position included in the library area;
respectively align the central coordinates x of the library positionsi0，xi1，...，xiM，yi0，yi1，...，yiMSorting to obtain the minimum value
Maximum value
Let the coordinate of the lower left corner of the detection area be (x)i1，yi1) The coordinate of the upper right corner is (x)i2，yi2) Then, then
Wherein, alpha is a scaling factor, and r is the maximum detection amplitude of the laser;
with (x)i1，yi1) And (x)i2，yi2) And making a rectangle for two vertexes on the diagonal line to obtain a detection area.
Optionally, after determining the detection area according to the configuration file of the library area, the method further includes:
determining a reservoir area grid area according to the configuration file of the reservoir area;
performing grid division on the grid area of the library area according to a preset grid size to obtain a plurality of grids;
determining initial hit probability and initial miss probability of each grid in the grid area of the library area according to a preset value;
determining the hit point and the non-hit point of a detection area according to the current pose data, the installation position of the laser radar and the current laser point cloud data, wherein the determining comprises the following steps:
determining whether each grid in the grid area of the library area contains a hit point and a miss point according to the current pose data, the installation position of the laser radar and the current laser point cloud data, and further determining the actual hit probability and the actual miss probability of each grid in the grid area of the library area;
determining the current hit probability and the current miss probability of each grid in the grid region of the library region according to the initial hit probability and the initial miss probability of each grid in the grid region of the library region, and the actual hit probability and the actual miss probability of each grid in the grid region of the library region;
determining a state of at least one of the plurality of bin locations according to the hit point and the hit point, including:
and determining the state of each bin according to the current hit probability and the current miss probability of each grid contained in each bin in the plurality of bins.
Optionally, the robot is multiple, the method further comprising:
counting the hitting points of the detection areas respectively determined by each robot to obtain the total hitting point of the detection areas;
and determining the state of at least one of the plurality of bin positions according to the total hit point.
A second aspect of the embodiments of the present invention provides a library bit state detection apparatus, where the apparatus includes:
the detection area determining module is used for acquiring a configuration file of a library area consisting of a plurality of library positions and determining a detection area according to the configuration file of the library area;
the acquisition module is used for acquiring current pose data of the robot and current laser point cloud data obtained by detecting a laser radar installed on the robot aiming at the detection area;
the hit point determining module is used for determining hit points of the detection area according to the current pose data, the installation position of the laser radar and the current laser point cloud data;
and the library position state determining module is used for determining the state of at least one library position in the plurality of library positions according to the hitting point.
A third aspect of the embodiments of the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory, where the processor executes the computer program to implement the method for detecting a library bit state according to the first aspect of the present invention.
A fourth aspect of the embodiments of the present invention provides a computer-readable storage medium, on which a computer program/instruction is stored, which, when being executed by a processor, implements the method for detecting a library bit state according to the first aspect of the present invention.
A fifth aspect of the embodiments of the present invention provides a computer program product, which includes a computer program/instruction, and when the computer program/instruction is executed by a processor, the computer program/instruction implements the method for detecting a library bit state according to the first aspect of the present invention.
In the embodiment of the invention, the laser radar arranged on the robot is used for scanning and detecting the library area to obtain the current laser point cloud data, and then the current pose data, the laser radar installation position and the current laser point cloud data of the robot are used for determining the hit point and the non-hit point in the library area, so that the state of at least one library position in a plurality of library positions in the library area is determined.
In the embodiment of the invention, the laser radar which is installed on the robot and is mainly used for positioning and navigation is directly utilized to realize the detection of the state of each storage position in the storage area, whether the storage position is occupied can be accurately determined, and the laser radar does not need to be additionally arranged in the storage area, so that the cost can be saved.
In the embodiment of the invention, the state of the library position is determined by using a simple statistical method of the total number of hit points, and the detection result can be obtained simply and efficiently. In addition, in the embodiment of the invention, the state of the reservoir area is determined to be the occupied state when the total number of the hit points contained in the reservoir position is greater than the preset threshold value, so that the reservoir area state can be prevented from being judged by mistake due to laser radar errors to a certain extent.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
FIG. 1 is a flow chart of a method for detecting a bin status according to an embodiment of the present invention;
FIG. 2 is a flow chart of another method for library bit status detection according to an embodiment of the present invention;
FIG. 3 is a flow chart of another method for library bit status detection according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a grid map obtained by performing grid division on a detection area in the embodiment of the present invention;
fig. 5 is a flowchart of a method for determining a library position detection result in a library position detection method according to an embodiment of the present invention;
FIG. 6 is a flowchart of a specific library position detection method according to an embodiment of the present invention
Fig. 7 is a block diagram of a device for detecting the status of a bin in an embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Referring to fig. 1, a flowchart of a method for detecting a library bit state according to an embodiment of the present invention is shown, where the method may be performed by a server, and the method includes the following steps:
s101, obtaining a configuration file of a library area formed by a plurality of library positions, and determining a detection area according to the configuration file of the library area.
In the embodiment of the present invention, before the robot performs the transportation task, the library area configuration file may be read, and information of a plurality of library locations included in the library area may be analyzed, where the library area configuration file at least includes: library area ID, library area center coordinate, library area length, width, each library position ID under the library area, library position center coordinate, library position length, width and initial state. Therefore, the detection area of each library area can be respectively planned according to the configuration file of each library area and is associated to the corresponding library area.
Specifically, in the embodiment of the present invention, after the information of the library area and the library position is obtained by parsing according to the library area configuration file, the detection area may be determined in the global map according to the box model, which specifically includes the following steps:
s1011, analyzing the configuration file of the library area, and determining the center coordinates of each library position included in the library area.
In the embodiment of the present invention, configuration files of multiple library areas may be processed simultaneously, and for convenience of distinguishing, numbers 1, 2, and 3 … … i of each library area may be set.
S1012, respectively aligning the center coordinates x of the library positionsi0，xi1，...，xiM，yi0，yi1，...，yiMSorting to obtain the minimum value
Maximum value
S1013, the lower left corner coordinate of the detection area is set as (x)i1，yi1) The coordinate of the upper right corner is (x)i2，yi2) Then, then
In the embodiment of the invention, the value of alpha is 0.5, and r is the maximum detection amplitude of the laser radar and is determined according to the parameter configuration of the laser radar in practical application.
S1014, with (x)i1，yi1) And (x)i2，yi2) And making a rectangle for two vertexes on the diagonal line to obtain a detection area.
In the embodiment of the invention, when the detection area is determined, the area covering all the library positions in the library area is considered, and the maximum detection amplitude of the laser radar is also considered. Therefore, effective laser point cloud data can be obtained as long as the robot enters the detection area, and then the robot can be set to start a detection program immediately when entering the detection area, so that the detection real-time performance in an effective range is guaranteed, and the storage position state detection efficiency is improved.
Optionally, in the embodiment of the present invention, the scaling factor α may also be 1.5, and the non-detection area is determined according to the method for determining the detection area. When the robot is in the non-detection area, the distance between the robot and the library position in the library area i exceeds the maximum detection amplitude of the laser, and the laser data is invalid, so that the detection is not required to be started in the area.
In the embodiment of the invention, the maximum detection amplitude of the laser radar is considered, the non-detection area is set, and the laser radar can be prevented from detecting in the non-detection area to obtain invalid data, so that the power consumption of the laser radar can be saved, the reliability of the laser point cloud data can be improved, meanwhile, invalid detection operation in the non-detection area is avoided, and the operation burden of a processor is reduced.
In the embodiment of the invention, the detection area and the non-detection area of the library area i can be associated with the library area i to generate the key value pair, so that the subsequent calling is facilitated.
And S102, acquiring current pose data of the robot and current laser point cloud data obtained by scanning a laser radar installed on the robot aiming at the detection area.
In the embodiment of the present invention, the current pose data of the robot may be determined according to any feasible method in the related art, for example: the robot coordinate system can be converted into a world coordinate system by means of an open source TF library function under an ROS robot operating system, and the current pose P of the robot is obtained as (x, y, theta), wherein theta is the robot direction.
In the embodiment of the invention, each robot can be provided with a corresponding pose sequence. Specifically, after the current pose data of the robot are obtained, a timestamp is added to the current pose data and stored in the tail of the corresponding pose sequence, and when the number of data in the movement feedback sequence is larger than two and the timestamp of the previous pose data is smaller than the difference between the timestamp of the current pose data and the time threshold, the data at the head of the movement feedback sequence is deleted so as to maintain the time difference between the pose sequence data not to exceed the time threshold. In the embodiment of the present invention, the time threshold may be set according to an actual demand, and for example, the time threshold may be 0.01 s.
In the embodiment of the invention, when the robot is in the detection area, scanning detection can be carried out to obtain the laser point cloud data of the current library area.
In the embodiment of the invention, in consideration of the motion state of the robot, when the robot is in a high-speed moving state, the pose change is fast, and very accurate laser point cloud coordinates cannot be calculated only according to the pose sequence.
Specifically, in the embodiment of the present invention, for each robot, a corresponding speed sequence may be set, the movement data may be stored, and the current movement data of the robot may be obtained, where the method includes:
the movement data includes: a moving velocity v, an angular velocity ω.
The moving speed v is the moving speed in the direction of an x axis, the coordinate system in which the robot is located takes the position right in front of the robot as the x axis, the vertical x axis is the y axis to the left, the z axis is vertical to the x-y plane, the angular speed is the rotation angular speed, the coordinate system in which the robot is located and the coordinate system in which the moving speed is located, the angular speed direction meets the right-hand rule, and the counterclockwise rotating direction around the z axis is taken as the positive.
Under the condition that the moving speed of the robot is greater than a preset speed threshold, determining the current pose data of the robot when laser point cloud is received according to the moving speed, the angular speed and the time difference of the robot and the latest pose data of the robot; and the time difference is the time difference between a timestamp of the laser point cloud when being received and a timestamp of the latest pose data.
In the embodiment of the present invention, the preset speed threshold may be preset in advance by a technician, for example, may be 2 meters per second, and when the moving speed of the robot is greater than or equal to 2 meters per second, it is determined that the robot is in a high-speed moving state, and motion compensation needs to be performed on pose data of the robot.
In practical application, the movement data of the robot can be obtained by the following method:
subscribing the speed feedback topic of the robot through an ROS robot topic communication mechanism, and executing a callback function to perform data analysis when data enters to obtain the current timestamp, the x-direction speed v and the rotation angular speed omega of the robot. And storing the 3 kinds of data as one element into the tail part of the speed sequence, executing a first round of filtering operation, and removing the head element of the sequence if the number of the elements in the sequence is more than 2 so as to keep the number of the objects in the sequence to be less than 2. And entering a second round of filtering operation, and if the time difference between the time of the tail element of the sequence and the time of the head element of the sequence exceeds a threshold value of 0.2s, so that the data in the sequence is proved not to be up-to-date, removing the tail object from the sequence, thereby ensuring that the number of elements in the speed sequence is 2 and the time difference between the elements does not exceed 0.2 s.
And in actual application, detecting whether the speed sequence is empty, if so, ending the step, and otherwise, determining that the tail object of the speed sequence contains a time stamp, a speed and an angular speed and is the latest movement data of the robot.
In the embodiment of the invention, the laser radar arranged on the robot body can scan the environment of the robot along with the movement of the robot to obtain the laser point cloud data of the current frame.
In the embodiment of the invention, the robot can be always in a moving state when the position of the warehouse is detected, and the robot leaves the original position within the time interval from the emitting of the laser to the receiving of the feedback during the high-speed movement. In order to ensure the accuracy of the position of the robot, motion compensation operation needs to be added to update the pose data when the robot receives the laser point cloud data.
Specifically, firstly, a time-stamped pose (x) at the tail of a pose sequence of the robot is obtainedback，yback，θback) Calculating the latest pose (x)new，ynew，θnew)：
θnew＝θback+0.5*(ωfront+ωback)*Δt
xnew＝xback+vback*Δt*cos(θnew+θback)/2
ynew＝yback+vback*Δt*sin(θnew+θback)/2
Wherein, ω isfront、ωback、vbackRespectively the angular velocity of the head element of the velocity sequence, the angular velocity of the tail element of the velocity sequence and the moving velocity of the tail of the velocity sequence, and delta t is the time stamp and the pose (x) when the laser point cloud data of the current frame is receivedback，yback，θback) The difference in time stamps.
In the embodiment of the present invention, in order to avoid data redundancy, the following redundancy judgment operations may be further performed:
judging whether the current frame laser point cloud data and the previous frame laser point cloud data simultaneously meet the following conditions:
(1) the current frame laser point cloud data is not the first frame laser point cloud data;
(2) the time difference between the current frame of laser point cloud data and the last frame of laser point cloud data is less than 1 s;
(3) the distance between the current position of the robot and the position of the robot when the last frame of laser point cloud data is received is less than 0.1m of threshold value.
(4) The angular difference between the current orientation of the robot and the orientation of the robot when the last frame of laser point cloud data is received is less than a threshold value of 0.1 (rad).
If the two frames of laser point cloud data are similar, the two frames of laser point cloud data are proved to be similar, the difference between the current frame of laser point cloud data and the previous frame of laser point cloud data is proved to be small, and the frame of data can be discarded in order to avoid repeated redundant judgment.
S103, determining the hit point of the detection area according to the current pose data, the installation position of the laser radar and the current laser point cloud data.
In the embodiment of the invention, a laser point cloud coordinate set can be determined according to the current pose data, the installation position of the laser radar and the current laser point cloud data, and the laser points in the laser point cloud coordinate set are used as the hit points.
Specifically, in the embodiment of the present invention, coordinate transformation may be performed according to current pose data of the robot and an installation position of the laser radar on the robot to obtain a coordinate Pl of the laser radar in a world coordinate system, and a coordinate P of the laser point cloud data in the world coordinate system is calculated according to a coordinate (ρ, θ) of a laser point in the returned laser point cloud data in a polar coordinate system, where ρ is a distance between a point in the laser point cloud and a laser carried by the robot, and θ is an angle of the laser point, where ρ is a distance between the point in the laser point cloud and the laser carried by the robotp。
Specifically, for the robot pose data (x, y, θ), the robot coordinate system to the world can be calculated as followsRotation matrix R under coordinate systemwrAnd a translation vector twr：
Measuring the installation coordinate x of the laser radar relative to the robot originrl＝(xll，yll) Angular deviation of thetalAnd the coordinate Pl of the laser radar in the world coordinate system is as follows:
the calculated lower attitude data of the laser radar in the world coordinate system is as follows: (x)l，yl，θ+θ1)。
In the embodiment of the invention, after the world coordinates of the laser radar are determined, the laser point cloud data can be analyzed, and the kth frame laser return distance rho and the angle can be directly obtained according to the laser point cloud data
The specific calculation method is as follows:
the above formula is applicable to the case of laser forward mounting, where βminFor laser detection of minimum angle, betamaxIs the maximum angle, t is the step size, and δ is the amount of angular change per step, i.e., angular velocity.
And after obtaining the distance and the angle, carrying out invalid laser point cloud filtering operation, and specifically comprising the following steps: if it is not
Not between the minimum angle and the maximum angle or p not between the minimum probe range and the maximum probe range, the frame data is discarded.
For the valid laser point cloud, the following operations are performed:
calculating the coordinate P of the point cloud under the world coordinate systemp：
Wherein, RwlIs a rotation matrix from the laser coordinate system to the world coordinate system, xlpAs the coordinates of the point cloud in the laser coordinate system, twlThe translation vector of the laser under the world coordinate system.
Storing the coordinates (x) of the frame of laser point cloud in the world coordinate systemp，yp) And storing the laser point cloud coordinate set. Meanwhile, storing the coordinate (x) of the laser radar in the world coordinate system when receiving the frame of laser point cloudl，yl) And a point cloud timestamp.
S104, determining the state of at least one of the plurality of library positions according to the hit point.
In the embodiment of the present invention, the library location area corresponding to each library location may be determined according to the library location center coordinates and the length and width obtained by parsing in the library location configuration file, and may specifically be implemented by using the following method:
in respective bin position coordinates (x)ij，yij) Centered, extending 0.5 times to the left and right
Each extending 0.5 times up and down
Get two vertexes of the library position as
The rectangular area created by using the two vertexes as opposite angles is the library bit area.
In the embodiment of the present invention, when a hit point falls in a certain bin position area, it may be simply considered that the bin position has a hit point, and count the total number of hit points included in each bin position in the bin area, compare the total number of hit points with a preset threshold, and when the total number of hit points is greater than the preset threshold, determine that the bin position is in an occupied state. Wherein the preset threshold value can be set in advance by a technician based on experience.
In the embodiment of the present invention, there may be a plurality of robots, and accordingly, each robot may obtain a frame of laser point cloud data and analyze the frame of laser point cloud data to obtain the hit point, where in this case, the embodiment of the present invention further includes:
counting the hitting points of the detection areas respectively determined by each robot to obtain the total hitting point of the detection areas; and determining the state of at least one of the plurality of bin positions according to the total hit point.
In the embodiment of the invention, the state of the library position is determined by using a simple statistical method of the total number of hit points, and the detection result can be obtained simply and efficiently. In addition, in the embodiment of the invention, the state of the reservoir area is determined to be the occupied state when the total number of the hit points contained in the reservoir position is greater than the preset threshold value, so that the reservoir area state can be prevented from being judged by mistake due to laser radar errors to a certain extent.
S201, obtaining a configuration file of a library area formed by a plurality of library positions, and determining a detection area according to the configuration file of the library area.
Step S201 is similar to step S101, and is not described herein again.
And S202, performing grid division on the detection area according to a preset grid size to obtain a plurality of grids.
As shown in fig. 4, fig. 4 is a schematic diagram of a grid map obtained by performing grid division on a detection area in the embodiment of the present invention.
In the embodiment of the present invention, the preset grid size may be determined according to the size of the detection area, or may be a fixed value set in advance by a technician, for example: the preset grid size may be 0.05 x 0.05 (m).
Specifically, the number num _ x and num _ y of grids to be divided in the x and y directions can be calculated according to the following formula:
wherein x ismax，xminFor maximum and minimum values of the projection of the detection area on the x-axis, and, similarly, ymax，yminThe maximum value and the minimum value of the projection of the detection area on the y axis, resolution is the grid resolution, the value is 0.05,
rounding the rounding operator.
In the embodiment of the present invention, a grid probability set cells may be further created, and data may be randomly accessed in the probability set according to the index, so as to update the grid probability in the following step, where the capacity of the grid probability set cells is n, and the initial probabilities are all 0, where n is Bum _ x num _ y + 1.
S203, determining the initial hit probability and the initial miss probability of each grid in the detection area according to a preset value.
Specifically, in the embodiment of the present invention, a hit (subsequently denoted by hit) probability table may be created, and the hit probability p of each grid hit by the laser of the current frame may be recorded, and a miss (subsequently denoted by miss) probability table may be created, and the miss probability of each grid not hit by the laser of the current frame may be recorded. In practical applications, it can be noted that the ratio of the probabilities of hit and miss is the difference ratio odd, and then:
the odds of a grid can be calculated according to the above formula, and a larger odds indicates a larger probability that the grid is occupied.
Solving the above equation reversely, the confidence of the grid can be obtained:
to avoid floating point operations, it is mapped to integers between [1, 32767], and the mapping formula is as follows:
in the embodiment of the invention, lower and upper are respectively 0.1 and 0.9.
In the embodiment of the invention, the odds values of the initial hit and miss can be 0.88 and 0.42, and the initial hit probability and the initial miss probability of each grid can be further calculated.
And S204, acquiring current pose data of the robot and current laser point cloud data obtained by detecting the detection area by the laser radar installed on the robot.
Step S204 is similar to step S102, and is not repeated herein.
S205, determining whether each grid in the detection area contains a hit point and a miss point according to the current pose data, the installation position of the laser radar and the current laser point cloud data, and further determining the actual hit probability and the actual miss probability of each grid in the detection area.
In the embodiment of the present invention, the method in step S103 may be adopted to determine the laser point cloud coordinate set.
After determining the laser point cloud coordinate set, in the embodiment of the present invention, the point cloud positions (x) in the laser point cloud coordinate set may be sequentially detectedp，yp) And if the laser point cloud data is not in the detection area, continuing waiting for new laser point cloud data.If the laser point cloud coordinate is concentrated in the point cloud location (x)p，yp) In the detection area, the laser radar coordinate (x) is usedl，yl) As a starting point, point cloud coordinates (x)p，yp) Making line segment a for the end pointi. Detecting step line segment aiAnd whether intersection exists with the library position area or not is judged, and if the intersection exists, the frame of laser point cloud end point is proved to hit the library position.
Will be associated with line segment aiThe intersected grid state is set as miss, and the specific calculation formula is as follows:
step is the number of grids passed by the line segment, the components of one grid on the x axis and the y axis are Δ x and Δ y, and the calculation formula is as follows:
sequentially calculating the coordinates of the kth miss grid
The calculation formula is as follows:
acquisition grid
Index of (2):
the index of the miss grid is then:
reading the corresponding grid probability through the grid probability set cells created by the index in step S202, and marking as pro, and then searching the probability corresponding to pro in the obtained miss table through pro, that is, the grid probability that needs to be updated in the current observation, so that the current probability value obtained by calculation is rewritten into the probability value corresponding to the index in the grid probability set cells in the following, and the old probability value is covered, thereby completing the probability updating of the grid.
If line segment aiIs less than the maximum detection range of the lidar, and aiEnd point (x) of (2)p，yp) In the grid region gammagridIf so, this hit is proved to be effective, (x)p，yp) I.e. the hit point.
In practical application, the target hit by the laser is not a point, but an object with an area larger than that of the point, and therefore, in the embodiment of the present invention, the coordinates of the hit point are expanded, and it is considered that the point in the expansion neighborhood is also the hit point. The expansion principle is as followsp，yp) Four points of 0.05 meters from the center, up, down, left, and right, which are the centers, thus obtaining 5 hit points in total.
The index of each hit point is obtained according to the method of calculating the index in step S205. Similarly, reading the corresponding grid probability in the grid probability set cells by using the index, and searching the corresponding probability in the hit table by using the probability value as the index, wherein the probability is the grid probability which needs to be updated in the current observation, so that the current probability value obtained by calculation is rewritten in the grid probability set cells in the following process, the old probability value is covered, and the probability updating of the grid is completed.
And S206, determining the current hit probability and the current miss probability of each grid in the detection region according to the initial hit probability and the initial miss probability of each grid in the detection region, and the actual hit probability and the actual miss probability of each grid in the detection region.
In the embodiment of the invention, in order to avoid repeated complicated probability operation, according to a newly observed result, a probability value after each observation value v (v belongs to [1, 32767]) is correspondingly updated in advance, and the v (v belongs to [1, 32767]) calculation steps are as follows:
(1) converting v to a floating point number t (v) between 0-1:
(2) and calculating the odds value of the current observation, and multiplying the odds value or the initial value of the previous observation to obtain the latest odds value.
(3) The latest odds value is converted to the latest probability.
(4) Finally, solving the latest probability according to the formula f (, x) in step S203 to obtain a corresponding integer value, which is the updated result of the current observation: the current hit probability and the current miss probability are then written into the corresponding table according to the observation classification "hit" or "miss" obtained in step S205.
S207, determining the state of each bin according to the current hit probability and the current miss probability of each grid contained in each bin of the plurality of bins.
In the embodiment of the present invention, fig. 5 is a flowchart of a method for determining a library position detection result in a library position detection method provided in the embodiment of the present invention, and the explanation is made with reference to fig. 5:
specifically, in the embodiment of the present invention, after receiving the detection result signal for obtaining the library area i, all library bits under the library area i are traversed, and the total number n of grids included in the library bits is calculatedcellsCounting the number n of all grids contained in the bin region, wherein the probability of all grids is greater than the hit probability thresholdhitThe number n of probabilities less than the miss probability thresholdmissAccording to the followingJudging the detection result of the library position according to the formula:
s301, obtaining a configuration file of a library area formed by a plurality of library positions, and determining a detection area according to the configuration file of the library area.
Step S301 is similar to step S101 described above, and is not described herein again.
S302, determining a reservoir grid area according to the configuration file of the reservoir.
Specifically, a configuration file of the library area is analyzed, and the center coordinates of each library position included in the library area are determined;
respectively align the central coordinates x of the library positionsi0，xi1，...，xiM，yi0，yi1，...，yiMSorting to obtain the minimum value
Maximum value of
Let the coordinate of the lower left corner of the detection area be (x)i1，yi1) The coordinate of the upper right corner is (x)i2，yi2) Then, then
Wherein, alpha is a scaling factor, r is the maximum detection amplitude of the laser, and r is taken as 0;
with (x)i1，yi1) And (x)i2，yi2) And (4) making a rectangle for two vertexes on the diagonal line to obtain a library area grid region.
And S303, carrying out grid division on the grid region of the library region according to a preset grid size to obtain a plurality of grids.
S304, determining the initial hit probability and the initial miss probability of each grid in the grid area of the library area according to a preset value.
S305, current pose data of the robot and current laser point cloud data obtained by detecting the detection area by a laser radar installed on the robot are obtained.
S306, determining whether each grid in the grid area of the library area contains a hit point and a miss point according to the current pose data, the installation position of the laser radar and the current laser point cloud data, and further determining the actual hit probability and the actual miss probability of each grid in the grid area of the library area.
S307, determining the current hit probability and the current miss probability of each grid in the grid region of the library region according to the initial hit probability and the initial miss probability of each grid in the grid region of the library region and the actual hit probability and the actual miss probability of each grid in the grid region of the library region.
S308, determining the state of each bin according to the current hit probability and the current miss probability of each grid contained in each bin of the plurality of bins.
In the embodiment of the present invention, steps S303 to S308 are similar to steps S202 to S207, and in the embodiment of the present invention, after the robot enters the detection area, library area scanning is started, and a detection result is obtained, but in the embodiment of the present invention, a grid is divided for a library area grid area, a grid probability is created, and the detection result is updated, and specific contents may refer to steps S202 to S207.
In the embodiment of the invention, the grids are only divided aiming at the grid region of the library region, and the grid probability is established, so that the data processing amount can be reduced, and the data efficiency is improved.
Fig. 6 is a flowchart of a specific library location detection method provided by the present invention, and the library location detection method provided by the embodiment of the present invention is further explained with reference to fig. 6 below:
in the embodiment of the invention, the library position detection method comprises the following steps:
(1) acquiring a library area configuration file, loading a library area map, and planning a detection area and a non-detection area of each library area;
(2) updating the pose of the robot and acquiring the latest pose data of the robot;
(3) initializing a hit table and a miss table;
(4) creating a grid map, setting the size of the grid, and initializing the probability value of each grid;
(5) acquiring robot movement data, and determining the speed and angular speed of the robot;
(6) judging whether the robot is in a high-speed moving state according to a preset speed threshold, if so, executing the following step (7), and if not, executing the following step (8)
(7) Performing motion compensation on the latest robot pose data based on the robot movement data;
(8) coordinate transformation is carried out to obtain robot coordinates PrLaser radar coordinate PlLaser point cloud coordinate Pp；
(9) Analyzing the laser point cloud data of the current frame;
(10) judging whether the laser point cloud coordinate is a hit point, if not, continuing to judge the next laser point cloud coordinate, and if so, executing the following step (11);
(11) expanding the hit grid to obtain an expanded hit grid, and traversing the miss grid and the hit grid;
(12) updating miss and hit grid probabilities;
(13) calculating the total number n of grids contained in the library bitcellsCounting the number n of all grids contained in the bin region, wherein the probability of all grids is greater than the hit probability thresholdhitThe number n of probabilities less than the miss probability thresholdmiss；
(14) According to ncells、nhit、nmissAnd judging whether a library position detection result can be obtained or not, if so, obtaining a library position state and returning, and if not, waiting for next frame of laser point cloud data and analyzing.
In the method for detecting the library position provided by the embodiment of the invention, the library area environment point cloud data obtained by scanning the laser radar installed on the robot is processed, the probability of the library position grid is updated, and the state detection of the library position is realized by counting the number of hit and miss grids. In the embodiment of the invention, the accuracy of judgment of the detection result can be improved by planning the library area into the high-resolution grid map. The invention also realizes the accurate detection of the state of the storage position by the robot in a high-speed running state in a motion compensation mode.
After the storage position detection method provided by the embodiment of the invention is adopted to determine the storage position state, the detection result can be sent to the robot scheduling server for the robot scheduling server to carry out storage position taking and unloading planning, robot path planning, obstacle avoidance planning and the like, so that the problems that the robot is in the following states are greatly improved: the efficiency, intelligence and reliability of cargo handling under the application scenes such as warehouse logistics and the like.
Based on the same inventive concept, the embodiment of the invention provides a library bit state detection device. Referring to fig. 7, fig. 7 is a schematic diagram of a library site status detection apparatus according to an embodiment of the present invention. As shown in fig. 7, the apparatus includes:
a detection region determining module 701, configured to obtain a configuration file of a library region composed of a plurality of library locations, and determine a detection region according to the configuration file of the library region;
an obtaining module 702, configured to obtain current pose data of the robot and current laser point cloud data detected by a laser radar installed on the robot for the detection area;
a hit point determining module 703, configured to determine a hit point of the detection area according to the current pose data, the installation position of the laser radar, and the current laser point cloud data;
a bin state determining module 704, configured to determine a state of at least one bin of the plurality of bins according to the hit point.
Optionally, the apparatus further comprises:
the first division module is used for carrying out grid division on the detection area according to a preset grid size to obtain a plurality of grids;
the first initial probability determining module is used for determining initial hit probability and initial miss probability of each grid in the detection area according to a preset value;
the hit point determining module 703 is specifically configured to:
determining whether each grid in the detection area contains a hit point and a miss point according to the current pose data, the installation position of the laser radar and the current laser point cloud data, and further determining the actual hit probability and the actual miss probability of each grid in the detection area;
determining the current hit probability and the current miss probability of each grid in the detection area according to the initial hit probability and the initial miss probability of each grid in the detection area and the actual hit probability and the actual miss probability of each grid in the detection area;
the library position status determining module 704 is specifically configured to:
and determining the state of each bin according to the current hit probability and the current miss probability of each grid contained in each bin in the plurality of bins.
Optionally, the obtaining module 702 is specifically configured to:
obtaining movement data of the robot, the movement data including: moving speed, angular velocity;
under the condition that the moving speed of the robot is greater than a preset speed threshold, determining the current pose data of the robot when laser point cloud is received according to the moving speed, the angular speed and the time difference of the robot and the latest pose data of the robot; and the time difference is the time difference between a timestamp of the laser point cloud when being received and a timestamp of the latest pose data.
Optionally, the detection region determining module 701 is specifically configured to:
analyzing the configuration file of the library area, and determining the center coordinates of each library position included in the library area;
respectively align the central coordinates x of the library positionsi0，xi1，...，xiM，yi0，yi1，...，yiMSorting to obtain the minimum value
Maximum value of
Let the coordinate of the lower left corner of the detection area be (x)i1，yi1) The coordinate of the upper right corner is (x)i2，yi2) Then, then
Wherein, alpha is a scaling factor, and r is the maximum detection amplitude of the laser;
with (x)i1，yi1) And (x)i2，yi2) And making a rectangle for two vertexes on the diagonal line to obtain a detection area.
Optionally, the apparatus further comprises:
the library region grid region determining module is used for determining a library region grid region according to the configuration file of the library region;
the second division module is used for carrying out grid division on the grid area of the library area according to a preset grid size to obtain a plurality of grids;
the second initial probability determining module is used for determining the initial hit probability and the initial miss probability of each grid in the grid area of the library area according to a preset value;
the hit point determining module 703 is specifically configured to:
determining whether each grid in the grid area of the library area comprises a hit point and a miss point according to the current pose data, the installation position of the laser radar and the current laser point cloud data, and further determining the actual hit probability and the actual miss probability of each grid in the grid area of the library area;
determining the current hit probability and the current miss probability of each grid in the grid region of the library region according to the initial hit probability and the initial miss probability of each grid in the grid region of the library region, and the actual hit probability and the actual miss probability of each grid in the grid region of the library region;
the library position status determining module 704 is specifically configured to:
and determining the state of each bin according to the current hit probability and the current miss probability of each grid contained in each bin in the plurality of bins.
Optionally, the robot is multiple, and the apparatus further comprises:
the counting module is used for counting the hitting points of the detection areas respectively determined by the robots to obtain the total hitting point of the detection areas;
and the determining module is used for determining the state of at least one of the plurality of library positions according to the total hit point.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
The embodiment of the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory, and when the processor executes the computer program, the steps in the method for detecting a library bit state according to any of the above embodiments are implemented.
An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program/instruction is stored, where the computer program/instruction, when executed by a processor, implements the steps in the library bit state detection method described in any of the above embodiments.
An embodiment of the present invention further provides a computer program product, which includes a computer program/instruction, and when the computer program/instruction is executed by a processor, the method for detecting a library bit state according to any of the above embodiments is implemented.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "include", "including" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or terminal device including a series of elements includes not only those elements but also other elements not explicitly listed or inherent to such process, method, article, or terminal device. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
The method, apparatus, electronic device, storage medium and computer program product for detecting a library bit state provided by the present invention are described in detail above, and specific examples are applied herein to explain the principles and embodiments of the present invention, and the descriptions of the above embodiments are only used to help understanding the method and core ideas of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A method for detecting a library bit state, the method comprising:
acquiring a configuration file of a library area consisting of a plurality of library positions, and determining a detection area according to the configuration file of the library area;
acquiring current pose data of the robot and current laser point cloud data obtained by detecting the detection area by a laser radar installed on the robot;
determining a hit point of the detection area according to the current pose data, the installation position of the laser radar and the current laser point cloud data;
and determining the state of at least one of the plurality of bin positions according to the hit point.
2. The library level status detection method according to claim 1, wherein after determining the detection area according to the configuration file of the library area, the method further comprises:
performing grid division on the detection area according to a preset grid size to obtain a plurality of grids;
determining initial hit probability and initial miss probability of each grid in the detection area according to a preset value;
determining a hit point in a detection area according to the current pose data, the installation position of the laser radar and the current laser point cloud data, and the method comprises the following steps:
determining whether each grid in the detection area contains a hit point and a miss point according to the current pose data, the installation position of the laser radar and the current laser point cloud data, and further determining the actual hit probability and the actual miss probability of each grid in the detection area;
determining the current hit probability and the current miss probability of each grid in the detection area according to the initial hit probability and the initial miss probability of each grid in the detection area and the actual hit probability and the actual miss probability of each grid in the detection area;
determining a state of at least one of the plurality of bin locations according to the hit point and the hit point, including:
and determining the state of each bin according to the current hit probability and the current miss probability of each grid contained in each bin in the plurality of bins.
3. The library level state detection method according to claim 1, wherein acquiring current pose data of the robot includes:
obtaining movement data of the robot, the movement data including: moving speed, angular velocity;
under the condition that the moving speed of the robot is greater than a preset speed threshold, determining the current pose data of the robot when laser point cloud is received according to the moving speed, the angular speed and the time difference of the robot and the latest pose data of the robot; and the time difference is the time difference between a timestamp of the laser point cloud when being received and a timestamp of the latest pose data.
4. The method for detecting the library location state according to claim 1, wherein the step of obtaining a configuration file of a library area composed of a plurality of library locations and determining the detection area according to the configuration file of the library area comprises:
analyzing the configuration file of the library area, and determining the center coordinates of each library position included in the library area;
respectively align the central coordinates x of the library positionsi0,xi1,...,xiM，yi0,yi1,...,yiMSorting to obtain the minimum value
Maximum value
Let the coordinate of the lower left corner of the detection area be (x)i1,yi1) The coordinate of the upper right corner is (x)i2,yi2) Then, then
Wherein, alpha is a scaling factor, and r is the maximum detection amplitude of the laser;
with (x)i1,yi1) And (x)i2,yi2) And making a rectangle for two vertexes on the diagonal line to obtain a detection area.
5. The method according to claim 4, wherein after determining the detection area according to the configuration file of the library area, the method further comprises:
determining a reservoir area grid area according to the configuration file of the reservoir area;
performing grid division on the grid area of the library area according to a preset grid size to obtain a plurality of grids;
determining initial hit probability and initial miss probability of each grid in the grid area of the library area according to a preset value;
determining the hit point and the non-hit point of a detection area according to the current pose data, the installation position of the laser radar and the current laser point cloud data, wherein the determining comprises the following steps:
determining whether each grid in the grid area of the library area contains a hit point and a miss point according to the current pose data, the installation position of the laser radar and the current laser point cloud data, and further determining the actual hit probability and the actual miss probability of each grid in the grid area of the library area;
determining the current hit probability and the current miss probability of each grid in the grid region of the library region according to the initial hit probability and the initial miss probability of each grid in the grid region of the library region and the actual hit probability and the actual miss probability of each grid in the grid region of the library region;
determining a state of at least one of the plurality of bin locations according to the hit point and the hit point, including:
and determining the state of each bin according to the current hit probability and the current miss probability of each grid contained in each bin in the plurality of bins.
6. The library site status detection method of claim 1, wherein the robot is plural, the method further comprising:
counting the hitting points of the detection areas respectively determined by each robot to obtain the total hitting point of the detection areas;
and determining the state of at least one of the plurality of bin positions according to the total hit point.
7. A bin state detection device, the device comprising:
the detection area determining module is used for acquiring a configuration file of a library area consisting of a plurality of library positions and determining a detection area according to the configuration file of the library area;
the acquisition module is used for acquiring current pose data of the robot and current laser point cloud data obtained by detecting a laser radar installed on the robot aiming at the detection area;
the hit point determining module is used for determining hit points of the detection area according to the current pose data, the installation position of the laser radar and the current laser point cloud data;
and the library position state determining module is used for determining the state of at least one library position in the plurality of library positions according to the hit point.
8. An electronic device comprising a memory, a processor, and a computer program stored on the memory, wherein the processor executes the computer program to implement the library bit state detection method of any of claims 1-6.
9. A computer-readable storage medium having stored thereon a computer program/instructions, characterized in that the computer program/instructions, when executed by a processor, implement the method of library bit status detection according to any one of claims 1-6.
10. A computer program product comprising computer programs/instructions, characterized in that the computer programs/instructions, when executed by a processor, implement the library bit state detection method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210302797.5A CN114675292A (en) | 2022-03-25 | 2022-03-25 | Location status detection method, device, equipment, storage medium and program product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210302797.5A CN114675292A (en) | 2022-03-25 | 2022-03-25 | Location status detection method, device, equipment, storage medium and program product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114675292A true CN114675292A (en) | 2022-06-28 |
Family
ID=82076054
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210302797.5A Pending CN114675292A (en) | 2022-03-25 | 2022-03-25 | Location status detection method, device, equipment, storage medium and program product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114675292A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115308709A (en) * | 2022-08-03 | 2022-11-08 | 浙江中力机械股份有限公司 | Laser radar-based library position detection method and system |
| CN115407355A (en) * | 2022-11-01 | 2022-11-29 | 小米汽车科技有限公司 | Library position map verification method and device and terminal equipment |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102270301A (en) * | 2011-06-07 | 2011-12-07 | 南京理工大学 | Method for detecting unstructured road boundary by combining support vector machine (SVM) and laser radar |
| US20120053755A1 (en) * | 2010-08-30 | 2012-03-01 | Denso Corporation | Traveling environment recognition device and method |
| US20200183011A1 (en) * | 2018-12-11 | 2020-06-11 | Shanghai Tusen Weilai Artificial Intelligence Technology Co., Ltd. | Method for creating occupancy grid map and processing apparatus |
| CN111652060A (en) * | 2020-04-27 | 2020-09-11 | 宁波吉利汽车研究开发有限公司 | A lidar-based height limit warning method, device, electronic device and storage medium |
| CN112466147A (en) * | 2020-11-18 | 2021-03-09 | 上海汽车集团股份有限公司 | Multi-sensor-based library position detection method and related device |
| CN112581613A (en) * | 2020-12-08 | 2021-03-30 | 纵目科技（上海）股份有限公司 | Grid map generation method and system, electronic device and storage medium |
| CN112882059A (en) * | 2021-01-08 | 2021-06-01 | 中国船舶重工集团公司第七0七研究所 | Unmanned ship inland river obstacle sensing method based on laser radar |
| CN113932799A (en) * | 2021-10-29 | 2022-01-14 | 上海有个机器人有限公司 | Laser map updating method, system, electronic device, medium, and program product |
| CN114063615A (en) * | 2021-11-04 | 2022-02-18 | 中南大学 | Backing navigation control method and system for intelligent vehicle for spraying pesticide between ridges in shed |
-
2022
- 2022-03-25 CN CN202210302797.5A patent/CN114675292A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120053755A1 (en) * | 2010-08-30 | 2012-03-01 | Denso Corporation | Traveling environment recognition device and method |
| CN102270301A (en) * | 2011-06-07 | 2011-12-07 | 南京理工大学 | Method for detecting unstructured road boundary by combining support vector machine (SVM) and laser radar |
| US20200183011A1 (en) * | 2018-12-11 | 2020-06-11 | Shanghai Tusen Weilai Artificial Intelligence Technology Co., Ltd. | Method for creating occupancy grid map and processing apparatus |
| CN111652060A (en) * | 2020-04-27 | 2020-09-11 | 宁波吉利汽车研究开发有限公司 | A lidar-based height limit warning method, device, electronic device and storage medium |
| CN112466147A (en) * | 2020-11-18 | 2021-03-09 | 上海汽车集团股份有限公司 | Multi-sensor-based library position detection method and related device |
| CN112581613A (en) * | 2020-12-08 | 2021-03-30 | 纵目科技（上海）股份有限公司 | Grid map generation method and system, electronic device and storage medium |
| CN112882059A (en) * | 2021-01-08 | 2021-06-01 | 中国船舶重工集团公司第七0七研究所 | Unmanned ship inland river obstacle sensing method based on laser radar |
| CN113932799A (en) * | 2021-10-29 | 2022-01-14 | 上海有个机器人有限公司 | Laser map updating method, system, electronic device, medium, and program product |
| CN114063615A (en) * | 2021-11-04 | 2022-02-18 | 中南大学 | Backing navigation control method and system for intelligent vehicle for spraying pesticide between ridges in shed |
Non-Patent Citations (2)
| Title |
|---|
| 张虎: "机器人SLAM导航核心技术与实践", 31 January 2022, 机械工业出版社, pages: 97 - 100 * |
| 杨光红 等: "无人系统基础", 31 August 2021, 机械工业出版社, pages: 44 - 45 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115308709A (en) * | 2022-08-03 | 2022-11-08 | 浙江中力机械股份有限公司 | Laser radar-based library position detection method and system |
| CN115407355A (en) * | 2022-11-01 | 2022-11-29 | 小米汽车科技有限公司 | Library position map verification method and device and terminal equipment |
| CN115407355B (en) * | 2022-11-01 | 2023-01-10 | 小米汽车科技有限公司 | Verification method, device and terminal equipment for location map |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113376650B (en) | Mobile robot positioning method and device, electronic equipment and storage medium | |
| CN107677279B (en) | Method and system for positioning and establishing image | |
| US20200333162A1 (en) | Ground texture image-based navigation method and device, and storage medium | |
| EP4170452A1 (en) | Path planning method and apparatus, robot, and storage medium | |
| CN109558854B (en) | Obstacle sensing method and device, electronic equipment and storage medium | |
| CN110221608A (en) | A kind of method and device of inspection device | |
| CN102538779A (en) | Robot system and map updating method | |
| CN113168189A (en) | Flight operation method, unmanned aerial vehicle and storage medium | |
| CN115112122B (en) | Positioning method, system, device and storage medium based on multi-sensor fusion | |
| CN114675292A (en) | Location status detection method, device, equipment, storage medium and program product | |
| CN109635861B (en) | Data fusion method and device, electronic equipment and storage medium | |
| CN116486406A (en) | Parking space labeling method, parking method, device, electronic equipment and storage medium | |
| CN113776520A (en) | Map construction method, map use method, map construction device, map use device, robot and medium | |
| CN115346041A (en) | Point position marking method, device and equipment based on deep learning and storage medium | |
| CN116105742A (en) | Composite scene inspection navigation method, system and related equipment | |
| CN116626700A (en) | A robot positioning method, device, electronic equipment and storage medium | |
| CN114648598B (en) | Global map construction method and device | |
| CN113581184B (en) | Method, device, equipment and medium for determining maximum passable area | |
| CN115979248A (en) | Map update method, system, and storage medium based on positioning pose as constraints | |
| CN119239582B (en) | A method, apparatus, device, and storage medium for determining a detour method | |
| CN109870163B (en) | A Mapping System Based on Multiple Models of Topological Maps | |
| CN112987010A (en) | System and method for multi-radar mapping of robot | |
| CN117406755B (en) | Robot obstacle avoidance method, device, equipment and readable storage medium | |
| US20230413712A1 (en) | Path finding method and system for weeding robot | |
| CN113819918B (en) | Positioning method, positioning device, electronic equipment and storage 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 |