CN120122670B - A high-precision stacker crane intelligent obstacle avoidance system and method based on hybrid guidance - Google Patents
A high-precision stacker crane intelligent obstacle avoidance system and method based on hybrid guidanceInfo
- Publication number
- CN120122670B CN120122670B CN202510613862.XA CN202510613862A CN120122670B CN 120122670 B CN120122670 B CN 120122670B CN 202510613862 A CN202510613862 A CN 202510613862A CN 120122670 B CN120122670 B CN 120122670B
- Authority
- CN
- China
- Prior art keywords
- precision
- stacker
- point cloud
- laser
- obstacle avoidance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/40—Control within particular dimensions
- G05D1/43—Control of position or course in two dimensions
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/60—Intended control result
- G05D1/617—Safety or protection, e.g. defining protection zones around obstacles or avoiding hazards
- G05D1/622—Obstacle avoidance
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The invention relates to the technical field of obstacle avoidance control, and particularly discloses an intelligent obstacle avoidance system and method of a high-precision stacker based on mixed guidance, wherein the system remarkably improves the operation safety and efficiency through a triple intelligent adjustment mechanism, firstly, laser reflection parameters are collected in real time, the reflection process is dynamically optimized, and the environment perception precision is ensured; finally, multi-source data are fused, an obstacle avoidance path is generated by adopting a mixed guiding strategy, abnormal fluctuation of decision parameters is synchronously monitored, closed loop optimization of path planning is realized, the technology breaks through the static response limitation of the traditional obstacle avoidance system, centimeter-level obstacle avoidance precision is realized in a complex storage environment by three-stage self-adaptive adjustment of laser-point cloud-decision, collision risk is effectively reduced, and the intellectualization and reliability of storage logistics are improved.
Description
Technical Field
The invention relates to the technical field of obstacle avoidance control, in particular to an intelligent obstacle avoidance system and method for a high-precision stacker based on mixed guidance.
Background
In the field of automatic storage, the high-precision stacker needs to consider the working efficiency, safety obstacle avoidance and positioning precision in a complex dynamic environment, so that an intelligent obstacle avoidance system integrating multi-mode sensing and dynamic prediction is constructed to break through the limitations of the traditional technology in terms of environmental adaptability, decision cooperativity and execution precision.
The invention patent with the bulletin number of CN112650225B discloses an AGV obstacle avoidance method, which comprises the following steps of setting an anchor point A on the AGV, detecting the position of an obstacle B around the anchor point A by an obstacle avoidance radar of the AGV to obtain a distance Lab between the anchor point A and the obstacle B, selecting a target point T according to a residual path planning, calculating a distance Lat between the anchor point A and the target point T, and calculating a reference distance Ltb according to the distance Lab between the anchor point A and the obstacle B and the distance Lat between the anchor point A and the target point T, wherein the method comprises the following steps ofAnd calculating the expected parking distance Ls and the expected parking acceleration a according to the reference distance Ltb, and adjusting the motion state of the AGV according to the expected parking distance Ls and the expected parking acceleration a.
For example, the invention patent application with publication number CN115562282A discloses an AGV dynamic obstacle avoidance method based on improved speed obstacle, which comprises the following steps of 1, predicting the position of an obstacle at the next moment by using a Kalman filtering algorithm according to the speed and direction of the dynamic obstacle, 2, constructing a speed obstacle buffer zone according to the predicted position of the obstacle, 3, performing multi-objective optimization on two objective functions of efficiency and safety, and selecting the optimal speed. The invention predicts the dynamic obstacle position based on Kalman filtering algorithm, and constructs a speed obstacle model according to the dynamic obstacle position.
However, in the process of realizing the embodiment of the application, the technical problems of the prior art are at least found that the prior art only depends on distance signals (such as infrared rays/ultrasonic waves), does not combine multi-mode data (such as visual textures and laser point clouds), is easy to misdetect in a complex reflectivity scene (such as a black light absorption object), and is accordingly invalid in a complex reflectivity environment (such as a low-reflectivity black light absorption object and a high-reflectivity metal surface), and obstacle avoidance abnormality is caused.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a high-precision intelligent obstacle avoidance system and method for a stacker based on mixed guidance, which can effectively solve the problems related to the background art.
The intelligent obstacle avoidance system for the high-precision stacker comprises a laser reflection adjusting module, a point cloud mapping adjusting module and an obstacle avoidance process adjusting module, wherein the laser reflection adjusting module is used for collecting and analyzing laser reflection parameters of the high-precision stacker to judge whether to intelligently adjust a laser reflection process of the high-precision stacker, the point cloud mapping adjusting module is used for collecting laser reflection results of the high-precision stacker and carrying out point cloud mapping to obtain and analyze point cloud mapping parameters to judge whether to intelligently adjust a point cloud mapping process of the high-precision stacker, the obstacle avoidance process adjusting module is used for obtaining and based on the point cloud mapping results of the high-precision stacker to carry out obstacle avoidance on the high-precision stacker, and collecting and analyzing obstacle avoidance decision parameters of the high-precision stacker to judge whether to adjust the obstacle avoidance process of the high-precision stacker.
The method comprises the steps of analyzing laser reflection parameters of a high-precision stacker to obtain a laser reflection index of the high-precision stacker, comparing the laser reflection index with a laser reflection reference interval, judging that the laser reflection process of the high-precision stacker is not intelligently regulated if the laser reflection index of the high-precision stacker belongs to the laser reflection reference interval, judging that the laser reflection process of the high-precision stacker is not intelligently recovered if a first condition exists, judging that the laser reflection process of the high-precision stacker is not intelligently recovered if the first condition does not exist, particularly, judging that the laser reflection recovery speed preset by an intelligent database is high, recovering the gain of an amplifier of the high-precision stacker to a basic amplifier gain, and recovering the exposure time of the high-precision stacker to the basic exposure time, judging that the laser reflection process of the high-precision stacker is intelligently regulated if the laser reflection index of the high-precision stacker does not belong to the laser reflection reference interval, particularly, judging that the laser reflection index of the high-precision stacker is larger than the obtained and the laser reflection index of the high-precision stacker is smaller than the first reference interval and the laser reflection time length is smaller than the first laser reflection interval, and the laser reflection time length of the high-precision stacker is smaller than the laser reflection time length of the laser reflection area of the high-precision stacker is increased when the laser reflection is high-precision is increased and the laser reflection time length is increased and the laser reflection section is high-adjusted to the laser reflection section is high-precision area is high, and the first condition refers to that the amplifier gain of the high-precision stacker is used as a basic amplifier gain and the exposure time of the high-precision stacker is used as a basic exposure time.
The method comprises the steps of obtaining the reflection type of a region of the high-precision stacker and the accurate deviation value of laser point cloud mapping of the high-precision stacker, increasing and adjusting the plane fitting iteration times and the reflectivity abrupt change response speed of the high-precision stacker based on the accurate deviation value of the laser point cloud mapping if the region of the high-precision stacker is the high-reflection region, and decreasing and adjusting the plane fitting iteration times and the reflectivity abrupt change response speed of the high-precision stacker based on the accurate deviation value of the laser point cloud mapping if the region of the high-precision stacker is the low-reflection region.
The method comprises the steps of judging whether a fourth condition exists or not, if so, carrying out decision pre-warning on the obstacle avoidance process of the high-precision stacker, if not, acquiring and carrying out reduction adjustment on the running speed of the high-precision stacker and carrying out increase adjustment on the safety margin of the high-precision stacker, wherein the fourth condition is that the running speed of the high-precision stacker is the minimum running speed and the safety margin of the high-precision stacker is the maximum safety margin.
The invention provides an intelligent obstacle avoidance method of a high-precision stacker based on mixed guidance, which comprises the steps of firstly collecting and analyzing laser reflection parameters of the high-precision stacker to judge whether to intelligently adjust the laser reflection process of the high-precision stacker, secondly collecting laser reflection results of the high-precision stacker, performing point cloud mapping, acquiring and analyzing point cloud mapping parameters to judge whether to intelligently adjust the point cloud mapping process of the high-precision stacker, thirdly acquiring and analyzing obstacle avoidance decision parameters of the high-precision stacker to judge whether to adjust the obstacle avoidance process of the high-precision stacker based on the point cloud mapping results of the high-precision stacker.
Compared with the prior art, the embodiment of the invention has at least the following advantages or beneficial effects:
(1) The invention provides a high-precision intelligent obstacle avoidance system and method for a stacker based on mixed guidance, which are characterized in that operation safety and efficiency are remarkably improved through a triple intelligent adjustment mechanism, laser reflection parameters are collected in real time, a reflection process is dynamically optimized, environment perception precision is guaranteed, high-density point cloud mapping is generated, space obstacle distribution is accurately restored, a mapping algorithm is automatically calibrated through parameter analysis, scene reduction degree is improved, multi-source data are fused, an obstacle avoidance path is generated through a mixed guidance strategy, abnormal fluctuation of decision parameters is synchronously monitored, closed loop optimization of path planning is realized, static response limitation of a traditional obstacle avoidance system is broken through by the technology, centimeter-level obstacle avoidance precision is realized in a complex storage environment through three-stage self-adaptive adjustment of laser-point cloud-decision, collision risk is effectively reduced, and intelligence and reliability of storage logistics are improved.
(2) The invention realizes double optimization of environment perception precision and equipment stability by dynamically analyzing laser reflection parameters through an intelligent regulation mechanism, a self-adaptive regulation strategy can deal with high/low reflection scenes in real time to ensure data acquisition reliability, an intelligent recovery function prevents parameter deviation to ensure long-term operation stability, a region mark provides environment priori information for subsequent obstacle avoidance, a triple mechanism synergistic effect obviously improves system robustness, and a stacker realizes higher-efficiency obstacle avoidance operation in a complex storage environment.
(3) According to the invention, by analyzing the point cloud mapping intelligent regulation mechanism, the algorithm parameters are dynamically optimized by identifying the environment reflection characteristics, the three-dimensional reconstruction precision under a complex scene is remarkably improved, the iteration times and response speed are increased for a high reflection area, the noise interference is effectively inhibited, the calculation redundancy is reduced for a low reflection area, the processing efficiency is improved, and the self-adaptive strategy enables the system to accurately restore the space forms of objects with different materials, provides a more reliable environment model for obstacle avoidance planning, and integrally improves the intelligent level of storage operation.
Drawings
The invention will be further described with reference to the accompanying drawings, in which embodiments do not constitute any limitation of the invention, and other drawings can be obtained by one of ordinary skill in the art without inventive effort from the following drawings.
Fig. 1 is a schematic diagram of a system module connection according to the present invention.
FIG. 2 is a flow chart of the method steps of the present invention.
Fig. 3 is a schematic diagram of a laser reflection adjustment flow chart according to the present invention.
Fig. 4 is a schematic diagram of a point cloud mapping adjustment flow chart according to the present invention.
Fig. 5 is a schematic diagram of an obstacle avoidance process adjustment flow of the present invention.
Detailed Description
The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, but not all embodiments, and all other embodiments obtained by those skilled in the art without making creative efforts based on the embodiments of the present invention are included in the protection scope of the present invention.
Referring to fig. 1, the first aspect of the invention provides a high-precision intelligent obstacle avoidance system of a stacker based on mixed guidance, which comprises a laser reflection adjusting module, a point cloud mapping adjusting module, an obstacle avoidance process adjusting module and an intelligent database.
The intelligent database is used for storing data contained in the intelligent obstacle avoidance system of the high-precision stacker based on mixed guidance.
The laser reflection adjusting module is connected with the point cloud mapping adjusting module, the point cloud mapping adjusting module is connected with the obstacle avoidance process adjusting module, and the laser reflection adjusting module, the point cloud mapping adjusting module and the obstacle avoidance process adjusting module are all connected with the intelligent database.
The laser reflection adjusting module is used for collecting and analyzing laser reflection parameters of the high-precision stacker, so as to judge whether to intelligently adjust the laser reflection process of the high-precision stacker.
The method comprises the steps of judging whether an intelligent adjustment is carried out on a laser reflection process of a high-precision stacker or not, wherein the specific judgment process comprises the steps of analyzing laser reflection parameters of the high-precision stacker to obtain a laser reflection index of the high-precision stacker, comparing the laser reflection index with a laser reflection reference interval, judging that the laser reflection process of the high-precision stacker is not subjected to intelligent adjustment if the laser reflection index of the high-precision stacker belongs to the laser reflection reference interval, judging whether a first condition exists at the same time, judging that the laser reflection process of the high-precision stacker is not subjected to intelligent recovery if the first condition exists, judging that the laser reflection process of the high-precision stacker is subjected to intelligent recovery if the first condition does not exist, particularly, recovering the gain of an amplifier of the high-precision stacker to a basic amplifier according to a preset reflection recovery speed of an intelligent database, and recovering the exposure time of the high-precision stacker to the basic exposure time, extracting the laser reflection reference interval from the intelligent database, and judging that the reflection condition of the area of the high-precision stacker is not belonged to, wherein the amplifier is required to be interpreted, when the gain of the amplifier is recovered, the amplifier is used, the amplifier is recovered, and the recovery speed is unified, and the recovery speed is recovered.
If the laser reflection index of the high-precision stacker does not belong to a laser reflection reference interval, the laser reflection process of the high-precision stacker is judged to be intelligently regulated, specifically, if the laser reflection index of the high-precision stacker is larger than the maximum value of the laser reflection reference interval, the amplifier gain and the exposure time length of the high-precision stacker are reduced and regulated based on the first laser reflection index of the high-precision stacker, meanwhile, the area where the high-precision stacker belongs is marked as a high reflection area, the first laser reflection index refers to the laser reflection index of the high-precision stacker minus the maximum value of the laser reflection reference interval, the processing result is divided by the maximum value of the laser reflection reference interval, so that the first laser reflection index is obtained, a first laser reflection index-amplifier gain reduction coefficient mapping table and a first laser reflection index-exposure time length reduction coefficient mapping table are stored in an intelligent database, the corresponding amplifier gain reduction coefficient and the exposure time length reduction coefficient of the high-precision stacker are directly queried in the intelligent database, the product of the amplifier gain reduction coefficient and the amplifier gain is obtained, the exposure time length of the high-precision stacker is reduced, the product of the exposure time length of the amplifier is reduced, the exposure time length of the exposure time length is reduced, and the exposure time length is reduced by the corresponding to the object gain after the high-precision stacker is reduced, and the product.
And if the laser reflection index of the high-precision stacker is smaller than the minimum value of the laser reflection reference interval, acquiring and increasing and adjusting the gain of an amplifier and the exposure time length of the high-precision stacker based on the second laser reflection index of the high-precision stacker, and marking the area of the high-precision stacker as a low reflection area, wherein the second laser reflection index is obtained by subtracting the laser reflection index of the high-precision stacker from the minimum value of the laser reflection reference interval, the processing result is divided by the minimum value of the laser reflection reference interval, so as to obtain the second laser reflection index, a second laser reflection-amplifier gain increase coefficient mapping table and a first laser reflection-exposure time length increase coefficient mapping table are stored in an intelligent database, the corresponding gain increase coefficient of the amplifier and the exposure time length increase coefficient are directly queried in the intelligent database, the gain increase coefficient of the amplifier and the gain of the amplifier are multiplied, the exposure time length increase coefficient and the exposure time length are multiplied, the result is the gain of the amplifier after the increase and adjustment, the gain increase coefficient of the gain of the amplifier is the gain of the laser reflection time length after the laser reflection value is increased, the laser reflection time length of the object is formed by the surface of the high-precision stacking area, and the object after the increase value is reflected by the surface.
The first condition is that the amplifier gain of the high-precision stacker is used as a basic amplifier gain and the exposure time of the high-precision stacker is used as a basic exposure time, wherein the basic amplifier gain is used as an initial amplifier gain set in the high-precision stacker, and the basic exposure time is used as an initial exposure time set in the high-precision stacker.
It should be explained that the amplifier gain and the exposure time length follow the synchronous adjustment principle, so when the amplifier gain is the basic amplifier gain, the exposure time length is also the basic exposure time length.
Further, the laser reflection index of the high-precision stacker is specifically analyzed by the specific analysis processes that the laser reflection parameters of the high-precision stacker comprise the laser reflection frequency of the high-precision stacker, the laser reflection rate of the high-precision stacker and the speckle contrast of the high-precision stacker, wherein the laser reflection frequency refers to the number of times of effective reflection of a laser beam in unit time and can be measured by a photoelectric detector, the laser reflection rate refers to the ratio of the laser power emitted by the high-precision stacker to the received laser power and is usually expressed by percentage and can be measured by a laser radar, the speckle contrast refers to the statistical measure of light intensity fluctuation of a bright and dark area in a speckle pattern formed when laser irradiates a rough surface, and the calculation formula is thatWherein sigma is the standard deviation of light intensity, mu is the average value of light intensity, speckle contrast reflects surface roughness information, which is an important index of laser reflected signal quality and can be measured by a laser speckle velocimeter.
And introducing an importance coefficient to quantify the influence degree of the deviation degree between the laser reflection frequency and the reference laser reflection frequency on the laser reflection index, the influence degree of the deviation degree between the laser reflectivity and the reference laser reflectivity on the laser reflection index and the influence degree of the deviation degree between the speckle contrast and the reference speckle contrast on the laser reflection index, and summarizing the influence degrees to obtain the laser reflection index of the high-precision stacker.
The laser reflection index of the high-precision stacker is used for measuring the numerical value of the comprehensive condition of the laser reflection characteristic of the stacker, and the specific expression is as follows:
;
In the formula, Is the laser reflection index of the high-precision stacker,The laser reflection frequency component of the high-precision stacker represents the deviation degree between the laser reflection frequency of the high-precision stacker and the reference laser reflection frequency, and specifically comprises the following components:; The laser reflectivity component of the high-precision stacker represents the deviation degree between the laser reflectivity of the high-precision stacker and the reference laser reflectivity, and specifically comprises the following components: , the speckle contrast component of the high-precision stacker is used for representing the deviation degree between the speckle contrast of the high-precision stacker and the reference speckle contrast, and specifically comprises the following steps: 。
for the importance coefficient of the laser reflection frequency component preset in the intelligent database, For the laser reflectivity component importance coefficients preset in the intelligent database,For a preset speckle contrast component importance factor in the intelligent database,For the laser reflection frequency of the high-precision stacker,For a reference laser reflection frequency preset in the intelligent database,For high precision laser reflectivity of the stacker,For a reference laser reflectivity preset in the intelligent database,For high precision stacker speckle contrast,And (5) presetting reference speckle contrast in the intelligent database.
The reference laser reflection frequency is a reference value indicating a laser reflection frequency, the reference laser reflectivity is a reference value indicating a laser reflectivity, and the reference speckle contrast is a reference value indicating a speckle contrast.
It should be explained that a high reflection area generally refers to a smooth surface, such as metal, glass, etc., on which the laser reflection frequency will be higher than the corresponding reference value, because of the reflected light intensity, the frequency of the signal received by the detector is high, and the laser reflection rate will also be higher than the corresponding reference value, because more incident light is reflected back, the speckle contrast is a parameter in laser speckle interference, and high speckle contrast means that the speckle pattern is clear, which generally occurs when the surface roughness is low (i.e., smooth surface), because a rough surface will cause speckle blurring, reducing contrast, whereas a low reflection area generally refers to a rough surface, such as dark cloth, rough plastic, etc. On such a surface, the laser reflection frequency is low, the signal frequency received by the detector is low because the reflected light is weak, the laser reflectivity is lower than the reference value, most of the incident light is absorbed or scattered, the speckle contrast is low, the speckle pattern is blurred due to the surface roughness, the contrast is reduced, and the parameters are related to each other to jointly reflect the reflection condition of the area of the high-precision stacker.
The laser reflection frequency component importance coefficient represents the proportion of the laser reflection frequency component to the laser reflection index, the laser reflection frequency component importance coefficient represents the proportion of the laser reflection index to the laser reflection frequency component, the speckle contrast component importance coefficient represents the proportion of the speckle contrast component to the laser reflection index, and the correspondence relation between the laser reflection frequency component, the laser reflection frequency component and the speckle contrast component and the corresponding importance coefficient is stored in the intelligent database, for example, the laser reflection frequency component and the speckle contrast component are input into the intelligent database, and the intelligent database can search the importance coefficient of the laser reflection frequency component, the importance coefficient of the laser reflection component and the importance coefficient of the speckle contrast component, and the value range of the speckle contrast component is 0 to 1.
In a specific embodiment, the invention realizes double optimization of environment perception precision and equipment stability by dynamically analyzing laser reflection parameters through an intelligent regulation mechanism, an adaptive regulation strategy can cope with high/low reflection scenes in real time, data acquisition reliability is ensured, an intelligent recovery function prevents parameter deviation and long-term operation stability is ensured, a region mark provides environment priori information for subsequent obstacle avoidance, and a triple mechanism cooperates to obviously improve system robustness, so that the stacker realizes higher-efficiency obstacle avoidance operation in a complex storage environment.
The point cloud mapping adjustment module is used for collecting laser reflection results of the high-precision stacker, performing point cloud mapping, and acquiring and analyzing point cloud mapping parameters so as to judge whether to intelligently adjust the point cloud mapping process of the high-precision stacker.
Analyzing the point cloud mapping parameters to obtain a laser point cloud mapping accuracy coefficient of the high-precision stacker, comparing the laser point cloud mapping accuracy coefficient with a laser point cloud mapping accuracy threshold, judging that the point cloud mapping process of the high-precision stacker is not intelligently regulated if the laser point cloud mapping accuracy coefficient of the high-precision stacker is larger than or equal to the laser point cloud mapping accuracy threshold, judging that a second condition exists or not, judging that the point cloud mapping process of the high-precision stacker is not intelligently recovered if the second condition exists, judging that the point cloud mapping process of the high-precision stacker is not intelligently recovered if the second condition does not exist, specifically, recovering the plane fitting iteration number of the high-precision stacker to the basic plane fitting iteration number according to the mapping recovery speed preset by an intelligent database, recovering the reflectivity mutation response speed of the high-precision stacker to the basic plane fitting iteration number, indicating that the laser point cloud mapping accuracy threshold is the minimum value allowed by the laser point cloud mapping coefficient of the high-precision stacker, and judging that the laser point cloud mapping accuracy threshold is the minimum value is allowed by the laser point cloud mapping process of the high-precision stacker, and carrying out the plane fitting iteration number is required to be recovered when the plane fitting response speed is required to be uniform when the mutation speed is recovered by the iteration number is required to be recovered, and the plane fitting response speed is recovered by the iteration number is required to be recovered.
If the accuracy coefficient of the laser point cloud mapping of the high-precision stacker is smaller than the accuracy threshold of the laser point cloud mapping, the intelligent adjustment of the point cloud mapping process of the high-precision stacker is judged.
The second condition refers to that a laser point cloud mapping accuracy margin value of the high-precision stacker is larger than or equal to a defined laser point cloud mapping accuracy margin value, and meanwhile, the plane fitting iteration number of the high-precision stacker is the basic plane fitting iteration number and the reflectivity abrupt response speed of the high-precision stacker are the basic reflectivity abrupt response speed, the laser point cloud mapping accuracy margin value refers to the degree that the laser point cloud mapping accuracy coefficient is larger than a laser point cloud mapping accuracy threshold value, specifically, the laser point cloud mapping accuracy coefficient is subtracted by the laser point cloud mapping accuracy threshold value, the processing result is divided by the laser point cloud mapping accuracy threshold value, and the final result is the laser point cloud mapping accuracy margin value, the defined laser point cloud mapping accuracy margin value refers to the minimum allowed by the laser point cloud mapping accuracy margin value, the minimum value is extracted from an intelligent database, the basic plane fitting iteration number refers to the initial plane fitting iteration number set in the high-precision stacker, and the basic reflectivity abrupt response speed refers to the initial reflectivity abrupt response speed set in the high-precision stacker.
It should be explained that the reflectivity abrupt response speed and the plane fitting iteration number follow the synchronous adjustment principle, so when the reflectivity abrupt response speed is the basic reflectivity abrupt response speed, the plane fitting iteration number is also the basic plane fitting iteration number.
The laser point cloud mapping accuracy coefficient of the high-precision stacker comprises a point cloud mapping parameter, a laser point cloud distribution density, a laser point cloud mapping time length deviation degree and a laser point cloud angle resolution, wherein the point cloud mapping parameter comprises the laser point cloud distribution density of the high-precision stacker, the laser point cloud distribution density refers to the number of laser points in a unit space volume and can be obtained through laser radar monitoring, the laser point cloud mapping time length deviation degree refers to the deviation ratio between the actual point cloud mapping time length and the defined time length of the high-precision stacker, the defined time length is subtracted from the actual point cloud mapping time length, the difference value is divided by the defined time length, the laser point cloud mapping time length deviation degree is finally obtained through embedded timer monitoring, the defined time length is represented by the maximum value allowed by the point cloud mapping time length and is extracted from an intelligent database, and the laser point cloud angle resolution refers to the minimum angle interval between two adjacent point clouds, which can be obtained through laser radar monitoring, wherein the laser scanning system is arranged in the same distance measuring unit.
And matching a correction coefficient from the intelligent database according to the laser reflection index of the high-precision stacker, wherein the correction coefficient represents a proportion value for carrying out data correction on the laser point cloud mapping accuracy coefficient and the obstacle avoidance decision efficiency index.
It should be explained that, according to the laser reflection index of the high-precision stacker, the correction coefficient corresponding to the laser reflection index is matched from the intelligent database, and the core value is that an intelligent closed loop system of environment perception-parameter self-adaption-efficiency improvement is constructed, the corrected data is closer to the real environment, the processing load of the subsequent algorithm is reduced, the accurate data enables the obstacle avoidance algorithm to adopt a simpler model (such as reducing redundant collision detection cycles), so that the response speed is improved, and the forward cycle of data quality improvement-algorithm efficiency improvement is the core mechanism that the correction coefficient can correct the data.
The influence degree of the deviation degree between the weighted quantification laser point cloud distribution density and the reference laser point cloud distribution density on the laser point cloud mapping accuracy coefficient, the influence degree of the proportional relation between the laser point cloud mapping duration deviation degree and the definition laser point cloud mapping duration deviation degree on the laser point cloud mapping accuracy coefficient and the influence degree of the proportional relation between the laser point cloud angle resolution and the definition laser point cloud angle resolution on the laser point cloud mapping accuracy coefficient are introduced, the influence degrees are aggregated, and meanwhile, the correction coefficient is introduced to correct the aggregation result, so that the laser point cloud mapping accuracy coefficient of the high-precision stacker is obtained.
The laser point cloud mapping accuracy coefficient of the high-precision stacker is used for quantifying the laser point cloud mapping accuracy degree of the high-precision stacker, and the specific expression is as follows:
;
In the formula, The laser point cloud mapping accuracy coefficient of the high-precision stacker,In order to correct the coefficient of the coefficient,The laser point cloud distribution density of the high-precision stacker,For a preset reference laser point cloud distribution density in the intelligent database,The laser point cloud mapping time length of the high-precision stacker deviates from the length,For defining the laser point cloud mapping time length deviation degree preset in the intelligent database,For high precision stacker laser point cloud angular resolution,For a predefined defined laser point cloud angular resolution in the intelligent database,Weighting the distribution density of laser point clouds preset in the intelligent database,The deviation degree weight of the laser point cloud mapping time length preset in the intelligent database,The method is characterized in that the method is used for weighting the angle resolution of the laser point cloud preset in the intelligent database, k is a constant, and k is not 0, so that the effectiveness of the accurate coefficient of the laser point cloud mapping is ensured.
The reference laser point cloud distribution density represents a reference value of the laser point cloud distribution density, the defined laser point cloud mapping time length deviation represents a maximum value allowed by the laser point cloud mapping time length deviation, and the defined laser point cloud angular resolution represents a minimum value allowed by the laser point cloud angular resolution.
When the distribution density of the laser point cloud is obviously deviated from a preset reference value, the abnormal fluctuation of the laser point cloud distribution density is directly indicated, so that the angular resolution is reduced, the space detail is lost, and an 'information blind area' is formed, for example, in a complex curved surface or an edge area, the low angular resolution can lead the point cloud to be incapable of tightly fitting the actual outline of an object, so that the mapping accuracy coefficient is reduced, the deviation degree of the mapping time length of the laser point cloud directly reflects the matching degree of the system instantaneity and the computing resource, when the distribution density or the angular resolution is improved, the data acquisition amount and the processing complexity are synchronously increased, if the hardware performance is not synchronously upgraded, the deviation degree of the mapping time length is obviously increased, at the same time, the distribution density or the angular resolution can be automatically reduced, the overall operation efficiency is replaced by sacrificing the local precision, the problem that the stacker reduces the operation speed due to waiting for data is solved, the distribution density of the laser point cloud is indirectly determined by influencing the data acquisition amount, the angular resolution is insufficient, the effectiveness of the distribution density is limited, the accuracy is formed, the mapping time length deviation degree is used as a real-time feedback signal of the efficiency of the high-precision stacker efficiency, the dynamic adjustment of the dynamic response coefficient is correspondingly, the dynamic response coefficient of the system is not matched with the dynamic response coefficient of the point cloud, the dynamic response coefficient is not matched with the dynamic response coefficient of the cloud, and the dynamic response coefficient is not matched with the dynamic response coefficient, and the dynamic response coefficient is greatly in the environment-restricted by the real-time, and the real-time is correspondingly improved, and the real-time is correspondingly under the situation, and the situation is correspondingly is greatly stressed in the situation.
The laser point cloud distribution density weighting value is used for quantifying the influence degree of the laser point cloud distribution density unit value on the laser point cloud mapping accuracy coefficient, the laser point cloud mapping time length deviation weighting value is used for quantifying the influence degree of the laser point cloud mapping time length deviation unit value on the laser point cloud mapping accuracy coefficient, the laser point cloud angle resolution weighting value is used for quantifying the influence degree of the laser point cloud angle resolution unit value on the laser point cloud mapping accuracy coefficient, the corresponding relation between the laser point cloud distribution density, the laser point cloud mapping time length deviation value and the laser point cloud angle resolution and the corresponding weighting value is stored in the intelligent database, for example, the laser point cloud distribution density, the laser point cloud mapping time length deviation value and the laser point cloud angle resolution are input into the intelligent database, and the intelligent database can retrieve the laser point cloud distribution density weighting value, the laser point cloud mapping time length deviation weighting value and the laser point cloud angle resolution weighting value, and the value of the laser point cloud angle resolution weighting value, and the range of the laser point cloud angle resolution weighting value are all between 0 and 1.
Further, the intelligent adjustment is carried out on the point cloud mapping process of the high-precision stacker, the specific adjustment process comprises the steps of obtaining the reflection type of the area where the high-precision stacker belongs and the laser point cloud mapping accuracy deviation value of the high-precision stacker, if the area where the high-precision stacker belongs is a high-reflection area, increasing and adjusting the plane fitting iteration times and the reflection rate mutation response speed of the high-precision stacker based on the laser point cloud mapping accuracy deviation value, wherein the laser point cloud mapping accuracy deviation value refers to the deviation value between the laser point cloud mapping accuracy coefficient of the high-precision stacker and the laser point cloud mapping accuracy threshold, specifically, subtracting the laser point cloud mapping accuracy coefficient of the high-precision stacker from the laser point cloud mapping accuracy deviation value, and obtaining the laser point cloud mapping accuracy deviation value as a result, and querying the corresponding plane fitting iteration time and reflection rate mutation response speed increase coefficient under the condition that the area where the high-precision stacker belongs is a high-reflection area, specifically, storing the laser point cloud mapping accuracy deviation value-plane fitting iteration time increase coefficient and the reflection rate increase the reflection rate response coefficient of the intelligent database in the plane fitting iteration time-plane fitting time and the reflection rate increase the corresponding to the reflection rate response coefficient of the high-reflection rate increase the laser point cloud mapping accuracy iteration time-plane fitting iteration time increase coefficient and the mutation response speed increase the reflection rate response of the intelligent database in the iteration time-plane fitting iteration time-increasing coefficient and the reflection rate response of the corresponding to the laser point cloud mapping iteration time increase iteration time response coefficient in the response factor after the high-reflection coefficient of the high-precision iteration time and mutation response coefficient increase the high-reflection coefficient of the high-precision iteration time to obtain the laser point cloud mapping accuracy response coefficient, the plane fitting iteration number increasing coefficient represents a proportion value for increasing the plane fitting iteration number, and the reflectivity abrupt change response speed increasing coefficient represents a proportion value for increasing the reflectivity abrupt change response speed.
If the area of the high-precision stacker is a low-reflection area, the plane fitting iteration times and the reflectivity abrupt response speed of the high-precision stacker are reduced and adjusted based on the laser point cloud mapping accuracy deviation value, under the condition that the area of the high-precision stacker is a low-reflection area, the corresponding plane fitting iteration times reduction coefficient and the reflectivity abrupt response speed reduction coefficient are inquired, specifically, the intelligent database stores the laser point cloud mapping accuracy deviation value-plane fitting iteration times reduction coefficient mapping table and the laser point cloud mapping accuracy deviation value-reflectivity abrupt response speed reduction coefficient mapping table, the corresponding plane fitting iteration times reduction coefficient and the reflectivity abrupt response speed reduction coefficient can be obtained by directly inquiring the laser point cloud mapping accuracy deviation value of the high-precision stacker in the intelligent database, the plane fitting iteration times reduction coefficient and the plane fitting iteration times are multiplied, the reflectivity abrupt response speed reduction coefficient is multiplied, and the multiplication result is the plane fitting iteration times and the reflectivity abrupt response speed after the reduction adjustment, wherein the plane fitting iteration times reduction coefficient represents the reduction of the reflectivity abrupt response speed reduction coefficient, and the reflection coefficient abrupt response speed reduction coefficient represents the ratio of the reflection response speed reduction of the plane fitting iteration times.
In a specific embodiment, the three-dimensional reconstruction precision under a complex scene is remarkably improved by analyzing the point cloud mapping intelligent regulation mechanism, identifying the environment reflection characteristic, dynamically optimizing algorithm parameters, increasing the iteration times and response speed aiming at a high reflection area, effectively inhibiting noise interference, reducing calculation redundancy and improving the processing efficiency aiming at a low reflection area, and the self-adaptive strategy enables the system to accurately restore the space forms of objects with different materials, provides a more reliable environment model for obstacle avoidance planning, and integrally improves the intelligent level of storage operation.
The obstacle avoidance process adjusting module is used for acquiring and based on the point cloud mapping result of the high-precision stacker, guiding the high-precision stacker in a mixed mode to avoid the obstacle, acquiring and analyzing obstacle avoidance decision parameters of the high-precision stacker, and accordingly judging whether to adjust the obstacle avoidance process of the high-precision stacker.
The method comprises the steps of judging whether an obstacle avoidance process of a high-precision stacker is regulated or not, wherein the specific judging process is to analyze obstacle avoidance decision parameters of the high-precision stacker to obtain an obstacle avoidance decision efficiency index of the high-precision stacker and compare the obstacle avoidance decision efficiency index with an obstacle avoidance decision efficiency threshold, if the obstacle avoidance decision efficiency index of the high-precision stacker is larger than or equal to the obstacle avoidance decision efficiency threshold, judging that the obstacle avoidance process of the high-precision stacker is not regulated, judging that whether a third condition exists or not, judging that the obstacle avoidance process of the high-precision stacker is not subjected to intelligent recovery, if the third condition does not exist, judging that the obstacle avoidance process of the high-precision stacker is subjected to intelligent recovery, particularly, recovering the operation speed of the high-precision stacker to a basic operation speed according to a decision recovery speed preset by an intelligent database, and recovering the safety margin of the high-precision stacker to the basic operation safety margin, wherein the obstacle avoidance decision efficiency threshold represents the minimum value allowed by the obstacle avoidance decision efficiency index, and is extracted from the intelligent database, and if the operation speed is recovered, the operation speed is required to be recovered to be a uniform, and the operation speed is set to the basic operation speed when the operation speed is recovered, and the safety margin is recovered to the basic operation speed is set to the basic operation speed.
And if the obstacle avoidance decision efficiency index of the high-precision stacker is smaller than the obstacle avoidance decision efficiency threshold, judging to adjust the obstacle avoidance process of the high-precision stacker, wherein the third condition is that the obstacle avoidance decision efficiency margin value of the high-precision stacker is larger than or equal to the limit obstacle avoidance decision efficiency margin value, and meanwhile, the running speed of the high-precision stacker is the basic running speed and the safety margin of the high-precision stacker is the basic safety margin.
It should be explained that the running speed and the safety margin follow the synchronous regulation principle, so when the running speed is the basic running speed, the safety margin is also the basic safety margin, the running speed is the running speed, and the safety margin is the safety distance.
The specific analysis process comprises the steps that the obstacle avoidance decision-making parameter of the high-precision stacker comprises instruction response time length of the high-precision stacker and an obstacle avoidance action accuracy factor of the high-precision stacker, wherein the instruction response time length refers to a physical time interval from the time when the high-precision stacker receives an instruction signal (such as an emergency stop instruction or a path adjustment instruction) to the time when an actuating mechanism (such as a servo motor) starts to respond, the physical time interval is usually in milliseconds, the unit is obtained through monitoring by a signal generator, and the obstacle avoidance action accuracy factor represents the coincidence degree of an actual movement track and a planned track when the stacker executes the obstacle avoidance action, and the calculation formula is as follows: Can be captured by a high-precision motion capture system (such as the ompartorax).
And respectively quantifying the influence degree of the laser point cloud mapping accuracy coefficient, the proportional relation between the instruction response time and the defined instruction response time and the proportional relation between the obstacle avoidance action accuracy factor and the defined obstacle avoidance action accuracy factor on the obstacle avoidance decision efficiency index through the importance value, summarizing the influence degrees, and correcting the summarized result through the correction coefficient, thereby obtaining the obstacle avoidance decision efficiency index of the high-precision stacker.
The obstacle avoidance decision efficiency index of the high-precision stacker is used for quantifying the obstacle avoidance decision efficiency of the high-precision stacker, and the specific expression is as follows:
;
In the formula, For the obstacle avoidance decision efficiency index of the high-precision stacker,In order to correct the coefficient of the coefficient,The laser point cloud mapping accuracy coefficient of the high-precision stacker,For the instruction response time of the high-precision stacker,For a defined instruction response duration preset in the intelligent database,Is an obstacle avoidance action accuracy factor of the high-precision stacker,For defining the obstacle avoidance action accuracy factors preset in the intelligent database,The importance value of the accurate coefficient is mapped for the laser point cloud preset in the intelligent database,For the importance value of the preset instruction response time length in the intelligent database,And the importance value of the obstacle avoidance action accuracy factor is preset in the intelligent database.
The defined instruction response time length represents the maximum value allowed by the instruction response time length, and the defined obstacle avoidance action accuracy factor represents the minimum value allowed by the obstacle avoidance action accuracy factor.
The method is characterized in that a strong coupling relation is formed between a laser point cloud mapping accuracy coefficient, an instruction response time length and an obstacle avoidance action accuracy factor through a sensing-decision-executing closed loop, the strong coupling relation is acted on an obstacle avoidance decision efficiency index together, a specific association mechanism is as follows, the laser point cloud mapping accuracy coefficient directly drives the obstacle avoidance action accuracy factor through environment sensing precision, when the coefficient is improved, obstacle contour resolution is improved, a space positioning reference is more accurate, the obstacle avoidance action accuracy factor is improved, the instruction response time length is restrained reversely through real-time, the obstacle avoidance action accuracy factor is restrained reversely through the real-time performance, the response time length is prolonged, the obstacle avoidance action accuracy factor is reduced due to the fact that path deviation risks caused by obstacle dynamic displacement (such as goods movement) are increased, the obstacle avoidance action accuracy factor is optimized through executing effect feedback, when the obstacle avoidance action accuracy factor is reduced, in order to increase accuracy of obstacle avoidance decision, local point cloud encryption resampling or reflectance compensation algorithm adjustment is automatically triggered, the obstacle avoidance action accuracy factor is improved, and a forward circulation mechanism of 'precision conducting, real-time constraint, feedback optimization' is formed in a dynamic environment, and reliability is improved.
The intelligent database stores the corresponding relation between the laser point cloud mapping accuracy coefficient, the instruction response time length and the obstacle avoidance action accuracy factor and the corresponding importance value thereof, for example, the laser point cloud mapping accuracy coefficient, the instruction response time length and the obstacle avoidance action accuracy factor are input into the intelligent database, and the intelligent database can search the importance value of the laser point cloud mapping accuracy coefficient, the importance value of the instruction response time length and the importance value of the obstacle avoidance action accuracy factor, which are all between 0 and 1.
Further, the obstacle avoidance process of the high-precision stacker is regulated, wherein the specific regulation process is to judge whether a fourth condition exists, if so, decision early warning is carried out on the obstacle avoidance process of the high-precision stacker, and specifically, an early warning instruction is generated and sent to technicians in the form of mails and the like.
And the intelligent database stores an obstacle avoidance decision efficiency deviation value-operation speed reduction coefficient mapping table and an obstacle avoidance decision efficiency deviation value-safety margin increase coefficient mapping table, the corresponding operation speed reduction coefficient and safety margin increase coefficient can be obtained by directly inquiring the obstacle avoidance decision efficiency deviation value of the high-precision stacker in the intelligent database, the operation speed reduction coefficient and the operation speed are multiplied, the product result is the operation speed after the adjustment is reduced, the safety margin increase coefficient and the safety margin are multiplied, the product result is the safety margin after the adjustment is increased, and the operation speed reduction coefficient is represented by the operation speed reduction coefficient after the adjustment, and the safety margin increase coefficient is represented by the safety margin increase.
The fourth condition is that the operation speed of the high-precision stacker is the minimum operation speed and the safety margin of the high-precision stacker is the maximum safety margin, and the minimum operation speed and the maximum safety margin are formulated by technicians.
In a specific embodiment, the invention provides a high-precision intelligent obstacle avoidance system of a stacker based on mixed guidance, which is characterized in that the operation safety and efficiency are obviously improved through a triple intelligent adjustment mechanism, firstly laser reflection parameters are collected in real time, the reflection process is dynamically optimized, the environment perception precision is ensured, then high-density point cloud mapping is generated, the space obstacle distribution is accurately restored, an automatic calibration mapping algorithm is performed through parameter analysis, the scene reduction degree is improved, finally multi-source data are fused, an obstacle avoidance path is generated through a mixed guidance strategy, abnormal fluctuation of decision parameters is synchronously monitored, the closed-loop optimization of path planning is realized, the technology breaks through the static response limitation of the traditional obstacle avoidance system, the centimeter-level obstacle avoidance precision is realized in a complex storage environment through three-stage self-adaptive adjustment of laser-point cloud-decision, the collision risk is effectively reduced, and the intellectualization and reliability of storage logistics are improved.
Referring to fig. 2, the second aspect of the present invention provides an intelligent obstacle avoidance method for a high-precision stacker based on mixed guidance, which includes the steps of firstly, collecting and analyzing laser reflection parameters of the high-precision stacker to determine whether to intelligently adjust a laser reflection process of the high-precision stacker, secondly, collecting laser reflection results of the high-precision stacker, performing point cloud mapping, acquiring and analyzing point cloud mapping parameters to determine whether to intelligently adjust a point cloud mapping process of the high-precision stacker, thirdly, acquiring and analyzing obstacle avoidance decision parameters of the high-precision stacker to determine whether to adjust an obstacle avoidance process of the high-precision stacker based on the point cloud mapping results of the high-precision stacker, and mixing and guiding the high-precision stacker.
FIG. 3 is a schematic diagram of a laser reflection adjustment flow chart of the invention, after the system is started, firstly collecting laser reflection parameters including reflection frequency, reflectivity and speckle contrast, calculating a reflection index, and comprehensively quantifying the deviation of each parameter and a reference value by introducing an importance coefficient to calculate the laser reflection index. The index is used for measuring the comprehensive condition of the current laser reflection characteristic, judging and adjusting, namely checking a first condition (whether gain/exposure is a basic value) if the reflection index is in a reference interval, if so, maintaining the current parameter, and if not, recovering the basic value of the gain and the exposure time according to a preset reflection recovery speed. If the reflection index exceeds the interval, the reflection index is larger than the maximum value, the current area is marked as a high reflection area, the gain and the exposure time length are reduced based on the first laser reflectivity, and the reflection index is smaller than the minimum value, the current area is marked as a low reflection area, and the gain and the exposure time length are increased based on the second laser reflectivity.
FIG. 4 is a schematic diagram of a point cloud mapping adjustment flow chart of the invention, which receives laser reflection adjusted data, analyzes point cloud mapping parameters including point cloud distribution density, mapping duration deviation degree and angle resolution, and calculates an accuracy coefficient, wherein the accuracy coefficient is calculated by comprehensively quantifying deviation of each mapping parameter and a reference value according to a laser reflection index matching correction coefficient, and the coefficient is used for quantifying accuracy degree of point cloud mapping. Judging and adjusting, namely checking a second condition (whether the mapping margin meets the standard or not) if the accuracy coefficient is more than or equal to a threshold value, if the second condition meets the standard or not, keeping the current mapping parameter, if the second condition does not meet the standard, recovering the plane fitting iteration number and the reflectivity abrupt change response speed to basic values according to a preset mapping recovery speed, and adjusting the plane fitting iteration number and the reflectivity abrupt change response speed based on the accuracy deviation value if the accuracy coefficient is more than or equal to the threshold value. The high reflection area increases the adjustment amount and the low reflection area decreases the adjustment amount.
FIG. 5 is a schematic diagram of an obstacle avoidance process, wherein based on the point cloud mapping result, obstacle avoidance decision parameters including instruction response time and obstacle avoidance action accuracy factors are analyzed, and efficiency index calculation is performed by quantifying deviation of each decision parameter from a reference value through an importance value, and calculating an obstacle avoidance decision efficiency index in a combined way. The index is used for quantifying the effectiveness of the obstacle avoidance decision, judging and adjusting, wherein if the effectiveness index is larger than or equal to a threshold value, checking a third condition (whether the effectiveness margin meets the standard), if the third condition is met, keeping the current obstacle avoidance parameter, if the third condition is not met, recovering the speed according to a preset decision, recovering the speed and the obstacle avoidance safety margin to a basic value, if the effectiveness index is smaller than the threshold value, judging whether a fourth condition (whether the minimum speed/maximum margin is reached) exists, if the fourth condition exists, triggering decision early warning, and if the fourth condition does not exist, reducing the speed and increasing the safety margin based on the effectiveness margin.
The foregoing is merely illustrative of the structures of this invention and various modifications, additions and substitutions for those skilled in the art of describing particular embodiments without departing from the structures of the invention or exceeding the scope of the invention as defined by the claims.
Claims (8)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510613862.XA CN120122670B (en) | 2025-05-13 | 2025-05-13 | A high-precision stacker crane intelligent obstacle avoidance system and method based on hybrid guidance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510613862.XA CN120122670B (en) | 2025-05-13 | 2025-05-13 | A high-precision stacker crane intelligent obstacle avoidance system and method based on hybrid guidance |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN120122670A CN120122670A (en) | 2025-06-10 |
| CN120122670B true CN120122670B (en) | 2025-09-05 |
Family
ID=95921467
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510613862.XA Active CN120122670B (en) | 2025-05-13 | 2025-05-13 | A high-precision stacker crane intelligent obstacle avoidance system and method based on hybrid guidance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120122670B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120621375B (en) * | 2025-08-18 | 2025-10-28 | 龙岩学院 | Multi-source sensing data fusion intelligent reversing decision and control system for semi-trailer |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118938945A (en) * | 2024-10-15 | 2024-11-12 | 军融装备智能制造(厦门)有限公司 | Intelligent obstacle avoidance method and system for flood drainage robot |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114564024A (en) * | 2022-03-15 | 2022-05-31 | 安歌科技(集团)股份有限公司 | Forklift AGV laser obstacle avoidance control method |
| CN115267825A (en) * | 2022-06-24 | 2022-11-01 | 奥比中光科技集团股份有限公司 | Obstacle avoidance and navigation method, device and storage medium for sweeper based on TOF sensor |
| ES3013898T3 (en) * | 2022-12-23 | 2025-04-15 | Hiab Ab | Image and range sensor-based position controller and associated method |
| CN118068841B (en) * | 2024-04-22 | 2024-06-28 | 东莞理工学院 | An intelligent obstacle avoidance system for logistics AGV based on multi-sensor technology |
| CN119612035B (en) * | 2025-02-14 | 2025-05-27 | 龙岩学院 | Intelligent warehousing operation auxiliary system and method based on mixed reality |
| CN119658721B (en) * | 2025-02-20 | 2025-04-25 | 北京信通泰克科技有限公司 | A robot rescue emergency control system based on voice interaction |
-
2025
- 2025-05-13 CN CN202510613862.XA patent/CN120122670B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118938945A (en) * | 2024-10-15 | 2024-11-12 | 军融装备智能制造(厦门)有限公司 | Intelligent obstacle avoidance method and system for flood drainage robot |
Also Published As
| Publication number | Publication date |
|---|---|
| CN120122670A (en) | 2025-06-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108896050B (en) | A long-term positioning system and method for mobile robot based on laser sensor | |
| CN120122670B (en) | A high-precision stacker crane intelligent obstacle avoidance system and method based on hybrid guidance | |
| CN117170354B (en) | Wheel type robot positioning method and system | |
| CN118877740A (en) | A blind spot monitoring system for quay crane operation | |
| CN118522181A (en) | Real-time early warning system of vehicle based on AI | |
| CN120024817B (en) | A crane anti-collision detection method, system, device and medium | |
| CN119785454A (en) | Dynamic monitoring system for safe driving behavior and safe production of mobile machinery on-site based on AI big model | |
| CN118864531A (en) | A multi-vehicle target tracking method based on roadside lidar point cloud data | |
| CN120472404A (en) | Adaptive context-aware vehicle target tracking and recognition system | |
| CN118419788A (en) | Intelligent control system for approaching protection and anti-collision protection of monorail crane personnel | |
| CN119828188B (en) | Goods dynamic tracking system and method adopting satellite accurate positioning | |
| CN119848436B (en) | Hydraulic and hydroelectric engineering data management method based on BIM information processing | |
| CN119197511A (en) | A mobile navigation system for intelligent service robots | |
| CN119088045A (en) | Intelligent adjustment system for harvester operating speed | |
| CN118618382B (en) | Automatic driving longitudinal control method and system based on underground mining scraper | |
| CN120431552B (en) | Obstacle detection method and unmanned vehicle | |
| CN119762788B (en) | Comprehensive calculation method, device and equipment for loss function | |
| CN118758430B (en) | Electromechanical temperature measurement analysis system and method based on machine vision | |
| CN118625813B (en) | Control method for preventing mowing robot from going out of limit | |
| CN120352877B (en) | An obstacle recognition device based on laser point cloud data | |
| CN119547627B (en) | An automatic leveling system for peanut harvesters in hilly and mountainous areas | |
| CN120920313A (en) | A vision-based adhesive application system for automotive production lines | |
| CN120927002A (en) | A method and system for ward round navigation of medical robots | |
| CN120687708A (en) | A transformer environmental risk assessment method and system based on dynamic threshold | |
| CN120974450A (en) | Multi-mode fusion tool magazine collision early warning method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |