CN113268055B - Obstacle avoidance control method and device for engineering vehicle and mechanical equipment - Google Patents
Obstacle avoidance control method and device for engineering vehicle and mechanical equipment Download PDFInfo
- Publication number
- CN113268055B CN113268055B CN202110370610.0A CN202110370610A CN113268055B CN 113268055 B CN113268055 B CN 113268055B CN 202110370610 A CN202110370610 A CN 202110370610A CN 113268055 B CN113268055 B CN 113268055B
- Authority
- CN
- China
- Prior art keywords
- information
- obstacle
- engineering vehicle
- actuating mechanism
- actuator
- 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
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000007246 mechanism Effects 0.000 claims abstract description 174
- 230000001133 acceleration Effects 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000013527 convolutional neural network Methods 0.000 claims description 8
- 230000000007 visual effect Effects 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 2
- 230000008569 process Effects 0.000 description 11
- 238000012545 processing Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000006378 damage Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 238000009412 basement excavation Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 210000000245 forearm Anatomy 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000008399 tap water Substances 0.000 description 1
- 235000020679 tap water Nutrition 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
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
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
- G05D1/0251—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means extracting 3D information from a plurality of images taken from different locations, e.g. stereo vision
-
- 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
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- 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
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0219—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory ensuring the processing of the whole working surface
-
- 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
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- 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
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Electromagnetism (AREA)
- Operation Control Of Excavators (AREA)
Abstract
The application provides an engineering vehicle obstacle avoidance control method, device and mechanical equipment, wherein the method comprises the following steps of; acquiring position information and image information of the engineering vehicle; calculating first position information of the actuating mechanism and obstacle information around the actuating mechanism through a trained model according to the image information; acquiring an angle parameter of the actuating mechanism, and calculating second position and attitude information of the actuating mechanism according to the angle parameter, the position information and a preset initial model parameter of the engineering vehicle; correcting the pose information of the executing mechanism based on the first pose information and the second pose information, and determining the relative position relation between the executing mechanism and the obstacle according to the corrected pose information and the obstacle information; and controlling the engineering vehicle to avoid the obstacle by adopting a preset obstacle avoiding strategy corresponding to the relative position relation. According to the method and the device, on the basis of low cost, the accuracy of recognizing the obstacle by the engineering vehicle is greatly improved, and the safety obstacle avoidance performance of the engineering vehicle is improved.
Description
Technical Field
The application belongs to the technical field of video processing, and particularly relates to an obstacle avoidance control method and device for an engineering vehicle and mechanical equipment.
Background
With the progress of science and technology, the development of the engineering machinery field also enters the period of accelerated development. In the construction process of an engineering vehicle (such as an excavator), the engineering vehicle belongs to a large-angle rotation process in space, and particularly under complex working conditions of tunnel excavation, trench excavation at the road side, normal rotation of the whole machine, overhead electric wires at the periphery and the like, serious damage to a tap water pipeline, a gas pipeline, a cable pipeline, an overhead high-voltage wire and peripheral fixed facilities and even serious accidents such as casualties can be caused by accidents due to the limited visual field range or misoperation of a manipulator and the like. Therefore, during the operation of the excavating machine, it is necessary to determine and avoid obstacles within the moving range of the working device, and to prevent collision and possible problems such as personal injury, article damage, and self-machine damage.
Disclosure of Invention
The application provides an engineering vehicle obstacle avoidance control method, device and mechanical equipment, which are used for acquiring operation information of an engineering vehicle and angle parameters of an actuating mechanism of the engineering vehicle, calculating the pose of the actuating mechanism through a trained model, the angle parameters and position information and correcting the pose.
The embodiment of the first aspect of the application provides an obstacle avoidance control method for an engineering vehicle, and the method comprises the following steps of;
acquiring operation information of the engineering vehicle, wherein the operation information comprises position information and image information of an actuating mechanism of the engineering vehicle, and the image information comprises the actuating mechanism, an environment information in a specified area around the actuating mechanism and a specified range of an operation direction;
calculating first position information of the actuating mechanism and obstacle information around the actuating mechanism through a trained model according to the image information;
acquiring an angle parameter of the actuating mechanism, and calculating second position and attitude information of the actuating mechanism according to the angle parameter, the position information and a preset initial model parameter of the engineering vehicle;
correcting the pose information of the executing mechanism based on the first pose information and the second pose information, and determining the relative position relation between the executing mechanism and the obstacle according to the corrected pose information and the obstacle information;
and controlling the engineering vehicle to avoid the obstacle by adopting a preset obstacle avoiding strategy corresponding to the relative position relation.
Optionally, the correcting the pose information of the actuator based on the first pose information and the second pose information includes:
determining a first coordinate of the tail end of the executing mechanism according to the first position and posture information and determining a second coordinate of the tail end of the executing mechanism according to the second position and posture information based on a preset model coordinate system of the engineering vehicle;
correcting the coordinates of the tail end of the executing mechanism based on the first coordinates and the second coordinates, and determining corrected coordinates of the tail end of the executing mechanism;
and determining coordinates at each rotating shaft of the executing mechanism based on the corrected coordinates and preset initial model parameters of the engineering vehicle so as to determine corrected pose information of the executing mechanism.
Optionally, the determining corrected coordinates of the tip end of the actuator by correcting coordinates of the tip end of the actuator by the first coordinates and the second coordinates includes:
correcting the coordinates of the end of the actuator based on the first coordinates and the second coordinates according to the following formula, and determining corrected coordinates of the end of the actuator:
T＝α×T imu +(1-α)×T stereo
wherein T is a corrected coordinate of the end of the actuator, T imu Is said second coordinate, T stereo For the first coordinate, a is ∈ (0, 1) is confidence.
Optionally, the calculating, according to the operation information, first attitude information of the actuator and obstacle information around the actuator by a trained model includes:
calculating first attitude information of the actuating mechanism through a trained convolutional neural network model according to the position information of the actuating mechanism;
and identifying obstacles around the executing mechanism through a clustering algorithm according to the environmental information in the specified area around the executing mechanism and the specified range of the operation direction, and determining the shape information and the position information of the obstacles.
Optionally, the determining a relative position relationship between the actuator and the obstacle according to the corrected pose information and the obstacle information includes:
and correcting the position information of the obstacle through the corrected pose information, and determining the relative position relation between the actuating mechanism and the obstacle according to the corrected pose information and the corrected position information of the obstacle.
Optionally, the calculating second position and orientation information of the actuator according to the angle parameter, the position information of the actuator, and a preset initial model parameter of the engineering vehicle includes:
calculating second position and posture information of the actuating mechanism according to the angle parameter, the position information of the actuating mechanism and a preset initial model parameter of the engineering vehicle and the following formula:
wherein, T is n The theta is the corrected coordinate of the nth rotation axis in the direction away from the engineering vehicle n Is the angle of the nth rotation axis in the direction away from the engineering vehicle n For the motion rotation amount of the n-th rotation axis in the direction away from the working vehicle, [ S ] n ]Is S n M is an initial pose matrix of the actuator.
Optionally, the controlling the engineering vehicle to avoid the obstacle by using a preset obstacle avoidance strategy corresponding to the relative position relationship includes:
determining the starting position of the actuating mechanism and the position of a target point avoiding the obstacle according to the relative position relation;
obtaining a target angle of the actuating mechanism moving from the starting point position to the target point position through a line kinematics inverse solution principle;
planning a path of the actuating mechanism through the target angle and the angle of the actuating mechanism at the starting point position;
and controlling the engineering vehicle to avoid the obstacle according to the planned path.
Optionally, if the method is implemented by remote control, the step of controlling the engineering vehicle to avoid the obstacle by using a preset obstacle avoidance strategy corresponding to the relative position relationship includes:
if the obstacle is identified to be in the current visual field, when the distance between the obstacle and the executing mechanism is smaller than a first preset threshold value, prompting a driver to drive carefully; when the distance between the obstacle and the executing mechanism is smaller than a second preset threshold value, stopping the remote control of the engineering vehicle; the second preset threshold is smaller than the first preset threshold;
if an obstacle is identified outside the current field of view and the distance between the obstacle and the executing mechanism is gradually reduced, prompting a driver to drive carefully when the distance between the obstacle and the executing mechanism is smaller than the first preset threshold value; and when the distance between the obstacle and the executing mechanism is smaller than a second preset threshold value, stopping the remote control of the engineering vehicle.
Optionally, the method further comprises:
and if the pixels of the image information of two adjacent frames change in a step-shaped manner, determining that an obstacle exists in the current visual field, and controlling the execution mechanism to move towards the direction far away from the obstacle.
Optionally, the obtaining operation information of the engineering vehicle includes:
the working information of the engineering vehicle is obtained through a plurality of binocular cameras which are respectively arranged at different positions of the engineering vehicle.
Optionally, the angle parameter includes an angular velocity and a rotational acceleration, and the obtaining the angle parameter of the actuator includes:
and acquiring the rotation angle and the rotation acceleration of the actuating mechanism through an inertial sensor arranged on the engineering vehicle.
An embodiment of the second aspect of the present application provides an obstacle avoidance control device for an engineering vehicle, the device includes:
the binocular camera is arranged on the engineering vehicle and used for shooting operation information of the engineering vehicle, wherein the operation information comprises position information and image information of an actuating mechanism of the engineering vehicle, and the image information comprises environmental information in a specified area around the actuating mechanism and a specified range of an operation direction;
the inertial sensor is arranged on an actuating mechanism of the engineering vehicle and used for acquiring angle parameters of the actuating mechanism;
the control unit, the control unit respectively with binocular camera the inertial sensor reaches engineering vehicle connects for:
calculating first position and orientation information of the executing mechanism through a trained model according to the image information, and determining obstacle information around the executing mechanism according to a clustering algorithm;
calculating second position and attitude information of the actuating mechanism according to the angle parameter, the position information and a preset initial model parameter of the engineering vehicle;
correcting the pose information of the executing mechanism based on the first pose information and the second pose information, and determining the relative position relation between the executing mechanism and the obstacle according to the corrected pose information and the obstacle information;
and controlling the engineering vehicle to avoid the obstacle by adopting a preset obstacle avoiding strategy corresponding to the relative position relation.
The embodiment of the third aspect of the application provides mechanical equipment, which comprises an engineering vehicle and further comprises an engineering vehicle obstacle avoidance control device of the second aspect, wherein the engineering vehicle obstacle avoidance control device is used for controlling the engineering vehicle to safely avoid obstacles.
Optionally, the engineering vehicle is an excavator, and an actuating mechanism of the excavator comprises a rotary table, a large arm, a small arm and an excavator bucket which are sequentially and rotatably connected;
the binocular camera comprises at least one camera which is arranged on the rotary table and can photograph the full view of the large arm, the full view of the small arm and the full view of the excavator bucket;
the inertial sensors comprise at least four inertial sensors which are respectively arranged on the rotary table, the large arm, the small arm and the bucket so as to respectively acquire angle parameters of the rotary table, the large arm, the small arm and the bucket.
The technical scheme provided in the embodiment of the application at least has the following technical effects or advantages:
the engineering vehicle obstacle avoidance control method provided by the embodiment of the application comprises the steps of respectively obtaining operation information of an engineering vehicle and angle parameters of an execution mechanism of the engineering vehicle, respectively calculating first position information of the execution mechanism and obstacle information around the execution mechanism through a trained model according to the operation information, calculating second position information of the execution mechanism according to the angle parameters, the position information and preset initial model parameters of the engineering vehicle, and correcting the first position information and the second position information to obtain corrected positions; and then obtaining the relative position relation between the actuating mechanism and the obstacle according to the corrected pose and obstacle information, and then adopting an obstacle avoidance strategy corresponding to the relative position relation to carry out an obstacle avoidance strategy on the engineering vehicle, so that the accuracy of the engineering vehicle in identifying the obstacle is greatly improved on the basis of low cost, and the safety obstacle avoidance performance of the engineering vehicle is improved.
Drawings
Various additional advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to refer to like parts throughout the drawings.
In the drawings:
fig. 1 is a schematic flow chart of an obstacle avoidance control method for an engineering vehicle according to an embodiment of the present invention;
fig. 2 is a schematic view of the structure and processing logic of the obstacle avoidance control device for the engineering vehicle according to the embodiment of the present invention;
FIG. 3 is a schematic front view of the positional relationship between the binocular camera and the respective rotating shafts of the excavator;
FIG. 4 is a schematic side view of the positional relationship between the binocular camera and the respective rotating shafts of the excavator;
fig. 5a-5f are simulation model demonstration process diagrams for controlling the excavator to avoid the obstacle according to the obstacle avoidance control method provided by the scheme.
Detailed Description
Exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which this application belongs.
The following describes an obstacle avoidance control method, an obstacle avoidance control device and mechanical equipment for an engineering vehicle according to an embodiment of the present application, with reference to the accompanying drawings.
The embodiment of the application provides an engineering vehicle obstacle avoidance control method, which can be applied to an engineering vehicle obstacle avoidance control device, wherein the control device can be a processor with a processing function, the method respectively acquires operation information of an engineering vehicle and angle parameters of an actuating mechanism of the engineering vehicle, calculates the pose of the actuating mechanism according to the operation information through a trained model and the angle parameters, and corrects the pose calculated in two modes to obtain the corrected pose; and identifying the obstacle through the trained model according to the operation information to obtain obstacle information, obtaining the relative position relation between the actuating mechanism and the obstacle according to the corrected pose and the obstacle information, and then adopting an obstacle avoidance strategy corresponding to the relative position relation to carry out an obstacle avoidance strategy on the engineering vehicle. Therefore, the pose of the actuating mechanism is calculated and corrected in two ways, the relative position relation between the actuating mechanism and the obstacle is determined according to the corrected pose, the accuracy of the engineering vehicle in identifying the obstacle can be greatly improved on the basis of low cost, and the safety obstacle avoidance performance of the engineering vehicle is improved.
Referring to fig. 1, the method specifically includes the following steps;
and S1, acquiring operation information of the engineering vehicle.
Wherein the work vehicle may be an excavator, a bulldozer, a loader, or the like. The work information may include position information of an actuator of the construction vehicle and image information, and the image information may include environmental information in a designated area around the actuator and a designated range of a work direction. The actuators of the work vehicle are to be understood as a generic term for the movement mechanisms during work operations, each of which can be regarded as a sub-actuator of the actuator. For example, the engineering vehicle is an excavator, and the sub-actuating mechanism of the engineering vehicle can comprise a rotary table, a big arm, a small arm, an excavator bucket and the like; if the working vehicle is a loader, the sub-actuator may include a stage, a lifting mechanism, a telescoping mechanism, and the like.
In this embodiment, as shown in fig. 2, a binocular camera capable of collecting depth information may be used to obtain the work information of the engineering vehicle, and accordingly, obtaining the work information of the engineering vehicle may include the following processes: the working information of the engineering vehicle is obtained through a plurality of binocular cameras respectively arranged at different positions of the engineering vehicle. Therefore, the binocular camera can be used for acquiring the operation information comprising the position information and the image information, so that the control device can calculate the pose of the actuating mechanism according to the preset operation information. Specifically, for the excavator, the binocular camera may include at least one camera which is provided on the turntable and can photograph the entire view of the boom, the boom and the bucket to ensure the operation information.
It should be noted that the binocular camera is only a preferred embodiment of the present embodiment, and the present embodiment is not limited to this, and other operation information collecting devices may also be used as long as the position information and the image information can be collected.
And S2, calculating first position information of the actuating mechanism and obstacle information around the actuating mechanism according to the image information through the trained model.
The trained models can comprise a convolutional neural network model for identifying and calculating pose information of the actuating mechanism and a clustering algorithm model for identifying and calculating obstacle information. The pose may be understood as the position pose of the actuator, and the pose information may include pose information of each actuator (e.g., an angle between two sub-actuators), coordinate data of each sub-actuator, and the like. The first pose information and the second pose information described below are only pose information calculated by two methods, and are used for distinction, without limitation.
Before practical application, a simulation test can be carried out, various scene images (namely the image information) possibly encountered in the practical operation process are collected through a binocular camera, a convolutional neural network model is trained through deep learning, and the control device can identify obstacles and execution mechanisms in the image information in real time (only any sub-execution mechanism can be identified, for example, a bucket of an excavator can be identified, and other sub-execution mechanisms can be obtained through calculation according to the information of the bucket). And a three-dimensional model can be established according to actual engineering vehicle data, and the convolutional neural network model can be trained by combining the three-dimensional model so as to obtain specific coordinate data of the obstacle and the actuating mechanism.
In a specific embodiment of this embodiment, calculating the first attitude information of the actuator and the obstacle information around the actuator by the trained model according to the operation information may include the following processes: calculating first attitude information of the actuating mechanism through a trained convolutional neural network model according to the position information of the actuating mechanism; and identifying obstacles around the actuating mechanism through a clustering algorithm according to the environmental information in the designated area around the actuating mechanism and the designated range of the operating direction, and determining the shape information and the position information of the obstacles.
Taking an excavator as an example, in the operation process of the excavator, the control device can continuously acquire operation information in a visual field range by adopting a binocular camera, and can calculate the pose information of the actuating mechanism by a trained convolutional neural network model. The executing mechanism and the obstacle (which part in the point cloud coordinate may be the obstacle) can be identified from the operation information by a clustering algorithm model (training of which can be understood as simple simulation calculation) and the shape, size, position information and the like of the obstacle can be calculated by using a clustering algorithm, and the information of the obstacle is stored. Therefore, in the operation process, the surrounding environment condition diagram is gradually constructed, and the surrounding environment condition diagram comprises the position in the diagram and the specific size and shape of the obstacle, so that the excavator can find the existence of the obstacle in time when the obstacle cannot be seen, and can take obstacle avoidance measures in time.
The present embodiment is not limited to the convolutional neural network model, and may be implemented as long as the first pose information of the actuator and the obstacle information around the actuator can be calculated from the image information after training, and may be, for example, a deep belief network model, a stacked self-coding network model, or the like.
And S3, acquiring the angle parameter of the actuating mechanism, and calculating second position and attitude information of the actuating mechanism according to the angle parameter, the position information and the preset initial model parameter of the engineering vehicle.
The angle parameters may include angular velocity and rotational acceleration, and specifically may include angular velocity and rotational acceleration of all actuators of the same work vehicle.
Specifically, the angular parameters of the actuators can be obtained through the inertial sensors arranged on the engineering vehicle, and the corresponding number of inertial sensors can be arranged corresponding to the number of the specific sub-actuators, so that the angular velocity and the rotational acceleration of each sub-actuator can be accurately obtained. For example, for an excavator, at least four inertial sensors may be used and respectively disposed on the turntable, the boom, the forearm and the bucket to respectively obtain angle parameters of the turntable, the boom, the forearm and the bucket.
Taking an excavator as an example, when calculating the second position and orientation information of the actuator, firstly, coordinates of each inertial sensor need to be unified, as shown in fig. 3 and 4, distance relationships between a coordinate system and each sub-actuator are marked in the figures, wherein L1 is a distance between a rotating shaft of the small arm and a rotating shaft of the large arm, L2 is a distance between a rotating shaft of the bucket and a rotating shaft of the small arm, and L3 is a distance between a bucket end and a rotating shaft of the bucket. A1, B1 and C1 are respectively three-dimensional coordinates of a binocular camera, the included angles between L1, L2 and L3 and a horizontal line are respectively theta 1, theta 2 and theta 3, the included angles can be calculated by using the rotation of rigid motion, and when all rotating shafts are at initial positions (all rotating shaft angles are 0 degrees), an initial pose matrix of an actuating mechanism is as follows:
considering that each rotating shaft (such as a large arm and a small arm bucket of a rotary table) has a zero pitch motion rotation, the motion rotation of each rotating shaft can be written as follows:
S 1 ＝[0 0 1 -A1 B1 0]
S 2 ＝[0 0 1 -A1 B1 -L1 0]
S 3 ＝[0 0 1 -A1 B1 -L1 -L2 0]
wherein S is 1 The motion rotation amount of the 1 st rotating shaft along the direction far away from the engineering vehicle is the motion rotation amount of the rotating shaft of the large arm; s 2 The motion screw amount of the 2 nd rotating shaft along the direction far away from the engineering vehicle is the motion screw amount of the rotating shaft of the small arm; s 3 The motion rotation of the 3 rd rotating shaft in the direction far away from the engineering vehicle, namely the motion rotation of the rotating shaft of the bucket.
Based on the above principle, calculating the second position and orientation information of the actuator according to the angle parameter, the position information of the actuator, and the preset initial model parameter of the engineering vehicle may include:
according to the angle parameter, the position information of the actuating mechanism and the preset initial model parameter of the engineering vehicle, calculating the second position and attitude information of the actuating mechanism according to the following formula:
wherein, T n Corrected coordinates, theta, for the nth axis of rotation in the direction away from the work vehicle n Is the angle of the nth rotation axis in the direction away from the working vehicle, S n The motion rotation amount of the nth rotating shaft in the direction far away from the engineering vehicle,
is S n Lie algebraic form of (w is angular velocity, v is rotational acceleration, [ w ]]Is a lie algebra form of w), and M is an initial pose matrix of the tail end of the actuating mechanism.
Thus, the calculated M and S of the bucket end are calculated n And theta n Substituting into the above formula, T can be calculated n Obtaining the coordinates of the end of the bucket, and then detecting L1 and L according to the preset initial model parameters2. L3, theta 1, theta 2 and theta 3, and then the coordinates of the rotating shafts of the large arm, the small arm and the rotary table can be respectively calculated, so that complete pose information of the actuating mechanism can be obtained.
And S4, correcting the pose information of the executing mechanism based on the first pose information and the second pose information, and determining the relative position relation between the executing mechanism and the obstacle according to the corrected pose information and the obstacle information.
In this embodiment, when identifying an obstacle, the pose information of the actuator is corrected based on the first pose information and the second pose information, so that more accurate pose information of the actuator can be obtained at a low cost. Thus, the relative position relationship between the actuating mechanism and the obstacle is determined according to the corrected pose information, so that the obstacle identification accuracy can be improved (the obstacle identification accuracy can be achieved by adopting an image acquisition device with low accuracy, such as a binocular camera, and expensive and high-accuracy identification accuracy).
In another specific implementation manner of this embodiment, the correcting the pose information of the actuator according to the coordinate data, and accordingly, correcting the pose information of the actuator based on the first pose information and the second pose information may include the following processes: determining a first coordinate of the tail end of the executing mechanism according to the first position and posture information and determining a second coordinate of the tail end of the executing mechanism according to the second position and posture information based on a preset model coordinate system of the engineering vehicle; correcting the coordinates of the tail end of the executing mechanism based on the first coordinates and the second coordinates, and determining corrected coordinates of the tail end of the executing mechanism; and determining coordinates of each rotating shaft of the executing mechanism based on the corrected coordinates and preset initial model parameters of the engineering vehicle so as to determine corrected pose information of the executing mechanism.
Further, determining corrected coordinates of the tip end of the actuator by correcting the coordinates of the tip end of the actuator for the first coordinates and the second coordinates may include: correcting the coordinates of the tail end of the actuator based on the first coordinates and the second coordinates according to the following formula, and determining corrected coordinates of the tail end of the actuator:
T＝α×T imu +(1-α)×T stereo
wherein T is the corrected coordinate of the end of the actuator, T imu Is a second coordinate, T stereo As the first coordinate, a is ∈ (0, 1) is the confidence. The specific value of A can be obtained through experiments, and specifically, before practical application, the real three-dimensional coordinate of the bucket is measured and substituted into T in the formula, and then the T is calculated respectively according to the obtained operation information, angle parameters and the like stereo And T imu Substituting the formula into the formula to calculate alpha, and after multiple calculations, selecting a value with the highest occurrence frequency from the multiple values obtained by solution, or determining the average value of the multiple values as the numerical value of alpha.
Further, considering that the value of T is more accurate, a multiplication conversion matrix of T can be obtained
And the coordinates of other points obtained according to the binocular camera can be corrected through the multiplication conversion matrix A, and the coordinates of the obstacle and the coordinates of the actuating mechanism are unified. When the information of the actuating mechanism and the obstacle is determined, the information can be determined through the corrected coordinates of the actuating mechanism and the corrected coordinates of the obstacle, so that the accuracy of identifying the obstacle is further improved.
And S5, controlling the engineering vehicle to avoid the obstacle by adopting a preset obstacle avoidance strategy corresponding to the relative position relation.
In this embodiment, the corresponding obstacle avoidance strategies may be preset in correspondence to various relative position relationships between the execution mechanism and the obstacle, so that timely responses may be performed for different situations when obstacle avoidance control is performed, and time errors caused by large data processing are avoided, which results in low operation efficiency and even causes an obstacle avoidance failure to cause a dangerous situation.
Based on the posture information correction principle, determining the relative position relationship between the actuating mechanism and the obstacle according to the corrected posture information and the obstacle information, and the method can comprise the following steps of: and correcting the position information of the obstacle through the corrected pose information, and determining the relative position relation between the actuating mechanism and the obstacle according to the corrected pose information and the corrected position information of the obstacle.
In another specific implementation manner of this embodiment, the controlling the engineering vehicle to avoid the obstacle by using a preset obstacle avoidance strategy corresponding to the relative position relationship may include the following steps: determining the starting position of the actuating mechanism and the position of a target point avoiding the obstacle according to the relative position relation; obtaining a target angle of the actuating mechanism moving from the starting point position to the target point position through a line kinematics inverse solution principle; planning a path of the actuating mechanism through the target angle and the angle of the actuating mechanism at the starting point position; and controlling the engineering vehicle to avoid the obstacle according to the planned path.
Specifically, taking the excavator automatic driving as an example, the work trajectory of the excavator is calculated by the control device. For example, a target point is set, a path from an actuator (e.g., a bucket) to the target point from a current position is planned, three target angles are obtained by inverse kinematic solution of three-dimensional coordinates of the target point, and the path is planned using spline functions between the three target angles and three initial angles, the spline functions being: s (t) = a 0 +a 1 t+a 2 t 2 +a 3 t 3 (ii) a To control the actuator more precisely, four constraints are added to the spline function: s (0) = θ 0 ，
s(T)＝θ t ，
Wherein the content of the first and second substances,
is s (0) = theta 0 Derivative function, θ 0 Is an initial angle, θ t Is the target angle. Thus, the angle of each time point in the T time period can be obtained. And then the planned angles are respectively transmitted to each sub-actuating mechanism of the excavator, so that the excavator can be controlled to automatically operate.
In the process of operating the automatic excavator, if there is an obstacle in the field of view, as shown in fig. 5a to 5f, for the action exploded view of controlling the excavator to avoid the obstacle by using the obstacle avoidance control method provided in this embodiment, the obstacle avoidance control device may consider the position information of the obstacle during path planning, and add a plurality of safety points between the starting point and the target point to avoid the obstacle during path planning, which is equivalent to adding more constraints during path planning, such as s (t 1) = θ = s t1 And s (t 2) = θ t2 Therefore, a new path for avoiding the obstacle can be calculated, and then the obstacle avoidance control device controls the executing mechanism to operate according to the calculated new path, so that the safe obstacle avoidance in the operation process can be realized. Similarly, if there are obstacles outside the field of view: the specific coordinates of the obstacle can be obtained from the previously stored operation information, and if the obstacle passes between the starting point and the target point, the coordinates of the obstacle can be used as a new constraint, and the same path algorithm is used to add a safety point and perform path planning again to avoid the obstacle.
In another specific implementation manner of this embodiment, the method is also implemented by remote control, and the control device can perform data interaction with a remote control end. The above-mentioned adopting the preset obstacle avoidance strategy corresponding to the relative position relationship to control the engineering vehicle to avoid the obstacle may specifically include the following processing: if the obstacle is identified to be in the current visual field, when the distance between the obstacle and the executing mechanism is smaller than a first preset threshold value, prompting a driver to drive carefully; when the distance between the obstacle and the executing mechanism is smaller than a second preset threshold value, stopping performing remote control on the engineering vehicle; the second preset threshold is smaller than the first preset threshold; if the obstacle is identified to be outside the current field of view and the distance between the obstacle and the execution mechanism is gradually reduced, prompting a driver to drive carefully when the distance between the obstacle and the execution mechanism is smaller than a first preset threshold value; and when the distance between the obstacle and the actuating mechanism is smaller than a second preset threshold value, stopping the remote control of the engineering vehicle.
Specifically, when the distance between the obstacle and the execution mechanism is smaller than a second preset threshold value, an instruction for invalidating the automatic program can be output through the operating console, the control device stops controlling the excavator, a warning is given, and after a driver notices a problem, the control device controls the excavator again through an unlocking instruction. Therefore, the position of the obstacle and the pose of the excavator bucket can be more accurately judged by combining data sent by the binocular camera and the imu sensor and experience of a driver, and a corresponding obstacle avoidance strategy can be timely made, so that the safety obstacle avoidance performance and the operation efficiency of remote control operation are improved.
In another specific implementation of this embodiment, the method further includes the following steps:
and if the pixel difference of the two adjacent frames of image information is greater than the preset difference value, determining that an obstacle exists in the current visual field, and controlling the actuating mechanism to move towards the direction far away from the obstacle. Therefore, the obstacle can be quickly identified through the pixel difference of the two adjacent frames of image information (when the pixel difference of the two adjacent frames of image information is smaller than the preset difference value, the model calculation can be adopted), so that the processing speed of the control device is further improved.
The method for controlling obstacle avoidance of an engineering vehicle, provided by this embodiment, includes obtaining operation information of the engineering vehicle and angle parameters of an execution mechanism of the engineering vehicle, calculating first position information of the execution mechanism and obstacle information around the execution mechanism according to the operation information through a trained model, calculating second position information of the execution mechanism according to the angle parameters, the position information and preset initial model parameters of the engineering vehicle, and correcting the first position information and the second position information to obtain a corrected position and posture; and then obtaining the relative position relation between the actuating mechanism and the obstacle according to the corrected pose and obstacle information, and then adopting an obstacle avoidance strategy corresponding to the relative position relation to carry out an obstacle avoidance strategy on the engineering vehicle, so that the accuracy rate of the engineering vehicle for identifying the obstacle is greatly improved on the basis of low cost, and the safety obstacle avoidance performance of the engineering vehicle is improved.
Based on the same concept of the above engineering vehicle obstacle avoidance control, the present embodiment further provides an engineering vehicle obstacle avoidance control device, as shown in fig. 2, the device includes:
the binocular camera is arranged on the engineering vehicle and used for shooting operation information and operation information of the engineering vehicle, wherein the operation information and operation information comprise position information and image information of an actuating mechanism of the engineering vehicle, and the image information comprises the actuating mechanism, an appointed area around the actuating mechanism and environment information in an appointed range of an operation direction;
the inertial sensor is arranged on an actuating mechanism of the engineering vehicle and used for acquiring angle parameters of the actuating mechanism;
the control unit is connected with binocular camera, inertial sensor and engineering vehicle respectively for:
calculating first position information of the actuating mechanism and obstacle information around the actuating mechanism through a trained model according to the image information;
calculating second position and attitude information of the actuating mechanism according to the angle parameter, the position information and a preset initial model parameter of the engineering vehicle;
correcting the pose information of the executing mechanism based on the first pose information and the second pose information, and determining the relative position relation between the executing mechanism and the obstacle according to the corrected pose information and the obstacle information;
and controlling the engineering vehicle to avoid the obstacle by adopting a preset obstacle avoiding strategy corresponding to the relative position relation.
The engineering vehicle obstacle avoidance control device provided by the embodiment can at least realize the beneficial effects that the engineering vehicle obstacle avoidance control method can realize, and the description is omitted here.
Based on the same concept of the obstacle avoidance control of the engineering vehicle, the embodiment further provides mechanical equipment which comprises the engineering vehicle and the obstacle avoidance control device of the engineering vehicle, wherein the obstacle avoidance control device of the engineering vehicle is used for controlling the engineering vehicle to safely avoid obstacles.
The mechanical equipment provided by the embodiment comprises the engineering vehicle obstacle avoidance control device, and also can at least realize the beneficial effects which can be realized by the engineering vehicle obstacle avoidance control method, and the details are not repeated herein.
In a specific embodiment of this embodiment, the engineering vehicle is an excavator, and the actuating mechanism of the excavator includes a turntable, a large arm, a small arm and an excavator bucket which are rotatably connected in sequence;
the binocular camera comprises at least one camera which is arranged on the rotary table and can photograph the full appearance of the big arm, the full appearance of the small arm and the full appearance of the bucket;
the inertial sensors comprise at least four inertial sensors which are respectively arranged on the rotary table, the large arm, the small arm and the bucket so as to respectively acquire angle parameters of the rotary table, the large arm, the small arm and the bucket.
It should be noted that the above-mentioned embodiments illustrate rather than limit the application, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means can be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
The above description is only for the preferred embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (13)
1. An obstacle avoidance control method for an engineering vehicle is characterized by comprising the following steps:
acquiring operation information of the engineering vehicle, wherein the operation information comprises position information and image information of an actuating mechanism of the engineering vehicle, and the image information comprises the actuating mechanism, an appointed area around the actuating mechanism and environment information in an appointed range of an operation direction;
calculating first position information of the actuating mechanism and obstacle information around the actuating mechanism through a trained model according to the image information;
acquiring an angle parameter of the actuating mechanism, and calculating second position and attitude information of the actuating mechanism according to the angle parameter, the position information and a preset initial model parameter of the engineering vehicle;
correcting the pose information of the executing mechanism based on the first pose information and the second pose information, and determining the relative position relation between the executing mechanism and the obstacle according to the corrected pose information and the obstacle information;
adopting a preset obstacle avoidance strategy corresponding to the relative position relationship to control the engineering vehicle to avoid obstacles;
wherein the correcting the pose information of the actuator based on the first pose information and the second pose information comprises:
determining a first coordinate of the tail end of the executing mechanism according to the first position and posture information and determining a second coordinate of the tail end of the executing mechanism according to the second position and posture information based on a preset model coordinate system of the engineering vehicle;
correcting the coordinates of the end of the actuator based on the first coordinates and the second coordinates according to the following formula, and determining corrected coordinates of the end of the actuator:
T＝α×T imu +(1-α)×T stereo
wherein T is a corrected coordinate of the end of the actuator, T imu Is said second coordinate, T stereo For the first coordinate, a is ∈ (0, 1) is confidence.
2. The method of claim 1, wherein after determining the corrective coordinates of the actuator tip, further comprising:
and determining coordinates at each rotating shaft of the executing mechanism based on the corrected coordinates and preset initial model parameters of the engineering vehicle so as to determine corrected pose information of the executing mechanism.
3. The method of claim 1, wherein the calculating the first pose information of the actuator and the obstacle information around the actuator from the image information by a trained model comprises:
calculating first attitude information of the actuating mechanism through a trained convolutional neural network model according to the position information of the actuating mechanism;
and identifying obstacles around the executing mechanism through a clustering algorithm according to the environmental information in the specified area around the executing mechanism and the specified range of the operation direction, and determining the shape information and the position information of the obstacles.
4. The method according to claim 3, wherein the determining the relative position relationship between the actuator and the obstacle according to the corrected pose information and the obstacle information comprises:
and correcting the position information of the obstacle through the corrected pose information, and determining the relative position relation between the actuating mechanism and the obstacle according to the corrected pose information and the corrected position information of the obstacle.
5. The method according to claim 1, wherein the calculating of the second position and orientation information of the actuator according to the angle parameter, the position information of the actuator and the preset initial model parameter of the engineering vehicle comprises:
calculating second position and posture information of the actuating mechanism according to the angle parameter, the position information of the actuating mechanism and a preset initial model parameter of the engineering vehicle and the following formula:
wherein, T is n The theta is the corrected coordinate of the nth rotation axis in the direction away from the engineering vehicle n Is the angle of the nth rotation axis in the direction away from the engineering vehicle n For the motion rotation amount of the n-th rotation axis in the direction away from the working vehicle, [ S ] n ]Is S n M is an initial pose matrix of the actuator.
6. The method according to claim 1, wherein the step of controlling the engineering vehicle to avoid an obstacle by adopting a preset obstacle avoidance strategy corresponding to the relative position relationship comprises:
determining the starting position of the actuating mechanism and the position of a target point avoiding the obstacle according to the relative position relation;
obtaining a target angle of the actuating mechanism moving from the starting point position to the target point position through a line kinematics inverse solution principle;
planning a path of the actuating mechanism through the target angle and the angle of the actuating mechanism at the starting point position;
and controlling the engineering vehicle to avoid the obstacle according to the planned path.
7. The method according to claim 1, wherein the method is implemented by remote control, and if the preset obstacle avoidance strategy corresponding to the relative position relationship is adopted to control the engineering vehicle to avoid an obstacle, the method includes:
if the obstacle is identified in the current visual field, when the distance between the obstacle and the execution mechanism is smaller than a first preset threshold value, prompting a driver to drive carefully; when the distance between the obstacle and the executing mechanism is smaller than a second preset threshold value, stopping the remote control of the engineering vehicle; the second preset threshold is smaller than the first preset threshold;
if an obstacle is identified outside the current field of view and the distance between the obstacle and the executing mechanism is gradually reduced, prompting a driver to drive carefully when the distance between the obstacle and the executing mechanism is smaller than the first preset threshold value; and when the distance between the obstacle and the executing mechanism is smaller than a second preset threshold value, stopping the remote control of the engineering vehicle.
8. The method of claim 1, further comprising:
and if the pixels of the image information of two adjacent frames change in a stepwise manner, determining that an obstacle exists in the current visual field, and controlling the execution mechanism to move towards the direction far away from the obstacle.
9. The method according to claim 1, wherein the obtaining operation information of the engineering vehicle comprises:
the working information of the engineering vehicle is obtained through a plurality of binocular cameras which are respectively arranged at different positions of the engineering vehicle.
10. The method of claim 1, wherein the angular parameters include angular velocity and rotational acceleration, and wherein obtaining the angular parameters of the actuator comprises:
and acquiring the rotation angle and the rotation acceleration of the actuating mechanism through an inertial sensor arranged on the engineering vehicle.
11. An obstacle avoidance control device for an engineering vehicle, the obstacle avoidance control device comprising:
the binocular camera is arranged on the engineering vehicle and used for shooting operation information of the engineering vehicle, wherein the operation information comprises position information and image information of an actuating mechanism of the engineering vehicle, and the image information comprises the actuating mechanism, an environment information in a specified area around the actuating mechanism and an operation direction specified range;
the inertial sensor is arranged on an actuating mechanism of the engineering vehicle and used for acquiring angle parameters of the actuating mechanism;
the control unit, the control unit respectively with binocular camera the inertial sensor reaches engineering vehicle connects for:
calculating first position information of the actuating mechanism and obstacle information around the actuating mechanism through a trained model according to the image information;
calculating second position and attitude information of the actuating mechanism according to the angle parameter, the position information and a preset initial model parameter of the engineering vehicle;
correcting the pose information of the executing mechanism based on the first pose information and the second pose information, and determining the relative position relation between the executing mechanism and the obstacle according to the corrected pose information and the obstacle information;
adopting a preset obstacle avoidance strategy corresponding to the relative position relationship to control the engineering vehicle to avoid obstacles;
wherein, the control unit is specifically configured to:
determining a first coordinate of the tail end of the executing mechanism according to the first position and posture information and determining a second coordinate of the tail end of the executing mechanism according to the second position and posture information based on a preset model coordinate system of the engineering vehicle;
correcting the coordinates of the end of the actuator based on the first coordinates and the second coordinates according to the following formula, and determining corrected coordinates of the end of the actuator:
T＝α×T imu +(1-α)×T stereo
wherein T is a corrected coordinate of the end of the actuator, T imu Is said second coordinate, T stereo For the first coordinate, a is ∈ (0, 1) is confidence.
12. Mechanical equipment comprises an engineering vehicle and is characterized by further comprising the engineering vehicle obstacle avoidance control device according to claim 11, wherein the engineering vehicle obstacle avoidance control device is used for controlling the engineering vehicle to safely avoid obstacles.
13. The mechanical equipment of claim 12, wherein the engineering vehicle is an excavator, and an actuating mechanism of the excavator comprises a rotary table, a large arm, a small arm and an excavator bucket which are sequentially and rotatably connected;
the binocular camera comprises at least one camera which is arranged on the rotary table and can photograph the full view of the big arm, the full view of the small arm and the full view of the excavator bucket;
the inertial sensors comprise at least four inertial sensors which are respectively arranged on the rotary table, the large arm, the small arm and the bucket so as to respectively acquire angle parameters of the rotary table, the large arm, the small arm and the bucket.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110370610.0A CN113268055B (en) | 2021-04-07 | 2021-04-07 | Obstacle avoidance control method and device for engineering vehicle and mechanical equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110370610.0A CN113268055B (en) | 2021-04-07 | 2021-04-07 | Obstacle avoidance control method and device for engineering vehicle and mechanical equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113268055A CN113268055A (en) | 2021-08-17 |
| CN113268055B true CN113268055B (en) | 2023-01-13 |
Family
ID=77228760
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110370610.0A Active CN113268055B (en) | 2021-04-07 | 2021-04-07 | Obstacle avoidance control method and device for engineering vehicle and mechanical equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113268055B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114463932B (en) * | 2022-01-14 | 2024-05-03 | 国网江苏省电力工程咨询有限公司 | Non-contact construction safety distance active dynamic identification early warning system and method |
| CN114740854A (en) * | 2022-04-11 | 2022-07-12 | 北京京东乾石科技有限公司 | Robot obstacle avoidance control method and device |
| CN115903853B (en) * | 2023-01-06 | 2023-05-30 | 北京理工大学 | Safe feasible domain generation method and system based on effective barrier |
| CN117066702B (en) * | 2023-08-25 | 2024-04-19 | 上海频准激光科技有限公司 | Laser marking control system based on laser |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110262508A (en) * | 2019-07-06 | 2019-09-20 | 深圳数翔科技有限公司 | Applied to the automated induction systems and method on the closing unmanned goods stock in place |
| CN112115929A (en) * | 2020-11-23 | 2020-12-22 | 国网瑞嘉(天津)智能机器人有限公司 | Method and device for determining moving pose of operation arm support and storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120114181A1 (en) * | 2010-11-01 | 2012-05-10 | Borthwick James R | Vehicle pose estimation and load profiling |
| CN109483529B (en) * | 2018-10-12 | 2021-02-26 | 华南智能机器人创新研究院 | Mechanical arm servo control method, system and device based on spiral theory |
| CN111360862B (en) * | 2020-02-29 | 2023-03-24 | 华南理工大学 | Method for generating optimal grabbing pose based on convolutional neural network |
| CN111622296B (en) * | 2020-04-22 | 2021-11-26 | 浙江大学 | Excavator safety obstacle avoidance system and method |
| CN112164115B (en) * | 2020-09-25 | 2024-04-02 | 清华大学深圳国际研究生院 | Object pose recognition method and device and computer storage medium |
-
2021
- 2021-04-07 CN CN202110370610.0A patent/CN113268055B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110262508A (en) * | 2019-07-06 | 2019-09-20 | 深圳数翔科技有限公司 | Applied to the automated induction systems and method on the closing unmanned goods stock in place |
| CN112115929A (en) * | 2020-11-23 | 2020-12-22 | 国网瑞嘉(天津)智能机器人有限公司 | Method and device for determining moving pose of operation arm support and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113268055A (en) | 2021-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113268055B (en) | Obstacle avoidance control method and device for engineering vehicle and mechanical equipment | |
| CN110696000B (en) | Obstacle avoidance method for mechanical arm heuristic sensing | |
| EP3740352B1 (en) | Vision-based sensor system and control method for robot arms | |
| CN113605483B (en) | Automatic operation control method and device for excavator | |
| JP5370128B2 (en) | Robot failure detection device | |
| US20080249659A1 (en) | Method and system for establishing no-entry zone for robot | |
| JP6826069B2 (en) | Robot motion teaching device, robot system and robot control device | |
| CN104476548A (en) | Excavating robot autonomous working control system and method | |
| CN111622296B (en) | Excavator safety obstacle avoidance system and method | |
| US11040451B2 (en) | Teaching device and teaching method | |
| KR101132713B1 (en) | Device for control of moving robot, moving robot system having the same and method for control of moving robot | |
| CN113172659A (en) | Flexible robot arm shape measuring method and system based on equivalent central point recognition | |
| RU124622U1 (en) | MOBILE ROBOT CONTROL SYSTEM | |
| WO2022216493A1 (en) | Methods and systems for determining machine state | |
| Liu et al. | A deep-learning based multi-modality sensor calibration method for usv | |
| CN110722547B (en) | Vision stabilization of mobile robot under model unknown dynamic scene | |
| US10434650B2 (en) | Programming device which generates operation program and method for generating program | |
| US20220241980A1 (en) | Object-Based Robot Control | |
| Djelal et al. | Target tracking by visual servoing | |
| JP5197647B2 (en) | Mobile image tracking device | |
| Šumanas et al. | Determination of excavator tool position using absolute sensors | |
| Chen et al. | Workspace Modeling: Visualization and Pose Estimation of Teleoperated Construction Equipment from Point Clouds | |
| JPH0772930A (en) | Positioning device | |
| JP7424122B2 (en) | Simulation equipment and programs | |
| JP7447568B2 (en) | Simulation equipment and programs |
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 |