Milling machine obstacle crossing control method and milling machine
Through the image acquisition system and obstacle detection model, the obstacles in front of the milling machine body are identified, and obstacle-surfing control is carried out according to the distance between the working devices, which solves the problems of inaccurate obstacle identification and low working efficiency in the prior art, and improves the Safety and efficiency of milling machines.
Patent Information
- Application Number
- CN202410871935.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-28
- Publication Date
- 2024-11-08
AI Technical Summary
The existing obstacle-over-blocking control technology of milling machine has problems such as inaccurate obstacle identification, low operating efficiency and safety hazards in large operating machinery. Traditional obstacle avoidance schemes have a great impact on normal operating processes and are difficult to effectively identify and avoid road surfaces. obstacle.
The image acquisition system is used to obtain image information in front of the milling machine body and the working device, identify obstacles through the preset obstacle detection model, calculate the distance between the obstacles and the working device, and control the lifting of the working device to cross the obstacles. , realize obstacle-breathing operation.
It improves the accuracy of obstacle identification and the accuracy of obstacle-surpassing operations, enhances operating efficiency and safety, avoids the blind spot problem of separate detection, and does not need to change the travel route of the milling machine.
Smart Images

Figure CN118915715A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of milling machines, and in particular relates to an obstacle crossing control method for a milling machine and a milling machine. Background Art
[0002] Milling machine is one of the common working machines in the field of road construction machinery, mainly used for milling and cutting old road surfaces. Due to the complex working environment of the milling machine, the milling machine body is large and there is a feeding mechanism at the front end of the body, the driver's field of vision is blocked, and it is difficult to timely and accurately observe obstacles such as manhole covers and bridge expansion joints on the construction road surface. The traditional working method usually requires multiple road workers to provide auxiliary guidance for the operation of the milling machine, which is labor-intensive, low-efficiency, and has certain safety hazards. Although some obstacle avoidance control schemes for assisting the detection of obstacles are provided in the prior art, such as detecting and identifying obstacles through laser radar and controlling the vehicle body to re-plan the path to avoid obstacles, the detection and identification means of the above schemes are relatively simple, and the method of re-planning the path to bypass or avoid obstacles is adopted. If it is applied to large-scale working machinery such as milling machines, a large area of unmilled road surface will be left near the obstacle, requiring subsequent manual work, and the obstacle avoidance method of re-planning the path has a great impact on the normal milling operation process, the operation efficiency is low, and there are certain safety hazards. Therefore, the above scheme is not suitable for application in milling machines. Summary of the invention
[0003] In view of this, in order to improve at least one of the above-mentioned problems existing in the prior art, the present invention provides a milling machine obstacle crossing control method and a milling machine.
[0004] A first aspect of the present invention provides a milling machine obstacle control method, which is applied to a milling machine having an image acquisition system, wherein the image acquisition system is used to acquire first image information of a first road surface area in front of a milling machine body and second image information of a second road surface area in front of a milling working device. The milling machine obstacle control method comprises:
[0005] Step S100: during the operation of the milling machine, first image information of a first road surface area in front of the milling machine body is obtained, and obstacles in the first image information are identified;
[0006] Step S200: acquiring second image information of a second road surface area in front of the milling working device, and determining the distance between the obstacle and the milling working device according to the second image information;
[0007] Step S300: controlling the milling device to rise according to the distance to cross the obstacle;
[0008] Wherein, in the traveling direction of the milling machine, the first road surface area is located in front of the second road surface area.
[0009] In a feasible implementation, step S100: during the operation of the milling machine, obtaining first image information of a first road surface area in front of the milling machine body, and identifying obstacles in the first image information, includes:
[0010] Step S110: During the operation of the milling machine, first image information of a first road surface area in front of the milling machine body is continuously acquired at a preset frequency;
[0011] Step S120: preprocessing the first image information to obtain a preprocessed image;
[0012] Step S130: detecting the preprocessed image using a preset obstacle detection model to determine size information and first position information of the obstacle;
[0013] Among them, the preprocessing includes distortion correction processing and cropping processing, and the obstacle detection model is preset in the controller of the milling machine.
[0014] In a feasible implementation, step S130: detecting the preprocessed image by using a preset obstacle detection model to determine the size information and the first position information of the obstacle includes:
[0015] Step S131: performing image segmentation processing on the pre-processed image using a preset obstacle detection model;
[0016] Step S132: extracting pixel features of obstacles in the segmented image to determine pixel size information of the obstacles in the image;
[0017] Step S133: predicting the probability value of the obstacle corresponding to each type of object in the obstacle detection model, and determining the type of the obstacle according to the relationship between the probability value and the first threshold;
[0018] Step S134: using a non-maximum suppression method to identify the IoU value of the obstacle, and determining the size information and first position information of the obstacle according to the IoU value and the pixel size information;
[0019] Step S135: marking the obstacle as a target obstacle, and storing the size information, first position information and pixel features of the target obstacle in the controller;
[0020] Step S136: determining a first distance d1 between the target obstacle and the milling device according to the first position information of the target obstacle, and controlling the milling machine to reduce the travel speed when the distance d1 is less than the first distance threshold D1;
[0021] Step S137: Control the alarm prompt device of the milling machine to continuously output alarm prompt information.
[0022] In a feasible implementation, step S200: obtaining second image information of a second road surface area in front of the milling working device, and determining the distance between the obstacle and the milling working device according to the second image information, includes:
[0023] Step S210: continuously displaying second image information of a second road surface area at a preset frequency;
[0024] Step S220: matching and identifying the second image information with the target obstacle identified in the first image information to determine whether the target obstacle appears in the second image information;
[0025] Step S230: When a target obstacle appears in the second image information, second position information of the target obstacle and a second distance d2 between the target obstacle and the milling working device are determined according to size information of the target obstacle and body structure parameters of the milling machine.
[0026] In a feasible implementation, step S220: matching and identifying the second image information with the target obstacle identified in the first image information to determine whether the target obstacle appears in the second image information includes:
[0027] Step S221: Detecting the type and size information of the obstacle in the second image information by using a preset obstacle detection model, and comparing the type and size with the target obstacle identified in the first image information to generate a first comparison result;
[0028] If the first comparison result is different, then execute step S222: maintain the current working state;
[0029] If the first comparison result is the same, executing step S223: extracting the pixel features of the obstacle in the second image information and comparing them with the pixel features of the target obstacle to generate a second comparison result;
[0030] If the second comparison result is different, execute step S222: maintain the current working state;
[0031] If the second comparison result is the same, step S224 is executed: determining whether a target obstacle appears in the second image information.
[0032] In a feasible implementation, step S300: controlling the milling working device to lift according to the spacing to cross the obstacle includes:
[0033] Step S310: when the second spacing d2<the second distance threshold D2, the milling working device is controlled to be lifted to the target height, and the lifting state moving distance of the milling working device in the traveling direction is calculated by fusion; wherein the target height is greater than the height dimension of the target obstacle, and a preset height difference is maintained between the target height and the height dimension of the target obstacle;
[0034] Step S320: determining whether the milling working device has crossed the target obstacle according to the structural parameters of the milling working device and the moving distance in the lifting state;
[0035] Step S330: When the milling working device has crossed the target obstacle, the milling working device is controlled to descend and return to the initial milling depth;
[0036] Step S340: controlling the milling machine to return to a normal operating speed;
[0037] Step S350: Control the alarm prompt device to stop outputting the alarm prompt information.
[0038] In a feasible implementation, step S310: when the second spacing d2<the second distance threshold D2, the milling working device is controlled to be lifted to the target height, and a fusion algorithm is used to calculate the lifting state moving distance of the milling working device in the traveling direction, including:
[0039] Step S311: when the second distance d2<the second distance threshold D2, the milling working device is controlled to be lifted from the initial milling depth to the target height, and the initial milling depth data is stored in the controller;
[0040] Step S312: using an algorithm model based on Kalman filtering, predicting the position information and moving speed information of the milling working device in the next preset period according to the odometer data of the milling machine in each preset period; wherein the position and speed are selected as Kalman state variables;
[0041] Step S313: correcting the accumulated error of the odometer data according to the position change and speed information of the milling machine in the first image information;
[0042] Step S314: updating the mean and covariance of the corrected position information and moving speed information of the milling working device;
[0043] Step S315: Calculate the lifting state moving distance according to the updated position information and moving speed information of the milling working device.
[0044] In a feasible implementation, step S320: determining whether the milling working device has crossed the target obstacle according to the structural parameters of the milling working device and the moving distance in the lifting state, includes:
[0045] Step S321: Calculate the sum of the size of the milling working device in the traveling direction, the length of the target obstacle, and the front and rear preset gaps, and record it as a reference length size;
[0046] Step S322: determine whether the moving distance in the lifting state is greater than the reference length dimension, and generate a determination result;
[0047] If the judgment result is yes, then executing step S323: determining that the milling working device has crossed the target obstacle;
[0048] If the judgment result is no, step S321 is executed again.
[0049] The second aspect of the technical solution of the present invention also provides a milling machine, including: a milling machine body; a milling working device connected to the bottom of the milling machine body, the milling working device can be raised and lowered relative to the milling machine body; an image acquisition system, arranged on the milling machine body, for collecting first image information of a first road surface area in front of the milling machine body and second image information of a second road surface area in front of the milling working device; a controller, arranged on the milling machine body, and communicated with the milling machine body, the milling working device and the image acquisition system, the controller identifies obstacles based on the first image information and the second image information, and controls the milling working device to cross the obstacles, so as to execute the milling machine obstacle crossing control method in any one of the above-mentioned first aspects.
[0050] In a feasible implementation, the image acquisition system includes: a first image collector, which is arranged at the front end of the milling machine body and located on the lateral side of the milling machine body, and is used to collect first image information of a first road surface area in front of the milling machine body; a second image collector, which is arranged at the bottom of the milling machine body and is spaced behind the first image collector in the direction of travel, and is used to collect second image information of a second road surface area in front of the milling working device.
[0051] The third technical solution of the present invention further provides an electronic device, comprising a processor and a memory, wherein the memory stores a computer program suitable for running in the processor. When the processor runs the computer program in the memory, the milling machine obstacle control method in any one of the first aspects above can be implemented.
[0052] The fourth technical solution of the present invention further provides a readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the milling machine obstacle control method in any one of the above-mentioned first aspects is implemented.
[0053] The beneficial effects of the above technical solution of the present invention are:
[0054] It is possible to utilize the coordination and comparison operations between the first image information and the second image information obtained by the image acquisition system, identify the relevant information of the obstacle based on the first image information to play a warning role, and then further determine the obstacle and the distance between the obstacle and the milling working device based on the second image information, so as to control the milling working device to perform corresponding obstacle crossing operations, overcome the blind spot problem of separate detection, greatly improve the accuracy of obstacle identification, and also improve the accuracy of the control of the obstacle crossing operation of the milling working device, without changing the travel route of the milling machine, which is beneficial to improving construction operation efficiency and safety. BRIEF DESCRIPTION OF THE DRAWINGS
[0055] Figure 1 The figure is a schematic flow chart of a milling machine obstacle crossing control method provided by an embodiment of the present invention.
[0056] Figure 2 Shown is a schematic block diagram of a milling machine provided by an embodiment of the present invention.
[0057] Figure 3 Shown is a side schematic diagram of a milling machine provided by an embodiment of the present invention.
[0058] Figure 4 The figure shows a top view of the installation position of the first image collector provided by one embodiment of the present invention.
[0059] Figure 5 FIG. 1 is a flow chart of a specific step of step S100 .
[0060] Figure 6 FIG. 1 is a flow chart of a specific step of step S130 .
[0061] Figure 7 Shown is a top view of a milling machine provided by one embodiment of the present invention.
[0062] Figure 8 FIG. 1 is a flow chart of a specific step of step S200 .
[0063] Fig. 9 FIG. 1 is a flow chart of a specific step of step S220 .
[0064] Fig.10 FIG. 1 is a flow chart of a specific step of step S300 .
[0065] Fig.11 FIG. 1 is a flow chart of a specific step of step S310 .
[0066] Fig.12 FIG. 1 is a flow chart of a specific step of step S320 .
[0067] Fig.13 The figure shows a schematic diagram of the positional relationship between the second image collector and the milling working device provided in one embodiment of the present invention.
[0068] Description of reference numerals:
[0069] 100 milling machines;
[0070] 1 milling machine body, 11 feeding mechanism, 12 front outrigger mechanism, 13 rear outrigger mechanism, 14 alarm prompt device;
[0071] 2 milling working device; 3 image acquisition system, 31 first image acquisition device, 32 second image acquisition device, 33 acquisition device bracket; 4 controller;
[0072] 51 Unmilled road surface, 52 Milled road surface, 53 Obstacles. DETAILED DESCRIPTION
[0073] In the description of the application, the meaning of "multiple" is at least two, for example, two, three, etc., unless otherwise clearly and specifically limited. In the embodiment of the present application, all directional indications (such as up, down, left, right, front, back, top, bottom ...) are only used to explain the relative position relationship, motion conditions, etc. between the components under a certain specific posture (as shown in the drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their deformations are intended to cover non-exclusive inclusions. For example, the process, method, system, product or equipment comprising a series of steps or units are not limited to the steps or units listed, but optionally also include the steps or units not listed, or optionally also include other steps or units inherent to these processes, methods, products or equipment.
[0074] In addition, the reference to "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0075] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0076] Some embodiments of the milling machine obstacle crossing control method, milling machine, electronic device and readable storage medium in the technical solution of the present invention are provided below.
[0077] In an embodiment of the first aspect of the present invention, a milling machine obstacle control method is provided, which is applied to a milling machine with an image acquisition system, wherein the image acquisition system is used to acquire first image information of a first road surface area in front of the milling machine body and second image information of a second road surface area in front of the milling working device.
[0078] like Figure 1 As shown, the obstacle crossing control method of the milling machine includes:
[0079] Step S100: during the operation of the milling machine, first image information of a first road surface area in front of the milling machine body is obtained, and obstacles in the first image information are identified;
[0080] Step S200: acquiring second image information of a second road surface area in front of the milling working device, and determining the distance between the obstacle and the milling working device according to the second image information;
[0081] Step S300: controlling the milling device to rise according to the distance to cross the obstacle;
[0082] Wherein, in the traveling direction of the milling machine, the first road surface area is located in front of the second road surface area.
[0083] like Figure 2 and Figure 3 As shown, the milling machine in this embodiment has an image acquisition system, which can acquire first image information of a first road surface area in front of the milling machine body and second image information of a second road surface area in front of the milling working device during the operation of the milling machine, for example Figure 3 In the example, the image acquisition system may include a first image collector and a second image collector spaced apart in the direction of travel of the milling machine body, the first image collector's acquisition viewing angle covers the first road area to collect the first image information, and the second image collector's acquisition viewing angle covers the second road area to collect the second image information, so that obstacles on the road ahead during the milling machine's travel can appear in the first image information and the second image information in sequence. The interval between the first road area and the second road area can be set according to the specific structural dimensions of the milling machine.
[0084] In this embodiment, through step S100, during the operation of the milling machine, the first image information of the first road surface area in front of the milling machine body is obtained, and the relevant information of the obstacle in the first image information is identified through image processing as early warning information, providing a data basis for the subsequent control of the milling working device to cross the obstacle. Through step S200, the second image information of the second road surface area in front of the milling working device is obtained, and the distance between the obstacle and the milling working device is determined by comparing it with the obstacle identified in the first image information, so as to prepare for controlling the milling working device to cross the obstacle. Through step S300, the distance between the obstacle and the milling working device is used as the basis for controlling the lifting of the milling working device, so that when the obstacle approaches, the height of the milling working device is raised so that the milling working device can cross the obstacle, thereby preventing the milling working device and the obstacle from colliding and interfering with each other. Among them, the types of obstacles include but are not limited to manhole covers, bridge expansion joints, etc.
[0085] It is understandable that Figure 3 In the example, since the first road area covered by the first image information is in front of the second road area covered by the second image information, the obstacle on the road in front of the milling machine body gradually approaches the milling working device as the milling machine moves forward after appearing in the first image information, and appears in the second image information after a certain time interval. If the first image information is used alone as the basis for controlling the obstacle-crossing operation of the milling working device, there will be a certain blind spot in the process of the obstacle approaching the milling working device, and it is difficult to accurately grasp the position change of the obstacle; and if the second image information is used alone as the basis for controlling the obstacle-crossing operation of the milling working device, the distance to the obstacle is short, and the reserved time for identification detection and lifting operation is short, so the accuracy of detection and identification is difficult to guarantee, and it is easy for the milling working device to contact the obstacle due to untimely lifting.
[0086] The obstacle crossing control method of the milling machine in this embodiment can utilize the coordination and comparison operations between the first image information and the second image information obtained at a certain distance in the direction of travel, utilize the first image information to identify the relevant information of the obstacle to serve as a warning, and then utilize the second image information to further determine the obstacle and the distance between the obstacle and the milling working device, and control the milling working device to perform corresponding obstacle crossing operations, thereby overcoming the blind spot problem of single detection. On the one hand, it greatly improves the accuracy of obstacle identification, and on the other hand, it improves the accuracy of the control of the obstacle crossing operation of the milling working device, without changing the travel route of the milling machine, which is beneficial to improving construction operation efficiency and safety.
[0087] It should be noted that when the image acquisition system adopts Figure 3When the first image collector and the second image collector are shown in FIG. 1 , the number of the first image collector and the second image collector can be one or more. In order to avoid the feeding mechanism in front of the milling machine body blocking the shooting field of view, the first image collector and the second image collector can be used. Figure 3 and Figure 4 In the example, the first image collector is installed on the left and right sides of the front end of the milling machine body using auxiliary structures such as a collector bracket.
[0088] In a further embodiment of the present invention, a milling machine obstacle control method is provided, such as Figures 1 to 5 As shown, step S100 includes:
[0089] Step S110: During the operation of the milling machine, first image information of a first road surface area in front of the milling machine body is continuously acquired at a preset frequency;
[0090] Step S120: preprocessing the first image information to obtain a preprocessed image;
[0091] Step S130: detecting the preprocessed image using a preset obstacle detection model to determine size information and first position information of the obstacle;
[0092] Among them, the preprocessing includes distortion correction processing and cropping processing, and the obstacle detection model is preset in the controller of the milling machine.
[0093] In this embodiment, on the basis of the above-mentioned embodiment, the specific method steps of step S100 are further described. First, the first image information of the first road surface area in front of the milling machine body is obtained through step S110 as the data basis for identifying obstacles; wherein, since the milling machine is in the process of continuous forward movement, the first image information is continuously acquired at a preset frequency to form real-time dynamic obstacle detection and recognition. Through step S120, the first image information is subjected to pre-processing operations such as distortion correction and cropping to remove useless information and noise information in the first image information, which is conducive to improving the work efficiency of the subsequent identification and detection process. Then, through step S130, the obtained pre-processed image is input into the obstacle detection model preset in the controller to perform obstacle detection on the pre-processed image, so as to obtain the size information and first position information of the obstacle, which is used as the initial data basis for the subsequent control of the obstacle crossing operation of the milling working device.
[0094] It is understandable that different types of obstacles have different features such as morphological structures. Accurately identifying the type of obstacle and the first position information in the first image information can help improve the accuracy of obstacle traversal operations and provide a basis for preliminary warnings.
[0095] Furthermore, if Figures 1 to 6 As shown, step S130 specifically includes the following steps:
[0096] Step S131: performing image segmentation processing on the pre-processed image using a preset obstacle detection model;
[0097] Step S132: extracting pixel features of obstacles in the segmented image to determine pixel size information of the obstacles in the image;
[0098] Step S133: predicting the probability value of the obstacle corresponding to each type of object in the obstacle detection model, and determining the type of the obstacle according to the relationship between the probability value and the first threshold;
[0099] Step S134: using a non-maximum suppression method to identify the IoU value of the obstacle, and determining the size information and first position information of the obstacle according to the IoU value and the pixel size information;
[0100] Step S135: marking the obstacle as a target obstacle, and storing the size information, first position information and pixel features of the target obstacle in the controller;
[0101] Step S136: determining a first distance d1 between the target obstacle and the milling device according to the first position information of the target obstacle, and controlling the milling machine to reduce the travel speed when the distance d1 is less than the first distance threshold D1;
[0102] Step S137: controlling the alarm prompt device of the milling machine to continuously output alarm prompt information;
[0103] In this embodiment, step S130 is further improved on the basis of the above-mentioned embodiment. Figure 6In the example, through step S131, the preprocessed image is first input into a preset obstacle detection model for image segmentation processing. The obstacle detection model is a vision-based image processing algorithm model used to process and detect images to identify obstacle information in the images. For example, AI models (artificial intelligence models) such as yoloV8 (an algorithm model for object detection using convolutional neural networks) or U-net (an algorithm model of convolutional neural networks) are used to segment the image using segmentation technology to pixelize the image. Among them, while using the AI model to detect obstacles, deep learning and training can also be achieved, thereby continuously improving the accuracy of the detection results. Through step S132, the obstacle detection model extracts the pixel features of the obstacles in the segmented image, and uses the pixel features to obtain the pixel size information of the obstacles in the image. Then, through step S133, the prediction result is output. The prediction result includes the probability value corresponding to each type of obstacle, and the type of the obstacle is determined according to the size relationship between the probability value and the first threshold. For example, in the prediction result, the probability value of the obstacle being of the manhole cover type is a1, and the probability value of the obstacle being of the bridge expansion joint type is a2. The preset first threshold of the model is L. When a2 < L < a1, it is determined that the obstacle is of the manhole cover type. After determining the type of the obstacle, through step S134, the non-maximum suppression method is used to identify the IoU value (Intersection over Union, a standard for measuring the accuracy of detecting corresponding objects in a specific dataset) of the obstacle, so as to calculate the overall size information and the first position information of the obstacle using the IoU value and the pixel size information, thereby completing the identification operation of the obstacles in the first image information. The first position information includes the relative position of the obstacle with respect to the milling machine. Moreover, using the IoU value can also improve the accuracy of the calculation results. At the same time, through step S135, the identified obstacles are marked as target obstacles, and the size information, the first position information, and the pixel features of the target obstacles are stored in the controller for retrieval and use in subsequent operations.
[0104] Then, through step S136, the position of the target obstacle is monitored, such as Figure 7In the example in , the first distance d1 between the target obstacle and the milling working device in the traveling direction is calculated based on the first position information. A first distance threshold D1 is preset in the controller. When the first distance d1 decreases to d1 < D1, it indicates that the target obstacle has entered the warning area of the milling machine. At this time, the traveling speed of the milling machine is controlled to decrease, so as to facilitate further accurate monitoring of the obstacle and reserve sufficient operation time for the subsequent obstacle-crossing operation of the milling working device. Among them, the first distance threshold D1 can be set in advance according to construction requirements. At the same time, through step S137, the alarm prompt device of the milling machine continuously outputs alarm prompt information to remind the driver of the milling machine. Among them, the alarm prompt device includes but is not limited to a buzzer, a warning light, and a display. Correspondingly, the alarm prompt information includes but is not limited to forms such as alarm sound prompt, warning light flashing, and graphic screen prompt.
[0105] In the milling machine obstacle-crossing control method provided in a further embodiment of the present invention, as Figures 1 to 8 shown, step S200 specifically includes:
[0106] Step S210: Continuously obtain second image information of a second road surface area in front of the milling working device at a preset frequency;
[0107] Step S220: Match and identify the second image information with the target obstacle identified in the first image information to determine whether the target obstacle appears in the second image information;
[0108] Step S230: When the target obstacle appears in the second image information, determine the second position information of the target obstacle and the second distance d2 between the target obstacle and the milling working device according to the size information of the target obstacle and the vehicle body structure parameters of the milling machine.
[0109] In this embodiment, on the basis of the foregoing embodiment, the specific process of step S200 is further described. After it is recognized through the first image information that the target obstacle has entered the warning area, through step S210, second image information of a second road surface area in front of the milling working device is obtained to provide data for subsequent identification of the target obstacle, and the second image information is continuously obtained at a preset frequency to form continuous monitoring. Through step S220, the second image information is matched and identified with the target obstacle identified in the first image information to determine whether the target obstacle appears in the second image information. If the matching identification is successful, it can be determined that the target obstacle has appeared in the second image information. Furthermore, through step S230, calculations are performed using the size information of the target obstacle and the vehicle body structure parameters of the milling machine to obtain the second position information of the target obstacle in the second image information and the second distance d2 between the target obstacle and the milling working device.
[0110] It can be understood that the image acquisition system and the milling working device are set in fixed positions on the milling machine and can be determined in advance based on the body structure parameters of the milling machine. Therefore, as long as the second position information of the target obstacle in the second image information is determined, the distance of the target obstacle relative to the milling machine body can be calculated, and then the second distance d2 between the target obstacle and the milling working device can be determined.
[0111] In this embodiment, it is only necessary to match and identify the second image information with the target obstacle identified in the first image information, that is, to use the relevant information of the target obstacle identified in the first image information to match with the second image information, so as to realize multi-camera collaboration and information sharing, greatly improve the recognition efficiency and accuracy, and also eliminate the blind spots in the process of the target obstacle approaching the milling working device, improve the accuracy of monitoring the position of the target obstacle, and facilitate the accuracy of the obstacle crossing operation control of the milling working device, thereby minimizing the area of the unmilled area left in the process of the milling working device crossing the obstacle.
[0112] Furthermore, if Fig. 9 As shown, step S220 specifically includes the following steps:
[0113] Step S220: matching and identifying the second image information with the target obstacle identified in the first image information to determine whether the target obstacle appears in the second image information, including:
[0114] Step S221: Detecting the type and size information of the obstacle in the second image information by using a preset obstacle detection model, and comparing the type and size with the target obstacle identified in the first image information to generate a first comparison result;
[0115] If the first comparison result is different, then execute step S222: maintain the current working state;
[0116] If the first comparison result is the same, executing step S223: extracting the pixel features of the obstacle in the second image information and comparing them with the pixel features of the target obstacle to generate a second comparison result;
[0117] If the second comparison result is different, execute step S222: maintain the current working state;
[0118] If the second comparison result is the same, step S224 is executed: determining whether a target obstacle appears in the second image information.
[0119] In this embodiment, the matching identification process in step S220 is further described based on the above embodiment. In step S221, the obstacle type and size information in the second image information detected by the preset obstacle detection model are compared with the type and size information of the target obstacle identified in the first image information to generate a first comparison result; if the first comparison result is different, it means that the initial matching and identification failed, and the target obstacle does not appear in the second image information. In step S222, the current working state is maintained, and the second image information is continuously acquired and monitored; if the first comparison result is the same, it means that the initial matching and identification is successful, and then a secondary comparison is performed in step S223 to extract the pixel features of the obstacle in the second image information and compare them with the pixel features of the target obstacle identified in the first image information to generate a second comparison result; if the second comparison result is different, it means that the matching and identification failed, and the target obstacle has not appeared. At this time, the current working state is maintained in step S222 to continue monitoring; if the second comparison result is the same, it means that the secondary matching and identification is successful, and it can be determined that the obstacle in the second image information is the target obstacle identified in the first image information, that is, the target obstacle has appeared in the second image information.
[0120] In this embodiment, by setting a double comparison mode, the target obstacle is matched and identified from the aspects of type, size, pixel features, etc., which can greatly improve the accuracy of the matching and identification results and prevent abnormal obstacle crossing operations caused by erroneous identification due to special reasons. In addition, by setting a double comparison mode, if the first comparison result is different, it can be directly determined that the matching and identification failed, without the need for a second comparison, which can also improve the recognition efficiency.
[0121] In a further embodiment of the present invention, a milling machine obstacle control method is provided, such as Fig.10 As shown, step S300 specifically includes:
[0122] Step S300: performing fuzzy control correction on the theoretical speed of the rear wheel and determining the corrected speed of the rear wheel, including:
[0123] Step S310: when the second spacing d2<the second distance threshold D2, the milling working device is controlled to be lifted to the target height, and the lifting state moving distance of the milling working device in the traveling direction is calculated by fusion; wherein the target height is greater than the height dimension of the target obstacle, and a preset height difference is maintained between the target height and the height dimension of the target obstacle;
[0124] Step S320: determining whether the milling working device has crossed the target obstacle according to the structural parameters of the milling working device and the moving distance in the lifting state;
[0125] Step S330: When the milling working device has crossed the target obstacle, control the milling working device to descend and resume to the initial milling depth;
[0126] Step S340: Control the milling machine to resume the driving speed for normal operation;
[0127] Step S350: Control the alarm prompt device to stop outputting alarm prompt information.
[0128] In this embodiment, based on the foregoing embodiment, the specific steps of controlling the milling working device to cross the obstacle in step S300 are further described. After determining that the target obstacle appears in the second image information, by continuously monitoring the change of the second distance d2 between the target obstacle and the milling working device, correspondingly, a second distance threshold D2 is preset in the controller. When the second distance d2 decreases to d2 < D2, as shown in the example in Figure 7 , it indicates that the target obstacle has entered the control area from the warning area. At this time, control the milling working device to lift to the target height through step S310, so that the milling working device can cross the target obstacle as the milling machine body continues to move forward; among them, since the size information (including length, width and height dimensions) of the target obstacle has been obtained in the foregoing steps, the target height can be determined according to the actual height dimension of the target obstacle at this time. The preset target height is higher than the height dimension of the target obstacle and a preset height difference is maintained between the two, so that for each type of obstacle, when the milling working device is lifted to the target height, it can smoothly cross the obstacle from above the target obstacle, and the time consumed for the lifting operation of the milling working device can be correspondingly reduced, further improving the efficiency of the obstacle crossing operation. Among them, the preset height difference can be set manually in advance, such as 10 cm, 20 cm. At the same time, the moving distance of the lifting state of the milling working device in the traveling direction is calculated by fusion. As the milling machine body moves forward, the milling working device moves forward relative to the target obstacle. Through step S320, calculate by combining the structural parameters of the milling working device and the moving distance of the lifting state to determine whether the milling working device has crossed the target obstacle. Through step S330, when it is determined that the milling working device has crossed the target obstacle, control the milling working device to descend and resume to the initial milling depth to complete the obstacle crossing control operation. Through step S340, control the milling machine to resume the driving speed for normal operation to continue milling the subsequent unpaved road surface. At the same time, through step S350, stop outputting the alarm prompt information to end the reminder operation for this obstacle crossing operation.
[0129] It should be noted that the second distance threshold D2 and the target height can be set in advance according to the construction requirements. In addition, in practical applications, when the obstacles at the construction site are obstacles with relatively small heights such as manhole covers and bridge expansion joints, the target height can also be directly set to a fixed height manually.
[0130] In this embodiment, by combining self-learning training and fuzzy processing, the data of the given distribution ratio of the front wheel torque determined during steering and the actual distribution ratio of the front wheel torque are made more accurate, and then the corresponding first error and the first error change rate are accurately calculated, which is beneficial to further improve the accuracy of subsequent speed correction and regulation.
[0131] In a further embodiment of the present invention, a milling machine obstacle control method is provided, such as Fig.10 and Fig.11 As shown, step S310 specifically includes:
[0132] Step S311: when the second distance d2<the second distance threshold D2, the milling working device is controlled to be lifted from the initial milling depth to the target height, and the initial milling depth data is stored in the controller;
[0133] Step S312: using an algorithm model based on Kalman filtering, predicting the position information and moving speed information of the milling working device in the next preset period according to the odometer data of the milling machine in each preset period; wherein the position and speed are selected as Kalman state variables;
[0134] Step S313: correcting the accumulated error of the odometer data according to the position change and speed information of the milling machine in the first image information;
[0135] Step S314: updating the mean and covariance of the corrected position information and moving speed information of the milling working device;
[0136] Step S315: Calculate the lifting state moving distance according to the updated position information and moving speed information of the milling working device.
[0137] In this embodiment, step S310 in the above embodiment is further described in detail. Specifically, first, through step S311, when the second spacing d2<the second distance threshold D2, the milling working device is lifted from the initial milling depth to the target height, so that the milling working device can cross over the obstacle as the milling machine body moves; at the same time, the initial milling depth data of the milling working device is stored in the controller for subsequent descent operations. Through step S312, a Kalman filter-based algorithm model is used for prediction, for example, MSCKF (Multi-State Constraint Kalman Filter, a Kalman filter under multi-state constraints, is a filter-based VIO algorithm) or ROVIO (Robust Visual Inertial Odometry, is a filter-based method that uses a visual and inertial measurement unit to fuse odometers), and position and speed are selected as Kalman state variables; specifically, in each preset period, the position information and moving speed information of the milling working device in the next preset period are predicted based on the odometer data of the milling machine, wherein the preset period can be set according to the construction requirements, for example, 100ms; and then through step S313, the accumulated error of the odometer data is corrected using the position change and speed information of the milling machine in the first image information, and through step S314, the mean and covariance of the corrected position information and moving speed information of the milling working device are updated to achieve correction and deviation correction of the position information and moving speed information, thereby improving the accuracy of the data. Then, through step S315, the lifting state moving distance of the milling working device is calculated based on the updated position information and moving speed information of the milling working device.
[0138] This embodiment adopts a fusion algorithm to calculate the moving distance of the milling working device in the lifting state, adopts rolling measurement for each preset period, and uses the first image information to correct the accumulated error of the odometer data of the milling machine, which can effectively improve the accuracy of the calculation results, thereby further improving the accuracy of subsequent obstacle control operations.
[0139] Further, Fig.10 and Fig.12 As shown, step S320 specifically includes the following steps:
[0140] Step S321: Calculate the sum of the size of the milling working device in the traveling direction, the length of the target obstacle, and the front and rear preset gaps, and record it as a reference length size;
[0141] Step S322: determine whether the moving distance in the lifting state is greater than the reference length dimension, and generate a determination result;
[0142] If the judgment result is yes, then executing step S323: determining that the milling working device has crossed the target obstacle;
[0143] If the judgment result is no, execute step S324: maintain the current working state.
[0144] In this embodiment, the specific process of determining whether the target obstacle has been crossed in step S320 of the aforementioned embodiment is further described. Specifically, first, through step S321, the size of the milling working device in the direction of travel, the length of the obstacle, and the preset gap before and after the target obstacle are added, and the sum is recorded as the reference length size, which is used as a reference for judging whether the milling working device has crossed the target obstacle. Through step S322, the lifting state moving distance of the milling working device is compared with the reference length size. That is, when the lifting state moving distance is greater than the reference length size, it is determined that the milling working device has crossed the target obstacle, and the subsequent step S330 is executed. Otherwise, it is determined that the milling working device has not crossed the target obstacle, and step S321 is executed again. As the milling machine moves, the change of the lifting state moving distance is continuously monitored until the milling working device crosses the target obstacle.
[0145] It should be noted that in order to prevent the milling device from contacting the target obstacle, a certain gap is set before and after the target obstacle, and a certain space can be reserved during the lifting and lowering of the milling device, thereby playing a safety buffer role.
[0146] In an embodiment of the second aspect of the present invention, a milling machine 100 is also provided. Figure 2 , Figure 3 , Figure 7 and Fig.13 As shown, the milling machine 100 includes a milling machine body 1, a milling working device 2, an image acquisition system 3 and a controller 4. The milling working device 2 is connected to the bottom of the milling machine body 1 to travel with the milling machine body 1 and perform milling operations on the road surface; the milling working device 2 can be lifted and lowered relative to the milling machine body 1 to adjust the milling depth, and can cross obstacles 53 on the road surface by similar lifting. The image acquisition system 3 and the controller 4 are both arranged on the milling machine body 1, and the image acquisition system 3 is used to collect first image information of a first road surface area in front of the milling machine body 1 and second image information of a second road surface area in front of the milling working device 2. The controller 4 is communicatively connected with the milling machine body 1, the milling working device 2 and the image acquisition system 3. The controller 4 can obtain the first image information and the second image information acquired by the image acquisition system 3, and identify the obstacle 53 on the road surface according to the first image information and the second image information, and then control the milling machine body 1 and the milling working device 2 to perform corresponding obstacle crossing operations, so that the milling working device 2 crosses the obstacle 53, thereby executing the milling machine obstacle crossing control method in any embodiment of the first aspect mentioned above.
[0147] It should be noted that, in the traveling direction of the milling machine body 1, the coverage of the first image system is located in front of the coverage of the second image information, that is, the coverage of the second image information is closer to the milling working device 2. The milling working device 2 includes but is not limited to a milling rotor and a side slide, such as Figure 7 and Fig.13 In the traveling direction, the road surface in front of the milling working device 2 is an unmilled road surface 51, and the road surface behind the milling working device 2 is a milled road surface.
[0148] The milling machine 100 in this embodiment can utilize the coordination and comparison operations between the first image information and the second image information acquired by the image acquisition system to identify the relevant information of the obstacle according to the first image information to play a warning role by executing the milling machine obstacle crossing control method, and then further determine the obstacle and the distance between the obstacle and the milling working device according to the second image information, and then control the milling working device to perform corresponding obstacle crossing operations, thereby overcoming the blind spot problem of individual detection, greatly improving the accuracy of obstacle identification, and also improving the accuracy of the control of the obstacle crossing operation of the milling working device, without changing the travel route of the milling machine, which is beneficial to improving construction efficiency and safety.
[0149] In addition, the milling machine 100 in this embodiment also has all the beneficial effects of the milling machine obstacle control method in any of the above embodiments, which will not be repeated here.
[0150] Furthermore, if Figure 3 and Figure 4 As shown, the image acquisition system 3 of the milling machine 100 includes a first image collector 31 and a second image collector 32. The first image collector 31 is arranged at the front end of the milling machine body 1 and is located on the lateral side of the milling machine body 1 to collect first image information of the first road surface area in front of the milling machine body 1, and can avoid the feeding mechanism 11 in front of the milling machine body 1 to prevent the shooting field of view of the first image collector 31 from being blocked; the second image collector 32 is arranged at the bottom of the milling machine body 1 and is located behind the first image collector 31 in the direction of travel to collect second image information of the second road surface area in front of the milling working device 2. Among them, the number of the first image collector 31 and the second image collector 32 can be one or more, for example Figure 4 and Fig.13 In the example, a first image collector 31 is provided on each of the lateral sides of the front end of the milling machine body 1, and a second image collector 32 is provided near the lateral middle area at the bottom of the milling machine body 1, specifically between the front legs 12 and the rear legs 13, and located at the front upper part of the milling working device 2. The first image collector 31 and the second image collector 32 are specifically not limited to cameras, video cameras or video cameras.
[0151] Preferably, as Figure 4 shown in the example of Figure 4 , an L-shaped collector bracket 33 can be provided on the outer side of the front leg 12 of the milling machine body 1, and the collector bracket 33 extends laterally outward and forward for fixing the first image collector 31, which is beneficial to further expand the viewing range of the first image collector 31. The lateral dimension x and the longitudinal dimension y of the collector bracket 33 can be pre-stored in the controller so as to add the dimension data of the collector bracket when calculating the obstacle position information. Taking Figure 4 as an example, the collector bracket can be provided on the outer side of the crawler of the front leg mechanism 12. Then, x is the horizontal distance of the collector bracket 33 relative to the outer edge of the crawler, and can be set within the range of 10 cm < x < 50 cm. Y is the longitudinal distance of the collector bracket 33 relative to the central axis of the crawler, and can be set within the range of 1 m < y < 1.3 m.
[0152] Furthermore, as Figure 3 shown, an alarm prompt device 14 is also provided on the milling machine body 1, which is communicatively connected to the controller 4 and is used to output an alarm prompt according to a control instruction, such as an alarm sound prompt, an alarm light flashing prompt, a graphic and text screen prompt, etc.
[0153] Furthermore, as Figure 2 shown, the controller 4 of the milling machine 100 includes a main control unit and a domain control unit that are communicatively connected. The domain control unit is communicatively connected to the image acquisition system, and the main control unit is respectively communicatively connected to the milling machine body 1, the milling working device 2, the odometer, and the alarm prompt device 14. The first image information and the second image information are detected by a preset obstacle detection model in the domain control unit to identify obstacles in the image, and the relevant information of the obstacles is transmitted to the main control unit. The main control unit operates and controls the milling machine body, the milling working device, the alarm prompt device, etc. to realize the obstacle crossing operation.
[0154] In an embodiment of the present invention, an electronic device is also provided. The electronic device includes a processor and a memory. Among them, a computer program suitable for running in the processor is stored in the memory. When the processor runs the computer program in the memory, it can implement the milling machine obstacle crossing control method in any of the above embodiments. Further, the electronic device can also be provided with a communication interface and a communication bus, and the processor, the communication interface, and the memory complete mutual communication through the communication bus. The electronic device in this embodiment has all the beneficial effects of the milling machine obstacle crossing control method in any of the above embodiments, which will not be elaborated here.
[0155] In addition, an embodiment of the present invention further provides a readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the milling machine obstacle control method in any of the above embodiments is implemented. Therefore, the readable storage medium in this embodiment has all the beneficial effects of the milling machine obstacle control method in any of the above embodiments, which will not be repeated here.
[0156] The basic principle of the present invention is described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, strengths, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. must be possessed by each embodiment of the present invention. In addition, the specific details disclosed above are only for the purpose of illustration and facilitation of understanding, rather than limitation, and the above details do not limit the present invention to being implemented by adopting the above specific details.
[0157] The block diagrams of the devices, apparatuses, equipment, and systems involved in the present invention are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them. It should also be noted that in the apparatus and equipment of the present invention, the components can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalents of the present invention.
[0158] The computer program product of the present invention may be written in any combination of one or more programming languages to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages such as Java, C++, etc., and conventional procedural programming languages such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user computing device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.
[0159] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present invention. Therefore, the present invention is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features of the present invention.
[0160] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A milling machine obstacle control method, applied to a milling machine with an image acquisition system, It is characterized in that The image acquisition system is used to acquire first image information of a first road surface area in front of the milling machine body and second image information of a second road surface area in front of the milling working device; The milling machine obstacle control method comprises: Step S100: during the operation of the milling machine, obtaining the first image information of the first road surface area in front of the milling machine body, and identifying obstacles in the first image information; Step S200: acquiring the second image information of the second road surface area in front of the milling working device, and determining the distance between the obstacle and the milling working device according to the second image information; Step S300: controlling the milling device to be lifted according to the distance to cross the obstacle; Wherein, in the traveling direction of the milling machine, the first road surface area is located in front of the second road surface area.
2. The obstacle control method for a milling machine according to claim 1, It is characterized in that The step S100: during the operation of the milling machine, obtaining the first image information of the first road surface area in front of the milling machine body, and identifying obstacles in the first image information, includes: Step S110: During the operation of the milling machine, continuously acquiring the first image information of the first road surface area in front of the milling machine body at a preset frequency; Step S120: preprocessing the first image information to obtain a preprocessed image; Step S130: detecting the preprocessed image using a preset obstacle detection model to determine size information and first position information of the obstacle; Wherein, the preprocessing includes distortion correction processing and cropping processing, and the obstacle detection model is preset in the controller of the milling machine.
3. The obstacle crossing control method for a milling machine according to claim 2, It is characterized in that The step S130: detecting the pre-processed image by using a preset obstacle detection model to determine the size information and the first position information of the obstacle, includes: Step S131: performing image segmentation processing on the pre-processed image using a preset obstacle detection model; Step S132: extracting pixel features of the obstacle in the segmented image to determine pixel size information of the obstacle in the image; Step S133: predicting the probability value of the obstacle corresponding to each type of object in the obstacle detection model, and determining the type of the obstacle according to the magnitude relationship between the probability value and the first threshold; Step S134: using a non-maximum suppression method to identify the IoU value of the obstacle, and determining the size information and the first position information of the obstacle according to the IoU value and the pixel size information; Step S135: marking the obstacle as a target obstacle, and storing the size information, first position information and pixel features of the target obstacle in the controller; Step S136: determining a first distance d1 between the target obstacle and the milling device according to the first position information of the target obstacle, and controlling the milling machine to reduce the travel speed when the distance d1 is less than the first distance threshold D1; Step S137: Control the alarm prompt device of the milling machine to continuously output alarm prompt information.
4. The obstacle crossing control method for a milling machine according to claim 3, It is characterized in that The step S200: acquiring the second image information of the second road surface area in front of the milling working device, and determining the distance between the obstacle and the milling working device according to the second image information, comprises: Step S210: continuously acquiring second image information of a second road surface area in front of the milling working device at a preset frequency; Step S220: matching and identifying the second image information with the target obstacle identified in the first image information to determine whether the target obstacle appears in the second image information; Step S230: When the target obstacle appears in the second image information, second position information of the target obstacle and a second distance d2 between the target obstacle and the milling working device are determined according to size information of the target obstacle and body structure parameters of the milling machine.
5. The obstacle crossing control method for a milling machine according to claim 4, It is characterized in that The step S220: matching and identifying the second image information with the target obstacle identified in the first image information to determine whether the target obstacle appears in the second image information, includes: Step S221: detecting the type and size information of the obstacle in the second image information by using a preset obstacle detection model, and comparing the type and size with the target obstacle identified in the first image information to generate a first comparison result; If the first comparison result is different, executing step S222: maintaining the current working state; If the first comparison result is the same, executing step S223: extracting the pixel features of the obstacle in the second image information, and comparing them with the pixel features of the target obstacle to generate a second comparison result; If the second comparison result is different, executing the step S222: maintaining the current working state; If the second comparison result is the same, step S224 is executed: determining whether the target obstacle appears in the second image information.
6. The obstacle-crossing control method for a milling machine according to claim 4, It is characterized in that The step S300: controlling the milling device to lift according to the distance to cross the obstacle, comprises: Step S310: when the second spacing d2<the second distance threshold D2, the milling working device is controlled to be lifted to a target height, and a lifting state moving distance of the milling working device in the traveling direction is calculated by fusion; wherein the target height is greater than the height dimension of the target obstacle, and a preset height difference is maintained between the target height and the height dimension of the target obstacle; Step S320: determining whether the milling working device has crossed the target obstacle according to the structural parameters of the milling working device and the moving distance in the lifting state; Step S330: When the milling working device has crossed the target obstacle, controlling the milling working device to descend and return to the initial milling depth; Step S340: controlling the milling machine to return to a normal operating speed; Step S350: Control the alarm prompt device to stop outputting the alarm prompt information.
7. The obstacle-crossing control method for a milling machine according to claim 6, It is characterized in that The step S310: when the second distance d2<the second distance threshold D2, controlling the milling device to be lifted to a target height, and using a fusion algorithm to calculate the lifting state moving distance of the milling device in the traveling direction, includes: Step S311: when the second distance d2<the second distance threshold D2, controlling the milling working device to be lifted from the initial milling depth to the target height, and storing the initial milling depth data in the controller; Step S312: using an algorithm model based on Kalman filtering, predicting the position information and moving speed information of the milling working device in the next preset period according to the odometer data of the milling machine in each preset period; wherein the position and speed are selected as Kalman state variables; Step S313: correcting the accumulated error of the odometer data according to the position change and speed information of the milling machine in the first image information; Step S314: updating the mean and covariance of the corrected position information and moving speed information of the milling working device; Step S315: Calculate the lifting state moving distance according to the updated position information and moving speed information of the milling working device.
8. The obstacle-crossing control method for a milling machine according to claim 6, It is characterized in that The step S320: determining whether the milling working device has crossed the target obstacle according to the structural parameters of the milling working device and the moving distance in the lifting state, comprises: Step S321: Calculate the sum of the size of the milling working device in the traveling direction, the length of the target obstacle, and the front and rear preset gaps, and record it as a reference length size; Step S322: determining whether the lifting state moving distance is greater than the reference length dimension, and generating a determination result; If the judgment result is yes, then executing step S323: determining that the milling working device has crossed the target obstacle; If the judgment result is no, the step S321 is executed again.
9. A milling machine, It is characterized in that include: Milling machine body; A milling device connected to the bottom of the milling machine body, the milling device being capable of lifting and lowering relative to the milling machine body; An image acquisition system is provided on the milling machine body and is used to acquire the first image information of a first road surface area in front of the milling machine body and the second image information of a second road surface area in front of the milling working device; A controller is disposed on the milling machine body and is communicatively connected with the milling machine body, the milling working device and the image acquisition system. The controller identifies obstacles based on the first image information and the second image information, and controls the milling working device to cross the obstacles, so as to execute the milling machine obstacle crossing control method as described in any one of claims 1 to 8.
10. The milling machine according to claim 9, It is characterized in that The image acquisition system comprises: A first image collector is provided at the front end of the milling machine body and is located at the lateral side of the milling machine body, and is used to collect the first image information of the first road surface area; The second image collector is disposed at the bottom of the milling machine body and is spaced behind the first image collector in the traveling direction, and is used to collect the second image information of the second road surface area.
Citation Information
Cited By
Obstacle crossing control method for curtain wall cleaning robot and related equipment
CN121286957A
Obstacle crossing control method for curtain wall cleaning robot and related equipment
CN121286957B
