Control method, device, vehicle and computer storage medium

Abstract

The present disclosure relates to a control method, device, vehicle and computer storage medium, and relates to the technical field of control. The control method comprises: transmitting, by at least one transmitting device installed on a vehicle, an optical signal to a track where the vehicle is located, to obtain at least one projection image of the optical signal on an edge of the track where the vehicle is located; determining a first pose adjustment parameter of the vehicle according to the at least one projection image; and determining whether to control the driving of the vehicle according to the first pose adjustment parameter. The technical solution of the present disclosure can improve the stability of vehicle control.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of control, and in particular, to a control method, a control device, a vehicle, and a computer storage medium. BACKGROUND

[0002] In complex vehicle operations, efficiency and accuracy control during multi-operation point switching are particularly critical. For example, in track slab laying and maintenance operations, track slab fine adjustment robots need to efficiently switch between multiple operation points to complete accurate adjustment of the track slab.

[0003] In related technologies, the position switching of a vehicle between multiple operation points relies on preset tracks or sensor navigation. SUMMARY

[0004] The present inventors have found that the above related technologies have the following problems: the vehicle is difficult to adapt to complex and variable route scenarios, resulting in poor stability of vehicle control.

[0005] In view of this, the present disclosure proposes a control technical solution that can improve the stability of vehicle control.

[0006] According to some embodiments of the present disclosure, a control method is provided, including: emitting, by at least one emitting device installed on a vehicle, an optical signal to a track on which the vehicle is located, to obtain at least one projection image of the optical signal on an edge of the track on which the vehicle is located; determining a first pose adjustment parameter of the vehicle according to the at least one projection image; and determining whether to control vehicle travel according to the first pose adjustment parameter.

[0007] In some embodiments, edge information of the track is determined in the at least one projection image; current pose information of the vehicle is determined according to the edge information, the current pose information including a travel direction of the vehicle and position information of the vehicle; and the first pose adjustment parameter of the vehicle is determined according to the current pose information of the vehicle.

[0008] In some embodiments, edge feature points of the track are extracted in the at least one projection image; and the edge information of the track is determined by fitting processing on the edge feature points.

[0009] In some embodiments, the first pose adjustment parameter of the vehicle is determined according to the current pose information and related information of the track, the related information of the track including an extension direction of the track and position information of the track.

[0010] In some embodiments, an offset amount of the vehicle is determined according to a difference between the position information of the vehicle and the position information of the track; an offset angle of the vehicle is determined according to a difference between the travel direction of the vehicle and the extension direction of the track; and the first pose adjustment parameter of the vehicle is determined according to the offset angle and the offset amount.

[0011] In some embodiments, in response to the first pose adjustment parameter being greater than the first threshold, the vehicle travel is controlled according to the first pose adjustment parameter.

[0012] In some embodiments, the second pose adjustment parameter is determined according to the first pose adjustment parameter by using a steering algorithm, and the vehicle travel is controlled according to the second pose adjustment parameter.

[0013] In some embodiments, in response to the first pose adjustment parameter being less than or equal to the first threshold, it is determined that the vehicle travel is not controlled, and the first pose adjustment parameter is stored as a historical adjustment parameter.

[0014] In some embodiments, in response to the first pose adjustment parameter being greater than the second threshold, the first pose adjustment parameter is updated according to the historical adjustment parameter, and it is determined whether to control the vehicle travel according to the updated first pose adjustment parameter.

[0015] In some embodiments, the at least one emitting device includes a first emitting device and a second emitting device, and the at least one projection image includes a first projection image obtained by the first emitting device and a second projection image obtained by the second emitting device.

[0016] In some embodiments, first pose information of the vehicle is determined according to the first projection image, second pose information of the vehicle is determined according to the second projection image, and the first pose adjustment parameter is determined according to the first pose information and the second pose information.

[0017] In some embodiments, the vehicle includes a track plate fine adjustment robot.

[0018] According to another embodiment of the present disclosure, a control device is provided, which includes: an acquisition unit configured to emit an optical signal to a track on which a vehicle is located by at least one emitting device installed on the vehicle to obtain at least one projection image of the optical signal on an edge of the track on which the vehicle is located; a determination unit configured to determine a first pose adjustment parameter of the vehicle according to the at least one projection image; and a control unit configured to determine whether to control a travel of the vehicle according to the first pose adjustment parameter.

[0019] In some embodiments, the determination unit determines edge information of the track in the at least one projection image, determines current pose information of the vehicle according to the edge information, the current pose information including a travel direction of the vehicle and position information of the vehicle, and determines the first pose adjustment parameter of the vehicle according to the current pose information of the vehicle.

[0020] In some embodiments, the determination unit extracts edge feature points of the track in the at least one projection image, and performs fitting processing on the edge feature points to determine the edge information of the track.

[0021] In some embodiments, the determining unit determines the first pose adjustment parameter of the vehicle according to the current pose information and the related information of the track, the related information of the track including an extension direction of the track and position information of the track.

[0022] In some embodiments, the determining unit determines an offset amount of the vehicle according to a difference between the position information of the vehicle and the position information of the track; determines an offset angle of the vehicle according to a difference between the travel direction and the extension direction of the track; and determines the first pose adjustment parameter of the vehicle according to the offset angle and the offset amount.

[0023] In some embodiments, the control unit controls the vehicle travel according to the first pose adjustment parameter in response to the first pose adjustment parameter being greater than a first threshold.

[0024] In some embodiments, the control unit determines a second pose adjustment parameter using a steering algorithm according to the first pose adjustment parameter, and controls the vehicle travel according to the second pose adjustment parameter.

[0025] In some embodiments, the control unit determines not to control the vehicle travel in response to the first pose adjustment parameter being less than or equal to a first threshold, and stores the first pose adjustment parameter as a historical adjustment parameter.

[0026] In some embodiments, the control unit updates the first pose adjustment parameter according to the historical adjustment parameter in response to the first pose adjustment parameter being greater than a second threshold, and determines whether to control the vehicle travel according to the updated first pose adjustment parameter.

[0027] In some embodiments, the at least one emitting device includes a first emitting device and a second emitting device, and the at least one projection image includes a first projection image obtained by the first emitting device and a second projection image obtained by the second emitting device.

[0028] In some embodiments, the determining unit determines first pose information of the vehicle according to the first projection image, determines second pose information of the vehicle according to the second projection image, and determines the first pose adjustment parameter according to the first pose information and the second pose information.

[0029] In some embodiments, the vehicle includes a track plate fine adjustment robot.

[0030] According to yet some embodiments of the present disclosure, a control device is provided, including a memory and a processor coupled to the memory, the processor being configured to perform the control method in any one of the above embodiments based on instructions stored in the memory device.

[0031] According to still some embodiments of the present disclosure, there is provided a vehicle comprising the control device in any of the above embodiments; a visual perception device comprising at least one emitting device for emitting optical signals to a track where the vehicle is located.

[0032] In some embodiments, the visual perception device further comprises an image acquisition device for acquiring at least one projection image of the optical signals on an edge of the track where the vehicle is located.

[0033] According to still some embodiments of the present disclosure, there is provided a computer storage medium having stored thereon a computer program, which, when executed by a processor, implements the control method in any of the above embodiments.

[0034] According to still some embodiments of the present disclosure, there is also provided a computer program product comprising instructions which, when executed by a processor, cause the processor to perform the control method according to any of the above embodiments.

[0035] In the above embodiments, by emitting optical signals to the track, projection images of the optical signals on the edge of the track are captured, so that a complex and changeable route scene is judged according to the projection images, and then the first pose adjustment parameter of the vehicle is accurately determined to determine whether to control the driving of the vehicle. In this way, the accuracy of the acquisition of the pose information of the vehicle can be improved, so that the stability of the vehicle control is improved, and then the efficiency of the movement of the vehicle is improved. BRIEF DESCRIPTION OF DRAWINGS

[0036] The accompanying drawings, which form a part of the specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0037] The present disclosure can be understood more readily by reference to the following detailed description, taken in connection with the accompanying drawings, in which:

[0038] Figure 1 flowcharts illustrating some embodiments of the control method of the present disclosure;

[0039] Figure 2 schematic diagrams illustrating some embodiments of the control method of the present disclosure;

[0040] Figure 3 schematic diagrams illustrating some other embodiments of the control method of the present disclosure;

[0041] Figure 4 schematic diagrams illustrating some embodiments of the track plate fine adjustment robot of the present disclosure;

[0042] Figure 5 flowcharts illustrating some other embodiments of the control method of the present disclosure;

[0043] Figure 6a flowchart showing yet other embodiments of the control method of the present disclosure;

[0044] Figure 7 a block diagram showing some embodiments of the control device of the present disclosure;

[0045] Figure 8 a block diagram showing other embodiments of the control device of the present disclosure;

[0046] Figure 9 a block diagram showing yet other embodiments of the control device of the present disclosure;

[0047] Figure 10 a block diagram showing some embodiments of the vehicle of the present disclosure. DETAILED DESCRIPTION

[0048] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. Note that the relative arrangement, numerical expressions, and numerical values of components and steps set forth in these embodiments are not limiting to the scope of the present disclosure unless otherwise specifically stated.

[0049] Meanwhile, it should be understood that the sizes of the various portions shown in the drawings are shown for illustrative purposes only and are not limiting to the scope of the present disclosure.

[0050] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way limiting to the scope of the disclosure and its applications or uses.

[0051] Techniques, methods, and apparatus known to those of ordinary skill in the relevant art can not be discussed in detail herein, but should be considered as part of the specification, where appropriate.

[0052] In all examples shown and discussed herein, any specific values should be interpreted as merely illustrative and not as limiting. Thus, other examples of the exemplary embodiments can have different values.

[0053] It should be noted that like reference numerals and letters refer to like items throughout the drawings, and once an item is defined in one drawing, it need not be discussed further in subsequent drawings.

[0054] As mentioned previously, in the related art, the position switching of the vehicle between multiple work points relies on preset tracks or sensor navigation, which is relatively sensitive to interference factors such as light changes and track stains, and can cause the vehicle route recognition to be ambiguous, resulting in deviation of the vehicle travel direction judgment, easy deviation from the predetermined route, and difficulty in adapting to diversified construction scenarios. Moreover, the route deviation also increases the operation time cost, and even exists the risk of collision, which can damage equipment, delay project progress, and cannot meet the needs of modern rail transit for efficient and safe construction.

[0055] Furthermore, the aforementioned control methods have limited ability to detect dynamic obstacles (such as temporary construction materials) and lack efficient real-time perception and obstacle avoidance mechanisms, making them difficult to handle. Furthermore, the open-loop or semi-closed-loop control modes employed in related technologies can result in delayed vehicle posture adjustments and low correction efficiency.

[0056] To address at least one of the aforementioned issues, the present disclosure provides a control method that emits an optical signal onto a track to capture its projected image on the track edge. This projected image can then be used to determine complex and changing route scenarios, accurately determining the vehicle's first posture adjustment parameter to determine whether to control the vehicle's movement. This improves the accuracy of vehicle posture information acquisition, thereby enhancing vehicle control stability and ultimately improving vehicle movement efficiency.

[0057] For example, the technical solutions of the present disclosure can be implemented through the following embodiments.

[0058] Figure 1 Flowcharts showing some embodiments of the control method of the present disclosure.

[0059] like Figure 1 As shown, in step 110, an optical signal is transmitted to the track where the vehicle is located by at least one transmitting device installed on the vehicle to obtain at least one projection image of the optical signal on the edge of the track where the vehicle is located.

[0060] For example, a visual perception device is mounted on the vehicle, and the visual perception device includes a transmitter. The transmitter may be a multi-line laser for projecting multiple laser lines onto the track. The visual perception device may also include an image acquisition device for acquiring an image of the projection of the light signal emitted by the transmitter onto the edge of the track.

[0061] By transmitting optical signals to the track and determining track information based on the projected image of the optical signals on the track, the impact of environmental factors such as lighting changes and track surface stains on track information acquisition can be reduced, improving the accuracy of information acquired through images and thus enhancing vehicle control stability. Furthermore, the collaborative operation of the transmitting device and the image acquisition device enhances the robustness of track recognition in complex environments.

[0062] In step 120, a first posture adjustment parameter of the vehicle is determined based on the at least one projected image. For example, track edge information can be determined in the projected image, and the vehicle's posture information can be determined based on the relative relationship between the track edge and the vehicle in terms of direction and position. The first posture adjustment parameter of the vehicle is then determined to determine whether the vehicle has deviated from the track.

[0063] In this way, the track edge information can be accurately captured by obtaining the projection image of the optical signal at the track edge, and the first pose adjustment parameter of the vehicle is determined according to the obtained track edge information, thereby improving the accuracy of the vehicle pose information.

[0064] In step 130, it is determined whether to control the vehicle driving according to the first pose adjustment parameter. For example, it can be determined according to the first pose adjustment parameter whether the vehicle deviates from the track, and in the case that the vehicle deviates from the track, the driving of the vehicle is controlled to make it normally drive.

[0065] In the above embodiment, the first pose adjustment parameter of the vehicle is accurately determined according to the projection image of the track edge by emitting the optical signal to the track and capturing the projection image of the optical signal at the track edge, so as to determine whether the vehicle deviates from the track, and further determine whether to control the driving of the vehicle. In this way, the accuracy of the acquisition of the vehicle pose information can be improved, thereby improving the stability of the vehicle control and further improving the efficiency of the vehicle movement.

[0066] The determination method of the first pose adjustment parameter in step 120 is exemplarily described below according to some embodiments.

[0067] In some embodiments, the edge information of the track is determined in the at least one projection image; the current pose information of the vehicle is determined according to the edge information, the current pose information including the driving direction of the vehicle and the position information of the vehicle; and the first pose adjustment parameter of the vehicle is determined according to the current pose information of the vehicle.

[0068] In this way, the pose information of the vehicle can be accurately determined according to the projection image of the track edge without being affected by environmental factors, thereby improving the accuracy of the vehicle pose information.

[0069] In some embodiments, the edge feature points of the track can be extracted in the at least one projection image; and the edge feature points are fitted to determine the edge information of the track.

[0070] For example, the track edge is usually higher than the ground, and due to the vertical height difference between the track edge and the cement pavement (such as the height of the track plate), the laser line in the projection image will be broken at the track edge to form edge feature points. The edge information of the track can be determined according to the obtained edge feature points.

[0071] For example, the edge information of the track includes the edge straight line of the track. The edge feature points of the track can be determined and fitted to determine the edge straight line of the track by drawing the ROI (Region of Interest), filtering, noise reduction, binarization and laser center line extraction algorithm.

[0072] The determination method of the first pose adjustment parameter in step 120 is exemplarily described below according to some embodiments.Figure 2 In some embodiments, the edge line of the track is determined according to the edge feature points in the projection image.

[0073] Figure 2 A schematic diagram showing some embodiments of the control method of the present disclosure.

[0074] In some embodiments, the edge feature points of the track in the projection image can be the breakpoints of the laser line. When the multi-line laser is projected to both sides of the track plate, the laser breakpoints are generated. By fitting a straight line to these breakpoints, the position and direction of the vehicle body can be determined.

[0075] With reference to Figure 2 , the image acquisition device can capture the projection image of the laser line with breakpoints, and the laser line and the background are two different colors in the projection image. The laser line can be extracted by image processing threshold method. The laser center line coordinates are extracted according to the gray center of gravity algorithm, and the breakpoint coordinates are obtained according to the ROI region. Then the extracted edge feature points are fitted into an edge line by the least square method. The first pose adjustment parameter of the vehicle is determined and the motion instruction is determined by using the offset information of the edge line relative to the track in angle and position. As shown in Figure 2 , the line in the block is the fitted edge line.

[0076] For example, the projection area of the laser line is the area on both sides of the track, Figure 2 the projection image of only one side of the track is shown in the figure, and the other side is not drawn.

[0077] In some embodiments, the current pose information of the vehicle can be determined according to the edge information of the track. For example, the direction of travel of the vehicle and the position information of the vehicle can be determined according to the extension direction of the edge line of the track and the position of the center point.

[0078] In this way, the pose information of the vehicle is determined according to the relative relationship between the track edge and the vehicle in direction and position, which can improve the accuracy of the pose information of the vehicle.

[0079] In the following, some embodiments are exemplarily illustrated to show how to determine the first pose adjustment parameter according to the obtained current pose information of the vehicle.

[0080] In some embodiments, the first pose adjustment parameter of the vehicle is determined according to the current pose information and the related information of the track. For example, the related information of the track includes the extension direction of the track and the position information of the track.

[0081] For example, the offset of the vehicle can be determined according to the difference between the position information of the vehicle and the position information of the track. The offset angle of the vehicle is determined according to the difference between the direction of travel and the extension direction of the track. The first pose adjustment parameter of the vehicle is determined according to the offset angle and the offset.

[0082] For example, the offset angle can be an angle between a direction in which the vehicle travels and a direction in which the track extends, for measuring the directional deviation. The offset amount can be a vertical distance between a center line of a path in which the vehicle travels and a center line of the track, for measuring the positional deviation.

[0083] For example, an angle between the edge straight line and a vertical direction of the projection image can be determined as the offset angle (a), and a distance between a center point of the edge straight line and a center point of the projection image can be determined as the offset amount (d).

[0084] In this way, by the difference between the current pose information of the vehicle and the track-related information, the first offset adjustment parameter of the vehicle can be accurately determined to determine the offset condition of the current driving of the vehicle, thereby improving the stability of the vehicle control.

[0085] The following will be described by some embodiments, which exemplarily illustrate the technical solutions in the step 130 of the method 100. Figure 1 In the step 130, the technical solution of determining whether to control the driving of the vehicle according to the determined first pose adjustment parameter.

[0086] In some embodiments, in response to the first pose adjustment parameter being less than or equal to a first threshold value, it is determined not to control the driving of the vehicle, and the first pose adjustment parameter is stored as a historical adjustment parameter. For example, the first threshold value can be used as a judgment condition for whether the vehicle deviates from the track. In the case that the first pose adjustment parameter of the vehicle is less than or equal to the first threshold value, it can be considered that the vehicle does not deviate from the track at present, so that the current driving of the vehicle is not controlled, thereby avoiding the instability of the driving of the vehicle due to frequent adjustment actions of the vehicle.

[0087] In some embodiments, in response to the first pose adjustment parameter being greater than the first threshold value, the driving of the vehicle is controlled according to the first pose adjustment parameter. For example, in the case that the first pose adjustment parameter of the vehicle is greater than the first threshold value, it can be considered that the vehicle has deviated from the track at present, so that the current driving of the vehicle needs to be controlled to make it drive normally.

[0088] For example, in response to the first pose adjustment parameter being greater than the first threshold value, a second pose adjustment parameter is determined according to the first pose adjustment parameter by using a steering algorithm, and the driving of the vehicle is controlled according to the second pose adjustment parameter.

[0089] For example, the first threshold value can be set as a1 = 1° or d1 = 2 cm, where a1 is the offset angle in the first pose adjustment parameter determined in step 120, and d1 is the offset amount. In the case of a1 > 1° or d1 > 2 cm, the second pose adjustment parameter (a3, d3) is dynamically calculated using the steering algorithm according to the relationship between a1 and d1. According to the second pose adjustment parameter, the PLC (Programmable Logic Controller) control instruction is adjusted to perform the deviation correction and achieve dynamic adjustment to control the vehicle running.

[0090] For example, the obtained second pose adjustment parameter can be stored as a historical adjustment parameter.

[0091] In this way, by comparing the first pose adjustment parameter with the first threshold value, it can be accurately determined whether the vehicle deviates from the track, and in the case of deviation, the vehicle can be adjusted according to the deviation condition, thereby improving the accuracy and stability of vehicle control.

[0092] In some embodiments, obstacles on the track can affect the generation of the projected image, causing the obtained first pose adjustment parameter to be abnormal, so that it can be determined whether the first pose adjustment parameter is abnormal and processed.

[0093] The following will be described by way of example with reference to the embodiments of the present disclosure. Figure 3 The projection image of the multi-line laser projected onto the obstacle region is exemplarily illustrated.

[0094] Figure 3 The schematic diagram showing another embodiment of the control method of the present disclosure.

[0095] In some embodiments, since the pressure bar structure is arranged on the track plate and the height of the pressure bar structure is higher than that of the track plate, in the case of multi-line laser projection onto the obstacle region, i.e., the pressure bar structure, the projected image will appear as a full black region without laser lines.

[0096] Referring to Figure 3 , the two upper laser lines are detected within the ROI, the offset angle and the offset amount are determined by fitting a straight line, and the direction route planning of the system is performed depending on the two parameters. In the case of multi-line laser projection onto the obstacle region, the corresponding region cannot be fitted with a straight line due to the full black, at which time the system can have no output result or output abnormal data, which is not counted in the operation.

[0097] For example, the first pose adjustment parameter can be compared with the second threshold value to determine whether the first pose adjustment parameter is abnormal due to the presence of obstacles in Figure 3 , and then the first pose adjustment parameter is adjusted.

[0098] The above technical solution of determining abnormal data according to the second threshold is exemplarily illustrated by some embodiments.

[0099] In some embodiments, in response to the first pose adjustment parameter being greater than the second threshold, the first pose adjustment parameter is updated according to historical adjustment parameters; and whether to control the vehicle driving is determined according to the updated first pose adjustment parameter.

[0100] For example, the second threshold can be set as a1=10° or d1=20cm. In the case of a1>10° or d1>20cm, the first pose adjustment parameter is determined as an abnormal value. The first pose adjustment parameter can be updated according to historical adjustment parameters, so that the first pose adjustment parameter can meet the requirement of the second threshold. In the case of the first pose adjustment parameter being less than or equal to the second threshold, the first pose adjustment parameter is determined as a normal value, and the first pose adjustment parameter can be used for the aforementioned determination process of whether the vehicle deviates from the track.

[0101] In this way, by comparing the first pose adjustment parameter with the second threshold and adjusting the first pose adjustment parameter in the case of abnormality, the interference of abnormal conditions such as route occlusion on the calculation result of the first pose adjustment parameter can be avoided, and the stability of vehicle control can be improved.

[0102] In some embodiments, in the case of detecting an abnormal value, the first pose adjustment parameter can be updated by weighted average of multiple sets of historical adjustment parameters.

[0103] For example, in the case of a full black state (i.e., unable to fit an edge straight line) in the detection region of the projection image or the angle deviation exceeding the threshold, the system determines the output first pose adjustment parameter as an abnormal value. At this time, the real-time detection result of the pose information cannot be output, and the vehicle needs to maintain the current driving state. Taking a track radius adjustment robot as an example, the working task thereof belongs to high-precision work, and the change amplitude of the track edge angle in the projection image is usually small, so the current reasonable output value, i.e., the updated first pose adjustment parameter, can be calculated by relying on the historical adjustment parameters.

[0104] For example, 5 sets of historical adjustment parameters can be used to calculate the mean value as the updated first pose adjustment parameter (a2, d2). In the case of the updated first pose adjustment parameter being less than or equal to the second threshold, the updated first pose adjustment parameter is used for the determination process of whether the vehicle deviates from the track.

[0105] In this way, by smoothing abnormal fluctuations through statistical characteristics of historical adjustment parameters, both the engineering characteristics of gradual change of track parameters and the continuity of system operation under abnormal working conditions can be ensured, thereby improving the stability of vehicle control.

[0106] In some embodiments, multiple emitting devices can be installed on the vehicle. Multiple projection images of the multiple emitting devices on the edges of the track are acquired by the image acquisition device, it is determined whether the vehicle deviates from the track, and it is determined whether to control it.

[0107] In the following, some embodiments are exemplarily described in the case of multiple emitting devices installed on the vehicle.

[0108] In some embodiments, the at least one emitting device includes a first emitting device and a second emitting device, and the at least one projection image includes a first projection image obtained by the first emitting device and a second projection image obtained by the second emitting device.

[0109] For example, the first emitting device and the second emitting device can be respectively installed on the left and right sides of the vehicle to emit optical signals to both sides of the track. The projection images of the optical signals on the edges of the left and right sides of the track are acquired by the image acquisition devices on the left and right sides, and the pose information of the vehicle is determined according to the projection images.

[0110] For example, the first pose information of the vehicle can be determined according to the first projection image, the second pose information of the vehicle can be determined according to the second projection image, and the first pose adjustment parameter can be determined according to the first pose information and the second pose information.

[0111] For example, due to the installation angle deviation, imaging perspective distortion (such as the effect of near large and far small), and parallax of the image acquisition devices and the emitting devices on the left and right sides, even when the vehicle is straight, the fitting result of the edge straight line can still have an angle deviation and a position deviation. Therefore, the information obtained from the projection images on the left and right sides needs to be fused.

[0112] In this way, by symmetrically arranging the visual perception devices on the left and right sides of the vehicle, the symmetry of the data detected by the visual perception devices can be used to offset the systematic errors, thereby improving the accuracy of the vehicle body pose detection and the stability of the vehicle control. Based on the visual data obtained by the visual perception devices on the left and right sides, the vehicle pose is calculated in real time and the adjustment control parameter is planned, which can realize dynamic obstacle avoidance and deviation correction of the vehicle, and further improve the stability of the vehicle control.

[0113] For example, in the case that the deflection angle of the edge straight line output by the visual perception device on the left side of the vehicle is -2°, and the deflection angle of the edge straight line output by the visual perception device on the right side of the vehicle is +3°, based on the error compensation mechanism arranged symmetrically, the actual deflection angle can be corrected to [(-2°)+(+3°)] / 2=+0.5°, and the correction principle of the offset amount is similar, that is, the non-symmetrical error component is eliminated by symmetrically calculating the data on the left and right sides, thereby improving the accuracy of the vehicle body pose detection.

[0114] In the above embodiment, by acquiring the projection image of the optical signal at the track edge, track edge information is precisely captured. Based on this track edge information, the vehicle's first posture adjustment parameter is accurately determined to determine whether the vehicle has deviated from the track. If the vehicle deviates from the track, it can be controlled based on the degree of deviation. This improves the accuracy of vehicle posture information acquisition, thereby enhancing the stability of vehicle control and, consequently, the efficiency of vehicle movement.

[0115] In some embodiments, the vehicle includes a track slab fine-tuning robot.

[0116] Below through Figure 4 The embodiment in the figure illustrates the structure of the track plate fine-tuning robot by way of example.

[0117] Figure 4 Schematic diagrams showing some embodiments of the track plate fine-tuning robot disclosed herein.

[0118] like Figure 4 As shown, the structure of the road surface includes walls on both sides, a cement road surface, and a track plate 405 , which is laid on the cement road surface. A track plate fine-tuning robot 401 operates on the track plate 405 .

[0119] The track plate fine-tuning robot 401 includes three parts: a visual perception device, a main control device and a motion control device.

[0120] The visual perception device includes an image acquisition device and an emission device. The image acquisition device can be an industrial camera 402, and the emission device can be a multi-line laser 403. The multi-line laser 403 is used to project laser stripes onto the track plate 405 to form a laser line projection area 404. The industrial camera 402 is used to capture laser images. The main control device includes an industrial computer 406, which is used for image processing, path planning and control instruction generation. The motion control device includes a PLC 407, which is used to execute movement posture adjustment instructions. The visual perception device is installed on the legs on both sides of the fine-tuning plate track robot 401, and the main control device and the motion control device are installed on the body of the fine-tuning plate track robot 401.

[0121] For example, the multi-line laser 403 can be installed on the vertical leg and projected toward the front and bottom, while the industrial camera 402 is fixed on the lateral leg, and the center of the field of view of the industrial camera 402 is precisely aligned with the laser line that produces the breakpoint.

[0122] Visual perception devices can be deployed on both legs of the track plate fine-tuning robot 401. If the visual perception device is installed on only one side of the track plate fine-tuning robot 401, the industrial camera 402's field of view and the vehicle's structural obstruction may prevent the complete capture of the laser lines on the other side. The relative positioning design creates a difference in projection angle between the industrial camera 402 and the multi-line laser 403, causing different laser lines within the industrial camera's field of view to shift due to the height difference, preventing them from overlapping on the same straight line.

[0123] For example, Figure 4 As shown, industrial camera 402 is mounted high inside, with the laser beam projected onto the outside of track plate 405. Because track plate 405 is higher than the concrete pavement, this mounting arrangement allows the laser beam to intermittently break within the field of view of industrial camera 402, thus preventing the laser beam from being continuous, making it difficult to identify angular features and thus affecting subsequent position and direction determination.

[0124] Below through Figure 5 In the embodiment, Figure 4 Taking the track plate fine adjustment robot in the example, the following is an example to illustrate Figure 1 The technical solution of steps 110-130.

[0125] Figure 5 Flowcharts showing other embodiments of the control method of the present disclosure.

[0126] like Figure 5 As shown, in step 510 , an initial offset angle (α0) and an offset amount (d0) are set.

[0127] In step 515 , an optical signal is transmitted to the track by a transmitting device, and a projection image of the optical signal on the edge of the track is acquired by an image acquiring device.

[0128] In step 520, the projection image is pre-processed to obtain edge information of the track. For example, the laser edge line can be fitted by ROI region drawing, filtering, noise reduction, binarization, and laser centerline extraction algorithm.

[0129] In step 525, the current posture information of the robot is determined by the edge information of the track, and then the offset angle and offset of the current driving state of the robot relative to the track are obtained, that is, the first posture adjustment parameter.

[0130] In step 530, it is determined whether the offset angle and offset amount are greater than a second threshold. If so, the offset angle and offset amount are determined to be abnormal values, and step 535 is executed. If not, the offset angle and offset amount are determined to be normal values, and subsequent operations can be continued using the offset angle and offset amount.

[0131] In step 535, the offset angle or offset amount is determined to be an abnormal value, and is updated according to the historical adjustment parameters so that the offset angle or offset amount can meet the requirement of the second threshold.

[0132] In step 540, it is determined whether the deviation angle and the deviation amount are greater than a first threshold. If so, step 545 is executed. If not, it is determined that the robot has not deviated from the track, and step 555 is executed to determine that the robot will not be controlled and only the historical adjustment parameters will be updated based on the first pose adjustment parameters.

[0133] In step 545, in response to the deviation angle or offset being greater than the first threshold, the robot is determined to have deviated from its trajectory. The steering algorithm dynamically calculates the second posture adjustment parameters (α3, d3). Then, step 550 is executed to adjust the PLC control instructions based on the second posture adjustment parameters, execute deviation correction, implement dynamic adjustment, and control the robot's movement.

[0134] In step 555 , the second posture adjustment parameter is stored as a historical adjustment parameter.

[0135] In step 560, it is determined whether an end instruction has been received. If an end instruction has been received, control of the robot ends. If not, step 565 is executed, and the historical adjustment parameters are used as the initial values ​​of the offset angle and offset amount, and the above steps are repeated.

[0136] In the above embodiment, by obtaining the projection image of the optical signal on the edge of the track, the track edge information is accurately captured, so that the current posture information of the robot is accurately determined based on the track edge information, and the robot posture is monitored and adjusted in real time based on the current posture information and the planned path, thereby realizing automatic deviation correction and intelligent track tracking of the vehicle, improving the stability of the robot control, and thereby improving the automation level and efficiency of the robot operation.

[0137] Below through Figure 6 The embodiment in the embodiment, exemplarily illustrates that Figure 5 The control method in the control logic of the track plate fine-tuning robot is used to correct the deviation.

[0138] Figure 6 Flowcharts illustrating further embodiments of the control method of the present disclosure are shown.

[0139] In step 610, a high-resolution industrial camera is used in combination with structured light imaging technology to enhance the ability to capture track edge features in complex lighting and stain environments; the field of view is expanded through the collaboration of multiple cameras to achieve real-time high-precision processing of track images and route positioning.

[0140] For example, the industrial camera shoots a plurality of broken laser lines to obtain a projection image. Then the projection image can be preprocessed by filtering, noise reduction, binarization, etc., and the edge feature points of the track are determined and fitted to determine the edge straight line of the track and calculate the offset and angle.

[0141] In step 620, the industrial computer processes the image and generates a control instruction according to the second pose adjustment parameter, and sends the control instruction to the PLC through the network port / serial port.

[0142] In step 630, the PLC receives the instruction and drives the robot through the fuzzy / PID control algorithm to correct the travel direction.

[0143] In step 640, the robot executes the action, i.e., performs the steering action, to realize dynamic deviation correction of the robot.

[0144] And after a new round of image acquisition, the deviation is calculated by comparing the current and historical adjustment parameters, and the control instruction can be corrected to realize real-time monitoring and dynamic adjustment. Through the closed loop formed by the visual perception device, the industrial computer and the PLC, real-time deviation correction and stable travel are ensured.

[0145] In this way, through the "collection-processing-execution-feedback" cycle, a visual feedback and motion control closed loop is realized, and based on the recognition result and the planned path, the robot pose is monitored and adjusted in real time, high-precision automatic deviation correction is realized, the robot is ensured to accurately follow the track, and the robot can stably cope with interference such as light changes and stains, improve the stability of robot control, and thus ensure the continuity of construction. And by dynamically optimizing the first pose adjustment parameter, manual intervention can be reduced, the automation and intelligence level of control can be improved, and thus the robot moving time can be shortened, the robot operation precision and efficiency can be improved, and the risk of equipment collision and construction delay can be reduced.

[0146] Figure 7 A block diagram showing some embodiments of the control device of the present disclosure.

[0147] According to another embodiment of the present disclosure, a control device 7 is provided, comprising: an acquisition unit 71 configured to emit an optical signal to a track on which a vehicle is located by at least one emitting device installed on the vehicle to obtain at least one projection image of the optical signal on an edge of the track on which the vehicle is located; a determination unit 72 configured to determine a first pose adjustment parameter of the vehicle according to the at least one projection image; and a control unit 73 configured to determine whether to control the travel of the vehicle according to the first pose adjustment parameter.

[0148] In some embodiments, the determining unit 72 determines edge information of the track in the at least one projection image; determines, according to the edge information, current pose information of the vehicle, the current pose information comprising a traveling direction of the vehicle and position information of the vehicle; and determines, according to the current pose information of the vehicle, the first pose adjustment parameter of the vehicle.

[0149] In some embodiments, the determining unit 72 extracts edge feature points of the track in the at least one projection image; and performs fitting processing on the edge feature points to determine the edge information of the track.

[0150] In some embodiments, the determining unit 72 determines, according to the current pose information and related information of the track, the first pose adjustment parameter of the vehicle, the related information of the track comprising an extension direction of the track and position information of the track.

[0151] In some embodiments, the determining unit 72 determines, according to a difference between the position information of the vehicle and the position information of the track, an offset amount of the vehicle; determines, according to a difference between the traveling direction and the extension direction of the track, an offset angle of the vehicle; and determines, according to the offset angle and the offset amount, the first pose adjustment parameter of the vehicle.

[0152] In some embodiments, the control unit 73, in response to the first pose adjustment parameter being greater than a first threshold value, controls the vehicle traveling according to the first pose adjustment parameter.

[0153] In some embodiments, the control unit 73 determines, according to the first pose adjustment parameter, a second pose adjustment parameter by using a steering algorithm; and controls the vehicle traveling according to the second pose adjustment parameter.

[0154] In some embodiments, the control unit 73, in response to the first pose adjustment parameter being less than or equal to the first threshold value, determines not to control the vehicle traveling, and stores the first pose adjustment parameter as a historical adjustment parameter.

[0155] In some embodiments, the control unit 73, in response to the first pose adjustment parameter being greater than a second threshold value, updates the first pose adjustment parameter according to the historical adjustment parameter; and determines whether to control the vehicle traveling according to the updated first pose adjustment parameter.

[0156] In some embodiments, the at least one emitting device comprises a first emitting device and a second emitting device, and the at least one projection image comprises a first projection image obtained by the first emitting device and a second projection image obtained by the second emitting device.

[0157] In some embodiments, the determining unit 72 determines, according to the first projection image, first pose information of the vehicle; determines, according to the second projection image, second pose information of the vehicle; and determines, according to the first pose information and the second pose information, the first pose adjustment parameter.

[0158] In some embodiments, the vehicle comprises a track plate fine adjustment robot.

[0159] In the above embodiments, by acquiring the projection image of the optical signal at the track edge, the track edge information is accurately captured, so that the first pose adjustment parameter of the vehicle is accurately determined according to the track edge information, to determine whether to control the driving of the vehicle. In this way, the accuracy of the acquisition of the vehicle pose information can be improved, thereby improving the stability of the vehicle control, and further improving the efficiency of the vehicle movement.

[0160] Figure 8 A block diagram illustrating another embodiment of the control device of the present disclosure.

[0161] As Figure 8 shown, the control device 8 of this embodiment comprises a memory 81 and a processor 82 coupled to the memory 81, and the processor 82 is configured to execute the control method in any one of the embodiments of the present disclosure based on the instructions stored in the memory 81.

[0162] The memory 81 may, for example, include a system memory, a fixed non-volatile storage medium, etc. The system memory may, for example, store an operating system, an application program, a Boot Loader, a database, and other programs, etc.

[0163] Figure 9 A block diagram illustrating still another embodiment of the control device of the present disclosure.

[0164] As Figure 9 shown, the control device 9 of this embodiment comprises a memory 910 and a processor 920 coupled to the memory 910, and the processor 920 is configured to execute the control method in any one of the preceding embodiments based on the instructions stored in the memory 910.

[0165] The memory 910 may, for example, include a system memory, a fixed non-volatile storage medium, etc. The system memory may, for example, store an operating system, an application program, a Boot Loader, and other programs, etc.

[0166] The control device 9 may, for example, further comprise an input / output interface 930, a network interface 940, a storage interface 950, etc. These interfaces 930, 940, 950 and the memory 910 and the processor 920 may, for example, be connected through a bus 960. The input / output interface 930 provides a connection interface for display, mouse, keyboard, touch screen, microphone, speaker, etc. Input / output devices. The network interface 940 provides a connection interface for various networking devices. The storage interface 950 provides a connection interface for external storage devices such as SD cards and U disks.

[0167] Figure 10 A block diagram showing some embodiments of a vehicle of the present disclosure.

[0168] According to still further embodiments of the present disclosure, there is provided a vehicle 10 comprising a control device 1010 according to any of the above described embodiments; a visual perception device 1020 comprising at least one emitting device 1021 for emitting optical signals towards a track on which the vehicle is located.

[0169] In some embodiments, the visual perception device further comprises an image acquisition device 1022 for acquiring at least one projection image of the optical signals on an edge of the track on which the vehicle is located.

[0170] It should be understood by those skilled in the art that the embodiments of the present disclosure can be provided as a method, a device, a vehicle or a computer program product. Therefore, the present disclosure can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Moreover, the present disclosure can take the form of a computer program product implemented on one or more computer-usable non-transitory storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) having computer-usable program code embodied therein.

[0171] So far, the control method, the control device, the vehicle or the computer program product according to the present disclosure have been described in detail. In order to avoid obscuring the concept of the present disclosure, some details known in the art have not been described. Those skilled in the art can fully understand how to implement the technical solutions disclosed herein according to the above description.

[0172] The methods and systems of the present disclosure can be implemented in a number of ways. For example, the methods and systems of the present disclosure can be implemented using software, hardware, firmware, or any combination of software, hardware, and firmware. The above described order of steps for the methods is merely for illustration, and the steps of the methods of the present disclosure are not limited to the above specifically described order unless otherwise specifically stated. Furthermore, in some embodiments, the present disclosure can also be implemented as programs recorded in recording media, which include machine readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers recording media storing programs for executing the methods according to the present disclosure.

[0173] Although some specific embodiments of the present disclosure have been described in detail by way of example, those skilled in the art should understand that the above examples are merely for illustration, and are not intended to limit the scope of the present disclosure. Those skilled in the art should understand that modifications can be made to the above embodiments without departing from the scope and spirit of the present disclosure.

Claims

1. A control method, comprising: transmitting an optical signal to the track on which the vehicle is located by at least one transmitting device installed on the vehicle, so as to obtain at least one projection image of the optical signal on an edge of the track on which the vehicle is located; determining a first posture adjustment parameter of the vehicle based on the at least one projection image; determining whether to control the vehicle's travel according to the first posture adjustment parameter; Wherein, determining the first posture adjustment parameter of the vehicle according to the at least one projection image includes: determining edge information of the track in the at least one projection image; Determining current position information of the vehicle based on the edge information, where the current position information includes a traveling direction of the vehicle and position information of the vehicle; Determine the first posture adjustment parameter of the vehicle according to the current posture information of the vehicle, Determining the first posture adjustment parameter of the vehicle according to the current posture information of the vehicle includes: Determine a first posture adjustment parameter of the vehicle according to the current posture information and relevant information of the track, wherein the relevant information of the track includes an extension direction of the track and position information of the track, Determining a first posture adjustment parameter of the vehicle according to the current posture information and the relevant information of the track includes: determining an offset of the vehicle according to a difference between the position information of the vehicle and the position information of the track; determining a deviation angle of the vehicle based on a difference between the travel direction and the extension direction of the track; A first posture adjustment parameter of the vehicle is determined according to the offset angle and the offset amount.

2. The control method according to claim 1, wherein: Determining edge information of the track in the at least one projection image comprises: extracting edge feature points of the track in the at least one projection image; Fitting is performed on the edge feature points to determine edge information of the track.

3. The control method according to claim 1, wherein: The determining whether to control the vehicle driving according to the first posture adjustment parameter includes: In response to the first posture adjustment parameter being greater than a first threshold, the vehicle driving is controlled according to the first posture adjustment parameter.

4. The control method according to claim 3, wherein: In response to the first posture adjustment parameter being greater than a first threshold, controlling the vehicle driving according to the first posture adjustment parameter includes: Determining a second posture adjustment parameter using a steering algorithm based on the first posture adjustment parameter; The vehicle driving is controlled according to the second posture adjustment parameter.

5. The control method according to claim 1, wherein: The determining whether to control the vehicle driving according to the first posture adjustment parameter includes: In response to the first posture adjustment parameter being less than or equal to a first threshold, it is determined not to control the driving of the vehicle, and the first posture adjustment parameter is stored as a historical adjustment parameter.

6. The control method according to claim 1, wherein: The determining whether to control the vehicle driving according to the first posture adjustment parameter includes: In response to the first posture adjustment parameter being greater than a second threshold, updating the first posture adjustment parameter according to a historical adjustment parameter; Determine whether to control the vehicle driving according to the updated first posture adjustment parameter.

7. The control method according to any one of claims 1 to 6, wherein: The at least one emitting device includes a first emitting device and a second emitting device, and the at least one projection image includes a first projection image obtained by the first emitting device and a second projection image obtained by the second emitting device.

8. The control method according to claim 7, wherein: Determining a first posture adjustment parameter of the vehicle according to the at least one projection image includes: Determining first posture information of the vehicle according to the first projection image; determining second position information of the vehicle according to the second projection image; Determine the first posture adjustment parameter according to the first posture information and the second posture information.

9. The control method according to any one of claims 1 to 6, wherein: The vehicle includes a track slab fine-tuning robot.

10. A control device comprising: an acquisition unit, configured to transmit an optical signal to the track where the vehicle is located through at least one transmitting device installed on the vehicle, so as to obtain at least one projection image of the optical signal on an edge of the track where the vehicle is located; a determining unit, configured to determine a first posture adjustment parameter of the vehicle based on the at least one projection image; a control unit, configured to determine whether to control the vehicle's travel according to the first posture adjustment parameter, The determining unit determines edge information of the track in the at least one projection image; determines current posture information of the vehicle based on the edge information, wherein the current posture information includes the direction of travel of the vehicle and the position information of the vehicle; determines a first posture adjustment parameter of the vehicle based on the current posture information of the vehicle, The determining unit determines a first posture adjustment parameter of the vehicle based on the current posture information and relevant information of the track, wherein the relevant information of the track includes an extension direction of the track and position information of the track. The determining unit determines an offset of the vehicle based on a difference between the position information of the vehicle and the position information of the track; The offset angle of the vehicle is determined according to the difference between the traveling direction and the extension direction of the track; and the first posture adjustment parameter of the vehicle is determined according to the offset angle and the offset amount.

11. A control device comprising: Memory; and A processor coupled to the memory, wherein the processor is configured to execute the control method according to any one of claims 1 to 9 based on instructions stored in the memory.

12. A vehicle comprising: The control device according to claim 10 or 11; The visual perception device includes at least one transmitting device for transmitting an optical signal to the track where the vehicle is located.

13. The vehicle according to claim 12, wherein: The visual perception device further comprises an image acquisition device for acquiring at least one projection image of the optical signal on the edge of the track where the vehicle is located.

14. A computer storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the control method according to any one of claims 1 to 9 is implemented.

15. A computer program product comprising instructions, which, when executed by a processor, cause the processor to perform the control method according to any one of claims 1 to 9.

Images