A method of collision risk warning for an articulated engineering machine and related apparatus

Abstract

The application discloses a collision risk early warning method and related equipment of an articulated engineering machine, and the method comprises the following steps: acquiring a collected original image; acquiring an articulated steering angle of the articulated engineering machine; identifying an obstacle in the original image and determining a pixel coordinate of the obstacle; mapping the pixel coordinate of the obstacle into a physical coordinate of the obstacle in a physical coordinate system; constructing an occupied area of the articulated engineering machine based on the articulated steering angle; calculating a static collision time between the obstacle and the occupied area according to the physical coordinate of the obstacle; calculating a dynamic collision time between the obstacle and a future motion sweeping path area of the articulated engineering machine according to the physical coordinate of the obstacle; determining a minimum comprehensive collision time according to the static collision time and the dynamic collision time, and performing collision risk early warning according to the minimum comprehensive collision time. The application can reduce false positives and false negatives of collision early warning, and can avoid early warning lag, and can be widely applied to the technical field of collision early warning.

Description

Technical Field

[0001] This application relates to the field of collision warning technology, and in particular to a collision risk warning method and related equipment for articulated engineering machinery. Background Technology

[0002] Articulated construction machinery (such as articulated dump trucks, loaders, and articulated trucks) is widely used in complex working environments such as mines and construction sites due to its small turning radius and high maneuverability. However, the front and rear bodies of these machines are connected by an articulation point, and when turning, the front and rear bodies form an angle. This causes the area occupied by the entire vehicle to change in real time with the turning angle, and at the same time, the driver's field of vision is limited, making collision accidents highly likely. Therefore, providing accurate and real-time collision risk warnings for articulated construction machinery is particularly important.

[0003] However, existing collision risk warning methods for articulated construction machinery still have the following shortcomings: On the one hand, most collision avoidance algorithms simplify the working vehicle into a point mass, sphere, or fixed rectangular bounding box for collision estimation, ignoring the characteristic that the physical space envelope occupied by the articulated machinery will significantly deform with the articulated steering angle when turning, which leads to problems such as false alarms and missed alarms in collision warnings; on the other hand, the risk assessment mechanism of existing methods is relatively simple, such as relying solely on distance sensors to determine the current gap between the vehicle body and obstacles. This static model cannot identify potential danger points located on the future sweep path of the vehicle, resulting in a lag in warnings. Summary of the Invention

[0004] The main objective of this application is to propose a collision risk warning method and related equipment for articulated engineering machinery, which can accurately describe the complex geometric dynamic occupancy of articulated machinery, thereby reducing false alarms and missed alarms in collision warning; at the same time, it takes into account the instantaneous gap risk of the current vehicle body and the sweeping conflict risk on the future movement trajectory, and can avoid warning lag.

[0005] To achieve the above objectives, one aspect of this application proposes a collision risk warning method for articulated engineering machinery, including: Acquire raw images from cameras mounted on articulated construction machinery; Obtain the articulated steering angle of the articulated engineering machinery; Identify obstacles in the original image and determine the pixel coordinates of the obstacles; Map the pixel coordinates of the obstacle to the physical coordinates of the obstacle in the physical coordinate system; The area occupied by the articulated engineering machinery is constructed based on the articulated steering angle; Calculate the static collision time between the obstacle and the occupied area based on the physical coordinates of the obstacle; The dynamic collision time between the obstacle and the area swept by the articulated engineering machinery in the future movement is calculated based on the physical coordinates of the obstacle. The minimum comprehensive collision time is determined based on the static collision time and the dynamic collision time, and a collision risk warning is issued based on the minimum comprehensive collision time.

[0006] In some embodiments, mapping the pixel coordinates of the obstacle to the physical coordinates of the obstacle in the physical coordinate system includes: Obtain the preset ground plane constraints; The homography matrix is ​​calculated based on the camera's intrinsic and extrinsic parameters and the preset ground plane constraints. Based on the homography matrix, the pixel coordinates of the obstacle are mapped to the physical coordinates of the obstacle in the physical coordinate system.

[0007] In some embodiments, constructing the occupied area of ​​the articulated engineering machinery based on the articulated steering angle includes: Obtain the length from the hinge center to the end of the front body of the machine, the width of the front body of the machine, and the length from the hinge center to the end of the rear body of the machine, and the width of the rear body of the machine. Based on the length from the hinge center to the end of the front body of the machine and the width of the front body of the machine, the fixed rectangular envelope area of ​​the front body of the machine is determined. The dynamic rectangular envelope region of the rear body of the machine is determined based on the length from the hinge center to the end of the rear body of the machine, the width of the rear body of the machine, and the hinge turning angle. The fixed rectangular envelope area of ​​the front body of the machine and the dynamic rectangular envelope area of ​​the rear body of the machine are combined to construct the occupied area of ​​the articulated engineering machinery.

[0008] In some embodiments, calculating the static collision time between the obstacle and the occupied area based on the physical coordinates of the obstacle includes: Obtain the preset nominal relative velocity; Calculate the minimum geometric Euclidean distance between the physical coordinates of the obstacle and the boundary of the occupied area; The static collision time is calculated based on the minimum geometric Euclidean distance and the preset nominal relative velocity.

[0009] In some embodiments, calculating the dynamic collision time between the obstacle and the area swept by the articulated engineering machinery in the future movement path based on the physical coordinates of the obstacle includes: Obtain the current forward linear velocity of the articulated engineering machinery; Calculate the physical coordinates of the obstacle and the path arc length distance corresponding to the first collision on the future predicted trajectory of the articulated engineering machinery; The dynamic collision time is calculated based on the path arc length and the current forward linear velocity.

[0010] In some embodiments, determining the minimum combined collision time based on the static collision time and the dynamic collision time includes: Compare the static collision time and dynamic collision time of each obstacle, and select the minimum value as the individual comprehensive collision time of each obstacle; Obtain the individual comprehensive collision time of all identified obstacles, and select the minimum value from the individual comprehensive collision times of all identified obstacles as the minimum comprehensive collision time.

[0011] In some embodiments, the collision risk warning based on the minimum comprehensive collision time includes: If the minimum combined collision time is greater than the deceleration warning threshold, the articulated engineering machinery shall continue to operate normally. A deceleration warning is issued when the minimum combined collision time is greater than the emergency braking threshold and less than or equal to the deceleration warning threshold. An emergency braking warning is issued when the minimum combined collision time is less than or equal to the emergency braking threshold.

[0012] To achieve the above objectives, another aspect of this application provides a collision risk warning device for articulated engineering machinery, the device comprising: The image acquisition module is used to acquire raw images captured by a camera mounted on an articulated engineering machine; A steering angle acquisition module is used to acquire the articulated steering angle of the articulated engineering machinery; A pixel coordinate determination module is used to identify obstacles in the original image and determine the pixel coordinates of the obstacles; A pixel coordinate mapping module is used to map the pixel coordinates of the obstacle to the physical coordinates of the obstacle in the physical coordinate system. An occupation area construction module is used to construct the occupation area of ​​the articulated engineering machinery based on the articulated steering angle. The static collision time calculation module is used to calculate the static collision time between the obstacle and the occupied area based on the physical coordinates of the obstacle. The dynamic collision time calculation module is used to calculate the dynamic collision time between the obstacle and the area swept by the articulated engineering machinery in the future movement based on the physical coordinates of the obstacle. The risk warning module is used to determine the minimum comprehensive collision time based on the static collision time and the dynamic collision time, and to issue a collision risk warning based on the minimum comprehensive collision time.

[0013] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method described above.

[0014] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods described above.

[0015] This application also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium and execute the computer instructions, causing the computer device to perform the aforementioned method.

[0016] The embodiments of this application include at least the following beneficial effects: This application provides a collision risk warning method for articulated construction machinery. The method first acquires original images captured by a camera mounted on the articulated construction machinery; acquires the articulated steering angle of the articulated construction machinery; identifies obstacles in the original images and determines the pixel coordinates of the obstacles; maps the pixel coordinates of the obstacles to the physical coordinates of the obstacles in the physical coordinate system; constructs the occupied area of ​​the articulated construction machinery based on the articulated steering angle; calculates the static collision time between the obstacles and the occupied area based on the physical coordinates of the obstacles; calculates the dynamic collision time between the obstacles and the future sweep path area of ​​the articulated construction machinery based on the physical coordinates of the obstacles; determines the minimum comprehensive collision time based on the static and dynamic collision times; and performs a collision risk warning based on the minimum comprehensive collision time. This application constructs the occupied area of ​​articulated engineering machinery based on the articulated steering angle, enabling the machinery's occupied area to dynamically adjust in real time with the articulated steering angle. This accurately describes the complex geometric dynamic occupancy of the articulated machinery, thereby reducing false alarms and missed alarms in collision warnings. At the same time, by calculating the static collision time between the obstacle and the currently occupied area of ​​the vehicle, and the dynamic collision time between the obstacle and the area swept by the vehicle's future movement path, and determining the comprehensive collision time by taking the minimum value for warning, this application takes into account both the instantaneous gap risk of the current vehicle body and the sweeping conflict risk on the future movement trajectory, thus avoiding warning lag. Attached Figure Description

[0017] Figure 1This is a schematic diagram of an implementation environment provided in an embodiment of this application; Figure 2 This is a flowchart of a collision risk warning method for articulated engineering machinery provided in an embodiment of this application; Figure 3 This is a schematic diagram of geometric occupancy modeling provided in an embodiment of this application; Figure 4 This is a schematic diagram illustrating the prediction of the collision risk of obstacles on the future movement path provided by an embodiment of this application; Figure 5 This is a visualization of the geometrically sensed dual risk field around the articulated rollers during a turning operation, as provided in an embodiment of this application. Figure 6 This is a schematic diagram of the collision risk warning architecture provided in an embodiment of this application; Figure 7 This is a system topology diagram provided in the embodiments of this application; Figure 8 This is a schematic diagram of the structure of a collision risk warning device for articulated engineering machinery provided in an embodiment of this application; Figure 9 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0019] It is understood that the terms "first," "second," "third," "fourth," etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0020] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0022] Existing collision risk warning methods for articulated construction machinery still have the following shortcomings: On the one hand, most collision avoidance algorithms simplify the working vehicle into a point mass, sphere, or fixed rectangular bounding box for collision estimation, ignoring the characteristic that the physical space envelope occupied by the vehicle body will significantly deform with the articulated steering angle when the machinery is turning, thus leading to problems such as false alarms and missed alarms in collision warnings; on the other hand, the risk assessment mechanism of existing methods is relatively simple, such as relying solely on distance sensors to determine the current gap between the vehicle body and obstacles. This static model cannot identify potential danger points located on the future sweep path of the vehicle, resulting in delayed warnings.

[0023] In view of this, this application provides a collision risk warning method and related equipment for articulated construction machinery. The method first acquires raw images captured by a camera mounted on the articulated construction machinery; acquires the articulated steering angle of the articulated construction machinery; identifies obstacles in the raw images and determines the pixel coordinates of the obstacles; maps the pixel coordinates of the obstacles to the physical coordinates of the obstacles in the physical coordinate system; constructs the occupied area of ​​the articulated construction machinery based on the articulated steering angle; calculates the static collision time between the obstacle and the occupied area based on the physical coordinates of the obstacle; calculates the dynamic collision time between the obstacle and the future sweep path area of ​​the articulated construction machinery based on the physical coordinates of the obstacle; determines the minimum comprehensive collision time based on the static and dynamic collision times, and performs a collision risk warning based on the minimum comprehensive collision time. This application constructs the occupied area of ​​articulated engineering machinery based on the articulated steering angle, enabling the machinery's occupied area to dynamically adjust in real time with the articulated steering angle. This accurately describes the complex geometric dynamic occupancy of the articulated machinery, thereby reducing false alarms and missed alarms in collision warnings. At the same time, by calculating the static collision time between the obstacle and the currently occupied area of ​​the vehicle, and the dynamic collision time between the obstacle and the area swept by the vehicle's future movement path, and determining the comprehensive collision time by taking the minimum value for warning, this application takes into account both the instantaneous gap risk of the current vehicle body and the sweeping conflict risk on the future movement trajectory, thus avoiding warning lag. The collision risk warning method for articulated construction machinery provided in this application relates to the field of collision warning technology. This collision risk warning method for articulated construction machinery can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or vehicle terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application implementing the collision risk warning method for articulated construction machinery, but is not limited to the above forms.

[0024] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0025] like Figure 1 The diagram shown is a schematic representation of an implementation environment provided in an embodiment of this application. (Refer to...) Figure 1 The implementation environment includes at least one terminal 102 and a server 101. The terminal 102 and the server 101 can be connected via a network, either wirelessly or via a wired connection, to complete data transmission and exchange.

[0026] Server 101 can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0027] Additionally, server 101 can also be a node server in a blockchain network. Blockchain is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms.

[0028] Terminal 102 can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, etc. It can also be a vehicle-mounted terminal of the various device types described above, but is not limited to these. Terminal 102 and server 101 can be directly or indirectly connected via wired or wireless communication, and this embodiment does not impose any limitations.

[0029] For example, based on Figure 1The implementation environment shown in this application embodiment provides a collision risk warning method for articulated construction machinery. The following description uses the application of this collision risk warning method for articulated construction machinery in server 101 as an example. It can be understood that this method can also be applied to terminal 102.

[0030] Reference Figure 2 , Figure 2 This is a flowchart illustrating a collision risk warning method for articulated engineering machinery applied to a server, provided as an embodiment of this application. The executing entity of this method can be any of the aforementioned computer devices (including a server or a terminal). (Refer to...) Figure 2 The method may include the following steps: S100: Acquire raw images captured by a camera mounted on an articulated construction machine.

[0031] In this embodiment, a fisheye camera with a field of view of 170° is installed at the front, rear, left, and right sides of an articulated construction machine (such as an articulated dump truck, loader, or articulated truck). These fisheye cameras together constitute full perimeter visual perception coverage; and the original images of the surrounding environment of the articulated construction machine are acquired through the fisheye cameras.

[0032] S200. Obtain the articulation steering angle of the articulated engineering machinery.

[0033] This application embodiment uses a CAN bus to access the speed sensor and steering angle sensor of the articulated engineering machinery in real time to obtain the instantaneous kinematic state of the machinery; wherein, the instantaneous kinematic state includes the vehicle's forward linear velocity. The real-time steering angle (i.e., the articulated steering angle δ), the forebody orientation angle θ, and the instantaneous center of rotation determined by the steering geometry.

[0034] S300: Identify obstacles in the original image and determine the pixel coordinates of the obstacles.

[0035] For example, embodiments of this application employ a lightweight YOLO series network optimized for edge computing for target detection and localization to identify obstacles, the steps of which include: In this application embodiment, a lightweight YOLO series network (such as YOLOv11s) is selected as the detection backbone, and the network is accelerated by operator fusion and quantization using inference frameworks such as TensorRT, so that the system can process four fisheye camera images in real time at a frame rate of 15-30 FPS, and the average perception latency is controlled within about 32.5ms. Secondly, distortion correction is performed on the original images acquired based on the intrinsic parameters and distortion coefficients of the fisheye camera to obtain geometrically consistent corrected images. These geometrically consistent corrected images are then input into a lightweight YOLO network to identify obstacles such as people, vehicles, and cones in the image in parallel, and output the two-dimensional bounding box and category label of each obstacle. Finally, in this embodiment, the bottom center point of each two-dimensional bounding box is extracted, and the pixel coordinates of the bottom center point are used as the ground point pixel coordinates of the obstacle. The logical basis is that in the subsequent inverse perspective mapping process, the bottom center point represents the actual contact point between the obstacle and the ground, which is the most accurate reference for calculating its real coordinates in the physical world.

[0036] S400: Map the pixel coordinates of the obstacle to the physical coordinates of the obstacle in the physical coordinate system.

[0037] In this embodiment, inverse perspective mapping technology is used to convert the pixel coordinates of obstacles into physical coordinates in a bird's-eye view (BEV) physical coordinate system with the center of the articulated engineering machinery as the origin, so as to facilitate subsequent collision time calculation. Exemplarily, the step of mapping the pixel coordinates of obstacles to the physical coordinates of obstacles in the physical coordinate system includes S410-S430: S410, Obtain the preset ground plane constraints; This application embodiment assumes that the observation environment is an approximately flat plane and presets ground plane constraints. Specifically, based on the assumption that the observation environment is an approximately flat plane, combined with the camera kinematic model and installation height, the three-dimensional (3D) spatial transformation can be simplified to a mapping between two-dimensional (2D) planes.

[0038] S420. Calculate the homography matrix based on the camera's intrinsic and extrinsic parameters and the preset ground plane constraints; The intrinsic parameters include camera internal parameters such as focal length and principal point coordinates; the extrinsic parameters include extrinsic rotation matrix and translation vector. The extrinsic parameters can be determined using radar-camera calibration or joint optimization algorithms to establish the rigid body transformation relationship from the camera coordinate system to the vehicle center BEV physical coordinate system.

[0039] Furthermore, the homography matrix can be derived based on the ground plane constraints and rigid body transformation relationships.

[0040] S430. Based on the homography matrix, map the pixel coordinates of the obstacle to the physical coordinates of the obstacle in the physical coordinate system.

[0041] For example, after obtaining the homography matrix, the pixel coordinates of the obstacle are mapped to the physical coordinates of the obstacle in the physical coordinate system based on the homography matrix. The formula is as follows:

[0042] Where (u,v) are the image pixel coordinates, (X) bev ,Y bev () represents the physical coordinates of the BEV. H The 3x3 homography matrix is ​​derived for camera intrinsic and extrinsic parameters and ground plane constraints. λ This is the scale factor in the projection transformation process.

[0043] This application utilizes four fisheye cameras to achieve 360° blind-spot-free coverage, unifies multi-view features to the BEV coordinate system through inverse perspective mapping technology, and the algorithm can run efficiently on embedded edge devices with low processing latency.

[0044] S500. Construct the occupied area of ​​the articulated engineering machinery based on the articulated steering angle.

[0045] Figure 3 This is a schematic diagram of geometric occupancy modeling provided in an embodiment of this application, such as... Figure 3 As shown, the machine is abstracted as two rigid rectangles connected by a hinge point, that is, the fixed rectangular envelope area of ​​the front fuselage of the machine. (Front Body) ) and the dynamic rectangular envelope region of the rear fuselage (Rear Body) ), of which the fixed rectangular envelope area of ​​the front fuselage The dynamic rectangular envelope region of the rear fuselage of the machine remains fixed in its local coordinate system. Spatial position and attitude change with real-time steering angle and articulated steering angle δ The fixed rectangular envelope area of ​​the front fuselage of the machine is dynamically adjusted according to changes. By combining the dynamic rectangular envelope region of the rear fuselage of the machine with that of the articulated construction machinery, the occupied area of ​​the articulated machinery can be obtained. Figure 3 The black dots in the diagram represent articulation joints.

[0046] In addition, for large single-unit machinery (such as excavators), collision risk calculations can be performed by adjusting geometric parameters to degenerate the "double rectangle" into a "single rectangle" or "multi-disc" model.

[0047] For example, the steps of constructing the occupied area of ​​the articulated construction machinery based on the articulated steering angle include S510-S540: S510, obtain the length from the hinge center to the end of the front body of the machine, the width of the front body of the machine, and the length from the hinge center to the end of the rear body of the machine, and the width of the rear body of the machine. S520. Determine the fixed rectangular envelope area of ​​the front body of the machine based on the length from the hinge center to the end of the front body of the machine and the width of the front body of the machine. Specifically, since the front fuselage does not rotate relative to the hinge angle, the position and orientation of the rectangular envelope region in the physical coordinate system remain fixed.

[0048] S530. Determine the dynamic rectangular envelope area of ​​the rear body of the machine based on the length from the hinge center to the end of the rear body of the machine, the width of the rear body of the machine, and the hinge turning angle. Specifically, the position and orientation of the dynamic rectangular envelope area are dynamically adjusted as the articulated steering angle changes, which can accurately reflect the changes in the space occupied by the rear body of the articulated machine when it turns.

[0049] S540: Perform a union operation on the fixed rectangular envelope area of ​​the front body of the machine and the dynamic rectangular envelope area of ​​the rear body of the machine to construct the occupied area of ​​the articulated engineering machinery.

[0050] Specifically, the fixed rectangular envelope region of the front fuselage and the dynamic rectangular envelope region of the rear fuselage are combined to obtain the overall space occupied by the articulated engineering machinery at the current articulated steering angle. V ( δ Its expression is: V ( δ )= ∪ The occupied area can accurately depict the true physical contours of articulated machinery in straight-line travel and turning at different angles.

[0051] This application embodiment abstracts the articulated mechanism as two rigid rectangles connected by the hinge point. By reading the steering angle data in real time, it dynamically adjusts the vehicle's positioning profile in the BEV space, which can accurately capture space intrusion during steering.

[0052] S600. Calculate the static collision time between the obstacle and the occupied area based on the physical coordinates of the obstacle.

[0053] In this embodiment, the static collision time is used to assess the instantaneous gap risk between the obstacle and the physical contour of the current articulated engineering machinery.

[0054] For example, the step of calculating the static collision time between the obstacle and the occupied area based on the physical coordinates of the obstacle includes S610-S630: S610, Obtain the preset nominal relative speed; Among them, the preset nominal relative speed (such as the typical walking speed of a pedestrian) is used to assess the degree of danger of a static object or pedestrian approaching.

[0055] S620. Calculate the minimum geometric Euclidean distance between the physical coordinates of the obstacle and the boundary of the occupied area; S630. Calculate the static collision time based on the minimum geometric Euclidean distance and the preset nominal relative velocity. Its expression is:

[0056] in, Obstacle points p To the area currently occupied by articulated construction machinery V ( δ The minimum geometric Euclidean distance of the boundary. This is the preset nominal relative velocity.

[0057] S700. Calculate the dynamic collision time between the obstacle and the area swept by the articulated engineering machinery in the future movement based on the physical coordinates of the obstacle.

[0058] Among them, dynamic collision time is used to predict the risk of collision with obstacles on their future movement paths. Figure 4 This is a schematic diagram illustrating the prediction of the collision risk of obstacles on future movement paths, as provided in the embodiments of this application. Figure 4 As shown, the instantaneous center of rotation (ICR) is determined based on the real-time articulated steering angle. Under the influence of the instantaneous turning radius, the machine is considered to be moving in an arc around the ICR, generating a swept path (Swept Path) swept out by the front and rear bodies of the articulated engineering machinery to find the expected collision point between the obstacle and the edge of this swept path. Figure 4 Front-body heading The orientation angle of the front fuselage is set to 0° in this embodiment and can be used as a reference direction. ) are the coordinates of the reference point of the front fuselage (e.g., the center of the front axle or the geometric center). Figure 4 In This indicates the physical distance from the hinge center to the front axle. Figure 4 In It represents the physical distance from the hinge center to the rear axle, used to accurately determine the vehicle's positional profile in the bird's-eye view (BEV) coordinate system.

[0059] For example, the step of calculating the dynamic collision time between the obstacle and the area swept by the articulated engineering machinery in the future movement path based on the physical coordinates of the obstacle includes S710-S730: S710. Obtain the current forward linear velocity of the articulated engineering machinery; S720. Calculate the physical coordinates of the obstacle and the path arc length distance corresponding to the first collision on the future predicted trajectory of the articulated engineering machinery. S730. Calculate the dynamic collision time based on the path arc length and the current forward linear velocity. Its expression is:

[0060] in, This refers to the arc length of the obstacle path at the time of the first collision on the predicted future trajectory of the articulated engineering machinery. This represents the forward linear velocity.

[0061] S800. Determine the minimum comprehensive collision time based on the static collision time and the dynamic collision time, and issue a collision risk warning based on the minimum comprehensive collision time.

[0062] This application integrates static collision time and dynamic collision time to determine the global minimum comprehensive collision time, and implements a graded intervention and early warning strategy accordingly.

[0063] For example, the step of determining the minimum combined collision time based on the static collision time and the dynamic collision time includes S810-S820: S810. Compare the static collision time and dynamic collision time of each obstacle, and select the minimum value as the individual comprehensive collision time of each obstacle. S820. Obtain the individual comprehensive collision time of all identified obstacles, and select the minimum value from the individual comprehensive collision times of all identified obstacles as the minimum comprehensive collision time.

[0064] Specifically, for each obstacle identified within the perception range The corresponding static collision time is compared with the dynamic collision time, and the smaller value is taken as the individual comprehensive collision time of the obstacle. The minimum value among the individual comprehensive collision times of all identified obstacles is selected as the global minimum comprehensive collision time. Its expression is:

[0065] The global minimum combined collision time The most urgent and minimum collision time for all obstacles in the system at the current moment is the basis for decision-making to trigger subsequent graded intervention and early warning.

[0066] Furthermore, to intuitively demonstrate the characteristics of the dual-collision time-integrated risk field in the embodiments of this application, Figure 5 A visualization of the risk field based on the time of two collisions is shown for articulated engineering machinery during turning operations. Figure 5 (a) is the risk field of static collision time (Static TTC), which is calculated from the static collision time. Its risk distribution closely follows the outline of the occupied area formed by the union of the fixed rectangular envelope area of ​​the front fuselage and the dynamic rectangular envelope area of ​​the rear fuselage of the machine. It has extremely high sensitivity to obstacles close to the machine boundary (such as people avoiding the side) and can effectively capture the instantaneous vehicle body closeness risk. Figure 5 (b) is the Dynamic Time Collision Risk Field (Dynamic TTC), which is calculated from the dynamic collision time. Its risk area mainly extends along the steering sweep path predicted by the vehicle based on the current articulated steering angle and forward linear velocity. It is highly sensitive to the collision point located on the future sweep path and can provide early warning before the obstacle approaches the current vehicle body outline. Figure 5 (c) represents the fused dual-TTC risk field, which is generated by fusing the minimum values ​​of the static and dynamic collision times and serves as the basis for the system's final early warning decision. This fused risk field fully covers instantaneous gap risks and future path conflicts, avoiding the omission of risks in the turning sweep area by a single static field and the neglect of lateral approach risks by a single dynamic field. It introduces a feature that allows the system to issue early warnings based on the future sweep path of an obstacle before it even contacts the current contour of the machine. It also overcomes the frequent false alarms caused by using an overly conservative fixed expanded envelope, thus ensuring that in complex dynamic construction environments, the system can make graded intervention decisions that are both safe and not overly conservative.

[0067] Furthermore, the steps for collision risk warning based on the minimum combined collision time include S830-S850: S810. If the minimum comprehensive collision time is greater than the deceleration warning threshold, maintain the normal operation of the articulated engineering machinery. Specifically, TTC min > To maintain the normal operation of articulated construction machinery. Among them, TTC min To minimize the overall collision time, This is the deceleration warning threshold.

[0068] S820. If the minimum comprehensive collision time is greater than the emergency braking threshold and less than or equal to the deceleration warning threshold, a deceleration warning is issued. Specifically, when <TTC min ≤ When a deceleration warning is issued, the system forces the vehicle to slow down; among other things, This is the emergency braking threshold (stop threshold).

[0069] S830. If the minimum comprehensive collision time is less than or equal to the emergency braking threshold, an emergency braking warning is issued.

[0070] Specifically, when TTC min ≤ Upon receiving an emergency braking warning, the system immediately issues an emergency braking command.

[0071] This application embodiment takes into account the inherent physical delays in the processes from sensor image acquisition, deep learning model inference, system communication to hydraulic braking system response, and introduces a time delay compensation mechanism to ensure that the safety margin conforms to physical reality. Specifically, the total system response delay time is preset. (Including sensing, inference, communication, and actuator response times), to obtain the global minimum combined collision time. Then, subtract the total system response delay time from it. To obtain the effective collision time ,Right now: ; Effective collision time It represents the actual reaction time left for the mechanical actuators and operators from the moment the system issues a control command until the collision occurs.

[0072] This application embodiment assesses the instantaneous gap between the obstacle and the current mechanical vehicle body outline (i.e., static collision time) and predicts the collision risk of the obstacle on the vehicle's future sweep path, i.e., dynamic collision time. By taking the minimum value to determine the comprehensive collision time for early warning, the advance amount and robustness of the early warning are greatly improved.

[0073] To explain in detail the principles of the technical solution of this application, the overall process of this application will be described below with reference to some specific embodiments. It is easy to understand that the following is an explanation of the technical principles of this application and should not be regarded as a limitation of this application.

[0074] Figure 6 This is a schematic diagram of the collision risk warning architecture provided in the embodiments of this application, as shown below. Figure 6As shown, in a specific embodiment, the collision risk warning process for the articulated engineering machinery of this application includes the following steps: S1, Multi-source sensing layout: Install a 170° fisheye camera at the front, rear, left, and right of the articulated construction machinery (such as articulated dump trucks, loaders, or articulated trucks) to achieve full perimeter coverage; and use the fisheye cameras to capture raw images of the surrounding environment of the articulated construction machinery.

[0075] S2. Obtain the instantaneous kinematic state: This application embodiment uses a CAN bus to access the speed sensor and steering angle sensor of the articulated engineering machinery in real time to obtain the instantaneous kinematic state of the machinery; wherein, the instantaneous kinematic state includes the vehicle's forward linear velocity. The real-time steering angle (i.e., the articulated steering angle δ), the forebody orientation angle θ, and the instantaneous center of rotation determined by the steering geometry.

[0076] Furthermore, such as Figure 7 The system topology diagram provided for the embodiments of this application is as follows: Figure 7 As shown, the raw image data acquired by the fisheye camera enters the computing core (such as Jetson Orin Nano) via the GMSL interface, and the processed control commands are sent to the chassis execution MCU of the articulated engineering machinery via the CAN bus.

[0077] S3, Obstacle Detection: In this application embodiment, a lightweight YOLO series network (such as YOLOv11s) can be used to detect obstacles in the original image. Other real-time detection algorithms such as SSD and MobileNet can also be used for obstacle detection.

[0078] S4. Determine the physical coordinates of the obstacle: The reverse perspective mapping technique is used to convert the pixel coordinates of obstacles from each camera viewpoint into physical coordinates in the bird's-eye view (BEV) physical coordinate system with the center of the articulated engineering machinery as the origin.

[0079] S5. Geometrically Perceived Dual Risk Field (TTC) Modeling: First, a fixed rectangular envelope region of the front body of the machine is constructed based on the length from the articulation center to the end of the front body and the width of the front body. Then, a dynamic rectangular envelope region of the rear body of the machine is constructed based on the length from the articulation center to the end of the rear body, the width of the rear body, and the articulation turning angle. Finally, the fixed rectangular envelope region of the front body and the dynamic rectangular envelope region of the rear body are combined to obtain the occupied area of ​​the articulated engineering machinery.

[0080] Secondly, the static collision time between the obstacle and the occupied area is calculated based on the obstacle's physical coordinates. It is used to assess the instantaneous gap risk between obstacles and the current physical contours of articulated construction machinery; and to calculate the dynamic collision time between the obstacle and the area swept by the articulated construction machinery in the future movement based on the obstacle's physical coordinates. Furthermore, for each obstacle identified within the perception range... The corresponding static collision time is compared with the dynamic collision time, and the smaller value between the two is taken as the individual comprehensive collision time of the obstacle. The minimum value among the individual comprehensive collision times of all identified obstacles is selected as the global minimum comprehensive collision time.

[0081] S6. Risk warning and control strategy: Specifically, TTC min > To maintain the normal operation of articulated construction machinery. Among them, TTC min To minimize the overall collision time, This is the deceleration warning threshold. When <TTC min ≤ When a deceleration warning is issued, the system forces the vehicle to slow down; among other things, This is the emergency braking threshold (stop threshold); when TTC min ≤ Upon receiving an emergency braking warning, the system immediately issues an emergency braking command.

[0082] This application embodiment takes into account the inherent physical delays in the processes from sensor image acquisition, deep learning model inference, system communication to hydraulic braking system response, and introduces a time delay compensation mechanism to ensure that the safety margin conforms to physical reality. Specifically, the total system response delay time is preset. (Including sensing, inference, communication, and actuator response times), to obtain the global minimum combined collision time. Then, subtract the total system response delay time from it. To obtain the effective collision time ,Right now: ; Effective collision time It represents the actual reaction time left for the mechanical actuators and operators from the moment the system issues a control command until the collision occurs.

[0083] In summary, this application provides a collision risk warning method and related equipment for articulated construction machinery. The method first acquires raw images from a camera mounted on the articulated construction machinery; then acquires the articulated steering angle of the machinery; identifies obstacles in the raw images and determines their pixel coordinates; maps the pixel coordinates of the obstacles to their physical coordinates in a physical coordinate system; constructs the occupied area of ​​the articulated construction machinery based on the articulated steering angle; calculates the static collision time between the obstacle and the occupied area based on the obstacle's physical coordinates; calculates the dynamic collision time between the obstacle and the future sweep path area of ​​the articulated construction machinery based on the obstacle's physical coordinates; determines the minimum comprehensive collision time based on the static and dynamic collision times, and provides a collision risk warning based on the minimum comprehensive collision time. This application constructs the occupied area of ​​articulated engineering machinery based on the articulated steering angle, enabling the machinery's occupied area to dynamically adjust in real time with the articulated steering angle. This accurately describes the complex geometric dynamic occupancy of the articulated machinery, thereby reducing false alarms and missed alarms in collision warnings. At the same time, by calculating the static collision time between the obstacle and the currently occupied area of ​​the vehicle, and the dynamic collision time between the obstacle and the area swept by the vehicle's future movement path, and determining the comprehensive collision time by taking the minimum value for warning, this application takes into account both the instantaneous gap risk of the current vehicle body and the sweeping conflict risk on the future movement trajectory, thus avoiding warning lag.

[0084] like Figure 8 As shown in the figure, this application embodiment also provides a structural schematic diagram of a collision risk warning device for articulated engineering machinery. This device can implement the above-mentioned method and may include: Image acquisition module 21 is used to acquire raw images captured by a camera mounted on an articulated engineering machine; Steering angle acquisition module 22 is used to acquire the articulated steering angle of the articulated engineering machinery; The pixel coordinate determination module 23 is used to identify obstacles in the original image and determine the pixel coordinates of the obstacles; The pixel coordinate mapping module 24 is used to map the pixel coordinates of the obstacle to the physical coordinates of the obstacle in the physical coordinate system. Occupancy area construction module 25 is used to construct the occupancy area of ​​the articulated engineering machinery based on the articulated steering angle; The static collision time calculation module 26 is used to calculate the static collision time between the obstacle and the occupied area based on the physical coordinates of the obstacle. The dynamic collision time calculation module 27 is used to calculate the dynamic collision time between the obstacle and the area swept by the articulated engineering machinery in the future movement based on the physical coordinates of the obstacle. The risk warning module 28 is used to determine the minimum comprehensive collision time based on the static collision time and the dynamic collision time, and to issue a collision risk warning based on the minimum comprehensive collision time.

[0085] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0086] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the aforementioned collision risk warning method for articulated engineering machinery. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0087] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0088] Please see Figure 9 , Figure 9 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 901 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 902 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 902 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902 and is called and executed by the processor 901 to execute the collision risk warning method for articulated engineering machinery according to the embodiments of this application. The input / output interface 903 is used to implement information input and output; The communication interface 904 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 905 transmits information between various components of the device (e.g., processor 901, memory 902, input / output interface 903, and communication interface 904); The processor 901, memory 902, input / output interface 903, and communication interface 904 are connected to each other within the device via bus 905.

[0089] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described collision risk warning method for articulated engineering machinery.

[0090] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0091] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0092] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0093] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0094] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0095] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0096] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0097] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0098] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0099] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks. The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A collision risk early warning method for articulated engineering machinery, characterized in that, include: Acquire raw images from cameras mounted on articulated construction machinery; Obtain the articulated steering angle of the articulated engineering machinery; Identify obstacles in the original image and determine the pixel coordinates of the obstacles; Map the pixel coordinates of the obstacle to the physical coordinates of the obstacle in the physical coordinate system; The area occupied by the articulated engineering machinery is constructed based on the articulated steering angle; Calculate the static collision time between the obstacle and the occupied area based on the physical coordinates of the obstacle; The dynamic collision time between the obstacle and the area swept by the articulated engineering machinery in the future motion is calculated based on the physical coordinates of the obstacle. The minimum comprehensive collision time is determined based on the static collision time and the dynamic collision time, and a collision risk warning is issued based on the minimum comprehensive collision time.

2. The collision risk warning method for articulated engineering machinery according to claim 1, characterized in that, The step of mapping the pixel coordinates of the obstacle to the physical coordinates of the obstacle in the physical coordinate system includes: Obtain the preset ground plane constraints; The homography matrix is ​​calculated based on the camera's intrinsic and extrinsic parameters and the preset ground plane constraints. Based on the homography matrix, the pixel coordinates of the obstacle are mapped to the physical coordinates of the obstacle in the physical coordinate system.

3. The collision risk warning method for articulated engineering machinery according to claim 1, characterized in that, The area occupied by the articulated engineering machinery, constructed based on the articulated steering angle, includes: Obtain the length from the hinge center to the end of the front body of the machine, the width of the front body of the machine, and the length from the hinge center to the end of the rear body of the machine, and the width of the rear body of the machine. Based on the length from the hinge center to the end of the front body of the machine and the width of the front body of the machine, the fixed rectangular envelope area of ​​the front body of the machine is determined. The dynamic rectangular envelope region of the rear body of the machine is determined based on the length from the hinge center to the end of the rear body of the machine, the width of the rear body of the machine, and the hinge turning angle. The fixed rectangular envelope area of ​​the front body of the machine and the dynamic rectangular envelope area of ​​the rear body of the machine are combined to construct the occupied area of ​​the articulated engineering machinery.

4. The collision risk warning method for articulated engineering machinery according to claim 1, characterized in that, The step of calculating the static collision time between the obstacle and the occupied area based on the physical coordinates of the obstacle includes: Obtain the preset nominal relative velocity; Calculate the minimum geometric Euclidean distance between the physical coordinates of the obstacle and the boundary of the occupied area; The static collision time is calculated based on the minimum geometric Euclidean distance and the preset nominal relative velocity.

5. The collision risk warning method for articulated engineering machinery according to claim 1, characterized in that, The calculation of the dynamic collision time between the obstacle and the area swept by the articulated engineering machinery in the future movement path based on the physical coordinates of the obstacle includes: Obtain the current forward linear velocity of the articulated engineering machinery; Calculate the physical coordinates of the obstacle and the path arc length distance corresponding to the first collision on the future predicted trajectory of the articulated engineering machinery; The dynamic collision time is calculated based on the path arc length and the current forward linear velocity.

6. The collision risk warning method for articulated engineering machinery according to claim 1, characterized in that, Determining the minimum combined collision time based on the static collision time and the dynamic collision time includes: Compare the static collision time and dynamic collision time of each obstacle, and select the minimum value as the individual comprehensive collision time of each obstacle; Obtain the individual comprehensive collision time of all identified obstacles, and select the minimum value from the individual comprehensive collision times of all identified obstacles as the minimum comprehensive collision time.

7. The collision risk warning method for articulated engineering machinery according to claim 1, characterized in that, The collision risk warning based on the minimum comprehensive collision time includes: If the minimum combined collision time is greater than the deceleration warning threshold, the articulated engineering machinery shall continue to operate normally. A deceleration warning is issued when the minimum combined collision time is greater than the emergency braking threshold and less than or equal to the deceleration warning threshold. An emergency braking warning is issued when the minimum combined collision time is less than or equal to the emergency braking threshold.

8. A collision risk warning device for articulated engineering machinery, characterized in that, The device includes: The image acquisition module is used to acquire raw images captured by a camera mounted on articulated engineering machinery; A steering angle acquisition module is used to acquire the articulated steering angle of the articulated engineering machinery; A pixel coordinate determination module is used to identify obstacles in the original image and determine the pixel coordinates of the obstacles; A pixel coordinate mapping module is used to map the pixel coordinates of the obstacle to the physical coordinates of the obstacle in the physical coordinate system. An occupation area construction module is used to construct the occupation area of ​​the articulated engineering machinery based on the articulated steering angle. The static collision time calculation module is used to calculate the static collision time between the obstacle and the occupied area based on the physical coordinates of the obstacle. The dynamic collision time calculation module is used to calculate the dynamic collision time between the obstacle and the area swept by the articulated engineering machinery in the future movement based on the physical coordinates of the obstacle. The risk warning module is used to determine the minimum comprehensive collision time based on the static collision time and the dynamic collision time, and to issue a collision risk warning based on the minimum comprehensive collision time.

9. An electronic device, characterized in that, Including the processor and memory; The memory is used to store programs; The processor executes the program to implement the collision risk warning method for articulated engineering machinery as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the collision risk warning method for articulated engineering machinery as described in any one of claims 1 to 7.

Images