A method and system for autonomous work swing anti-collision of unmanned engineering machinery

Abstract

The application discloses an unmanned engineering machine autonomous operation turning anti-collision method and system, the method comprises the following steps: obtaining the spatial position information of the obstacle edge feature corner point around the engineering machine, and converting the spatial position information into the cylindrical coordinate data under the lower vehicle coordinate system of the engineering machine; determining the left and right limit boundary point cylindrical coordinates according to the cylindrical coordinate data of the obstacle edge feature corner point; based on the left and right limit boundary point cylindrical coordinates, combining the actual physical width of the shovel and the expansion coefficient, calculating the left and right turning boundary safety compensation angle, and calculating the left anti-collision upper limit angle and the right anti-collision lower limit angle to generate a dynamic safety turning area; determining the first safety reference position and the second safety reference position of horizontal avoidance according to the target operation position and the dynamic safety turning area; based on the dynamic safety turning area, the first safety reference position and the second safety reference position, the five-stage cooperative motion planning method is used to control the autonomous operation of the engineering machine.

Description

Technical Field

[0001] This application belongs to the field of intelligent control technology for unmanned construction machinery, specifically relating to a method and system for autonomous operation and collision avoidance of unmanned construction machinery. Background Technology

[0002] The unmanned operation of construction machinery is the core direction of the industry's intelligent transformation. Unmanned construction machinery is widely used in high-risk scenarios such as open-pit mines and earthwork projects. It has a high frequency of slewing operations and a large operating range. The bucket is very easy to collide with the vehicle body, transport vehicles, and site materials. Slewing collision avoidance has become an essential technology for the safety control of unmanned construction machinery.

[0003] In related technologies, slewing collision avoidance solutions have evolved into two generations: early methods relied on defining fixed static restricted areas and using single radar / visual threshold alarms for passive protection; with the maturity of multi-sensor hardware, the industry has gradually evolved towards multi-source perception fusion for active obstacle avoidance. Caterpillar, Komatsu, and domestic construction machinery companies have all equipped their systems with multi-sensor environmental perception systems, attempting to improve collision avoidance reliability through 3D modeling. However, mines and construction sites generally have characteristics such as high dust levels, drastic fluctuations in lighting, and dynamic changes in obstacles. Existing mature solutions struggle to simultaneously achieve all-weather detection stability, dynamic obstacle adaptability, and multi-joint motion adaptability. High-precision, highly adaptable slewing collision avoidance remains a technological bottleneck for the deployment of unmanned construction machinery. Summary of the Invention

[0004] Objective: In view of at least one of the above technical problems, this application provides a method and system for autonomous operation and collision avoidance of unmanned engineering machinery.

[0005] Technical solution: To solve the above-mentioned technical problems, the technical solution adopted in this application is as follows:

[0006] Firstly, a method for autonomous operation and collision avoidance of unmanned engineering machinery is provided, including:

[0007] S1. Obtain the spatial location information of the feature corner points of the obstacles around the construction machinery and convert them into cylindrical coordinate data in the coordinate system of the construction machinery.

[0008] S2. Determine the cylindrical coordinates of the left and right limit boundary points based on the cylindrical coordinate data of the characteristic corner points of the obstacle edge;

[0009] S3. Based on the coordinates of the left and right limit boundary points, combined with the actual physical width of the bucket and the expansion coefficient, calculate the safety compensation angles of the left and right swing boundaries, and combine them with the preset system safety redundancy threshold to calculate the upper limit angle of the left anti-collision and the lower limit angle of the right anti-collision, and generate a dynamic safety swing zone.

[0010] S4. Based on the target work location and the dynamic safe turning zone, determine the first and second safety reference positions for horizontal avoidance;

[0011] S5. Based on the dynamic safe turning zone, the first safe reference position, and the second safe reference position, the five-stage cooperative motion planning method is used to control the autonomous operation of the engineering machinery.

[0012] In a second aspect, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect.

[0013] Thirdly, an autonomous operation and slewing collision avoidance system for unmanned construction machinery is provided, including a memory and a processor. The memory is used to store instructions, which are used to control the processor to perform operations to execute the aforementioned autonomous operation and slewing collision avoidance method for unmanned construction machinery.

[0014] Fourthly, this application provides an unmanned construction machinery equipped with the aforementioned autonomous operation and rotation anti-collision system for unmanned construction machinery.

[0015] Beneficial effects: The autonomous operation and collision avoidance method and system for unmanned engineering machinery provided in this application has the following advantages:

[0016] (1) By constructing an asymmetric dynamic safety domain through a bucket width compensation algorithm, the shortcomings of traditional static boundaries in adapting to changes in the physical size of the bucket and dynamic working conditions are solved. It can adapt to loading scenarios of mining trucks with different vehicle models, different parking angles, and different working distances without the need for manual recalibration of parameters. By introducing an expansion coefficient α, the effective physical width of the bucket is expanded from Wb to α×Wb, thereby adaptively adjusting the slewing safety compensation angle to achieve intelligent expansion of the safety domain. When α>1, the safety domain expands outward, and when α=1, it degenerates into the original geometric compensation. The safety margin can be flexibly adjusted according to different working conditions.

[0017] (2) The active tiered strategy of “avoiding first, then lifting and turning at high altitude” is adopted, which avoids the invalid shutdown caused by false alarm threshold in the traditional method, makes full use of the multi-degree-of-freedom advantage of engineering machinery, and significantly shortens the single loading cycle time.

[0018] (3) The algorithm is based on the dynamic calculation of the truck corner coordinates in real time. It does not require recalibrating fixed parameters for different vehicle models and automatically adapts to different parking angles, wheelbases and vehicle size changes.

[0019] (4) The complex nonlinear obstacle avoidance problem is decomposed into three simple linear / circular interpolation tasks. Multi-degree-of-freedom decoupling smooth control is used to eliminate hydraulic shock and emergency stop vibration, and reduce the wear of core components such as the main pump and multi-way valve.

[0020] (5) High-frequency closed-loop monitoring and dual safety position design can achieve predictive active protection under working conditions such as small sensor error and slight equipment displacement, and the safety is far superior to the transmission passive anti-collision scheme. Attached Figure Description

[0021] Figure 1 This is a schematic diagram of the autonomous operation and collision avoidance method for unmanned construction machinery according to an embodiment of this application;

[0022] Figure 2 This is a schematic diagram of the autonomous operation and collision avoidance method system for unmanned construction machinery in the embodiments of this application;

[0023] Figure 3 This is a top view schematic diagram of the safe turning zone of the engineering machinery in the embodiments of this application;

[0024] Figure 4 This is a schematic diagram of the five-stage coordinated motion trajectory in the embodiments of this application. Detailed Implementation

[0025] The present application will be further described below with reference to the accompanying drawings and embodiments. The following embodiments are only used to more clearly illustrate the technical solutions of the present application, and should not be used to limit the scope of protection of the present application.

[0026] In the description of this application, "several" means one or more, "multiple" means two or more, "greater than," "less than," and "exceeding" are understood to exclude the stated number, while "above," "below," and "within" are understood to include the stated number. The use of "first" and "second" in the description is merely for distinguishing technical features and should not be construed as indicating or implying relative importance, or implicitly indicating the number of indicated technical features, or implicitly indicating the order of the indicated technical features.

[0027] In the description of this application, the terms "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0028] Currently, robot navigation methods are generally based on SLAM (Simultaneous Localization and Mapping) environment mapping technology, relying on pre-built global grids or topological maps, and then using global or local path planning algorithms to plan navigation paths. Representative existing technical solutions can be divided into the following four categories:

[0029] The technical terms used in this application are defined as follows:

[0030] Slewing collision avoidance is a subdivided active collision avoidance control technology for engineering machinery. It is designed for large-scale rotation of slewing platforms. It matches the platform's slewing trajectory, the spatial envelope contour of the boom-stick-bucket multi-joints, and the coordinates of surrounding obstacles in real time. During autonomous operation, it actively restricts the slewing motion to avoid risks such as the bucket scraping against the vehicle body, mining trucks, or stacked materials, ensuring the safety of the overall machine structure and external equipment. Unlike fixed area limiters, it focuses on dynamic interference control throughout the entire slewing stroke.

[0031] The collision avoidance scheme for unmanned construction machinery still has significant shortcomings in related technologies, which restricts its implementation in complex working conditions:

[0032] (1) Insufficient environmental adaptability: Most anti-collision systems rely on manual preset static safety restricted areas, which are only suitable for fixed sites and cannot be adapted to dynamic scenarios such as moving mining trucks and temporary material storage; many solutions use a single sensor for detection, and obstacles are frequently missed or falsely triggered to stop in dusty, strong light and dark environments, resulting in poor operational stability.

[0033] (2) Ignoring multi-degree-of-freedom motion coupling constraints: There is strong motion coupling in the rotation, boom lifting, and stick extension and retraction of construction machinery, and the spatial position of the bucket is determined by the linkage of multiple joints. Most existing collision avoidance algorithms simplify the motion model, do not fully incorporate the change law of the multi-joint linkage envelope, and the trajectory planning does not match the kinematic boundary of the whole machine, resulting in insufficient collision avoidance judgment accuracy.

[0034] (3) It is difficult to balance safety and work efficiency: Due to inaccurate perception and rough motion model, the system often experiences unnecessary emergency braking and frequent work interruptions; if the safety threshold is relaxed, it will bring collision risks, and it is impossible to meet the requirements of safety reliability and continuous work efficiency at the same time.

[0035] To address the above shortcomings, this application proposes a method and system for autonomous operation and collision avoidance of unmanned construction machinery. The solution relies on multi-source sensor data to construct a dynamic environment model in real time, and combines this with the multi-degree-of-freedom kinematic constraints of the entire construction machinery to carry out adaptive trajectory planning and multi-joint cooperative motion control. This achieves high-precision, low-latency collision avoidance control in complex construction sites and mining conditions, balancing operational safety and construction continuity.

[0036] Example 1: This example provides a method for collision avoidance during autonomous operation and rotation of unmanned construction machinery, such as... Figure 1 As shown, it includes:

[0037] S1. Obtain the spatial location information of the feature corner points of the obstacles around the construction machinery and convert them into cylindrical coordinate data in the coordinate system of the construction machinery.

[0038] S2. Determine the cylindrical coordinates of the left and right limit boundary points based on the cylindrical coordinate data of the characteristic corner points of the obstacle edge;

[0039] S3. Based on the coordinates of the left and right limit boundary points, combined with the actual physical width of the bucket and the expansion coefficient, calculate the safety compensation angles of the left and right swing boundaries, and combine them with the preset system safety redundancy threshold to calculate the upper limit angle of the left anti-collision and the lower limit angle of the right anti-collision, and generate a dynamic safety swing zone.

[0040] S4. Based on the target work location and the dynamic safe turning zone, determine the first and second safety reference positions for horizontal avoidance;

[0041] S5. Based on the dynamic safe turning zone, the first safe reference position, and the second safe reference position, the five-stage cooperative motion planning method is used to control the autonomous operation of the engineering machinery.

[0042] The steps are explained in detail below:

[0043] S1. Obtain the spatial location information of the feature corner points of the obstacles around the construction machinery and convert them into cylindrical coordinate data in the coordinate system of the construction machinery.

[0044] In some embodiments, step S1 specifically involves: performing a panoramic visual scan of the mining truck bed using a multi-channel sensor on the top of the engineering machinery cab, selecting and extracting high-recognition effective feature corner points on the edge of the truck bed, and calculating the three-dimensional spatial coordinates P of each feature corner point in the image coordinate system. c,k Where variable k is the index of the effective feature corner point. Based on the pre-calibrated hand-eye calibration homogeneous transformation matrix, the coordinate transformation from the image coordinate system to the engineering machinery unloading coordinate system is completed, and the Cartesian coordinates of each feature corner point are obtained. =( , , ), further converted to obtain the cylindrical coordinates in the coordinate system of the construction machinery unloading ( ), , , ),in, The straight-line distance from the kth characteristic corner point to the rotation center of the engineering machinery; In the coordinate system of the unloading machinery, the angle is the angle corresponding to the horizontal orientation of the feature corner point, rotated counterclockwise from the negative X-axis of the unloading coordinate system. The height of the feature corner points is used to accurately model the spatial position of the obstacle.

[0045] The multiple sensors are selected from at least one of LiDAR, millimeter-wave radar, or vision camera. In this embodiment, the multi-source perception fusion system uses LiDAR, millimeter-wave radar, and industrial vision camera as core hardware to complete the time alignment and spatial coordinate unification of the raw data from multiple sensors, and to perform complementary fusion of feature-level information: LiDAR provides high-precision three-dimensional contours, millimeter-wave radar resists dust and backlight interference, and vision camera supplements obstacle category information; after fusion, a 360° real-time dynamic environment model of the whole machine is constructed, outputting obstacle position, size, and movement speed, providing a global environmental basis for turning trajectory planning and collision avoidance decisions, and solving the pain point of poor adaptability of single sensor working conditions.

[0046] S2. Determine the cylindrical coordinates of the left and right limit boundary points based on the cylindrical coordinate data of the characteristic corner points of the obstacle edge.

[0047] In some embodiments, the cylindrical coordinates of the left and right limit boundary points are respectively represented as ( , , ), ( , , ); , The straight-line distance from the left and right extreme boundary points to the rotation center of the engineering machinery; , In the coordinate system of the engineering machinery unloading vehicle, the included angle is the horizontal orientation corresponding to the left and right limit boundary points when rotating counterclockwise from the negative X-axis. , The heights of the left and right extreme boundary points;

[0048] In this embodiment, the method for determining the cylindrical coordinates of the left and right limit boundary points includes: traversing all valid feature corner points. Determine the maximum value among them. and minimum value The corresponding effective feature corner points are the left and right limit boundary points. The cylindrical coordinates of the left limit boundary point constraining the engineering machinery to rotate to the right are obtained through this selection process. , , ) and the right limit boundary point coordinates constraining the engineering machinery to rotate to the left ( , , ), locking the boundary of the foundation that the mining trucks block from the rotation of the construction machinery.

[0049] S3. Based on the coordinates of the left and right limit boundary points, combined with the actual physical width of the bucket. and expansion coefficient Calculate the safety compensation angles of the left and right slewing boundaries to generate a dynamic safety slewing zone (clockwise direction).

[0050] This application addresses the scraping hazard caused by traditional solutions that neglect the bucket's width and only identify obstacle outlines. It calculates a dynamic safety compensation angle based on triangular geometry and introduces an expansion coefficient. ( ≥1) The effective physical width of the bucket is dynamically expanded, and the calculation formula for the safety compensation angle of the left and right swing boundaries is as follows:

[0051] ,

[0052] ;

[0053] in, , These are the safety compensation angles for the left and right slewing boundaries, respectively. This refers to the actual physical width of the bucket. The coefficient of thermal expansion is 1 / 3. ≥1, when When =1, it degenerates into the primitive geometric compensation. When the value is greater than 1, the security domain expands outward. , It represents the straight-line distance from the left and right limit boundary points to the rotation center of the engineering machinery.

[0054] The above steps incorporate the physical dimensions of the bucket into the safety threshold calculation, covering the collision risk areas on the left and right edges of the bucket, and using the expansion coefficient... To achieve intelligent expansion and control of the security domain.

[0055] Then, based on the left and right turning boundary safety compensation angles and the preset system safety redundancy threshold, the final collision avoidance threshold is obtained, expressed as:

[0056] ;

[0057] ;

[0058] in, These are the upper limit angle for left-side collision protection and the lower limit angle for right-side collision protection, respectively. , In the coordinate system of the engineering machinery unloading vehicle, the included angle is the horizontal orientation corresponding to the left and right limit boundary points when rotating counterclockwise from the negative X-axis. This is a preset system security redundancy threshold.

[0059] The final result is a dynamic safety turning zone in the clockwise direction. .

[0060] S4 is based on the target work location ( , , ) and dynamic safety turning zone, to determine the first safety reference position for horizontal avoidance ( , , ) and second security reference position ( , , ),in, The straight-line distance from the target work location to the rotation center of the construction machinery; This refers to the angle between the horizontal orientation of the target working position, rotated counterclockwise from the negative X-axis of the unloading coordinate system in the coordinate system of the construction machinery. The height of the target work position. These are the upper limit angle for left-side collision protection and the lower limit angle for right-side collision protection, respectively.

[0061] In this embodiment, the area outside the dynamic safety turning zone is the restricted turning zone.

[0062] like Figure 3 The diagram shown is a top view of the obstacle-avoidance turning safety of the construction machinery according to this application; where 201 is the turning center point O of the construction machinery, 202 is the construction machinery, 203 is the obstacle (mining truck), 204 is the left limit boundary of the obstacle based on the feature corner point, 205 is the left dynamic safety boundary of the obstacle considering the bucket width, 206 is the left limit boundary of the obstacle's restricted turning zone, i.e., the second safety reference position, 207 is the right limit boundary of the obstacle based on the feature corner point, 208 is the right dynamic safety boundary of the obstacle considering the bucket width, 209 is the right limit boundary of the obstacle's restricted turning zone, i.e., the first safety reference position, 210 is the restricted turning zone, and 211 is the dynamic safety turning zone.

[0063] S5. Based on the dynamic safe turning zone, the first safe reference position, and the second safe reference position, the five-stage cooperative motion planning method is used to control the autonomous operation of the engineering machinery.

[0064] (1) When the target working position is in the dynamic safe turning zone, the bucket is directly raised to the preset safe turning height and conventional digging, turning and unloading operations are performed;

[0065] (2) When the target working position is outside the dynamic safe turning zone, spatial geometric constraints are applied to the working device of the construction machinery, that is, the lowest point height of the boom and stick is controlled to be greater than or equal to the lowest point height of the bucket, so as to ensure that the working device presents a safe configuration of "bucket low position, boom and stick high position suspended" above the obstacle; under this global constraint, a five-stage conflict-free action sequence is executed, such as Figure 4 As shown, it includes:

[0066] Phase 1: Full-machine anti-collision pre-inspection and coordinated lifting: Implement multi-arm coordinated trajectory control for the boom, stick, and bucket. While maintaining the bucket's predetermined working posture, use inverse kinematics to control the coordinated lifting of the boom, stick, and bucket, raising the bucket to the preset safe swing height H. swing Simultaneously, the distance between the machine's actuators and obstacles is monitored in real time (ensuring that the minimum distance between the boom and stick and obstacles is greater than the safety threshold), and the distance from the bucket to the slewing axis is adjusted to the straight-line distance from the target working position to the slewing center of the construction machinery. During this stage, the entire linkage envelope is monitored to avoid the risk of ground and lateral interference during the initial stage of rotation.

[0067] Phase 2: Initial avoidance horizontal attitude adjustment: With the first or second safety reference position as the target, control the slewing mechanism to rotate at a low speed and smoothly, so that the bucket is completely out of the horizontal projection restriction zone of the mining truck. The boom and stick remain at their current heights. Horizontal avoidance is completed only through the slewing degree of freedom, without the need to stop the entire machine.

[0068] Phase 3: Vertical Obstacle Clearance Dynamic Lifting: After confirming that horizontal obstacle avoidance is completed (reaching the first or second safety reference position), coordinate the boom lifting and stick extension / retraction movements, dynamically match the hydraulic flow, and raise the lowest point of the bucket to the safe height H of the mining truck. lift =H t +H margin ; where H t H is the height of the truck bed for mining trucks. margin This is a preset safety margin to ensure that the lowest point of the bucket is completely higher than the highest point of the obstacle;

[0069] Phase 4: High-altitude precision positioning and rotation: Within the safe height plane of the mining truck, control the rotation mechanism to directly rotate to the angle corresponding to the target working position. The bucket is kept at a safe height throughout the process, eliminating the risk of collision.

[0070] Phase 5: Safe Lowering Operation. Upon reaching the target work position, the system performs collision pre-planning of the lowering path again to confirm that the boom and stick will not interfere with the edge of the bucket or the ground during the lowering process. Then, the boom and stick are lowered smoothly according to the work requirements, the bucket posture is finely adjusted, and the digging or unloading operation is completed.

[0071] Furthermore, when crossing obstacles, the control method applies spatial geometric constraints to the working device of the engineering machinery, that is, it controls the lowest point height of the boom and stick to always be greater than or equal to the lowest point height of the bucket.

[0072] It should be noted that, in the execution of the five-stage conflict-free action sequence in this embodiment, the spatial position information of the edge feature corner points of obstacles around the unmanned construction machinery is continuously monitored and acquired at a set period (e.g., 50ms). If displacement of the mining truck is detected, the dynamic safe turning zone and the first and second safety reference positions are recalculated using the methods in steps S1 to S4. Then, the construction machinery is controlled to operate autonomously based on the updated dynamic safe turning zone and the first and second safety reference positions, dynamically adjusting the avoidance trajectory or pausing the operation to wait for the working conditions to stabilize. Emergency braking is only triggered when there is an extreme risk of sudden foreign object intrusion that cannot be avoided through trajectory planning, so as to minimize invalid shutdowns and ensure the continuity of operation.

[0073] Example 2: Based on Example 1, this example provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in Example 1.

[0074] Example 3: Based on Example 1, this example provides an autonomous operation and slewing collision avoidance system for unmanned construction machinery, including a memory and a processor. The memory is used to store instructions, which are used to control the processor to perform operations to execute the autonomous operation and slewing collision avoidance method for unmanned construction machinery described in Example 1.

[0075] In some embodiments, such as Figure 2 As shown, the autonomous operation and slewing collision avoidance system for unmanned construction machinery also includes a perception layer, a core control unit, and a working device assembly; wherein,

[0076] The core control unit is used to execute the autonomous operation and collision avoidance method for unmanned engineering machinery described in Example 1;

[0077] The perception layer includes: a lidar / vision camera mounted on the top of the engineering machinery's cab to acquire obstacle position and distance information; and a combination of GNSS / IMU / tilt sensor / travel sensor to collect the system's pose information. All of the above perception data is transmitted to the multi-source information fusion and processing center in the core control unit for unified processing.

[0078] In this embodiment, the core control unit runs on an in-vehicle embedded industrial computer (x86 architecture, running a real-time Linux system + C++ algorithm library). It includes a safety monitoring and collision avoidance decision module, which receives the fused information and generates safety constraints or emergency stop commands; and a trajectory planning and motion control module, which plans the motion trajectory based on the safety commands and controls the hydraulic drive system. The hydraulic drive system then drives the working device assembly to perform the work task. Simultaneously, the system has a status feedback and error correction loop, feeding back the actual status of the working device assembly to the trajectory planning and motion control module to achieve closed-loop precise control.

[0079] In this embodiment, the working device assembly includes a boom, stick, bucket, and slewing mechanism. The main control ECU of the construction machinery obtains phase commands and speed setpoints via the CAN bus, and coordinates with the proportional relief valve and servo drive in the hydraulic system to smoothly adjust the speed curve of the actuator, thereby achieving high-precision continuous control, rather than simple start-stop control.

[0080] Example 4: Based on Example 1, this example provides an unmanned construction machinery equipped with the autonomous operation and rotation anti-collision system for unmanned construction machinery described in Example 3.

[0081] In some embodiments, the unmanned construction machinery may be an unmanned excavator.

[0082] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0083] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0084] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0085] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0086] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for collision avoidance during autonomous operation and rotation of unmanned engineering machinery, characterized in that, include: S1. Obtain the spatial location information of the feature corner points of the obstacles around the construction machinery and convert them into cylindrical coordinate data in the coordinate system of the construction machinery. S2. Determine the cylindrical coordinates of the left and right limit boundary points based on the cylindrical coordinate data of the characteristic corner points of the obstacle edge; S3. Based on the coordinates of the left and right limit boundary points, combined with the actual physical width of the bucket and the expansion coefficient, calculate the safety compensation angles of the left and right swing boundaries, and combine them with the preset system safety redundancy threshold to calculate the upper limit angle of the left anti-collision and the lower limit angle of the right anti-collision, and generate a dynamic safety swing zone. S4. Based on the target work location and the dynamic safe turning zone, determine the first and second safety reference positions for horizontal avoidance; S5. Based on the dynamic safe turning zone, the first safe reference position, and the second safe reference position, the five-stage cooperative motion planning method is used to control the autonomous operation of the engineering machinery.

2. The method for autonomous operation and collision avoidance of unmanned engineering machinery as described in claim 1, characterized in that, Step S1 specifically includes: High-recognition effective feature corner points are extracted from the edge of the mining truck bed, and the three-dimensional spatial coordinates of each feature corner point in the image coordinate system are calculated. Based on the pre-calibrated hand-eye calibration homogeneous transformation matrix, the coordinate transformation from the image coordinate system to the engineering machinery unloading coordinate system is completed to obtain the Cartesian coordinates of each feature corner point, which are further converted to obtain the cylindrical coordinates in the engineering machinery unloading coordinate system. , , ),in, The straight-line distance from the kth characteristic corner point to the rotation center of the engineering machinery; In the coordinate system of the unloading machinery, the angle is the angle corresponding to the horizontal orientation of the feature corner point, rotated counterclockwise from the negative X-axis of the unloading coordinate system. The height of the feature corner point.

3. The method for autonomous operation and collision avoidance of unmanned engineering machinery as described in claim 1, characterized in that, Step S3: Based on the coordinates of the left and right limit boundary points, combined with the actual physical width of the bucket and the expansion coefficient, calculate the safety compensation angles of the left and right swing boundaries, and generate a dynamic safe swing zone by combining the preset system safety redundancy threshold, represented as: ， ； ； ； in, , These are the safety compensation angles for the left and right slewing boundaries, respectively. This refers to the actual physical width of the bucket. The coefficient of thermal expansion is 1 / 3. , The straight-line distance from the left and right extreme boundary points to the rotation center of the engineering machinery; These are the upper limit angle for left-side collision protection and the lower limit angle for right-side collision protection, respectively. , In the coordinate system of the construction machinery unloading vehicle, the included angle is the horizontal orientation corresponding to the left and right limit boundary points when rotating counterclockwise from the negative X-axis. This is a preset system security redundancy threshold.

4. The method for autonomous operation and collision avoidance of unmanned engineering machinery according to claim 1, characterized in that, S4 include: According to the target work location ( , , ) and dynamic safety turning zone, to determine the first safety reference position for horizontal avoidance ( , , ) and second safety reference position ( , , ); in, The straight-line distance from the target work location to the rotation center of the construction machinery; This refers to the angle between the horizontal orientation of the target working position, rotated counterclockwise from the negative X-axis of the unloading coordinate system in the coordinate system of the construction machinery. The height of the target work position. These are the upper limit angle for left-side collision protection and the lower limit angle for right-side collision protection, respectively.

5. The method for autonomous operation and collision avoidance of unmanned engineering machinery as described in claim 1, characterized in that, Step S5 includes: (1) When the target working position is in the dynamic safe turning zone, directly raise the bucket to the preset safe turning height and perform conventional excavation, turning and unloading operations; (2) When the target working position is outside the dynamic safe turning zone, spatial geometric constraints are applied to the working device of the construction machinery, that is, the lowest point height of the boom and stick is controlled to be greater than or equal to the lowest point height of the bucket; under global constraints, a five-stage conflict-free action sequence is executed, including: Phase 1: Full-Machine Collision Prevention Pre-inspection and Coordinated Lifting: While maintaining the bucket's predetermined working posture, the boom, stick, and bucket are coordinated and lifted using inverse kinematics control to raise the bucket to a preset safe swing height. Simultaneously, the distance between the machine's working devices and obstacles is monitored in real time to ensure that the minimum distance between the boom and stick and obstacles is greater than a safe threshold. The distance from the bucket to the swing axis is adjusted to the straight-line distance from the target working position to the center of rotation of the construction machinery. ; Second stage: Initial avoidance horizontal attitude adjustment: With the first or second safety reference position as the target, control the slewing mechanism to rotate smoothly so that the bucket is completely out of the horizontal projection restriction zone of the mining truck. The boom and stick remain at their current heights, and horizontal avoidance is completed only through the slewing degree of freedom. Phase 3: Vertical obstacle crossing dynamic lifting: After confirming that the horizontal obstacle avoidance has been completed, the boom lifting and stick extension actions are coordinated and adjusted, and the hydraulic flow is dynamically matched to raise the lowest point of the bucket to the safe height of the mining truck; where the safe height of the mining truck is the sum of the height of the mining truck bucket and the preset safety margin, which is used to ensure that the lowest point of the bucket is completely higher than the highest point of the obstacle; Phase 4: High-altitude precision positioning and rotation: Within the safe height plane of the mining truck, the slewing mechanism is controlled to rotate directly to the angle corresponding to the target working position, maintaining the safe height of the bucket throughout the process, with no risk of collision; Phase 5: Safe lowering operation. After reaching the target work position, the lowering trajectory is pre-planned. After confirming that there is no interference, the boom and stick are lowered smoothly. The bucket posture is finely adjusted to complete the excavation or unloading operation.

6. The method for autonomous operation and collision avoidance of unmanned engineering machinery as described in claim 5, characterized in that, During the execution of the five-stage conflict-free action sequence, the spatial position information of the edge feature corner points of obstacles around the unmanned engineering machinery is continuously monitored and acquired at a set periodic frequency. If the displacement of the obstacle mining truck is detected, the dynamic safe turning zone and the first safety reference position and the second safety reference position are recalculated and updated using the methods of steps S1 to S4. Then, the engineering machinery is controlled to operate autonomously based on the updated dynamic safe turning zone and the first safety reference position and the second safety reference position.

7. A computer-readable storage medium, characterized in that, It stores a computer program, which, when executed by a processor, implements the autonomous operation and collision avoidance method for unmanned engineering machinery according to any one of claims 1-6.

8. A collision avoidance system for autonomous operation and rotation of unmanned engineering machinery, characterized in that, It includes a memory and a processor, the memory being used to store instructions for controlling the processor to perform the autonomous operation and collision avoidance method for unmanned engineering machinery according to any one of claims 1-6.

9. The autonomous operation and slewing collision avoidance system for unmanned engineering machinery according to claim 8, characterized in that, Also includes: The perception layer includes: a lidar / vision camera installed on the top of the cab of the construction machinery, used to acquire information on the position and distance of obstacles; And a combination of GNSS / IMU / tilt sensor / stroke sensor is used to acquire the system's pose information; The working device assembly includes the boom, stick, bucket, and slewing mechanism.

10. An unmanned engineering machine, characterized in that, It is equipped with the autonomous operation and rotation collision avoidance system for unmanned engineering machinery as described in claim 8 or 9.

Images