Dynamic obstacle avoidance method and device based on model combination

Abstract

The application provides a dynamic obstacle avoidance method and device based on model combination, and relates to the fields of engineering machinery and automatic driving technology.The method comprises the following steps: acquiring shape parameters and motion parameters of engineering machinery; constructing a multi-circle combination model based on the shape parameters; generating a plurality of initial parameter combinations based on the motion parameters; screening the initial parameter combinations based on obstacle information and the multi-circle combination model to obtain a target parameter combination; and controlling the engineering machinery to perform an obstacle avoidance action based on the target parameter combination.The dynamic obstacle avoidance method and device based on model combination improve the response real-time performance and accuracy of autonomous obstacle avoidance of engineering machinery.

Description

Technical Field

[0001] This invention relates to the fields of engineering machinery and autonomous driving technology, and in particular to a dynamic obstacle avoidance method and device based on model combination. Background Technology

[0002] In construction machinery operations, due to the large size of construction machinery (such as drilling rigs, excavators, and cranes), there are multiple blind spots during operation. They are very prone to crushing and colliding with surrounding obstacles (such as other equipment, construction workers, and buildings), which can not only cause equipment damage and project delays, but also endanger the lives of construction workers.

[0003] To reduce the risk of such accidents, existing technologies use autonomous driving technology to assist construction machinery in carrying out construction operations, combined with autonomous obstacle avoidance algorithms to control the construction machinery to avoid obstacles.

[0004] However, existing autonomous obstacle avoidance algorithms are computationally complex, resulting in high computational load and low computational efficiency, leading to untimely obstacle avoidance responses from construction machinery. At the same time, inaccurate calculation results result in low obstacle avoidance accuracy for construction machinery. Summary of the Invention

[0005] This invention provides a dynamic obstacle avoidance method and device based on model combination to solve the technical problems of untimely response and low accuracy of autonomous obstacle avoidance in engineering machinery in the prior art.

[0006] This invention provides a dynamic obstacle avoidance method based on model combination, comprising the following steps: Obtain the external shape parameters and motion parameters of the construction machinery; the external shape parameters include the overall width and overall length; Based on the aforementioned shape parameters, a multi-circle combination model is constructed; Based on the motion parameters, multiple initial parameter combinations are generated; Based on obstacle information and the multi-circle combination model, the initial combination parameters are filtered to obtain the target parameter combination; the obstacle information is collected by multiple sensors; the multiple sensors are installed on the engineering machinery; the obstacle information includes at least one of the obstacle's position, size, speed, and direction of movement; Based on the target parameter combination, the engineering machinery is controlled to perform obstacle avoidance actions.

[0007] According to the present invention, a dynamic obstacle avoidance method based on model combination is provided, wherein constructing a multi-circle combination model based on the shape parameters includes: Based on the overall length, determine the number of combinations of the circles to be combined; The overall length is divided into multiple segments along the direction of the overall length; wherein the length of each segment is the ratio of the overall length to the number of combinations. Construct a multi-circle combination model by taking the center of each segment as the target center of each circle to be combined.

[0008] According to the dynamic obstacle avoidance method based on model combination provided by the present invention, the calculation expression for the target radius of the circle to be combined is: In the formula, Indicates the radius, This refers to the overall width. Indicates the overall length. This indicates the number of combinations.

[0009] According to a dynamic obstacle avoidance method based on model combination provided by the present invention, before generating multiple initial parameter combinations based on the multi-circle combination model and the motion parameters of the engineering machinery, the method further includes: Boundary verification is performed on the multi-circle combination model. If the multi-circle combination model cannot completely cover the engineering machinery, the size of the target radius and / or the position of the target circle center are adjusted until the multi-circle combination model completely covers the engineering machinery.

[0010] According to a dynamic obstacle avoidance method based on model combination provided by the present invention, the generation of multiple initial parameter combinations based on the motion parameters includes: Select any driving speed, any angular velocity, any driving speed increment, and any angular velocity increment respectively; The initial parameter combination is the combination of any driving speed, any angular velocity, any driving speed increment, and any angular velocity increment.

[0011] According to a dynamic obstacle avoidance method based on model combination provided by the present invention, the initial parameter combination is filtered based on obstacle information and the multi-circle combination model to obtain a target parameter combination, including: Based on parameters from multiple initial parameter combinations, the multi-circle combination model is controlled to move, resulting in multiple motion trajectories; wherein, each initial parameter combination corresponds one-to-one with each motion trajectory. Based on the obstacle information, the initial parameter combination corresponding to the motion trajectory that collides with the obstacle is removed to obtain the intermediate parameter combination; Based on a preset evaluation function, obstacle avoidance scoring is performed on the intermediate parameter combinations to obtain the obstacle avoidance score corresponding to each intermediate parameter combination. The intermediate parameter combination with the highest obstacle avoidance score is used as the target parameter combination.

[0012] The present invention also provides a dynamic obstacle avoidance device based on model combination, comprising the following modules: The acquisition module is used to acquire the shape parameters and motion parameters of the construction machinery; the shape parameters include the overall width and overall length. A construction module is used to construct a multi-circle combination model based on the aforementioned shape parameters; A generation module is used to generate multiple initial parameter combinations based on the motion parameters; A filtering module is used to filter the initial combination parameters based on obstacle information and the multi-circle combination model to obtain a target parameter combination; the obstacle information is collected by multiple sensors; the multiple sensors are installed on the engineering machinery; the obstacle information includes at least one of the obstacle's position, size, speed, and direction of movement; The control module is used to control the engineering machinery to perform obstacle avoidance actions based on the target parameter combination.

[0013] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the dynamic obstacle avoidance method based on model combination as described above.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the dynamic obstacle avoidance method based on model combination as described above.

[0015] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the dynamic obstacle avoidance method based on model combination as described above.

[0016] The present invention provides a dynamic obstacle avoidance method and device based on model combination. This method acquires the shape and motion parameters of an engineering machinery. The shape parameters include the overall width and overall length. Based on these shape parameters, a multi-circle combination model is constructed, simplifying the modeling of the engineering machinery's shape, reducing computational complexity, and improving modeling accuracy. Based on the motion parameters, multiple initial parameter combinations are generated. Based on obstacle information and the multi-circle combination model, the initial combination parameters are filtered to obtain a target parameter combination. The obstacle information is collected by multiple sensors installed on the engineering machinery. The obstacle information includes at least one of the obstacle's position, size, speed, and direction of movement. By filtering the target parameter combination from the initial parameter combinations, collision risks caused by local modeling omissions or computational delays are avoided. Based on the target parameter combination, the engineering machinery is controlled to perform obstacle avoidance actions. By driving the actual movement of the engineering machinery according to the target parameter combination, a closed-loop control is formed, timely correction of trajectory deviations is achieved, and accurate execution of obstacle avoidance actions is ensured, improving the real-time response and accuracy of the engineering machinery's autonomous obstacle avoidance. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating the dynamic obstacle avoidance method based on model combination provided by the present invention.

[0019] Figure 2 This is a schematic diagram of the shape of the multi-circle combination model provided by the present invention under ideal conditions.

[0020] Figure 3 This is a schematic diagram of the shape of the multi-circle combination model provided by the present invention under a non-ideal state.

[0021] Figure 4 This is a schematic diagram of the dynamic obstacle avoidance device based on model combination provided by the present invention.

[0022] Figure 5 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0024] Construction machinery often has an irregular shape, and existing autonomous obstacle avoidance algorithms have many problems that need improvement in practical applications, mainly in the following two aspects: (1) Dynamic window algorithm using a single circular model: In order to simplify the modeling of the shape of construction machinery, the traditional method often uses a circular model to represent the entire construction machinery. However, this modeling method will result in an excessively large obstacle avoidance radius. On the one hand, it requires the construction machinery to reserve a wider safety distance during operation, which wastes the working space, especially in narrow construction sites where it has poor applicability. On the other hand, an excessively large obstacle avoidance radius may cause the path planned by the algorithm to be too conservative, resulting in the target point being unreachable, which affects the work efficiency.

[0025] (2) Dynamic window algorithm using polygon model: In order to more accurately represent the irregular shape of construction machinery, the existing technology uses polygon model for modeling. However, the polygon model has a large number of vertices. In the calculation process of dynamic window algorithm, it is necessary to predict the motion state of each vertex of the polygon and perform collision detection, which leads to a sharp increase in the amount of calculation, making the algorithm response untimely and unable to meet the real-time obstacle avoidance needs of construction machinery. In the dynamic working environment, it is easy to cause safety hazards.

[0026] To address the aforementioned issues, this invention proposes a dynamic obstacle avoidance method and device based on model combination. By combining multiple circular models, the shape of the engineering machinery is represented in a refined manner, thereby ensuring modeling accuracy while effectively controlling the computational load and balancing the accuracy and real-time performance of obstacle avoidance.

[0027] The following is combined Figures 1 to 5 The present invention describes a dynamic obstacle avoidance method and apparatus based on model combination.

[0028] Figure 1 This is a flowchart illustrating the dynamic obstacle avoidance method based on model combination provided by the present invention, as shown below. Figure 1 As shown, the method includes the following: Step 101: Obtain the external shape parameters and motion parameters of the construction machinery; the external shape parameters include the overall width and overall length; Specifically, construction machinery can be mechanical equipment such as drilling rigs, excavators, and cranes.

[0029] The external parameters of construction machinery include a variety of parameters such as the overall width W, overall length L, protrusion dimensions and position coordinates of key parts of the machine body, etc. The external shape of construction machinery can be characterized by these parameters.

[0030] The motion parameters of construction machinery include a variety of motion parameters such as maximum travel speed, minimum travel speed, maximum angular velocity, minimum angular velocity, any speed increment, any angular velocity increment, any travel speed between the maximum and minimum travel speeds, and any angular velocity between the maximum and minimum angular velocities.

[0031] Step 102: Based on the aforementioned shape parameters, construct a multi-circle combination model; Furthermore, the construction of the multi-circle combination model based on the shape parameters includes: Based on the overall length, determine the number of combinations of the circles to be combined; The overall length is divided into multiple segments along the direction of the overall length; wherein the length of each segment is the ratio of the overall length to the number of combinations. Construct a multi-circle combination model by taking the center of each segment as the target center of each circle to be combined.

[0032] Specifically, based on the obtained external parameters of the engineering machinery, a multi-circle combination model is constructed to characterize the external shape of the engineering machinery.

[0033] Figure 2 This is a schematic diagram of the shape of the multi-circle combination model provided by the present invention under ideal conditions, as shown below. Figure 2 As shown, firstly, the number of circles to be combined is determined based on the overall length L of the engineering machinery (n≥2, which can be adaptively adjusted according to the complexity of the engineering machinery's shape and the required calculation accuracy; for example, 2~3 circles can be selected for regular-shaped engineering machinery, and 4~6 circles can be selected for irregular-shaped engineering machinery. In this embodiment of the invention, n=3 is used as an example for explanation). Then, the overall length of the engineering machinery is evenly divided into n segments, and the length of each segment is L / n. Then, with the center of each segment as the center of the target circle, n circular models are constructed to obtain a multi-circle combination model.

[0034] Furthermore, the calculation expression for the target radius of the circle to be combined is: In the formula, Indicates the radius, This refers to the overall width. Indicates the overall length. This indicates the number of combinations.

[0035] For example, taking the three-circle model (i.e., n=3) as an example, an actual test was conducted on the SWDE165IF drilling rig, which has an overall width W=2.8 meters and an overall length L=8.8 meters.

[0036] If based on the original algorithm in existing technology Calculations yield the obstacle radius R. 原始 ≈4.62 meters; however, according to the above formula for calculating the target radius, the target radius R is obtained. 改进 ≈2.03 meters.

[0037] Therefore, it can be seen that the obstacle avoidance radius calculated by the target radius calculation expression provided by the present invention is reduced by about 56% compared with the prior art; it improves the shape modeling accuracy and calculation efficiency of engineering machinery, and reduces the obstacle avoidance radius on the basis of effective obstacle avoidance, making the path planning more refined. It solves the problem that engineering machinery is difficult to reach the target point in narrow working space, and can better adapt to narrow working space, improving the utilization rate of working space and the rationality of path planning.

[0038] Step 103: Based on the motion parameters, generate multiple initial parameter combinations; Furthermore, the generation of multiple initial parameter combinations based on the motion parameters includes: Select any driving speed, any angular velocity, any driving speed increment, and any angular velocity increment respectively; The initial parameter combination is the combination of any driving speed, any angular velocity, any driving speed increment, and any angular velocity increment.

[0039] Specifically, based on the maximum travel speed, minimum travel speed, maximum angular velocity, and minimum angular velocity in the motion parameters, the travel speed range and angular velocity range of the construction machinery can be determined.

[0040] Within the driving speed range, select any driving speed (including the maximum driving speed and the minimum driving speed); within the angular velocity range, select any angular velocity (including the maximum angular velocity and the minimum angular velocity); at the same time, select any driving speed increment (i.e., the driving speed variation range supported by the construction machinery) and any angular velocity increment (i.e., the angular velocity variation range supported by the construction machinery), and perform discrete combination to obtain an initial parameter combination.

[0041] Based on the above range of motion parameters, all possible combinations of driving speed (v), angular velocity (ω), driving speed increment, and angular velocity increment can be determined, generating multiple initial parameter combinations and forming a dynamic window for parameter changes.

[0042] Step 104: Based on the obstacle information and the multi-circle combination model, the initial combination parameters are filtered to obtain the target parameter combination; the obstacle information is collected by multiple sensors; the multiple sensors are installed on the engineering machinery; the obstacle information includes at least one of the obstacle's position, size, speed, and direction of movement; Furthermore, the step of filtering the initial parameter combination based on obstacle information and the multi-circle combination model to obtain the target parameter combination includes: Based on parameters from multiple initial parameter combinations, the multi-circle combination model is controlled to move, resulting in multiple motion trajectories; wherein, each initial parameter combination corresponds one-to-one with each motion trajectory. Based on the obstacle information, the initial parameter combination corresponding to the motion trajectory that collides with the obstacle is removed to obtain the intermediate parameter combination; Based on a preset evaluation function, obstacle avoidance scoring is performed on the intermediate parameter combinations to obtain the obstacle avoidance score corresponding to each intermediate parameter combination. The intermediate parameter combination with the highest obstacle avoidance score is used as the target parameter combination.

[0043] Specifically, based on the driving speed, angular velocity, driving speed increment, and angular velocity increment corresponding to each initial parameter combination, the motion of the multi-circle combination model within a preset time t (t is usually 0.5-2s and can be dynamically adjusted according to the work scenario) is predicted, and multiple corresponding motion trajectories are obtained, that is, the motion trajectory of each circular model in the multi-circle combination model.

[0044] By integrating multiple sensors such as LiDAR, millimeter-wave radar, and cameras, obstacle information around the construction machinery is collected in real time, including at least one of the obstacle's position, size, speed, and direction of movement. The obstacle information is processed using multi-sensor data fusion technology (such as Kalman filtering and particle filtering algorithms) to eliminate the detection error of a single sensor, improve the accuracy and reliability of obstacle detection, and convert the processed obstacle information into coordinate data in the coordinate system of the construction machinery.

[0045] Based on the coordinate data corresponding to the obstacle information, it can be directly determined whether the motion trajectory of each circular model in the multi-circle combination model collides with the obstacles around the construction machinery. If any circular model collides with an obstacle, the initial parameter combination corresponding to this motion trajectory is removed, and the initial parameter combination corresponding to the remaining motion trajectory that did not collide is used as the intermediate parameter combination.

[0046] To further improve the control precision of engineering machinery, an obstacle avoidance score is obtained for intermediate parameter combinations based on a preset evaluation function. The intermediate parameter combination with the highest obstacle avoidance score is then used as the target parameter combination.

[0047] The expression for the evaluation function is: In the formula, Represents the evaluation function; The proximity index to the target point represents the reciprocal of the distance between the end point of the trajectory and the target point. This is a path smoothness index, representing the rate of change of curvature of the motion trajectory; α represents the speed magnitude index, which is the ratio of the current speed to the maximum speed of the construction machinery. The current speed can be the driving speed or angular velocity, and the maximum speed is the corresponding maximum driving speed or maximum angular velocity. α, β, and γ are the weight parameters of each index, and α+β+γ=1.

[0048] In some embodiments, the weight parameters of each indicator can be adjusted according to the operational requirements of the engineering machinery. For example, the weight of the target point approach index can be increased in a precision operation scenario, and the weight of the speed index can be increased in a dynamic environment, so as to select the intermediate parameter combination with the highest obstacle avoidance score as the optimal motion parameters (i.e., the target parameter combination).

[0049] This invention first performs trajectory prediction and obstacle distance calculation for each circle in the multi-circle combination model to ensure comprehensive collision risk detection and avoid collision omissions caused by single or local modeling. Since collision risk assessment only requires calculating the distance between the circle and the obstacle, complex polygon vertex calculations are unnecessary, reducing computational load and ensuring real-time algorithm response (response time controllable within 100ms). This meets the real-time obstacle avoidance requirements of engineering machinery in dynamic operating environments, preventing safety accidents caused by response delays, and quickly removing parameter combinations with collision risks, reducing subsequent computational load and improving the real-time performance of autonomous obstacle avoidance response. Then, an evaluation function is used to optimize intermediate parameter combinations. By comprehensively considering target proximity, path smoothness, and speed, a safe, efficient, and stable target parameter combination is selected to meet the operational needs of different scenarios, thereby improving the accuracy of autonomous obstacle avoidance.

[0050] Step 105: Based on the target parameter combination, control the engineering machinery to perform obstacle avoidance actions.

[0051] Specifically, the target parameter combination is converted into execution instructions for the construction machinery, which control the machinery's power system, steering system, and other actuators, enabling the machinery to move along a planned trajectory and achieve autonomous obstacle avoidance.

[0052] At the same time, the parameters in the target parameter combination can be fine-tuned according to the actual movement state of the construction machinery (such as actual speed and position), and the trajectory deviation caused by external environmental interference or actuator error can be corrected in a timely manner. This ensures that the construction machinery strictly follows the planned path to avoid obstacles until the construction machinery reaches the target work point or completes the current work task, thereby forming a closed-loop control, ensuring the accuracy of obstacle avoidance actions, further improving the reliability and accuracy of obstacle avoidance of construction machinery, and reducing the risk of work accidents.

[0053] The present invention provides a dynamic obstacle avoidance method based on model combination. This method acquires the shape and motion parameters of an engineering machinery. The shape parameters include the overall width and overall length. Based on these shape parameters, a multi-circle combination model is constructed, simplifying the modeling of the engineering machinery's shape, reducing computational complexity, and improving modeling accuracy. Based on the motion parameters, multiple initial parameter combinations are generated. Based on obstacle information and the multi-circle combination model, the initial combination parameters are filtered to obtain a target parameter combination. The obstacle information is collected by multiple sensors installed on the engineering machinery. The obstacle information includes at least one of the obstacle's position, size, speed, and direction of movement. By filtering the target parameter combination from the initial parameter combinations, the method avoids collision risks caused by omissions in local modeling or computational delays. Based on the target parameter combination, the method controls the engineering machinery to perform obstacle avoidance actions. By driving the actual movement of the engineering machinery according to the target parameter combination, a closed-loop control is formed, timely correcting trajectory deviations, ensuring accurate execution of obstacle avoidance actions, and improving the real-time response and accuracy of the engineering machinery's autonomous obstacle avoidance.

[0054] Furthermore, before generating multiple initial parameter combinations based on the multi-circle combination model and the motion parameters of the engineering machinery, the method further includes: Boundary verification is performed on the multi-circle combination model. If the multi-circle combination model cannot completely cover the engineering machinery, the size of the target radius and / or the position of the target circle center are adjusted until the multi-circle combination model completely covers the engineering machinery.

[0055] Specifically, the boundary of the multi-circle model is checked to ensure that it completely covers the shape of the engineering machinery. If there is insufficient coverage or excessive overlap, the radius or center position of the circle is adjusted until the modeling requirements are met.

[0056] Figure 3This is a schematic diagram of the shape of the multi-circle combination model provided by the present invention under a non-ideal state, such as... Figure 3 As shown, for engineering machinery with highly irregular shapes, the ideally defined center of the circle and the formulaic radius may not be able to completely cover all protruding parts (such as the cab, the base of the excavator arm, etc.). Therefore, verification and adjustment are needed to ensure the completeness and safety of the model in practical applications.

[0057] In one embodiment, such as Figure 3 As shown, when the engineering machinery is a drilling rig, after initially determining the three circles in the multi-circle combination model, verification through 3D simulation or geometric calculation reveals that one corner of the drilling rig's cab may be outside the coverage area of ​​the three circles. In this case, the following adjustments can be made: slightly move the center of the foremost circle closer to the cab, and / or appropriately increase the radius of that circle until the multi-circle combination model can completely encompass the entire outline of the drilling rig.

[0058] This invention uses a combination of multiple circular models to model the irregular shape of construction machinery. The number of circles, n, used for combined modeling can be flexibly adjusted according to the complexity of the construction machinery's shape and the accuracy requirements of the actual operation scenario. For construction machinery with relatively regular shapes, fewer circles can be selected to further reduce the amount of computation; for construction machinery with complex shapes, the number of circles can be increased to improve modeling accuracy. This invention is applicable to various types of construction machinery with different shapes, such as drilling rigs, excavators, and cranes, thereby improving applicability and modeling accuracy.

[0059] The following describes the dynamic obstacle avoidance device based on model combination provided by the present invention. The dynamic obstacle avoidance device based on model combination described below and the dynamic obstacle avoidance method based on model combination described above can be referred to in correspondence.

[0060] Figure 4 This is a schematic diagram of the dynamic obstacle avoidance device based on model combination provided by the present invention, as shown below. Figure 4 As shown. An embodiment of the present invention provides a dynamic obstacle avoidance device based on model combination, comprising an acquisition module 401, a construction module 402, a generation module 403, a filtering module 404, and a control module 405, wherein: The acquisition module 401 is used to acquire the shape parameters and motion parameters of the construction machinery; the shape parameters include the overall width and overall length; the construction module 402 is used to construct a multi-circle combination model based on the shape parameters; the generation module 403 is used to generate multiple initial parameter combinations based on the motion parameters; the filtering module 404 is used to filter the initial combination parameters based on obstacle information and the multi-circle combination model to obtain a target parameter combination; the obstacle information is collected by multiple sensors; the multiple sensors are installed on the construction machinery; the obstacle information includes at least one of the obstacle's position, size, speed, and direction of movement; the control module 405 is used to control the construction machinery to perform obstacle avoidance actions based on the target parameter combination.

[0061] The present invention provides a dynamic obstacle avoidance device based on model combination. This device acquires the shape and motion parameters of an engineering machinery. The shape parameters include the overall width and overall length. Based on these shape parameters, a multi-circle combination model is constructed, simplifying the modeling of the engineering machinery's shape, reducing computational complexity, and improving modeling accuracy. Based on the motion parameters, multiple initial parameter combinations are generated. Based on obstacle information and the multi-circle combination model, the initial combination parameters are filtered to obtain a target parameter combination. The obstacle information is collected by multiple sensors installed on the engineering machinery. The obstacle information includes at least one of the obstacle's position, size, speed, and direction of movement. By filtering the target parameter combination from the initial parameter combinations, the device avoids collision risks caused by omissions in local modeling or computational delays. Based on the target parameter combination, the device controls the engineering machinery to perform obstacle avoidance actions. By driving the actual movement of the engineering machinery according to the target parameter combination, a closed-loop control is formed, timely correcting trajectory deviations, ensuring accurate execution of obstacle avoidance actions, and improving the real-time response and accuracy of the engineering machinery's autonomous obstacle avoidance.

[0062] Figure 5 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 5 As shown, the electronic device may include: a processor 510, a communications interface 520, a memory 530, and a communication bus 540, wherein the processor 510, the communications interface 520, and the memory 530 communicate with each other via the communication bus 540. The processor 510 can call logical instructions in the memory 530 to execute a model-based dynamic obstacle avoidance method, which includes: Obtain the external shape parameters and motion parameters of the construction machinery; the external shape parameters include the overall width and overall length; Based on the aforementioned shape parameters, a multi-circle combination model is constructed; Based on the motion parameters, multiple initial parameter combinations are generated; Based on obstacle information and the multi-circle combination model, the initial combination parameters are filtered to obtain the target parameter combination; the obstacle information is collected by multiple sensors; the multiple sensors are installed on the engineering machinery; the obstacle information includes at least one of the obstacle's position, size, speed, and direction of movement; Based on the target parameter combination, the engineering machinery is controlled to perform obstacle avoidance actions.

[0063] Furthermore, the logical instructions in the aforementioned memory 530 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a 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 several 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 described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0064] On the other hand, the present invention also provides a computer program product, the computer program product comprising a computer program that can be stored on a non-transitory computer-readable storage medium, wherein when the computer program is executed by a processor, the computer is able to execute the dynamic obstacle avoidance method based on model combination provided by the above methods, the method comprising: Obtain the external shape parameters and motion parameters of the construction machinery; the external shape parameters include the overall width and overall length; Based on the aforementioned shape parameters, a multi-circle combination model is constructed; Based on the motion parameters, multiple initial parameter combinations are generated; Based on obstacle information and the multi-circle combination model, the initial combination parameters are filtered to obtain the target parameter combination; the obstacle information is collected by multiple sensors; the multiple sensors are installed on the engineering machinery; the obstacle information includes at least one of the obstacle's position, size, speed, and direction of movement; Based on the target parameter combination, the engineering machinery is controlled to perform obstacle avoidance actions.

[0065] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the model-combination-based dynamic obstacle avoidance method provided by the above methods, the method comprising: Obtain the external shape parameters and motion parameters of the construction machinery; the external shape parameters include the overall width and overall length; Based on the aforementioned shape parameters, a multi-circle combination model is constructed; Based on the motion parameters, multiple initial parameter combinations are generated; Based on obstacle information and the multi-circle combination model, the initial combination parameters are filtered to obtain the target parameter combination; the obstacle information is collected by multiple sensors; the multiple sensors are installed on the engineering machinery; the obstacle information includes at least one of the obstacle's position, size, speed, and direction of movement; Based on the target parameter combination, the engineering machinery is controlled to perform obstacle avoidance actions.

[0066] The device embodiments described above are merely illustrative. The units described 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 modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0067] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0068] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0069] In this invention, the term "and / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0070] In this application's embodiments, "determine B based on A" means that factor A must be considered when determining B. It is not limited to "B can be determined based solely on A," but should also include: "determine B based on A and C," "determine B based on A, C, and E," "determine C based on A, and further determine B based on C," etc. Additionally, it can include using A as a condition for determining B, for example, "when A meets the first condition, determine B using the first method"; another example, "when A meets the second condition, determine B," etc.; another example, "when A meets the third condition, determine B based on the first parameter," etc. Of course, it can also be a condition where A is a factor in determining B, for example, "when A meets the first condition, determine C using the first method, and further determine B based on C," etc.

[0071] It should also be noted that the terms "target," "first," and "second" in this invention are used to distinguish similar objects, not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same class, without limiting the number of objects; for example, the first object can be one or more.

[0072] In this invention, the term "multiple" refers to two or more, and other quantifiers are similar.

[0073] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A dynamic obstacle avoidance method based on model combination, characterized in that, include: Obtain the external shape parameters and motion parameters of the construction machinery; the external shape parameters include the overall width and overall length; Based on the aforementioned shape parameters, a multi-circle combination model is constructed; Based on the motion parameters, multiple initial parameter combinations are generated; Based on obstacle information and the multi-circle combination model, the initial combination parameters are filtered to obtain the target parameter combination; The obstacle information was collected through multiple sensors; The various sensors are installed on the engineering machinery; the obstacle information includes at least one of the obstacle's position, size, speed of movement, and direction of movement. Based on the target parameter combination, the engineering machinery is controlled to perform obstacle avoidance actions.

2. The dynamic obstacle avoidance method based on model combination according to claim 1, characterized in that, The construction of a multi-circle combination model based on the aforementioned shape parameters includes: Based on the overall length, determine the number of combinations of the circles to be combined; The overall length is divided into multiple segments along the direction of the overall length; wherein the length of each segment is the ratio of the overall length to the number of combinations. Construct a multi-circle combination model by taking the center of each segment as the target center of each circle to be combined.

3. The dynamic obstacle avoidance method based on model combination according to claim 2, characterized in that, The formula for calculating the target radius of the circles to be combined is: In the formula, Indicates the target radius. This refers to the overall width. Indicates the overall length. This indicates the number of combinations.

4. The dynamic obstacle avoidance method based on model combination according to claim 3, characterized in that, Before generating multiple initial parameter combinations based on the multi-circle combination model and the motion parameters of the engineering machinery, the method further includes: Boundary verification is performed on the multi-circle combination model. If the multi-circle combination model cannot completely cover the engineering machinery, the size of the target radius and / or the position of the target circle center are adjusted until the multi-circle combination model completely covers the engineering machinery.

5. The dynamic obstacle avoidance method based on model combination according to claim 1, characterized in that, Based on the motion parameters, multiple initial parameter combinations are generated, including: Select any driving speed, any angular velocity, any driving speed increment, and any angular velocity increment respectively; The initial parameter combination is the combination of any driving speed, any angular velocity, any driving speed increment, and any angular velocity increment.

6. The dynamic obstacle avoidance method based on model combination according to claim 1, characterized in that, The process of filtering the initial parameter combinations based on obstacle information and the multi-circle combination model to obtain the target parameter combinations includes: Based on parameters from multiple initial parameter combinations, the multi-circle combination model is controlled to move, resulting in multiple motion trajectories; wherein, each initial parameter combination corresponds one-to-one with each motion trajectory. Based on the obstacle information, the initial parameter combination corresponding to the motion trajectory that collides with the obstacle is removed to obtain the intermediate parameter combination; Based on a preset evaluation function, obstacle avoidance scoring is performed on the intermediate parameter combinations to obtain the obstacle avoidance score corresponding to each intermediate parameter combination. The intermediate parameter combination with the highest obstacle avoidance score is used as the target parameter combination.

7. A dynamic obstacle avoidance device based on model combination, characterized in that, include: The acquisition module is used to acquire the shape parameters and motion parameters of the construction machinery; the shape parameters include the overall width and overall length. A construction module is used to construct a multi-circle combination model based on the aforementioned shape parameters; A generation module is used to generate multiple initial parameter combinations based on the motion parameters; The filtering module is used to filter the initial combination parameters based on obstacle information and the multi-circle combination model to obtain the target parameter combination; The obstacle information was collected through multiple sensors; The various sensors are installed on the engineering machinery; the obstacle information includes at least one of the obstacle's position, size, speed of movement, and direction of movement. The control module is used to control the engineering machinery to perform obstacle avoidance actions based on the target parameter combination.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the dynamic obstacle avoidance method based on model combination as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the dynamic obstacle avoidance method based on model combination as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the dynamic obstacle avoidance method based on model combination as described in any one of claims 1 to 6.

Images