Full-boom obstacle avoidance path planning method, device, operating equipment and storage medium
By detecting dynamic obstacles and updating the speed vector, the tower crane's obstacle avoidance path is optimized, and the problems of low efficiency and poor stability of obstacle avoidance planning in autonomous tower cranes are solved, and the accuracy and motion stability of obstacle avoidance paths are improved.
Patent Information
- Application Number
- CN202410980772.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-22
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-07-22
AI Technical Summary
The prior art has low efficiency in obstacle avoidance planning in autonomous tower cranes, and frequent start and stop of equipment affects movement stability, making it difficult to ensure obstacle avoidance reliability and movement stability.
By detecting dynamic obstacles, obtaining path points and velocity vectors, determining the target collision boundary and collision risk area, updating the speed vector to avoid collision risk areas, optimizing path points, and improving the accuracy and stability of obstacle avoidance paths.
It improves the efficiency and accuracy of obstacle avoidance path planning of the autonomous tower crane, optimizes the stability and safety of the boom movement, and reduces the invalid obstacle avoidance path.
Smart Images

Figure CN118514084B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of engineering equipment, and in particular to a full-boom obstacle avoidance path planning method, device, operating equipment and storage medium. Background Art
[0002] Boom-type operating equipment, such as tower cranes, truck cranes, pump trucks, aerial work machinery, and high-rise jet fire trucks, usually have the requirement of boom obstacle avoidance during operation. Take tower cranes as an example. Tower cranes are the most commonly used lifting equipment on construction sites, used to transport various construction raw materials, such as concrete, steel bars, formwork, and steel pipes. At present, tower cranes are mainly operated by full-time drivers in the high-altitude driver's cab on the tower, which places high requirements on the driver's proficiency and control accuracy. Drivers go up and down the tower every day, with high labor intensity; and high-altitude operations have high safety risks and poor working environment. With the development of autonomous driving technology, combined with actual needs, unmanned tower cranes have been proposed. Unmanned tower cranes can automatically plan paths and automatically control tower cranes to complete automatic lifting operations, freeing up manual labor. During the automatic lifting operation, environmental information is constantly changing, and the tower crane has a probability of encountering dynamic obstacles. Therefore, to achieve automatic driving of tower cranes, it is necessary to solve the problem of dynamic planning of obstacle avoidance during the operation of tower cranes.
[0003] At present, most of the obstacle avoidance planning methods for related lifting equipment are to stop the current movement, wait or go to a certain place to avoid. This method has low execution efficiency, and the frequent start and stop of the equipment will affect the smoothness of movement. In some conventional obstacle avoidance path planning, obstacle avoidance is achieved by correcting the velocity vector of the path point. The velocity vector correction method is usually to directly add a velocity component in a specific direction to the velocity vector to obtain a composite velocity, and generate a new obstacle avoidance path point based on the composite velocity. This method is difficult to ensure the reliability of obstacle avoidance due to the complexity of determining the velocity component, and the method of superimposing the velocity component has a greater impact on the change in the operating speed of the equipment, and it is also difficult to ensure the smoothness of the equipment's movement. Summary of the invention
[0004] In view of the above-mentioned deficiencies in the prior art, an object of the embodiments of the present invention is to provide a full-boom obstacle avoidance path planning method, device, operating equipment and storage medium.
[0005] In order to achieve the above objectives, the first aspect of the present application provides a full-boom obstacle avoidance path planning method, comprising:
[0006] When a dynamic obstacle is detected in the target working area, a first path point of the boom, a first velocity vector corresponding to the first path point, and a second velocity vector of the dynamic obstacle are obtained, wherein the first path point is a path point of the boom in the current motion cycle;
[0007] Determine a target collision boundary of the boom relative to the dynamic obstacle, wherein the target collision boundary uses the first path point as a reference point and the dynamic obstacle is located in the target collision boundary;
[0008] translating the target collision boundary along the second velocity vector, and determining the collision risk area based on the translated target collision boundary;
[0009] When the first velocity vector falls into the collision risk area, updating the first velocity vector until the updated first velocity vector does not fall into the collision risk area;
[0010] Determine a second path point based on the first path point and the updated first velocity vector, the second path point being a path point of the boom in the next motion cycle;
[0011] The determination of the target collision boundary of the boom relative to the dynamic obstacle includes:
[0012] Obtain the size of the dynamic obstacle, the position of the dynamic obstacle, and the size of the preset part of the boom;
[0013] The first radius is determined according to the size of the preset part of the boom, and the second radius is determined according to the size of the dynamic obstacle;
[0014] Determine a circular boundary corresponding to the dynamic obstacle according to the first radius, the second radius and the position of the dynamic obstacle, wherein the circular boundary takes the position of the dynamic obstacle as a circle center, and the radius of the circular boundary is greater than or equal to the sum of the first radius and the second radius;
[0015] The tangent line from the first path point to the circle boundary is used as the target collision boundary.
[0016] In an embodiment of the present application, determining a target collision boundary of the boom relative to a dynamic obstacle includes:
[0017] determining a target dynamic obstacle based on the first velocity vector and the second velocity vector, where the target dynamic obstacle is a dynamic obstacle with a collision risk;
[0018] Determine the target collision boundary of the boom relative to the target dynamic obstacle.
[0019] In an embodiment of the present application, the full boom obstacle avoidance path planning method further includes:
[0020] When no dynamic obstacles are detected in the target operating area, the boom is controlled to move according to a pre-planned first preset motion trajectory, which is a global motion trajectory planned based on a global starting point, a global target point, and environmental information corresponding to the target operating area.
[0021] In the embodiment of the present application, the first preset motion trajectory is obtained by planning through the following steps:
[0022] Determine multiple sub-paths based on the global starting point, the global target point and obstacle information in the environmental information;
[0023] Based on the environmental information of the working area and a preset random sampling algorithm, multiple sub-paths are respectively planned offline to obtain multiple sub-motion trajectories;
[0024] A first preset motion trajectory is determined based on the plurality of sub-motion trajectories.
[0025] In the embodiment of the present application, obtaining a first velocity vector corresponding to a first path point includes:
[0026] Obtain the collision risk points at the end point of the planned path and the target operation area;
[0027] Constructing an attraction vector based on the first path point and the end point of the planned path;
[0028] constructing a repulsion vector based on the first path point and the collision risk point;
[0029] A first velocity vector is determined based on the attraction vector and all repulsion vectors.
[0030] In an embodiment of the present application, the full boom obstacle avoidance path planning method further includes:
[0031] Determine the operation scenario of the target operation area;
[0032] When the working scene is a low obstacle scene, the step of controlling the boom to move according to a pre-planned first preset motion trajectory is performed when no dynamic obstacles in the target working area are detected.
[0033] In an embodiment of the present application, the full boom obstacle avoidance path planning method further includes:
[0034] When the operation scene is a high obstacle scene, the boom is controlled to move based on a second preset motion trajectory;
[0035] During the process of the boom moving based on the second preset motion trajectory, if there is a dynamic obstacle, modifying the remaining path in the second preset motion trajectory based on the position information of the dynamic obstacle;
[0036] Replan the remaining paths based on a preset random sampling algorithm;
[0037] Based on the preset sampling pruning algorithm and path point quadratic fitting algorithm, the remaining path after replanning is smoothed to obtain the obstacle avoidance trajectory.
[0038] In the embodiment of the present application, the step of constructing the second preset motion trajectory includes:
[0039] Determine the global starting point, global target point and environmental information corresponding to the target operation area of the boom;
[0040] Based on the environmental information and a preset random sampling algorithm, global offline planning is performed between the global starting point and the global target point to obtain a second preset motion trajectory.
[0041] A second aspect of the present application provides a full-arm obstacle avoidance path planning device, comprising:
[0042] a memory configured to store instructions; and
[0043] The processor is configured to call instructions from the memory and implement the full-arm obstacle avoidance path planning method as described in the above embodiment when executing the instructions.
[0044] The third aspect of the present application provides an operating device, comprising:
[0045] Boom;
[0046] A full-boom obstacle avoidance path planning device as described in the above embodiment.
[0047] A fourth aspect of the present application provides a machine-readable storage medium having instructions stored thereon, the instructions being used to enable a machine to execute the full-boom obstacle avoidance path planning method as described in the above-mentioned embodiment.
[0048] Through the above technical solution, in this embodiment, when a dynamic obstacle is detected in the target working area, the first path point of the boom, the first velocity vector corresponding to the first path point, and the second velocity vector of the dynamic obstacle are obtained; to determine the target collision boundary of the boom relative to the dynamic obstacle; and the target collision boundary is translated along the second velocity vector, and the collision risk area is determined based on the translated target collision boundary; by determining the collision risk area, an effective data reference is provided for the obstacle avoidance path planning of the whole boom, the invalid obstacle avoidance path planning is reduced, and the efficiency of the obstacle avoidance path planning of the whole boom is improved. In the case where the first velocity vector falls into the collision risk area, the first velocity vector is updated until the updated first velocity vector does not fall into the collision risk area; the second path point is determined based on the first path point and the updated first velocity vector. The first velocity vector corresponding to the path point of the boom is adjusted based on the collision risk area, the accuracy of dynamic obstacle avoidance is improved, the quality of the generation of the obstacle avoidance path of the boom is optimized, and the stability and safety of the boom movement are improved.
[0049] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS
[0050] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:
[0051] Figure 1 A schematic diagram of a process flow of a full-boom obstacle avoidance path planning method according to an embodiment of the present application is shown;
[0052] Figure 2 A schematic diagram of the range of the target collision boundary according to an embodiment of the present application is schematically shown;
[0053] Figure 3 A schematic diagram of the range of a collision risk area according to an embodiment of the present application is schematically shown;
[0054] Figure 4 A schematic diagram of planning a first preset motion trajectory according to an embodiment of the present application is schematically shown;
[0055] Figure 5 A schematic diagram of a vector potential field synthesized by a first velocity vector according to an embodiment of the present application is schematically shown;
[0056] Figure 6 A schematic diagram of planning a second preset motion trajectory according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION
[0057] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.
[0058] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), such directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.
[0059] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.
[0060] Figure 1 The following is a schematic diagram showing a flow chart of a full boom obstacle avoidance path planning method according to an embodiment of the present application. Figure 1 As shown, an embodiment of the present application provides a full-arm obstacle avoidance path planning method, which may include the following steps:
[0061] Step 100, when a dynamic obstacle is detected in the target working area, a first path point of the boom, a first velocity vector corresponding to the first path point, and a second velocity vector of the dynamic obstacle are obtained, wherein the first path point is a path point of the boom in the current motion cycle;
[0062] In the present embodiment, it should be noted that the target operation area refers to the range in which the operation equipment performs operations in actual applications. In actual applications, the operation equipment moves from the starting point to the target point based on the operation requirements, and the target operation area includes the range that the operation equipment passes from the starting point to the target point. In one embodiment, the target operation area can be determined based on the width of the contour of the operation equipment, and the length is determined based on the distance from the starting point to the end point. After the width and length are extended by a certain distance respectively, the target operation area is constructed based on the extended width and the extended length, wherein the certain distance can be adjusted based on the actual application scenario. In the process of the operation equipment moving from the starting point to the target point, it is necessary to determine the movement trajectory of the operation equipment based on the actual operation requirements to achieve accurate operation, and if there are obstacles in the process, it is necessary to control the operation equipment to avoid the obstacles and reduce the risk of collision. In the present embodiment, the operation equipment includes a boom, and the operation equipment controls the boom to move in the target operation area to complete the relevant operations.
[0063] It should be noted that the motion trajectory of the working equipment includes path points associated with multiple motion cycles, and each path point corresponds to a velocity vector, wherein the velocity vector represents the speed and direction of the working equipment along the motion path in the current motion cycle. Generally speaking, the motion trajectory of the boom may include path points associated with multiple motion cycles. In this embodiment, the first path point is the path point of the boom in the current motion cycle, and the first path point corresponds to the first velocity vector.
[0064] It is understandable that before the boom movement starts, in order to improve the continuity and efficiency of the boom movement control, the boom is controlled to move according to the pre-planned path by pre-planning the boom's movement path. The pre-planned trajectory is constructed based on the environmental information corresponding to the moment before the boom movement starts. Therefore, in the motion trajectory obtained by the trajectory planning, only the obstacles included in the moment before the start can be effectively avoided, and dynamic obstacles that may appear and change their positions in real time during the boom movement cannot be accurately avoided. In this embodiment, when a dynamic obstacle is detected in the target working area, an effective data basis is provided for the subsequent avoidance planning of the dynamic obstacle by obtaining the first path point of the boom, the first velocity vector corresponding to the first path point, and the second velocity vector of the dynamic obstacle.
[0065] Step 200, determining a target collision boundary of the boom relative to the dynamic obstacle, wherein the target collision boundary uses the first path point as a reference point, and the dynamic obstacle is located in the target collision boundary;
[0066] In this embodiment, it should be noted that the target collision boundary refers to the range in which the dynamic obstacle may affect the movement of the boom in the current motion cycle. By determining the target collision boundary of the boom compared to the dynamic obstacle, the range in which the boom and the dynamic obstacle may collide in the current motion cycle can be obtained. The first path point is the path point of the boom in the current motion cycle. The target collision boundary uses the first path point as a reference point to define the boundary toward the location of the dynamic obstacle, and encloses the dynamic obstacle within the defined boundary to generate a target collision boundary.
[0067] Specifically, in one embodiment, step 200, determining a target collision boundary of the boom relative to the dynamic obstacle, includes:
[0068] Obtain the size of the dynamic obstacle, the position of the dynamic obstacle, and the size of the preset part of the boom;
[0069] The first radius is determined according to the size of the preset part of the boom, and the second radius is determined according to the size of the dynamic obstacle;
[0070] Determine a circular boundary corresponding to the dynamic obstacle according to the first radius, the second radius and the position of the dynamic obstacle, wherein the circular boundary takes the position of the dynamic obstacle as a circle center, and the radius of the circular boundary is greater than or equal to the sum of the first radius and the second radius;
[0071] The tangent line from the first path point to the circle boundary is used as the target collision boundary.
[0072] It should be noted that different sizes of dynamic obstacles or different positions of dynamic obstacles will have different effects on the movement of the boom. For example, the larger the size of the dynamic obstacle or the closer it is to the boom, the higher the risk of collision between the boom and the dynamic obstacle. Therefore, in this embodiment, the accuracy of the target collision boundary determination is achieved by obtaining the size of the dynamic obstacle and the position of the dynamic obstacle. The size of the dynamic obstacle may include information such as the length, style, height and shape of the dynamic obstacle. The size of the dynamic obstacle and the position of the dynamic obstacle can be obtained by installing perception sensors such as laser radar, millimeter wave radar, ultrasonic sensor or camera on the operating equipment to obtain environmental information. The perception sensor collects environmental data in real time and generates data such as point cloud, image or radar signal. These data include information such as the position, shape, speed, etc. of the dynamic obstacle.
[0073] After determining the size and position of the dynamic obstacle, an influence boundary of the dynamic obstacle can be determined based on the size and position of the dynamic obstacle, and the first path point is used as a reference point to define the target collision boundary toward the influence boundary to improve the accuracy of the target collision boundary definition.
[0074] It should be noted that the preset part of the boom refers to the part of the boom that may collide with a dynamic obstacle. For example, during the movement of the boom, it is mainly the end effector or the working device that performs related operations, and the end effector or the working device of the boom is a high-risk component that collides with a dynamic obstacle. For example, the hook or load of a crane, the working platform of an aerial work machinery, the fire cannon of a high-rise fire truck and other components. It is understandable that the sizes of different preset parts of the boom will also bring different collision risks. For example, if the preset part is larger in size and occupies a larger space, the risk of collision with a dynamic obstacle is higher. In this embodiment, by obtaining the size of the preset part of the boom and considering the possible impact of the preset part of the boom itself on the collision, a target collision boundary is constructed to improve the accuracy and practicality of determining the target collision boundary.
[0075] Specifically, the first radius is determined according to the size of the preset part of the boom, the second radius is determined according to the size of the dynamic obstacle, and the circular boundary is determined with the position of the dynamic obstacle as the center and the sum of the first radius and the second radius as the radius. It can be understood that, in one embodiment, the radius of the circular boundary can also be greater than the sum of the first radius and the second radius. For example, the sum of the first radius and the second radius plus a preset threshold value is added to determine the radius of the circular boundary. The tangent from the first path point to the circular boundary is used as the target collision boundary. Reference Figure 2Assuming that the first radius is r and the second radius is R, the circular boundary is determined with the position of the dynamic obstacle A as the center and R+r as the radius. Tangents l1 and l2 are drawn to the circular boundary based on the first path point. The part between the tangents l1 and l2 is the target collision boundary.
[0076] Of course, in other embodiments, the size of the dynamic obstacle can be determined according to a cubic bounding box, which can be divided into the distance corresponding to the second radius of expansion in the length, width and height directions of the bounding box to obtain an expanded bounding box, and then the target collision boundary is determined in combination with the first path point and the expanded bounding box, and the expanded bounding box is located between the target collision boundaries.
[0077] In this embodiment, by comprehensively considering the size of the preset part of the boom, the size of the dynamic obstacle, and the possible collision impact caused by the position of the dynamic obstacle, the target collision boundary is determined, the effectiveness of the target collision boundary determination is improved, and an effective data reference is provided for the subsequent calculation of the obstacle avoidance path of the boom, so as to improve the efficiency and accuracy of obstacle avoidance path planning.
[0078] Further, in one embodiment, determining a target collision boundary of the boom relative to the dynamic obstacle includes:
[0079] determining a target dynamic obstacle based on the first velocity vector and the second velocity vector, where the target dynamic obstacle is a dynamic obstacle with a collision risk;
[0080] Determine the target collision boundary of the boom relative to the target dynamic obstacle.
[0081] It should be noted that during the movement of the arm, multiple dynamic obstacles may be detected, but not every dynamic obstacle poses a risk of collision with the arm. Therefore, in this embodiment, in order to improve the accuracy of avoiding dynamic obstacles and reduce invalid obstacle avoidance behaviors, all detected dynamic obstacles are screened, and dynamic obstacles with a collision risk are determined as target dynamic obstacles, so as to further determine the target collision boundary of the arm relative to the target dynamic obstacle.
[0082] Specifically, for each dynamic obstacle, by obtaining the first velocity vector corresponding to the first path point of the boom and the second velocity vector corresponding to the dynamic obstacle, the relative velocity vector between the first velocity vector and the second velocity vector is calculated. The first radius is determined according to the size of the preset part of the boom, the second radius is determined according to the size of the dynamic obstacle, and the circular boundary is determined with the position of the dynamic obstacle as the center and the sum of the first radius and the second radius as the radius. The tangent from the first path point to the circular boundary is used as the collision boundary. It is determined whether the relative velocity vector falls within the collision boundary. If the relative velocity vector falls within the collision boundary, the current dynamic obstacle is determined to be the target dynamic obstacle; if the relative velocity vector does not fall within the collision boundary, the current dynamic obstacle is determined not to be the target dynamic obstacle.
[0083] Please continue to refer to Figure 2 Assuming the first radius is r and the second radius is R, the circular boundary is determined with the position of the dynamic obstacle as the center and R+r as the radius. Tangent lines l1 and l2 are drawn to the circular boundary based on the first path point. The first velocity vector is V t , the second velocity vector is V obs , the relative velocity vector is V t -V obs , relative velocity vector V t -V obs The part that falls between the tangent lines l1 and l2 is the relative velocity vector V t -V obs Falls into the collision boundary, therefore, it can be determined that the dynamic obstacle is the target dynamic obstacle.
[0084] In this embodiment, by screening the target dynamic obstacles, invalid obstacle avoidance behaviors are reduced and the accuracy of the boom in avoiding dynamic obstacles is improved.
[0085] Step 300, translating the target collision boundary along the second velocity vector, and determining the collision risk area based on the translated target collision boundary;
[0086] It should be noted that the target collision boundary refers to the range in which the dynamic obstacle may affect the movement of the boom in the current motion cycle. In order to achieve effective avoidance of dynamic obstacles, it is necessary to determine the area in the next motion cycle where the dynamic obstacle may cause a collision risk to the boom movement, so that the motion trajectory of the boom can be planned in advance to achieve avoidance of the collision risk area. It can be understood that the second velocity vector corresponding to the dynamic obstacle can characterize the speed and direction of the dynamic obstacle along its motion path at a certain moment. By translating the target collision boundary determined in the current motion cycle along the second velocity vector, the collision risk area where the dynamic obstacle may collide with the boom in the next motion cycle can be obtained.
[0087] In this embodiment, the arm path point is corrected based on a graphical method. After determining the target collision boundary, the target collision boundary is translated based on the second velocity vector of the dynamic obstacle to obtain a collision risk area. By translating the determined target collision boundary based on the second velocity vector, the influence of the second velocity vector of the dynamic obstacle is merged into the collision risk area. That is, when determining whether there is a collision risk in the operation of the arm, there is no need to integrate the influence of other factors such as the second velocity vector of the dynamic obstacle. It can be judged only based on the first velocity vector corresponding to the arm path point. When the first velocity vector falls into the collision risk area, it can be directly determined that there is a collision risk between the arm and the dynamic obstacle. The decoupling of the mutual influence between the first velocity vector of the arm itself and the second velocity vector of the dynamic obstacle in the collision risk judgment is realized. The computational complexity of the collision risk judgment is reduced, the influencing factors of the collision risk judgment are simplified, and the judgment efficiency is improved. Furthermore, in the case of determining that there is a collision risk, the embodiment only needs to adjust the first velocity vector corresponding to the arm, and other factors such as the velocity vector of the dynamic obstacle do not need to be considered during the adjustment, and the adjustment process is simple and fast. And by translating the target collision boundary based on the second velocity vector of the dynamic obstacle, the collision risk area itself has combined all other collision influencing factors except the first velocity vector corresponding to the boom. By adjusting the first velocity vector, it can be ensured that the boom can achieve effective obstacle avoidance behavior.
[0088] Step 400, when the first velocity vector falls into the collision risk area, updating the first velocity vector until the updated first velocity vector does not fall into the collision risk area;
[0089] It should be noted that when the first velocity vector corresponding to the first path point of the boom falls into the collision risk area, it can be said that the boom is very likely to collide with the dynamic obstacle in the next motion cycle. Figure 3 , translate the target collision boundary based on the second velocity vector Vobs to V obs ' is the translation reference. After translation, the collision risk area formed by the part sandwiched by l1' and l2' is obtained. The first velocity vector V t It falls into the collision risk area. Therefore, if the boom still moves based on the first velocity vector at the path point of the next motion cycle, it is very likely to collide with a dynamic obstacle.
[0090] In this embodiment, when the first velocity vector falls into the collision risk area, the first velocity vector is updated until the updated first velocity vector does not fall into the collision risk area. Specifically, the first velocity vector may be updated by changing the direction or magnitude of the first velocity vector so that the first velocity vector is updated in a minimal cost updating manner until the updated first velocity vector does not fall into the collision risk area.
[0091] Step 500, determining a second path point based on the first path point and the updated first velocity vector, the second path point being the path point of the boom in the next motion cycle.
[0092] It should be noted that after the first velocity vector is updated, the first path point is used as the starting point, and the second path point is obtained based on the updated first velocity vector movement, wherein the second path point is the path point of the boom in the next movement cycle. For each movement cycle of the boom operation, it is cyclically detected whether there are dynamic obstacles in the target operation area, so as to achieve effective obstacle avoidance for the entire movement path of the boom.
[0093] In this embodiment, when a dynamic obstacle is detected in the target working area, the first path point of the boom, the first velocity vector corresponding to the first path point, and the second velocity vector of the dynamic obstacle are obtained; to determine the target collision boundary of the boom relative to the dynamic obstacle; and the target collision boundary is translated along the second velocity vector, and the collision risk area is determined based on the translated target collision boundary; by determining the collision risk area, an effective data reference is provided for the obstacle avoidance path planning of the entire boom, and invalid obstacle avoidance path planning is reduced, thereby improving the efficiency of the obstacle avoidance path planning of the entire boom. In the case where the first velocity vector falls into the collision risk area, the first velocity vector is updated until the updated first velocity vector does not fall into the collision risk area; the second path point is determined based on the first path point and the updated first velocity vector. The first velocity vector corresponding to the path point of the boom is adjusted based on the collision risk area, the accuracy of dynamic obstacle avoidance is improved, the quality of the generation of the obstacle avoidance path of the boom is optimized, and the smoothness and efficiency of the boom movement are improved.
[0094] In one embodiment, the full boom obstacle avoidance path planning method further includes:
[0095] When no dynamic obstacles are detected in the target operating area, the boom is controlled to move according to a pre-planned first preset motion trajectory, which is a global motion trajectory planned based on a global starting point, a global target point, and environmental information corresponding to the target operating area.
[0096] In this embodiment, it should be noted that before the boom starts to move, in order to improve the continuity and efficiency of the boom movement control, the boom is controlled to move according to the pre-planned path by planning the movement path of the boom in advance. The path corresponding to the pre-planned trajectory is the first preset motion trajectory. That is, when no dynamic obstacles are detected in the target working area, the boom will be controlled to move according to the pre-planned first preset motion trajectory.
[0097] It should be noted that when the boom is moving, based on the preset operation requirements, the starting point and end point of the boom when performing the operation can be determined, wherein the starting point in the operation requirements is the global starting point, and the end point is the global target point. The environmental information corresponding to the target operation area where the boom is located is obtained by three-dimensional panoramic scanning, and path planning is performed based on the global starting point, the global target point, and the environmental information corresponding to the target operation area to obtain the first preset motion trajectory. Among them, the path planning method can be to use a traditional path planning algorithm, such as the Dijkstra algorithm, the A* algorithm, etc.; it can also be a sampling-based path planning algorithm, such as the PRM algorithm (Probabilistic Roadmap), the RRT algorithm (Rapidly-Exploring Random Trees), etc.
[0098] Specifically, in one embodiment, the first preset motion trajectory is obtained by planning through the following steps:
[0099] Determine multiple sub-paths based on the global starting point, the global target point and obstacle information in the environmental information;
[0100] Based on the environmental information of the working area and a preset random sampling algorithm, multiple sub-paths are respectively planned offline to obtain multiple sub-motion trajectories;
[0101] A first preset motion trajectory is determined based on the plurality of sub-motion trajectories.
[0102] In this embodiment, it should be noted that for the planning of the first preset motion trajectory, a segmented offline planning method is adopted. The segmented offline planning method can be to divide the global motion trajectory into multiple sub-paths and perform offline planning respectively to obtain multiple sub-path trajectories, and then splice the multiple sub-motion trajectories to obtain the first preset motion trajectory. For example, refer to Figure 4Taking the motion trajectory planning of the end effector of the tower crane when the tower crane performs the lifting transportation as an example, assuming that it is divided into three stages, the motion trajectory planning is carried out respectively based on the lifting trajectory S1 of the tower crane's hook from the global starting point start, the moving trajectory S2 of the hook above the global target point end, and the lowering trajectory S3 of the hook. It can be understood that based on the differences in the global starting point, the global target point, and the obstacle information in the environmental information, the number of sub-paths and the length division of each sub-path can be different.
[0103] In this embodiment, the first preset motion trajectory is determined by utilizing segmented trajectory planning to achieve crossing over multiple obstacles, realize a preliminary obstacle avoidance function, and enhance the effectiveness of the first preset motion trajectory.
[0104] In one embodiment, obtaining a first velocity vector corresponding to a first path point includes:
[0105] Obtain the collision risk points at the end point of the planned path and the target operation area;
[0106] Constructing an attraction vector based on the first path point and the end point of the planned path;
[0107] constructing a repulsion vector based on the first path point and the collision risk point;
[0108] A first velocity vector is determined based on the attraction vector and all repulsion vectors.
[0109] In this embodiment, it should be noted that during the movement of the boom, based on the first preset motion trajectory, it moves from the global starting point to the global target point. When the first preset motion trajectory is long and there are fewer dynamic obstacles, or the dynamic obstacles have little impact on the global first preset motion trajectory, if the first preset motion trajectory is re-planned directly based on the dynamic obstacles that appear, although the dynamic obstacles can be avoided, the calculation of re-executing the global planning is complex and the solution efficiency is low. The method of simply adopting local path planning is very easy to fall into the local optimum and fail to find a feasible solution. Therefore, in this implementation, the planning of the boom obstacle avoidance path is carried out by combining global planning and local planning.
[0110] Specifically, before the boom moves, global trajectory planning is performed in advance by obtaining global information to obtain a first preset motion trajectory. The first preset motion trajectory adopts an offline planning method, and the planning can be completed before the boom officially moves. The boom does not need real-time planning during the actual movement process, thereby improving the stability of the boom movement. Since the first preset motion trajectory is planned based on the environmental information before the boom moves, the first preset motion trajectory cannot accurately avoid dynamic obstacles. In this embodiment, if a dynamic obstacle is detected in the target operating area of the boom movement, a part of the planned path will be determined from the overall first preset motion trajectory based on the position information of the detected dynamic obstacle. The planned path is partially modified to avoid dynamic obstacles. Among them, the method of determining a part of the planned path can be based on the position of one or more obstacles detected, determining the starting point and end point in the first preset motion trajectory that need to be partially modified, and based on the starting point according to the preset motion cycle, the real-time planning of the path between the starting point and the end point is realized.
[0111] In this embodiment, the movement of the boom is controlled based on a first preset motion trajectory. During the movement of the boom, if there is a dynamic obstacle, the path range that needs to be partially modified is determined based on the position of the dynamic obstacle, and the first path point of the boom, the first velocity vector corresponding to the first path point, and the second velocity vector of the dynamic obstacle are obtained based on the starting position in the path range, where the first path point is the path point of the boom in the current motion cycle; a target collision boundary of the boom relative to the dynamic obstacle is determined, wherein the target collision boundary takes the first path point as a reference point, and the dynamic obstacle is located in the target collision boundary; the target collision boundary is translated along the second velocity vector, and a collision risk area is determined based on the translated target collision boundary; when the first velocity vector falls into the collision risk area, the first velocity vector is updated until the updated first velocity vector does not fall into the collision risk area; a second path point is determined based on the first path point and the updated first velocity vector, where the second path point is the path point of the boom in the next motion cycle, until all the path points in the path range that needs to be partially modified are planned.
[0112] It should be noted that the end point of the planned path may refer to the end point of the path range that needs to be locally modified or the global end point; the collision risk point in the target working area refers to the position where a collision with a dynamic obstacle may occur. Taking the tower crane as an example, it may include the positions of the suspension rope, boom, tower body and balance arm. In this embodiment, the first velocity vector corresponding to the first path point is determined by constructing a vector potential field model. Specifically, an attraction vector is constructed based on the first path point and the end point of the planned path; a repulsion vector is constructed based on the first path point and the collision risk point; the attraction vector and all repulsion vectors are vector synthesized to obtain the first velocity vector. Reference Figure 5, taking the tower crane as an example, establish the attraction vector V att , the direction is from the crane end execution point curr to the planned path end goal; based on the closest point on the dynamic obstacle and the closest point on the tower body, a repulsion vector V is established rep1 ; Establish a repulsion vector V based on the closest point on the dynamic obstacle and the closest point on the balance arm rep2 ; Establish a repulsion vector V based on the closest point on the dynamic obstacle and the closest point on the rope rep3 ; Establish a repulsion vector V based on the closest point on the dynamic obstacle and the closest point on the boom rep4 If there are multiple dynamic obstacles, the total repulsion vector V on the dynamic obstacles 2~n is established based on the positions of the multiple dynamic obstacles. rep2总 ~V repn总 After solving the repulsion vectors of all dynamic obstacles and each boom of the tower crane, according to the kinematic model of the tower crane, each vector is mapped to the joint space of the tower crane for vector synthesis to obtain the first velocity vector. The following calculation formula can be used:
[0113] V f = V att + V rep
[0114] Among them, V f represents the first velocity vector;
[0115] V rep = V rep1总 + V rep2总 + … + V repn总 ;
[0116] V rep1总 =V rep1 +V rep2 +V rep3 +V rep4 .
[0117] In this embodiment, the first velocity vector is determined by vector synthesis, and the influence of all collision risk points in the target operation area is comprehensively considered to improve the accuracy and effectiveness of collision risk judgment.
[0118] In one embodiment, the full boom obstacle avoidance path planning method further includes:
[0119] Determine the operation scenario of the target operation area;
[0120] When the working scene is a low obstacle scene, the step of controlling the boom to move according to a pre-planned first preset motion trajectory is performed when no dynamic obstacles in the target working area are detected.
[0121] In this embodiment, the division of the operation scene is realized according to the height of all obstacles in the target operation area. And there are different motion trajectory planning methods for different operation scenes. Specifically, the operation scene includes a low obstacle scene and a high obstacle scene. An overall height is determined for the height of all obstacles in the target operation area, and the overall height is compared with a preset height threshold. When the overall height is less than the height threshold, the operation scene is determined to be a low obstacle scene, and the operation equipment moves with the preset motion trajectory corresponding to the low obstacle scene; when the overall height is greater than the height threshold, the operation scene is determined to be a high obstacle scene, and the operation equipment moves with the preset motion trajectory corresponding to the high obstacle scene; when the overall height is equal to the height threshold, the operation equipment can move with the preset motion trajectory corresponding to the low obstacle scene, or with the preset trajectory corresponding to the high obstacle scene. It should be noted that the determination of the overall height can be determined by averaging the heights of all obstacles in the target operation area or taking the median. It can be understood that in one embodiment, the division of the operation scene can be more or less, for example, multiple height thresholds can be set, and the calculated overall height can be compared with different height thresholds respectively to achieve the division of multiple different operation scenes. In one embodiment, the work scene may also be divided based on the width of the obstacle and a preset width threshold. This division method is similar to the division method based on height and will not be described in detail here.
[0122] It should be noted that for low-obstacle scenarios, the first preset motion trajectory is determined through segmented path planning, and the operating equipment is controlled to move based on the first preset motion trajectory to complete the operation from the global starting point to the global target point, so as to achieve simple and efficient avoidance of most obstacles.
[0123] For high obstacle scenarios, the obstacles are relatively high. If segmented planning is used again, it will take a lot of time to lift and lower the lifting joint, affecting the overall efficiency. Therefore, in high obstacle scenarios, offline planning is performed directly from the global starting point corresponding to the boom to the global target point, and a second preset motion trajectory is generated. The operating equipment is controlled to move based on the second preset motion trajectory to complete the operation from the global starting point to the global target point.
[0124] Specifically, in one embodiment, the step of constructing the second preset motion trajectory includes:
[0125] Determine the global starting point, global target point and environmental information corresponding to the target operation area of the boom;
[0126] Based on the environmental information and a preset random sampling algorithm, global offline planning is performed between the global starting point and the global target point to obtain a second preset motion trajectory.
[0127] In this embodiment, it should be noted that the environmental information corresponding to the target operating area includes obstacle information of the target operating area, such as obstacle size, obstacle position, distance between the obstacle and the boom, etc. The environmental information refers to the environmental information corresponding to the target operating area before the boom starts to move. In this embodiment, for high obstacle scenes, offline planning is performed based on the environmental information before the boom moves to ensure the continuity and efficiency of the control of the second preset motion trajectory.
[0128] Specifically, based on the operation requirements of the boom, the global starting point and the global target point corresponding to the boom during operation are determined, and the motion trajectory between the global starting point and the global target point is globally offline planned based on the above environmental information through a preset random sampling algorithm to obtain a second preset motion trajectory. It can be understood that, with reference to Figure 6 When planning the second preset motion trajectory, considering the avoidance of obstacles and the overall efficiency of the operating equipment, a global overall planning method is adopted from directly planning from the global starting point start to the global target point end. It should be noted that the preset random sampling algorithm can adopt the PRM algorithm (Probabilistic Roadmap), RRT algorithm (Rapidly-Exploring Random Trees), RRT-Connect algorithm, RRT* algorithm, etc.
[0129] In this embodiment, the second preset motion trajectory is determined by utilizing global overall planning to avoid obstacles at high heights, thereby improving the effectiveness of the second preset motion trajectory.
[0130] In one embodiment, the full boom obstacle avoidance path planning method further includes:
[0131] When the operation scene is a high obstacle scene, the boom is controlled to move based on a second preset motion trajectory;
[0132] During the process of the boom moving based on the second preset motion trajectory, if there is a dynamic obstacle, modifying the remaining path in the second preset motion trajectory based on the position information of the dynamic obstacle;
[0133] Replan the remaining paths based on a preset random sampling algorithm;
[0134] Based on the preset sampling pruning algorithm and path point quadratic fitting algorithm, the remaining path after replanning is smoothed to obtain the obstacle avoidance trajectory.
[0135] In this embodiment, it should be noted that in a high obstacle scenario, the second preset motion trajectory is directly planned from the global starting point to the global target point. In the process of the boom moving based on the second preset motion trajectory, there may be a risk of colliding with various dynamic obstacles in the target operating area. Therefore, it is necessary to accurately explore the environmental information and locate the position information of the dynamic obstacles to generate the optimal obstacle avoidance path. Specifically, the dynamic obstacle closest to the current boom is determined based on the position information of all dynamic obstacles, and the path point with a collision risk in the second preset motion trajectory is determined based on the nearest dynamic obstacle. The path point with a collision risk is used as the starting point, and the end point of the second preset motion trajectory is used as the target point to obtain the remaining path in the second preset motion trajectory. The remaining path in the second preset motion trajectory is replanned to generate an obstacle avoidance trajectory that avoids all dynamic obstacles. Then, the movement of the operating equipment is controlled based on the obstacle avoidance trajectory to reduce the collision risk of the boom.
[0136] It should be noted that the preset random sampling algorithm can adopt the PRM algorithm (Probabilistic Roadmap), RRT algorithm (Rapidly-Exploring Random Trees), RRT-Connect algorithm, RRT* algorithm, etc. The preset sampling and pruning algorithm is a method of selecting a part of the parameters or connections from the original model for retention through random or importance-based sampling, and pruning the other parts. This method can reduce the redundancy of the model and improve the efficiency of the model. In this embodiment, the preset sampling and pruning algorithm can be used to exclude those path branches that are obviously unlikely to become the optimal solution, thereby improving the efficiency of path planning. Furthermore, the path points processed by the sampling and pruning algorithm are quadratically fitted using cubic Hermite splines. The Hermite spline curve has the advantages of continuity and smoothness, which can make the curvature of the planned path continuous, and the construction calculation amount is small, which can meet the real-time requirements.
[0137] In this embodiment, the dynamic obstacles are avoided by replanning the remaining path in the high obstacle scene, thereby reducing the collision risk of the boom in the high obstacle scene and improving the stability of the boom movement.
[0138] In one embodiment, the obstacle avoidance path planning method further includes:
[0139] When determining the obstacle avoidance trajectory generated in the high obstacle scenario or the local path planned in real time in the low obstacle scenario in the above embodiments, the obstacle avoidance trajectory or local path is roughly interpolated based on the preset kinematic acceleration and deceleration algorithm. It should be noted that the kinematic acceleration and deceleration algorithm is one of the key technologies in motion control, which is used to achieve a smooth and stable acceleration and deceleration process. The preset kinematic acceleration and deceleration algorithm may include a trapezoidal acceleration and deceleration algorithm, an S-shaped acceleration and deceleration algorithm, an exponential curve acceleration and deceleration algorithm, a parabolic curve acceleration and deceleration algorithm, and the like. The preset kinematic acceleration and deceleration algorithm can be comprehensively considered according to the specific application scenarios and requirements.
[0140] Based on the obstacle avoidance trajectory after rough interpolation or the modified planned path and the inverse kinematics algorithm, the trajectory points of each joint of the arm are determined; based on the preset high-order polynomial algorithm, the trajectory points of each joint are finely interpolated to obtain the executable trajectory of each joint.
[0141] It should be noted that the inverse kinematics algorithm can be used to solve the angle values of each joint that can reach a given position and posture when the position and posture of the end effector are known. The obstacle avoidance trajectory after rough interpolation or the modified planned path is solved based on the inverse kinematics algorithm to determine the trajectory points of each joint of the arm, and the trajectory points of each joint of the arm include information such as the rotation angle and motion acceleration of the joint. In this embodiment, a high-order polynomial is constructed to approximate or interpolate the given path points to generate an executable trajectory that is smooth and meets specific constraints. The high-order polynomial can more accurately approximate or interpolate the given path points, and the executable trajectory of each joint generated is smoother in terms of position, speed, acceleration, etc., which is conducive to reducing mechanical vibration and wear. And by adjusting the order of the polynomial and the constraints, a motion trajectory that meets different needs can be flexibly generated.
[0142] In this embodiment, the obstacle avoidance trajectory is smoothed to optimize the kinematic curves of each joint, ensure the continuity of the velocity and acceleration curves of each joint of the boom, and improve the stability of the boom movement.
[0143] The present application also provides a full-arm obstacle avoidance path planning device, comprising:
[0144] a memory configured to store instructions; and
[0145] The processor is configured to call instructions from the memory and implement the full-arm obstacle avoidance path planning method as described in the above embodiment when executing the instructions.
[0146] The present application also provides an operating device, including:
[0147] Boom;
[0148] A full-boom obstacle avoidance path planning device as described in the above embodiment.
[0149] In some embodiments, the operating equipment may be a tower crane, a truck crane, a truck-mounted crane, an aerial work vehicle, a pump truck or other engineering machinery with a boom, or it may be a high-rise jet fire truck, agricultural machinery with a boom, or an operating robot, etc.
[0150] An embodiment of the present application also provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to enable a machine to execute the above-mentioned full-arm obstacle avoidance path planning method.
[0151] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
[0152] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0153] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0154] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0155] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0156] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0157] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0158] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0159] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.
Claims
1. A full-arm obstacle avoidance path planning method, characterized in that: include: Determine the operation scenario of the target operation area; If the operation scene is a low obstacle scene, when a dynamic obstacle is detected in the target operation area, a first path point of the boom, a first velocity vector corresponding to the first path point, and a second velocity vector of the dynamic obstacle are obtained, wherein the first path point is a path point of the boom in the current motion cycle; Determining a target collision boundary of the boom relative to the dynamic obstacle, wherein the target collision boundary uses the first path point as a reference point and the dynamic obstacle is located in the target collision boundary; translating the target collision boundary along the second velocity vector, and determining a collision risk area based on the translated target collision boundary; When the first velocity vector falls into the collision risk area, updating the first velocity vector until the updated first velocity vector does not fall into the collision risk area; Determine a second path point based on the first path point and the updated first velocity vector, the second path point being a path point of the boom in the next motion cycle; Wherein, determining a target collision boundary of the boom relative to the dynamic obstacle comprises: Acquire the size of the dynamic obstacle, the position of the dynamic obstacle, and the size of the preset part of the boom; Determine a first radius according to the size of a preset portion of the boom, and determine a second radius according to the size of the dynamic obstacle; Determine a circular boundary corresponding to the dynamic obstacle according to the first radius, the second radius, and the position of the dynamic obstacle, wherein the circular boundary takes the position of the dynamic obstacle as a center, and the radius of the circular boundary is greater than or equal to the sum of the first radius and the second radius; Using the tangent line from the first path point to the circular boundary as the target collision boundary; When the operation scene is a high obstacle scene, controlling the boom to move based on a second preset motion trajectory; During the movement of the boom based on the second preset motion trajectory, if there is a dynamic obstacle, modifying the remaining path in the second preset motion trajectory based on the position information of the dynamic obstacle; Replanning the remaining path based on a preset random sampling algorithm; Based on the preset sampling pruning algorithm and path point quadratic fitting algorithm, the remaining path after replanning is smoothed to obtain the obstacle avoidance trajectory.
2. The full boom obstacle avoidance path planning method according to claim 1, characterized in that: The determining a target collision boundary of the boom relative to the dynamic obstacle comprises: determining a target dynamic obstacle based on the first velocity vector and the second velocity vector, wherein the target dynamic obstacle is a dynamic obstacle with a collision risk; A target collision boundary of the boom relative to the target dynamic obstacle is determined.
3. The full boom obstacle avoidance path planning method according to claim 1, characterized in that: The full boom obstacle avoidance path planning method further includes: When no dynamic obstacles are detected in the target working area, the boom is controlled to move according to a pre-planned first preset motion trajectory, where the first preset motion trajectory is a global motion trajectory planned based on a global starting point, a global target point and environmental information corresponding to the target working area.
4. The full boom obstacle avoidance path planning method according to claim 3, characterized in that: The first preset motion trajectory is obtained by planning through the following steps: Determine a plurality of sub-paths based on the global starting point, the global target point, and obstacle information in the environmental information; Based on the environmental information of the target operation area and a preset random sampling algorithm, offline path planning is performed on the multiple sub-paths to obtain multiple sub-motion trajectories; A first preset motion trajectory is determined based on the plurality of sub-motion trajectories.
5. The full boom obstacle avoidance path planning method according to claim 1, characterized in that: The obtaining a first velocity vector corresponding to the first path point includes: Obtaining a collision risk point between an end point of a planned path and the target operation area; Constructing an attraction vector based on the first path point and the end point of the planned path; constructing a repulsion vector based on the first path point and the collision risk point; A first velocity vector is determined based on the attraction vector and all repulsion vectors.
6. The full boom obstacle avoidance path planning method according to claim 1, characterized in that: The step of constructing the second preset motion trajectory includes: Determine the global starting point, the global target point and the environmental information corresponding to the target operation area corresponding to the boom; Based on the environmental information and a preset random sampling algorithm, global offline planning is performed between the global starting point and the global target point to obtain a second preset motion trajectory.
7. A full-arm obstacle avoidance path planning device, characterized in that: include: a memory configured to store instructions; as well as A processor is configured to call the instructions from the memory and to implement the full-boom obstacle avoidance path planning method according to any one of claims 1 to 6 when executing the instructions.
8. An operating device, characterized in that: include: Boom; The full-boom obstacle avoidance path planning device according to claim 7.
9. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores instructions for enabling a machine to execute the full-boom obstacle avoidance path planning method according to any one of claims 1 to 6.
