Path planning method, device, equipment and storage medium

Abstract

The disclosed embodiments relate to a path planning method, device, equipment and storage medium. The method comprises: using a deterministic annealing algorithm and a synthetic potential field of an improved artificial potential field method to determine the minimum potential energy posture in a motion environment; introducing temperature variables and cooling factors into the gravitational potential field and the repulsive potential field of the improved artificial potential field method; determining the initial posture as the current motion posture, and determining its current combined potential energy through the synthetic potential field; determining each candidate motion posture and its candidate combined potential energy except the minimum potential energy posture contained in the neighborhood of the current motion posture; if the minimum candidate combined potential energy is less than or equal to the current combined potential energy, then taking the candidate motion posture corresponding to the minimum candidate combined potential energy as the next motion posture, and using it to update the current motion posture, so as to cyclically determine the steps of the next motion posture until the target posture, and forming a motion path. In this way, the planning efficiency and surgical efficiency of a collision-free safe path are improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of path planning, and in particular to a path planning method, device, equipment and storage medium. Background Art

[0002] With the development of robotics technology, robots are widely used in surgical operations (such as joint replacement surgery) to improve the accuracy and safety of surgery while reducing surgical risks and the possibility of complications. When using medical surgical robots for surgical operations, extremely high requirements are placed on the safety of the robots. For example, in joint replacement surgery, before bone grinding, the robotic arm must reach the specified position in advance. If the robotic arm is not collided from the current position to the target position, the robotic arm may collide with the reference frame or the patient's leg, causing a medical accident.

[0003] The currently used joint replacement surgery robots usually use the method of manually dragging the robot arm to the above-mentioned designated position before performing bone grinding. For example, when the doctor performs the anterior condylar surface grinding in total knee replacement surgery, the robot arm needs to be dragged to the designated position in advance. Figure 1 The designated area 100 shown can trigger the automatic approach mode of the robotic arm to move the robotic arm to the anterior condylar surface.

[0004] Although the above-mentioned method of manually dragging the robotic arm to the designated position can effectively avoid collisions when the robotic arm automatically approaches the surgical site of the patient, it undoubtedly increases the doctor's operating burden and affects the efficiency of the operation. Summary of the invention

[0005] In order to solve the above technical problems, the present disclosure provides a path planning method, device, equipment and storage medium.

[0006] In a first aspect, an embodiment of the present disclosure provides a path planning method, the method comprising:

[0007] Determine the minimum potential energy posture in the motion environment by using a deterministic annealing algorithm and a synthetic potential field pre-constructed by an improved artificial potential field method; wherein the gravitational potential field and the repulsive potential field of the improved artificial potential field method both introduce temperature variables and cooling factors related to the deterministic annealing algorithm; and the synthetic potential field is obtained by adding the gravitational potential field and the repulsive potential field;

[0008] Determine the initial posture as the current motion posture, and determine the current resultant potential energy of the current motion posture through the synthetic potential field;

[0009] Determine each candidate motion posture contained in the neighborhood of the current motion posture, and determine the candidate combined potential energy of each candidate motion posture through the synthetic potential field; wherein each candidate motion posture does not contain the minimum potential energy posture;

[0010] If the smallest candidate combined potential energy is less than or equal to the current combined potential energy, the candidate motion posture corresponding to the smallest candidate combined potential energy is used as the next motion posture, and the current motion posture is updated using the next motion posture;

[0011] Return to the step of determining the current combined potential energy of the current motion posture through the synthetic potential field until the current motion posture is the target posture, and the current motion postures between the initial posture and the target posture constitute the motion path in the motion environment.

[0012] In a second aspect, an embodiment of the present disclosure further provides a path planning method, the method comprising:

[0013] Determine the minimum potential energy posture in the motion environment by using a deterministic annealing algorithm and a synthetic potential field pre-constructed by an improved artificial potential field method; wherein the gravitational potential field and the repulsive potential field of the improved artificial potential field method both introduce temperature variables and cooling factors related to the deterministic annealing algorithm; and the synthetic potential field is obtained by adding the gravitational potential field and the repulsive potential field;

[0014] Determining an initial path from an initial posture to a target posture; wherein the initial path does not pass through the minimum potential energy posture;

[0015] Traverse each initial motion posture in the initial path in the order of the total potential energy from large to small, and execute for each traversed initial motion posture:

[0016] Determine the current resultant potential energy of the traversed initial motion posture through the synthetic potential field;

[0017] Through the synthetic potential field, determine the candidate combined potential energy of each candidate motion posture contained in the neighborhood of the traversed initial motion posture, and determine whether the smallest candidate combined potential energy is less than or equal to the traversed initial motion posture.

[0018] The total potential energy of the initial motion posture;

[0019] If so, replace the candidate motion posture corresponding to the smallest candidate combined potential energy with the candidate motion posture traversed

[0020] The initial motion pose is obtained to update the initial path;

[0021] If not, keep the initial motion pose traversed;

[0022] The updated initial path at the end of the traversal is determined as the motion path in the motion environment.

[0023] In a third aspect, an embodiment of the present disclosure further provides a path planning device, the device comprising:

[0024] A minimum potential energy posture determination module is used to determine the minimum potential energy posture in a motion environment by using a deterministic annealing algorithm and a synthetic potential field pre-constructed by an improved artificial potential field method; wherein the gravitational potential field and the repulsive potential field of the improved artificial potential field method both introduce temperature variables and cooling factors related to the deterministic annealing algorithm; and the synthetic potential field is obtained by adding the gravitational potential field and the repulsive potential field;

[0025] A current resultant potential energy determination module, used to determine the initial posture as the current motion posture, and determine the current resultant potential energy of the current motion posture through the synthetic potential field;

[0026] A candidate total potential energy determination module, used to determine each candidate motion posture contained in the neighborhood of the current motion posture, and determine the candidate total potential energy of each candidate motion posture through the synthetic potential field; wherein each candidate motion posture does not contain the minimum potential energy posture;

[0027] A current motion posture updating module, configured to use the candidate motion posture corresponding to the smallest candidate combined potential energy as the next motion posture if the smallest candidate combined potential energy is less than or equal to the current combined potential energy, and to update the current motion posture using the next motion posture;

[0028] A loop planning trigger module is used to return to the step of determining the current combined potential energy of the current motion posture through the synthetic potential field until the current motion posture is the target posture, and the current motion postures between the initial posture and the target posture constitute the motion path in the motion environment.

[0029] In a fourth aspect, an embodiment of the present disclosure further provides a path planning device, the device comprising:

[0030] A minimum potential energy posture determination module is used to determine the minimum potential energy posture in a motion environment by using a deterministic annealing algorithm and a synthetic potential field pre-constructed by an improved artificial potential field method; wherein the gravitational potential field and the repulsive potential field of the improved artificial potential field method both introduce temperature variables and cooling factors related to the deterministic annealing algorithm; and the synthetic potential field is obtained by adding the gravitational potential field and the repulsive potential field;

[0031] An initial path determination module, used to determine an initial path from an initial posture to a target posture; wherein the initial path does not pass through the minimum potential energy posture;

[0032] The initial path updating module is used to traverse each initial motion posture in the initial path in the order of total potential energy from large to small, and execute for each traversed initial motion posture:

[0033] Determine the current resultant potential energy of the traversed initial motion posture through the synthetic potential field;

[0034] Through the synthetic potential field, determine the candidate combined potential energy of each candidate motion posture contained in the neighborhood of the traversed initial motion posture, and determine whether the smallest candidate combined potential energy is less than or equal to the traversed initial motion posture.

[0035] The total potential energy of the initial motion posture;

[0036] If so, replace the candidate motion posture corresponding to the smallest candidate combined potential energy with the candidate motion posture traversed

[0037] The initial motion pose is obtained to update the initial path;

[0038] If not, keep the initial motion pose traversed;

[0039] The motion path determination module is used to determine the updated initial path at the end of the traversal as the motion path in the motion environment.

[0040] In a fifth aspect, an embodiment of the present disclosure further provides an electronic device, the electronic device comprising:

[0041] Processor and memory;

[0042] The processor is used to execute the path planning method described in any embodiment of the present disclosure by calling the program or instruction stored in the memory.

[0043] In a sixth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a program or instructions, wherein the program or the instructions enable a computer to execute the steps of the path planning method described in any embodiment of the present disclosure.

[0044] The technical solution for path planning provided by the embodiment of the present disclosure can calculate the minimum potential energy posture in the motion environment by using a deterministic annealing algorithm and a synthetic potential field pre-constructed by an improved artificial potential field method; the temperature variables and cooling factors related to the deterministic annealing algorithm are introduced into the gravitational potential field and the repulsive potential field of the improved artificial potential field method here, and the synthetic potential field is obtained by adding the gravitational potential field and the repulsive potential field; the initial posture is determined as the current motion posture, and the current combined potential energy of the current motion posture is determined by the synthetic potential field; each candidate motion posture contained in the neighborhood of the current motion posture except the minimum potential energy posture is determined, and the candidate combined potential energy of each candidate motion posture is determined by the synthetic potential field; if the minimum candidate combined potential energy is less than or equal to the current combined potential energy, the candidate motion posture corresponding to the minimum candidate combined potential energy is used as the next motion posture, and the current motion posture is updated by using the next motion posture, so as to repeat the above process until the current motion posture is the target posture, and each current motion posture passed from the initial posture to the target posture constitutes a motion path in the motion environment. We have realized the introduction of deterministic annealing strategy into the artificial potential field method, so that the improved artificial potential field method can be used to calculate in real time the collision-free safe path of the robot from the initial position to the final target position, so that the robot can automatically reach the target position from the initial position without collision, replacing the operation of manually dragging the robot arm to the designated area, thereby reducing the doctor's operating burden, improving the accuracy and safety of the robot's participation in surgery, and thus improving the efficiency of the surgery.

[0045] The technical solution for path planning provided by the embodiment of the present disclosure can utilize a deterministic annealing algorithm and a synthetic potential field pre-constructed by an improved artificial potential field method to calculate the minimum potential energy posture in a motion environment; the gravitational potential field and the repulsive potential field of the improved artificial potential field method here both introduce temperature variables and cooling factors related to the deterministic annealing algorithm, and the synthetic potential field is obtained by adding the gravitational potential field and the repulsive potential field; determine an initial path from an initial posture to a target posture that does not pass through the minimum potential energy posture; traverse each initial motion posture in the initial path in order from large to small combined potential energy, and for each traversed initial motion posture, search for a candidate motion posture corresponding to the minimum combined potential energy in its neighborhood to replace the traversed initial motion posture in the initial path, update the initial path, and determine the updated initial path after the traversal as the motion path in the motion environment. The deterministic annealing strategy is introduced into the artificial potential field method, so that the initial path constructed statically in the motion environment can be gradually improved by using the improved artificial potential field method, and a collision-free safe path can be obtained from the initial position of the robot to the final target position. This replaces the operation of manually dragging the robot arm to the designated area, thereby reducing the doctor's operating burden, improving the accuracy and safety of the robot's participation in surgery, and thus improving the efficiency of the surgery. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0048] Figure 1 A schematic diagram of a robotic arm of a surgical robot reaching a designated surgical area on anterior condylar surface in the related art;

[0049] Figure 2 A schematic diagram of a flow chart of a path planning method provided by an embodiment of the present disclosure;

[0050] Figure 3 A flowchart of another path planning method provided by an embodiment of the present disclosure;

[0051] Figure 4 A flowchart of another path planning method provided by an embodiment of the present disclosure;

[0052] Figure 5 A schematic diagram of the structure of a path planning device provided in an embodiment of the present disclosure;

[0053] Figure 6 A schematic diagram of the structure of another path planning device provided in an embodiment of the present disclosure;

[0054] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0055] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described in detail below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0056] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0057] The path planning method provided in the embodiment of the present disclosure is mainly applicable to the scenario of automatically planning a driving path for a robot. Exemplarily, the path planning method in the embodiment of the present disclosure can be applied to planning a safe path for a surgical robot to automatically move from its initial position to the target position at the body part of a patient participating in the operation. For example, a safe path can be planned for the robot in a joint replacement operation to move from its initial position to the position to be operated at the patient's knee joint. The path planning method provided in the embodiment of the present disclosure can be executed by a path planning device, which can be implemented by software and / or hardware, and the device can be integrated in an electronic device with certain computing capabilities, such as a laptop computer, desktop computer or medical-related operating equipment that is communicatively connected to the robot.

[0058] Figure 2 is a flow chart of a path planning method provided by an embodiment of the present disclosure. The path planning method is a process of planning a motion path in real time and dynamically. Figure 2 , the path planning method specifically includes:

[0059] S210, using a deterministic annealing algorithm and a synthetic potential field pre-constructed by an improved artificial potential field method to determine a minimum potential energy posture in a motion environment.

[0060] Among them, deterministic annealing is an optimization technology. Based on the annealing process, it transforms the optimal point of solving the optimization problem into the minimum value of the free energy function of a series of physical systems that change with temperature (i.e., the objective function in the optimization process), so that the algorithm tends to the global minimum. The artificial potential field method is a path planning technology based on the force field model. Its basic idea is to define the motion environment of the moving object (such as a robot) with a synthetic potential field, and control the obstacle avoidance of the moving object through the posture (position information and posture information). In this synthetic potential field, the target point generates a gravitational potential field for the moving object, and the direction is from the moving object to the target point; while the obstacle generates a repulsive potential field for the moving object of the mobile machine, and the direction is from the obstacle to the moving object. The synthetic potential field of the operating space is the superposition of the repulsive potential field and the gravitational potential field, so that the movement of the moving object is controlled by the combined force of gravity and repulsion. The improved artificial potential field method is an algorithm obtained by improving the potential field representation method of the artificial potential field method in the related technology. In the disclosed embodiments, temperature variables and cooling factors related to the deterministic annealing algorithm are introduced into the gravitational potential field and repulsive potential field of the artificial potential field method in the related art, and an improved artificial potential field method is obtained to avoid the problem of falling into local minimum points and unreachable targets in the path planning process to a certain extent. The temperature variables and cooling factors in the improved artificial potential field method are associated / linked with the corresponding variables in the deterministic annealing algorithm, that is, the changes in the values ​​of the temperature variables and cooling factors in the deterministic annealing algorithm and the improved artificial potential field method affect each other, rather than being independent. The minimum potential energy posture is the posture where the global minimum synthetic potential energy is located in the motion environment.

[0061] Specifically, before starting path planning, the electronic device first constructs the gravitational potential field and the repulsive potential field of the motion environment by using an improved artificial potential field method, and constructs a synthetic potential field of the motion environment by using the two.

[0062] In some embodiments, the gravitational potential field in the improved artificial potential field method is shown in formula (1):

[0063]

[0064] Among them, U a (q) represents the gravitational potential energy at the current motion position (i.e., current motion position) q of the moving object. a Represents the gain parameter of the gravitational potential field, which can be set empirically. T represents the temperature variable, which is only a temperature characterization quantity related to the deterministic annealing algorithm, not the actual ambient temperature value. α represents the cooling factor, which ranges from (0,1), and the smaller the cooling factor, the faster the temperature cools. σ 0represents the target pose q g The gravitational distance threshold for the gravitational influence on the moving object. If the distance between the moving object and the target point exceeds the gravitational distance threshold, the gravitational influence of the target point on the moving object will be 0. The gravitational distance threshold can be set in advance according to the application scenario. For example, the larger the target object at the target point, the larger the gravitational distance threshold; conversely, the smaller the target object, the smaller the gravitational distance threshold. σ(q,q g ) represents the current motion pose q and the target pose q g The Euclidean distance between g )=||qq g ||2. σ(q,q g ) is always positive and at the target pose q g The global minimum value 0 is obtained.

[0065] Based on the above gravitational potential field, the corresponding gravitational force f a (q) is defined as shown in formula (2):

[0066]

[0067] Therefore, when the current motion posture q approaches the target posture q g When f a Converges to zero.

[0068] In order to prevent the moving object from being a When moving under the action of the gravitational potential field, the object collides with the obstacle. The repulsive potential field is introduced on the basis of the gravitational potential field. The basic idea of ​​the repulsive potential field is to build a barrier near the obstacle to drive the moving object to avoid it. Considering that there may be more than one obstacle in the moving environment, all obstacles contained in the moving environment can be determined as multiple obstacle zones CO i , i = 1, ..., n. For example, in an actual knee replacement surgery scenario, the obstacle area CO1 of the patient's leg, the obstacle area CO2 of the reference frame, and the obstacle area CO3 of the bed may be included. i , the repulsive potential field in the improved artificial potential field method can be expressed as formula (3):

[0069]

[0070] Among them, U r,i (q) represents the i-th obstacle area CO i The repulsive potential energy generated at the current motion posture q. r,i represents the i-th obstacle area CO iThe corresponding gain parameter of the repulsive potential field can be set empirically. T represents the temperature variable, which is also just a temperature characterization quantity related to the deterministic annealing algorithm, not the actual ambient temperature value. α represents the cooling factor, and its value range is (0,1). η 0,i is a positive constant, indicating the i-th obstacle area CO i The repulsion distance threshold that produces a repulsive effect on the moving object. If the distance between the moving object and the obstacle exceeds the repulsion distance threshold, the repulsion effect of the obstacle on the moving object will be 0. The repulsion distance threshold can be set in advance according to the application scenario. For example, the larger the obstacle, the larger the repulsion distance threshold; conversely, the smaller the obstacle, the smaller the repulsion distance threshold. η i (q) represents the i-th obstacle area CO i The minimum distance to the current motion posture q, which is the distance value calculated in real time, that is, for all obstacles contained in the i-th obstacle area CO i The distance between each point q′ and the current motion posture q is calculated, and the minimum value is taken: η i (q)=min‖qq′‖(q′∈CO i ). γ represents a constant parameter, γ = 2, 3, .... In the obstacle area CO i Outside the scope of influence (η i (q)>η 0,i ), the repulsive force it generates on the current motion posture is zero; in the obstacle area CO i Within the influence range (η i (q)≤η 0,i ), the repulsive force generated on the current motion posture is positive; when approaching the obstacle area CO i At the boundary / edge of the obstacle zone CO i The repulsive force generated at the current motion position approaches infinity. The larger γ is, the faster the repulsive force increases. For example, γ can be set to 2.

[0071] Based on the above repulsive potential field, the corresponding obstacle area CO i The repulsive force f r,i (q) is defined as shown in formula (4):

[0072]

[0073] The total repulsive potential field in the entire motion environment can be the superposition result of the repulsive potential fields corresponding to each convex obstacle area C, that is, the total repulsive potential field U r (q) can be expressed as formula (5):

[0074]

[0075] The total synthetic potential field U can be obtained by superimposing the gravitational potential field of formula (1) and the total repulsive potential field of formula (5): t , as shown in formula (6):

[0076] U t (q) = U a (q)+U r (q)(6)

[0077] Then, the deterministic annealing algorithm is used to gradually change the synthetic potential field U t The temperature variables involved in the calculation are used to obtain the synthetic potential field distribution at different temperature values, thereby calculating the minimum potential energy in the motion environment and determining the minimum potential energy posture corresponding to the minimum potential energy. If the minimum potential energy posture is not the posture that the moving object will eventually reach (i.e., the target posture), then the minimum potential energy posture may be a local minimum point. In this way, when starting path planning, it is necessary to try to avoid the minimum potential energy posture.

[0078] In some embodiments, S210 includes: for any current temperature value among the temperature values ​​of the deterministic annealing algorithm, determining the minimum potential energy corresponding to the current temperature value through the minimum value of the objective function of the deterministic annealing algorithm; if the difference between the minimum potential energy corresponding to the current temperature value and the minimum potential energy corresponding to the previous adjacent temperature value is greater than the potential energy threshold, then using the cooling factor to reduce the current temperature value, obtain the next adjacent temperature value to update the current temperature value, and return to execute the step of determining the minimum potential energy corresponding to the current temperature value through the minimum value of the objective function of the deterministic annealing algorithm until the corresponding difference is less than or equal to the potential energy threshold; if the difference between the minimum potential energy corresponding to the current temperature value and the minimum potential energy corresponding to the previous adjacent temperature value is less than or equal to the potential energy threshold, then the posture at the minimum potential energy corresponding to the current temperature value is determined as the minimum potential energy posture.

[0079] Among them, the objective function is the optimization object when the deterministic annealing algorithm is used to solve the optimal solution, which can also be called the free potential energy function.

[0080] Exemplarily, based on the above-mentioned gravitational potential field, repulsive potential field and synthetic potential energy, the objective function of the deterministic annealing algorithm can be shown in formula (7):

[0081] E(q,T)=U t (q)-TH(7)

[0082] Where E(q,T) represents the free potential energy of the current motion posture q at the temperature value T. H represents the system entropy, Represents the probability of the moving object passing through the current motion pose q.

[0083] Specifically, the process of calculating the minimum potential energy pose by the deterministic annealing algorithm in this embodiment is:

[0084] Step A: Assume that the initial temperature T0 = ∞ and the number of iterations / cycles k = 0. Set the initial temperature to the current temperature value. Use the conjugate gradient method to solve the minimum / optimal solution of the objective function shown in formula (7), i.e., minE(q,T k ), and let it be the current temperature value T k The minimum potential field p(T k ).

[0085] Step B: Use cooling factor α (0<α<1) to cool down the current temperature value, that is, T k+1 =αT k . And use T k+1 Update the current temperature value. Continue to use the conjugate gradient method to solve the optimal solution minE(q,T k ), and let it be the current temperature value T k+1 The minimum potential field p(T k+1 ).

[0086] Step C: Determine the current temperature value T k+1 The corresponding minimum potential energy p(T k+1 ) and the previous adjacent temperature value T k The corresponding minimum potential energy p(T k ) (i.e. |p(T k+1 )-p(T k )|) is greater than the potential energy threshold tolerance. If yes, it means that the global optimal solution has not been reached, then set k=k+1, and return to step B for loop processing. If no, it means that the global optimal solution has been obtained, then execute step D.

[0087] Step D, |p(T k+1 )-p(T k )|≤tolerance, the annealing process is stopped and p(T k+1 ) is the optimal solution, that is, the synthetic potential energy U t (q) is the global minimum p. The pose at the global minimum p is the pose with the minimum potential energy.

[0088] S220: Determine the initial posture as the current motion posture, and determine the current combined potential energy of the current motion posture through the synthetic potential field.

[0089] Specifically, when the moving object is at any position in the moving environment and starts path planning, its position at the current moment (i.e., initial position) is determined as the current moving position. Then, the synthetic potential energy at the current moving position is calculated using the synthetic potential energy function shown in formula (6) using the temperature value, i.e., the current synthetic potential energy. In this process, the temperature value in the synthetic potential energy function can be the temperature value corresponding to the minimum potential energy position or the initial temperature value. If annealing or tempering has been performed before, the temperature value here can be the temperature value corresponding to the end of annealing or tempering.

[0090] S230, determining each candidate motion posture included in the neighborhood of the current motion posture, and determining a candidate combined potential energy of each candidate motion posture through a synthetic potential field.

[0091] The candidate motion pose is a motion pose at a motion position that may become the next motion pose of the current motion pose, and the candidate resultant potential energy is the resultant potential energy at the candidate motion pose.

[0092] Specifically, when the improved artificial potential field method is used for path dynamic planning, the next motion posture to be reached (ie, the next motion posture) can be determined based on the current motion posture through the distribution of the synthetic potential field around it.

[0093] In a specific implementation, the electronic device can determine the neighborhood range according to the motion step length of the moving object or the driving requirements in the application scenario. Then, within the neighborhood range of the current motion posture, postures in various directions can be selected as candidate motion postures. In order to prevent the running object from falling into local extreme points during driving, these candidate motion postures should avoid the minimum potential energy posture determined by the above process. That is, the minimum potential energy posture should be excluded from the determined candidate motion postures. Then, the candidate combined potential energy at each candidate motion posture is calculated by the synthetic potential energy function shown in formula (6). In this process, the temperature value in the synthetic potential energy function can be the temperature value corresponding to the minimum potential energy posture or the initial temperature value. If it has been annealed or tempered before, the temperature value here can be the temperature value corresponding to the end of annealing or tempering.

[0094] S240: If the minimum candidate combined potential energy is less than or equal to the current combined potential energy, the candidate motion posture corresponding to the minimum candidate combined potential energy is used as the next motion posture, and the current motion posture is updated using the next motion posture.

[0095] Specifically, the minimum value is selected from each candidate combined potential energy. Then, it is compared with the current combined potential energy. If the minimum candidate combined potential energy is less than or equal to the current combined potential energy, it means that there is a motion posture with a smaller combined potential energy in the neighborhood of the current motion posture. Then, based on the purpose that the moving object will eventually move to the posture with the smallest global combined potential energy, the candidate motion posture corresponding to the minimum candidate combined potential energy can be used as the next motion posture. In addition, the current motion posture is updated using the next motion posture to continue the dynamic programming process of the next motion posture.

[0096] If the smallest candidate combined potential energy is greater than the current combined potential energy, it means that the current motion posture is likely to fall into a local minimum and cannot continue to move. In this case, it is necessary to perform an escape process to make the moving object jump out of the local minimum motion posture. The escape process can adopt various optimization strategies in related technologies, such as adjusting the potential energy function, introducing random perturbations, finding the global optimal solution through optimization algorithms such as genetic algorithms, simulated annealing algorithms or neural networks, setting virtual target points, etc.

[0097] S250, return to execute the step of determining the current combined potential energy of the current motion posture through the synthetic potential field in S220, until the current motion posture is the target posture, and the current motion postures between the initial posture and the target posture constitute the motion path in the motion environment.

[0098] Specifically, when the current motion posture is updated in S240, the electronic device can continue to plan the next new motion posture according to the current motion posture, that is, return to the step of determining the current combined potential energy of the current motion posture through the synthetic potential field in S220 to loop the dynamic planning process of the above motion posture. The loop planning process ends the loop planning process when it is determined that the updated current motion posture reaches the target posture. At this time, the current motion postures from the initial posture to the target posture obtained in the above loop planning process can be obtained, and these current motion postures constitute the driving path / motion path of the moving object in the moving environment.

[0099] In some embodiments, the target posture is that the grinding drill bit on the robotic arm of the surgical robot is aligned with the drilling axis of the surgical object; the motion path is used to guide the robotic arm to move from the initial posture to the target posture.

[0100] Specifically, in the application scenario of knee replacement surgery, the initial position can be the position of the surgical robot at any position in the operating room environment, and the target position is the alignment of the grinding drill carried by the surgical robot's mechanical arm with the drilling axis of the patient's knee joint. In this way, the motion path obtained through the above process can guide the mechanical arm to move to the target position safely and without collision from any initial position, without the doctor having to drag the mechanical arm to the designated area corresponding to the knee joint (also called a safety zone or pre-approach zone, etc.), which reduces the doctor's operating burden and improves the efficiency of knee replacement surgery.

[0101] The path planning method provided by the above-mentioned embodiments of the present disclosure can calculate the minimum potential energy posture in the motion environment by using the deterministic annealing algorithm and the synthetic potential field pre-constructed by the improved artificial potential field method; the temperature variables and cooling factors related to the deterministic annealing algorithm are introduced into the gravitational potential field and the repulsive potential field of the improved artificial potential field method here, and the synthetic potential field is obtained by adding the gravitational potential field and the repulsive potential field; the initial posture is determined as the current motion posture, and the current combined potential energy of the current motion posture is determined by the synthetic potential field; each candidate motion posture contained in the neighborhood of the current motion posture except the minimum potential energy posture is determined, and the candidate combined potential energy of each candidate motion posture is determined by the synthetic potential field; if the minimum candidate combined potential energy is less than or equal to the current combined potential energy, the candidate motion posture corresponding to the minimum candidate combined potential energy is used as the next motion posture, and the current motion posture is updated by using the next motion posture, so as to repeat the above process until the current motion posture is the target posture, and each current motion posture passed from the initial posture to the target posture constitutes the motion path in the motion environment. We have realized the introduction of deterministic annealing strategy into the artificial potential field method, so that the improved artificial potential field method can be used to calculate in real time the collision-free safe path of the robot from the initial position to the final target position, so that the robot can automatically reach the target position from the initial position without collision, replacing the operation of manually dragging the robot arm to the designated area, thereby reducing the doctor's operating burden, improving the accuracy and safety of the robot's participation in surgery, and thus improving the efficiency of the surgery.

[0102] Figure 3 is a flow chart of another path planning method provided by an embodiment of the present disclosure. It adds the steps related to the local minimum of the synthetic potential field of the current motion posture escape. The explanations of the terms that are the same or corresponding to the above embodiments are not repeated here. Figure 3 , the path planning method includes:

[0103] S310, using a deterministic annealing algorithm and a synthetic potential field pre-constructed by an improved artificial potential field method to determine a minimum potential energy posture in a motion environment.

[0104] S320: Determine the initial posture as the current motion posture, and determine the current combined potential energy of the current motion posture through the synthetic potential field.

[0105] S330, determining each candidate motion posture included in the neighborhood of the current motion posture, and determining the candidate combined potential energy of each candidate motion posture except the minimum potential energy posture through the synthetic potential field.

[0106] S340: Determine whether the minimum candidate total potential energy is greater than the current total potential energy. If yes, execute S370 to S380; if no, execute S350 to S360.

[0107] S350: taking the candidate motion posture corresponding to the smallest candidate combined potential energy as the next motion posture, and using the next motion posture to update the current motion posture.

[0108] S360, returning to the step of determining the current combined potential energy of the current motion posture through the synthetic potential field in S320, until the current motion posture is the target posture.

[0109] S370, adjusting the gravitational potential field and the repulsive potential field corresponding to the current motion posture through a deterministic annealing algorithm, so that the current motion posture jumps out of the posture at the local minimum potential energy.

[0110] Specifically, if the current combined potential energy is greater than the smallest candidate combined potential energy in its neighborhood, it means that the current motion posture is very likely to fall into a local minimum and cannot continue to move. In the disclosed embodiment, the temperature value can be continuously adjusted by a deterministic annealing algorithm to change the gravitational potential field and the repulsive potential field in the motion environment to optimize the objective function and find the global optimal solution at a faster speed to assist the motion object to jump out of the posture at the local minimum of the combined potential field.

[0111] In some embodiments, S370 may be implemented as the following steps E to I:

[0112] Step E: Determine the minimum potential energy corresponding to each temperature value by minimizing the objective function of the deterministic annealing algorithm.

[0113] Specifically, the electronic device starts from a maximum initial temperature and gradually cools down using a cooling factor to obtain various temperature values. Then, according to the process of step A to step B, each temperature value T is calculated. i The corresponding minimum potential energy p i .

[0114] Step F: determine the highest temperature value as the current temperature value, and determine whether the optimization condition is met.

[0115] The optimization condition is the end condition of the iterative / loop optimization of the deterministic annealing algorithm, for example, the current temperature value is less than the preset temperature threshold Tf .

[0116] Specifically, the electronic device starts the escape process from the highest temperature. Therefore, the highest temperature value is determined as the current temperature value, and it is determined whether the optimization condition is reached.

[0117] If the optimization condition is not met, such as the current temperature value is greater than or equal to the temperature threshold, then continue to step G.

[0118] If the optimization condition has been met, such as the current temperature value is less than the temperature threshold, the optimization process ends. If the current motion posture is still at the local minimum of the synthetic potential field, it is considered that there is no escape or a collision. At this time, relevant information about the failure of path planning can be fed back to notify relevant personnel to handle it. For example, the doctor can be notified to manually drag the robotic arm to the specified area.

[0119] Step G: Determine that the current minimum potential energy corresponding to the current temperature value is within the neighborhood of the current motion posture. When the distance between the posture at the current minimum potential energy and the current motion posture is less than or equal to the repulsive distance threshold, increase the current temperature value based on the cooling factor until the distance between the posture at the minimum potential energy corresponding to the increased current temperature value and the current motion posture is greater than the repulsive distance threshold.

[0120] The repulsive distance threshold is the maximum distance value at which the obstacle area in the motion environment exerts a repulsive effect on the moving object.

[0121] Specifically, the purpose of optimizing electronic devices using a deterministic annealing algorithm is to make the current motion posture away from the minimum potential energy corresponding to each temperature value through the annealing optimization process within the optimization conditions, that is, to make the distance between the current motion posture and the posture at each minimum potential energy greater than the repulsive distance threshold, so as to avoid the repulsive influence of each obstacle area on the moving object, thereby achieving the effect of escaping the local minimum of the synthetic potential field.

[0122] First, the electronic device must determine whether the minimum potential energy corresponding to the current temperature value (i.e., the current minimum potential energy) is within the neighborhood of the current motion posture. If the current minimum potential energy is the current combined potential energy of the current motion posture, or the current minimum potential energy is not the current combined potential energy, but it is within the neighborhood of the current motion posture, then it can be considered that the current minimum potential energy is within the neighborhood of the current motion posture. Then, the electronic device determines whether the distance between the posture at the current minimum potential energy and the current motion posture is greater than the repulsive distance threshold. If not, it means that the current minimum potential energy has a repulsive effect on the current motion posture, and the current temperature value is heated up by the cooling factor, i.e., T i+1 =T i / α, until the distance between the posture at the minimum potential energy corresponding to the current temperature value and the current motion posture is greater than the repulsive distance threshold, the escape is considered successful.

[0123] In some examples, if it is determined that the current minimum potential energy corresponding to the current temperature value is not within the neighborhood of the current motion posture, the minimum candidate combined potential energy is determined within the neighborhood of the current motion posture, and when the minimum candidate combined potential energy is less than or equal to the current combined potential energy, the candidate motion posture corresponding to the minimum candidate combined potential energy is used as the next motion posture, and the current motion posture is updated using the next motion posture until it is determined that the current minimum potential energy corresponding to the current temperature value is within the neighborhood of the current motion posture.

[0124] Specifically, if the electronic device determines that the current minimum potential energy is not within the neighborhood of the current motion posture, the electronic device can calculate the distribution of the new synthetic potential field at the current temperature value, and refer to the process of S230 to S240, and continuously update the current motion posture according to the gradient descent potential field guidance strategy until the current minimum potential energy is within the neighborhood of the current motion posture.

[0125] Step H: Based on the increased current temperature value, determine the minimum candidate combined potential energy within the neighborhood of the current motion posture, and when the minimum candidate combined potential energy is less than or equal to the current combined potential energy, use the candidate motion posture corresponding to the minimum candidate combined potential energy as the next motion posture, and use the next motion posture to update the current motion posture.

[0126] Specifically, after the escape is successful, the distribution of the new synthetic potential field in the motion environment is calculated with the current temperature value increased during the last tempering treatment. Then, the next motion posture is determined according to the process of S230 to S240, and the current motion posture is updated. If the current synthetic potential energy is greater than the minimum candidate synthetic potential energy, the current motion posture is not updated.

[0127] Step I: Cool down the current temperature value based on the cooling factor, and use the cooled temperature value to update the current temperature value, and return to the step of determining whether the optimization condition is met.

[0128] Specifically, after the current motion posture is determined, the annealing cooling process is continued for the current temperature value increased during the last tempering process, that is, T i+1 =αT i Then, the temperature value after cooling is used as the new current temperature value, and the step of determining whether the optimization condition is met in step F is returned to execute, so as to cycle through each temperature value for escape processing until the optimization condition is met, thereby ending the adjustment process of the deterministic annealing algorithm.

[0129] S380, determining the motion posture at the end of the adjustment as the current motion posture, and returning to execute the step of determining the current combined potential energy of the current motion posture through the synthetic potential field in S320, until the current motion posture is the target posture.

[0130] Specifically, according to the description of each of the above steps, the current motion posture is continuously updated during the adjustment process of the deterministic annealing algorithm. Then, at the end of the adjustment, the corresponding motion posture has jumped out of the local minimum of the previous synthetic potential field with a high probability. Therefore, the motion posture at the end of the adjustment is determined as the new current motion posture, and then returns to execute S320 to cycle the dynamic programming process of the motion posture until the target posture is reached.

[0131] S390: If the current motion posture is the target posture, each current motion posture from the initial posture to the target posture constitutes a motion path in the motion environment.

[0132] The path planning method provided by the above-mentioned embodiments of the present disclosure, when the current motion posture falls into the local minimum of the synthetic potential field, adjusts the gravitational potential field and the repulsive potential field corresponding to the current motion posture through a deterministic annealing algorithm, so that the current motion posture jumps out of the posture at the local minimum potential energy; the motion posture at the end of the adjustment is determined as the current motion posture, and returns to execute the step of determining the current combined potential energy of the current motion posture through the synthetic potential field until the current motion posture is the target posture, and the current motion postures passing between the initial posture and the target posture constitute the motion path in the motion environment; it can assist the current motion posture to jump out of the local minimum of the synthetic potential field more quickly, thereby more efficiently planning a collision-free safe path, further improving the safety and efficiency of path planning.

[0133] Figure 4 1 is a flow chart of another path planning method provided by an embodiment of the present disclosure. The path planning method is a process of statically planning a motion path. The explanation of the terms or steps in the path planning method that are the same or similar to those in the above embodiments can be found in the relevant descriptions in the above embodiments, and will not be repeated in this embodiment.

[0134] See also Figure 4 , the path planning method specifically includes:

[0135] S410, using a deterministic annealing algorithm and a synthetic potential field pre-constructed by an improved artificial potential field method to determine a minimum potential energy posture in a motion environment.

[0136] Among them, temperature variables and cooling factors related to the deterministic annealing algorithm are introduced into the gravitational potential field and repulsive potential field of the improved artificial potential field method; the synthetic potential field is obtained by adding the gravitational potential field and the repulsive potential field.

[0137] For a detailed explanation of this step, please refer to the relevant description in the above S210.

[0138] S420: Determine an initial path from the initial posture to the target posture.

[0139] The initial path is a motion path preliminarily planned according to the motion environment. Based on the relevant description in the above S230, the initial path does not pass through the minimum potential energy posture.

[0140] Specifically, for some relatively fixed motion environments of obstacles and targets, the improved artificial potential field method can be used to obtain the final motion path before the robot moves. In this case, the electronic device can use the path planning algorithm in the relevant technology to calculate the initial path based on the initial posture of the robot in the motion environment and the target posture it finally reaches. The initial path only avoids the minimum potential energy posture, but the combined potential energy of each motion posture (i.e., the initial motion posture) contained therein may not be the smaller combined potential energy at the corresponding position, so that the initial motion posture may not be a collision-free safe motion posture. Therefore, the initial path still needs to be improved according to the distribution of the synthetic potential field of the motion environment and the improved artificial potential field method.

[0141] S430, traversing each initial motion posture in the initial path in order of total potential energy from large to small, and executing the following process S431 to S434 for each traversed initial motion posture.

[0142] Specifically, the electronic device can use the synthetic potential field to calculate the combined potential energy corresponding to each initial motion posture in the initial path. Then, based on the consideration of eliminating the local maximum combined potential energy, the electronic device sorts the initial motion postures in order from large to small combined potential energy. And, traverse each initial motion posture in order. For each traversed initial motion posture, the electronic device searches for a motion posture with a smaller combined potential energy in its neighborhood.

[0143] S431. Determine the current combined potential energy of the traversed initial motion posture through the synthetic potential field.

[0144] For a detailed explanation of this step, please refer to the relevant description in the above S220.

[0145] S432. Determine the candidate combined potential energy of each candidate motion posture contained in the neighborhood of the traversed initial motion posture through the synthetic potential field, and determine whether the minimum candidate combined potential energy is less than or equal to the combined potential energy of the traversed initial motion posture.

[0146] Specifically, referring to the relevant description of S230 and S240 above, the electronic device compares the minimum value of each candidate resultant potential energy with the resultant potential energy of the traversed initial motion posture. If the minimum value is greater than the resultant potential energy of the traversed initial motion posture, S434 is executed; otherwise, S433 is executed.

[0147] S433. Replace the traversed initial motion pose with the candidate motion pose corresponding to the smallest candidate combined potential energy to update the initial path.

[0148] Specifically, the electronic device replaces the initial motion pose traversed in the initial path with the candidate motion pose corresponding to the minimum value, updates the initial path, and then traverses to the next initial motion pose in order for processing.

[0149] S434, retaining the traversed initial motion posture;

[0150] Specifically, if the minimum value is greater than the combined potential energy of the traversed initial motion pose, it means that the traversed initial motion pose is a pose with a smaller combined potential energy within the current local range, and the traversed initial motion pose is retained without updating the initial path. Then, the next initial motion pose is traversed in order for processing.

[0151] S440: Determine the updated initial path at the end of the traversal as the motion path in the motion environment.

[0152] Specifically, each initial motion posture in the initial path is traversed according to S430. At the end of the traversal, the overall update and improvement of the initial path is completed, which is a collision-free safe path in the motion environment, so the updated initial path at the end of the traversal is determined as the final motion path.

[0153] The technical solution for path planning provided by the embodiment of the present disclosure can utilize a deterministic annealing algorithm and a synthetic potential field pre-constructed by an improved artificial potential field method to calculate the minimum potential energy posture in a motion environment; the gravitational potential field and the repulsive potential field of the improved artificial potential field method here both introduce temperature variables and cooling factors related to the deterministic annealing algorithm, and the synthetic potential field is obtained by adding the gravitational potential field and the repulsive potential field; determine an initial path from an initial posture to a target posture that does not pass through the minimum potential energy posture; traverse each initial motion posture in the initial path in order from large to small combined potential energy, and for each traversed initial motion posture, search for a candidate motion posture corresponding to the minimum combined potential energy in its neighborhood to replace the traversed initial motion posture in the initial path, update the initial path, and determine the updated initial path after the traversal as the motion path in the motion environment. The deterministic annealing strategy is introduced into the artificial potential field method, so that the initial path constructed statically in the motion environment can be gradually improved by using the improved artificial potential field method, and a collision-free safe path can be obtained from the initial position of the robot to the final target position. This replaces the operation of manually dragging the robot arm to the designated area, thereby reducing the doctor's operating burden, improving the accuracy and safety of the robot's participation in surgery, and thus improving the efficiency of the surgery.

[0154] Figure 5 Schematic diagram of a path planning device provided by an embodiment of the present disclosure. Figure 5 As shown, the path planning device 500 includes:

[0155] The minimum potential energy posture determination module 510 is used to determine the minimum potential energy posture in the motion environment by using a deterministic annealing algorithm and a synthetic potential field pre-constructed by an improved artificial potential field method; wherein the temperature variable and cooling factor related to the deterministic annealing algorithm are introduced into the gravitational potential field and the repulsive potential field of the improved artificial potential field method; and the synthetic potential field is obtained by adding the gravitational potential field and the repulsive potential field;

[0156] A current resultant potential energy determination module 520, for determining the initial posture as the current motion posture, and determining the current resultant potential energy of the current motion posture through a synthetic potential field;

[0157] A candidate total potential energy determination module 530 is used to determine each candidate motion posture contained in the neighborhood of the current motion posture, and determine the candidate total potential energy of each candidate motion posture through a synthetic potential field; wherein each candidate motion posture does not contain a minimum potential energy posture;

[0158] The current motion posture updating module 540 is used to take the candidate motion posture corresponding to the minimum candidate combined potential energy as the next motion posture if the minimum candidate combined potential energy is less than or equal to the current combined potential energy, and use the next motion posture to update the current motion posture;

[0159] The loop planning trigger module 550 is used to return to the step of determining the current combined potential energy of the current motion posture through the synthetic potential field until the current motion posture is the target posture. The current motion postures between the initial posture and the target posture constitute the motion path in the motion environment.

[0160] The path planning device provided by the above-mentioned embodiments of the present disclosure can calculate the minimum potential energy posture in the motion environment by using a deterministic annealing algorithm and a synthetic potential field pre-constructed by an improved artificial potential field method; the temperature variables and cooling factors related to the deterministic annealing algorithm are introduced into the gravitational potential field and the repulsive potential field of the improved artificial potential field method here, and the synthetic potential field is obtained by adding the gravitational potential field and the repulsive potential field; the initial posture is determined as the current motion posture, and the current combined potential energy of the current motion posture is determined by the synthetic potential field; each candidate motion posture contained in the neighborhood of the current motion posture except the minimum potential energy posture is determined, and the candidate combined potential energy of each candidate motion posture is determined by the synthetic potential field; if the minimum candidate combined potential energy is less than or equal to the current combined potential energy, the candidate motion posture corresponding to the minimum candidate combined potential energy is used as the next motion posture, and the current motion posture is updated by using the next motion posture, so as to repeat the above process until the current motion posture is the target posture, and each current motion posture passed from the initial posture to the target posture constitutes a motion path in the motion environment. We have realized the introduction of deterministic annealing strategy into the artificial potential field method, so that the improved artificial potential field method can be used to calculate in real time the collision-free safe path of the robot from the initial position to the final target position, so that the robot can automatically reach the target position from the initial position without collision, replacing the operation of manually dragging the robot arm to the designated area, thereby reducing the doctor's operating burden, improving the accuracy and safety of the robot's participation in surgery, and thus improving the efficiency of the surgery.

[0161] In some embodiments, the minimum potential energy pose determination module 510 is specifically used to:

[0162] For any current temperature value among the temperature values ​​of the deterministic annealing algorithm, the minimum potential energy corresponding to the current temperature value is determined by the minimum value of the objective function of the deterministic annealing algorithm;

[0163] If the difference between the minimum potential energy corresponding to the current temperature value and the minimum potential energy corresponding to the previous adjacent temperature value is greater than the potential energy threshold, the current temperature value is reduced by using the cooling factor to obtain the next adjacent temperature value to update the current temperature value, and the step of determining the minimum potential energy corresponding to the current temperature value by performing the minimum value of the objective function of the deterministic annealing algorithm is returned until the corresponding difference is less than or equal to the potential energy threshold;

[0164] If the difference between the minimum potential energy corresponding to the current temperature value and the minimum potential energy corresponding to the previous adjacent temperature value is less than or equal to the potential energy threshold, the posture at the minimum potential energy corresponding to the current temperature value is determined as the minimum potential energy posture.

[0165] In some embodiments, the path planning device 500 further includes a current motion posture adjustment module, which is used to:

[0166] After determining each candidate motion posture contained in the neighborhood of the current motion posture and determining the candidate combined potential energy of each candidate motion posture through the synthetic potential field, if the smallest candidate combined potential energy is greater than the current combined potential energy, the gravitational potential field and the repulsive potential field corresponding to the current motion posture are adjusted through a deterministic annealing algorithm so that the current motion posture jumps out of the posture at the local minimum potential energy;

[0167] Accordingly, the cycle planning triggering module 550 is also used for:

[0168] The motion posture at the end of the adjustment is determined as the current motion posture, and the step of determining the current combined potential energy of the current motion posture through the synthetic potential field is returned to execute until the current motion posture is the target posture. The current motion postures between the initial posture and the target posture constitute the motion path in the motion environment.

[0169] In some embodiments, the current motion posture adjustment module is specifically used to:

[0170] By minimizing the objective function of the deterministic annealing algorithm, the minimum potential energy corresponding to each temperature value is determined;

[0171] The highest temperature value is determined as the current temperature value, and whether the optimization condition is met;

[0172] If not, and it is determined that the current minimum potential energy corresponding to the current temperature value is within the neighborhood of the current motion posture, then when the distance between the posture at the current minimum potential energy and the current motion posture is less than or equal to the repulsion distance threshold, the current temperature value is increased based on the cooling factor until the distance between the posture at the minimum potential energy corresponding to the increased current temperature value and the current motion posture is greater than the repulsion distance threshold; wherein the repulsion distance threshold is the maximum distance value of the obstacle area in the motion environment that exerts a repulsive effect on the moving object;

[0173] Based on the increased current temperature value, determine the minimum candidate combined potential energy within the neighborhood of the current motion posture, and when the minimum candidate combined potential energy is less than or equal to the current combined potential energy, use the candidate motion posture corresponding to the minimum candidate combined potential energy as the next motion posture, and use the next motion posture to update the current motion posture;

[0174] The current temperature value after heating is cooled down based on the cooling factor, and the current temperature value is updated with the temperature value after cooling down, and the step of determining whether the optimization condition is met is returned to be executed.

[0175] In some embodiments, the current motion posture adjustment module is further specifically used to:

[0176] If it is determined that the current minimum potential energy corresponding to the current temperature value is not within the neighborhood of the current motion posture, the minimum candidate combined potential energy is determined within the neighborhood of the current motion posture, and when the minimum candidate combined potential energy is less than or equal to the current combined potential energy, the candidate motion posture corresponding to the minimum candidate combined potential energy is used as the next motion posture, and the current motion posture is updated using the next motion posture until it is determined that the current minimum potential energy corresponding to the current temperature value is within the neighborhood of the current motion posture.

[0177] In some embodiments, the gravitational potential field is:

[0178]

[0179] Among them, U a (q) represents the gravitational potential energy at the current motion position q; δ a represents the gain parameter of the gravitational potential field; T represents the temperature variable; α represents the cooling factor, and its value range is (0,1); σ 0 represents the target pose q g The gravitational distance threshold that exerts gravitational influence on the moving object; σ(q,q g ) represents the current motion pose q and the target pose q g The Euclidean distance between g )=||qq g ||2;

[0180] The repulsive potential field is:

[0181]

[0182] Among them, U r,i (q) represents the i-th obstacle area CO i The repulsive potential energy generated at the current motion posture q; δ r,i represents the i-th obstacle area CO i The corresponding gain parameter of the repulsive potential field; T represents the temperature variable; α represents the cooling factor, and its value range is (0,1); η 0,i is a positive constant, indicating the i-th obstacle area CO i The repulsive distance threshold that produces a repulsive effect on the moving object; η i (q) represents the i-th obstacle area CO i The minimum distance to the current motion pose q, η i (q)=min‖qq′‖(q′∈CO i ); γ represents a constant parameter, γ = 2, 3, ...;

[0183] The objective function of the deterministic annealing algorithm is:

[0184] E(q,T)=U t(q)-TH;

[0185] Where E(q,T) represents the free potential energy of the current motion posture q at temperature T; U t (q) represents the total potential energy at the current motion posture q, U t (q) = U a (q)+U r (q), i represents the serial number of the obstacle zone in the motion environment, n represents the total number of obstacle zones; H represents the system entropy, Represents the probability of the moving object passing through the current motion pose q.

[0186] In some embodiments, the target posture is that the grinding drill bit on the robotic arm of the surgical robot is aligned with the drilling axis of the surgical object; the motion path is used to guide the robotic arm to move from the initial posture to the target posture.

[0187] The path planning device provided in the embodiments of the present disclosure can execute the path planning method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0188] It is worth noting that in the embodiment of the above-mentioned path planning device, the various modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the various functional modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present disclosure.

[0189] Figure 6 This is a schematic diagram of the structure of another path planning device provided by an embodiment of the present disclosure. Figure 6 As shown, the path planning device 600 includes:

[0190] The minimum potential energy posture determination module 610 is used to determine the minimum potential energy posture in the motion environment by using a deterministic annealing algorithm and a synthetic potential field pre-constructed by an improved artificial potential field method; wherein the temperature variable and cooling factor related to the deterministic annealing algorithm are introduced into the gravitational potential field and the repulsive potential field of the improved artificial potential field method; and the synthetic potential field is obtained by adding the gravitational potential field and the repulsive potential field;

[0191] An initial path determination module 620, for determining an initial path from an initial posture to a target posture; wherein the initial path does not pass through a posture with minimum potential energy;

[0192] The initial path updating module 630 is used to traverse each initial motion posture in the initial path in the order of the total potential energy from large to small, and execute for each traversed initial motion posture:

[0193] Determine the current resultant potential energy of the traversed initial motion posture through the synthetic potential field;

[0194] By synthesizing the potential field, the candidate combined potential energy of each candidate motion posture contained in the neighborhood of the traversed initial motion posture is determined, and it is determined whether the minimum candidate combined potential energy is less than or equal to the traversed initial motion posture.

[0195] The resultant potential energy of the movement posture;

[0196] If so, the candidate motion pose corresponding to the smallest candidate combined potential energy is used to replace the initial pose traversed.

[0197] Movement pose to update the initial path;

[0198] If not, keep the initial motion pose traversed;

[0199] The motion path determination module 640 is used to determine the updated initial path at the end of the traversal as the motion path in the motion environment.

[0200] Figure 7 The structure diagram of an electronic device provided by the embodiment of the present disclosure is shown in FIG. Figure 7 As shown, the electronic device 700 includes one or more processors 701 and a memory 702 .

[0201] The processor 701 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 700 to perform desired functions.

[0202] The memory 702 may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on a computer-readable storage medium, and the processor 701 may run the program instructions to implement the path planning method and / or other desired functions in any embodiment of the present disclosure described above. Various contents such as gain factors, cooling factors, and each current motion posture constituting the motion path may also be stored in the computer-readable storage medium.

[0203] In one example, the electronic device 700 may further include: an input device 703 and an output device 704, which are interconnected via a bus system and / or other forms of connection mechanisms (not shown). The input device 703 may include, for example, a keyboard, a mouse, etc. The output device 704 may output various information to the outside. The output device 704 may include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, etc.

[0204] Of course, to simplify, Figure 7 Only some of the components related to the present disclosure in the electronic device 700 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device 700 may also include any other appropriate components.

[0205] In addition to the above methods and devices, the embodiments of the present disclosure may also be a computer program product, which includes computer program instructions. When the computer program instructions are executed by a processor, the processor executes the path planning method provided by any embodiment of the present disclosure.

[0206] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the disclosed embodiments, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0207] In addition, the embodiments of the present disclosure may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the path planning method provided by any embodiment of the present disclosure.

[0208] Computer readable storage media can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0209] It should be noted that the terms used in the present disclosure are only for describing specific embodiments, rather than limiting the scope of the present application. As shown in the present disclosure specification and claims, unless the context clearly indicates an exception, the words "one", "a", "a kind of" and / or "the" do not specifically refer to the singular, but may also include the plural. The term "and / or" includes any one and all combinations of one or more related listed items. The terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method or device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the presence of other identical elements in the process, method or device including the elements.

[0210] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A path planning method, characterized in that: include: Determine the minimum potential energy posture in the motion environment by using a deterministic annealing algorithm and a synthetic potential field pre-constructed by an improved artificial potential field method; wherein the gravitational potential field and the repulsive potential field of the improved artificial potential field method both introduce temperature variables and cooling factors related to the deterministic annealing algorithm; and the synthetic potential field is obtained by adding the gravitational potential field and the repulsive potential field; Determine the initial posture as the current motion posture, and determine the current resultant potential energy of the current motion posture through the synthetic potential field; Determine each candidate motion posture contained in the neighborhood of the current motion posture, and determine the candidate combined potential energy of each candidate motion posture through the synthetic potential field; wherein each candidate motion posture does not contain the minimum potential energy posture; If the smallest candidate combined potential energy is less than or equal to the current combined potential energy, the candidate motion posture corresponding to the smallest candidate combined potential energy is used as the next motion posture, and the current motion posture is updated using the next motion posture; Return to the step of determining the current combined potential energy of the current motion posture through the synthetic potential field until the current motion posture is the target posture, and the current motion postures between the initial posture and the target posture constitute the motion path in the motion environment.

2. The method according to claim 1, characterized in that Using a deterministic annealing algorithm and a pre-constructed synthetic potential field using an improved artificial potential field method, the minimum potential energy pose in the motion environment is determined, including: For any current temperature value among the temperature values ​​of the deterministic annealing algorithm, determine the minimum potential energy corresponding to the current temperature value by using the minimum value of the objective function of the deterministic annealing algorithm; If the difference between the minimum potential energy corresponding to the current temperature value and the minimum potential energy corresponding to the previous adjacent temperature value is greater than the potential energy threshold, the current temperature value is reduced by using the cooling factor to obtain the next adjacent temperature value to update the current temperature value, and the step of returning to execute the minimum value of the objective function of the deterministic annealing algorithm and determining the minimum potential energy corresponding to the current temperature value is performed until the corresponding difference is less than or equal to the potential energy threshold; If the difference between the minimum potential energy corresponding to the current temperature value and the minimum potential energy corresponding to the previous adjacent temperature value is less than or equal to the potential energy threshold, the posture at the minimum potential energy corresponding to the current temperature value is determined as the minimum potential energy posture.

3. The method according to claim 1, characterized in that After determining each candidate motion posture included in the neighborhood of the current motion posture and determining the candidate resultant potential energy of each candidate motion posture through the synthetic potential field, the method further includes: If the minimum candidate combined potential energy is greater than the current combined potential energy, the gravitational potential field and the repulsive potential field corresponding to the current motion posture are adjusted by the deterministic annealing algorithm so that the current motion posture jumps out of the posture at the local minimum potential energy; The motion posture at the end of the adjustment is determined as the current motion posture, and the step of determining the current combined potential energy of the current motion posture through the synthetic potential field is returned to execute until the current motion posture is the target posture. The current motion postures between the initial posture and the target posture constitute the motion path in the motion environment.

4. The method according to claim 3, characterized in that: The step of adjusting the gravitational potential field and the repulsive potential field corresponding to the current motion posture by the deterministic annealing algorithm so as to make the current motion posture jump out of the posture at the local minimum potential energy includes: Determining the minimum potential energy corresponding to each temperature value by the minimum value of the objective function of the deterministic annealing algorithm; The highest temperature value is determined as the current temperature value, and whether the optimization condition is met; If not, and it is determined that the current minimum potential energy corresponding to the current temperature value is within the neighborhood of the current motion posture, then when the distance between the posture at the current minimum potential energy and the current motion posture is less than or equal to the repulsive distance threshold, the current temperature value is increased based on the cooling factor until the distance between the posture at the minimum potential energy corresponding to the increased current temperature value and the current motion posture is greater than the repulsive distance threshold; wherein the repulsive distance threshold is the maximum distance value of the obstacle area in the motion environment that exerts a repulsive effect on the moving object; Based on the increased current temperature value, determine the minimum candidate combined potential energy within the neighborhood of the current motion posture, and when the minimum candidate combined potential energy is less than or equal to the current combined potential energy, use the candidate motion posture corresponding to the minimum candidate combined potential energy as the next motion posture, and use the next motion posture to update the current motion posture; The current temperature value after the temperature rise is cooled down based on the cooling factor, and the current temperature value is updated with the temperature value after the temperature drop, and the step of determining whether the optimization condition is met is returned to be executed.

5. The method according to claim 4, characterized in that The method further comprises: If it is determined that the current minimum potential energy corresponding to the current temperature value is not within the neighborhood of the current motion posture, the minimum candidate combined potential energy is determined within the neighborhood of the current motion posture, and when the minimum candidate combined potential energy is less than or equal to the current combined potential energy, the candidate motion posture corresponding to the minimum candidate combined potential energy is used as the next motion posture, and the current motion posture is updated using the next motion posture until it is determined that the current minimum potential energy corresponding to the current temperature value is within the neighborhood of the current motion posture.

6. A path planning method, characterized in that: include: Determine the minimum potential energy posture in the motion environment by using a deterministic annealing algorithm and a synthetic potential field pre-constructed by an improved artificial potential field method; wherein the gravitational potential field and the repulsive potential field of the improved artificial potential field method both introduce temperature variables and cooling factors related to the deterministic annealing algorithm; and the synthetic potential field is obtained by adding the gravitational potential field and the repulsive potential field; Determining an initial path from an initial posture to a target posture; wherein the initial path does not pass through the minimum potential energy posture; Traverse each initial motion posture in the initial path in the order of the total potential energy from large to small, and execute for each traversed initial motion posture: Determine the current resultant potential energy of the traversed initial motion posture through the synthetic potential field; Determine the candidate combined potential energy of each candidate motion posture contained in the neighborhood of the traversed initial motion posture through the synthetic potential field, and determine whether the minimum candidate combined potential energy is less than or equal to the combined potential energy of the traversed initial motion posture; If so, the candidate motion posture corresponding to the smallest candidate combined potential energy is used to replace the traversed initial motion posture to update the initial path; If not, keep the initial motion pose traversed; The updated initial path at the end of the traversal is determined as the motion path in the motion environment.

7. A path planning device, characterized in that: include: A minimum potential energy posture determination module is used to determine the minimum potential energy posture in a motion environment by using a deterministic annealing algorithm and a synthetic potential field pre-constructed by an improved artificial potential field method; wherein the gravitational potential field and the repulsive potential field of the improved artificial potential field method both introduce temperature variables and cooling factors related to the deterministic annealing algorithm; and the synthetic potential field is obtained by adding the gravitational potential field and the repulsive potential field; A current resultant potential energy determination module, used to determine the initial posture as the current motion posture, and determine the current resultant potential energy of the current motion posture through the synthetic potential field; A candidate total potential energy determination module, used to determine each candidate motion posture contained in the neighborhood of the current motion posture, and determine the candidate total potential energy of each candidate motion posture through the synthetic potential field; wherein each candidate motion posture does not contain the minimum potential energy posture; A current motion posture updating module, configured to use the candidate motion posture corresponding to the smallest candidate combined potential energy as the next motion posture if the smallest candidate combined potential energy is less than or equal to the current combined potential energy, and to update the current motion posture using the next motion posture; A loop planning trigger module is used to return to the step of determining the current combined potential energy of the current motion posture through the synthetic potential field until the current motion posture is the target posture, and the current motion postures between the initial posture and the target posture constitute the motion path in the motion environment.

8. A path planning device, characterized in that: include: A minimum potential energy posture determination module is used to determine the minimum potential energy posture in a motion environment by using a deterministic annealing algorithm and a synthetic potential field pre-constructed by an improved artificial potential field method; wherein the gravitational potential field and the repulsive potential field of the improved artificial potential field method both introduce temperature variables and cooling factors related to the deterministic annealing algorithm; and the synthetic potential field is obtained by adding the gravitational potential field and the repulsive potential field; An initial path determination module, used to determine an initial path from an initial posture to a target posture; wherein the initial path does not pass through the minimum potential energy posture; The initial path updating module is used to traverse each initial motion posture in the initial path in the order of total potential energy from large to small, and execute for each traversed initial motion posture: Determine the current resultant potential energy of the traversed initial motion posture through the synthetic potential field; Determine the candidate combined potential energy of each candidate motion posture contained in the neighborhood of the traversed initial motion posture through the synthetic potential field, and determine whether the minimum candidate combined potential energy is less than or equal to the combined potential energy of the traversed initial motion posture; If so, the candidate motion posture corresponding to the smallest candidate combined potential energy is used to replace the traversed initial motion posture to update the initial path; If not, keep the initial motion pose traversed; The motion path determination module is used to determine the updated initial path at the end of the traversal as the motion path in the motion environment.

9. An electronic device, characterized in that: The electronic device comprises: Processor and memory; The processor is used to execute the path planning method according to any one of claims 1 to 6 by calling the program or instruction stored in the memory.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program or an instruction, and the program or the instruction enables a computer to execute the path planning method according to any one of claims 1 to 6.

Images