Robot trajectory evaluation method, related device, equipment, system and storage medium

Abstract

The invention discloses a robot track evaluation method, a related device, equipment, a system and a storage medium, and the method comprises the steps: obtaining a to-be-evaluated track of a target robot; obtaining a first score of the to-be-evaluated track about smoothness based on the curvature of the track points on the to-be-evaluated track, and obtaining a second score of the to-be-evaluated track about smoothness based on the track curve function of the to-be-evaluated track; and fusing the first score and the second score of the to-be-evaluated track about the smoothness to obtain a final score of the to-be-evaluated track about the smoothness. According to the scheme, the smoothness of the motion trail of the robot can be accurately evaluated.

Description

Technical Field

[0001] The present application relates to the field of robotics technology, and in particular to a robot trajectory evaluation method and related devices, equipment, systems and storage media. Background Art

[0002] With the rapid development of robotics technology, robots have been widely used in many scenarios. In some application scenarios, the smoothness of the robot's motion trajectory is one of the important indicators of the robot.

[0003] For example, a chess-playing robot usually needs to use its mechanical arm to perform operations such as picking up and dropping pieces, and its motion trajectory is the route taken by the end of the mechanical arm. Usually, the movements of a chess-playing robot are required to be smooth, natural, and efficient, while a bad route will make the movements of the chess-playing robot look stiff, sluggish, and inefficient. In view of this, how to accurately evaluate the smoothness of the robot's motion trajectory is particularly important. Summary of the invention

[0004] The main technical problem solved by the present application is to provide a robot trajectory evaluation method and related devices, equipment, system and storage medium, which can accurately evaluate the smoothness of the robot's motion trajectory.

[0005] In order to solve the above technical problems, the first aspect of the present application provides a robot trajectory evaluation method, including: obtaining a trajectory to be evaluated of a target robot; obtaining a first score of the trajectory to be evaluated regarding smoothness based on the curvature of the trajectory points on the trajectory to be evaluated, and obtaining a second score of the trajectory to be evaluated regarding smoothness based on the trajectory curve function of the trajectory to be evaluated; fusing the first score and the second score of the trajectory to be evaluated regarding smoothness to obtain a final score of the trajectory to be evaluated regarding smoothness.

[0006] In order to solve the above technical problems, the second aspect of the present application provides a robot trajectory evaluation device, including: a trajectory acquisition module, a trajectory scoring module and a scoring fusion module, the trajectory acquisition module is used to acquire the trajectory to be evaluated of the target robot; the trajectory scoring module is used to obtain a first score of the trajectory to be evaluated regarding smoothness based on the curvature of the trajectory points on the trajectory to be evaluated, and to obtain a second score of the trajectory to be evaluated regarding smoothness based on the trajectory curve function of the trajectory to be evaluated; the scoring fusion module is used to fuse the first score and the second score of the trajectory to be evaluated regarding smoothness to obtain a final score of the trajectory to be evaluated regarding smoothness.

[0007] In order to solve the above technical problems, the third aspect of the present application provides an electronic device, which at least includes a memory and a processor coupled to each other, the memory at least stores program instructions, and the processor is used to execute the program instructions to implement the robot trajectory evaluation method in the above first aspect.

[0008] In order to solve the above-mentioned technical problems, the fourth aspect of the present application provides a robot trajectory evaluation system, including a measuring instrument, a target robot and a data processing device, the measuring instrument is used to measure the actual motion trajectory of the target robot, the measuring instrument is communicatively connected to the data processing device, the data processing device obtains the actual motion trajectory from the measuring instrument as the trajectory to be evaluated, and the data processing device is the electronic device in the above-mentioned third aspect.

[0009] In order to solve the above technical problems, the fifth aspect of the present application provides a computer-readable storage medium storing program instructions that can be executed by a processor, and the program instructions are used to implement the robot trajectory evaluation method of the first aspect.

[0010] The above scheme obtains the trajectory to be evaluated of the target robot, and then obtains a first score of the trajectory to be evaluated regarding smoothness based on the curvature of the trajectory points on the trajectory to be evaluated, and obtains a second score of the trajectory to be evaluated regarding smoothness based on the estimated trajectory curve function to be evaluated, and the first score and the second score of the trajectory to be evaluated regarding smoothness are merged to obtain a final score of the trajectory to be evaluated regarding smoothness. Therefore, the two mathematical indicators of curve curvature and curve function can be combined to comprehensively characterize the smoothness of the trajectory to be evaluated, and the smoothness of the robot motion trajectory can be evaluated as accurately as possible. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 It is a flowchart of an embodiment of the robot trajectory evaluation method of the present application;

[0012] Figure 2 It is a schematic diagram of the framework of an embodiment of a robot trajectory evaluation device of the present application;

[0013] Figure 3 It is a schematic diagram of the framework of an embodiment of the electronic device of the present application;

[0014] Figure 4 It is a schematic diagram of the framework of an embodiment of the robot trajectory evaluation system of the present application;

[0015] Figure 5 It is a schematic diagram of a framework of an embodiment of a computer-readable storage medium of the present application. DETAILED DESCRIPTION

[0016] The scheme of the embodiment of the present application is described in detail below in conjunction with the drawings of the specification.

[0017] In the following description, for the purpose of explanation rather than limitation, specific details such as specific system structures, interfaces, and technologies are provided to facilitate a thorough understanding of the present application.

[0018] The terms "system" and "network" are often used interchangeably in this article. The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the fragment " / " in this article generally indicates that the associated objects before and after are in an "or" relationship. In addition, "many" in this article means two or more than two.

[0019] See also Figure 1 , Figure 1 This is a flow chart of an embodiment of the robot trajectory evaluation method of the present application. Specifically, it may include the following steps:

[0020] Step S11: Obtain the trajectory to be evaluated of the target robot.

[0021] In one implementation scenario, the target robot may include but is not limited to a chess-playing robot, such as a Go robot, etc. The specific type of the target robot is not limited here.

[0022] In one implementation scenario, the target robot may be provided with a mechanical arm, and the trajectory to be evaluated may be the end motion trajectory of the mechanical arm. Of course, the trajectory to be evaluated may not be limited to the end motion trajectory of the mechanical arm. For example, when the mechanical arm also includes an elbow joint to realize free rotation under multiple degrees of freedom, the trajectory to be evaluated may also include the joint motion trajectory of the mechanical arm. Here, the specific part of the target robot to which the trajectory to be evaluated belongs is not limited.

[0023] In one implementation scenario, the trajectory to be evaluated can be obtained by measuring the target robot during its motion using a measuring instrument. Exemplarily, the measuring instrument may include, but is not limited to, a laser tracker, a camera, etc., and the specific type of the measuring instrument is not limited here. In addition, in order to further enable the trajectory to be evaluated to reflect the actual motion trajectory of the target robot as realistically as possible, a high-precision, high-frame-rate measuring instrument may be used to improve the distribution density and coordinate accuracy of the trajectory points on the trajectory to be evaluated.

[0024] In an implementation scenario, the trajectory to be evaluated may be a trajectory in a two-dimensional coordinate system. Taking the chess robot as an example, a two-dimensional coordinate system may be established on the plane where the chessboard is located, so that the motion trajectory of the target robot may be measured by a measuring instrument in a direction perpendicular to the plane where the chessboard is located, so as to obtain the trajectory to be evaluated in the two-dimensional coordinate system; or, the trajectory to be evaluated may be a trajectory in a three-dimensional coordinate system. Taking the chess robot as an example, an XOY coordinate plane may be established on the plane where the chessboard is located, and a Z axis may be established perpendicular to the XOY coordinate plane, so as to establish a three-dimensional coordinate system, and then a measuring instrument may be used to measure the motion trajectory of the target robot in a direction inclined to the X-axis, Y-axis, and Z-axis, so as to obtain the trajectory to be evaluated in the three-dimensional coordinate system. Of course, the above examples are only several possible examples of obtaining the trajectory to be evaluated, and do not limit other possible ways of obtaining the trajectory to be evaluated. Other possible ways of obtaining the trajectory to be evaluated will not be given examples one by one here.

[0025] Step S12: obtaining a first score of the trajectory to be evaluated regarding smoothness based on the curvature of the trajectory points on the trajectory to be evaluated, and obtaining a second score of the trajectory to be evaluated regarding smoothness based on the trajectory curve function of the trajectory to be evaluated.

[0026] In an implementation scenario, after obtaining the trajectory to be evaluated, three adjacent trajectory points on the trajectory to be evaluated can be obtained, and they are sequentially used as the first trajectory point, the second trajectory point, and the third trajectory point. Based on the trajectory coordinates of the first trajectory point, the trajectory coordinates of the second trajectory point, and the trajectory coordinates of the third trajectory point, the angle between the first connecting line and the second connecting line is obtained, and the first connecting line is the connecting line between the first trajectory point and the second trajectory point, and the second connecting line is the connecting line between the second trajectory point and the third trajectory point. Based on the angle and the length of either the first connecting line or the second connecting line, the radius of the target circle is obtained, and the target circle is the circle where the first trajectory point, the second trajectory point, and the third trajectory point are located together, and based on the radius of the target circle, the curvature of the trajectory to be evaluated at the second trajectory point is obtained. In the above method, by performing correlation calculations on the three adjacent trajectory points to obtain the curvature of the trajectory to be evaluated at the middle position trajectory point among the three adjacent trajectory points, the accuracy of the curvature at each trajectory point can be improved.

[0027] In a specific implementation scenario, taking the trajectory to be evaluated as represented in a two-dimensional coordinate system as an example, the trajectory to be evaluated can be represented as:

[0028] Path = {[x 1 ,y 1 ],[x 2 ,y 2 ],…,[x n ,y n ]}……(1)

[0029] In the above formula (1), n ​​represents the total number of trajectory points on the trajectory to be evaluated, [x i ,y i ] represents the trajectory coordinates of the i-th trajectory point on the trajectory to be evaluated in the two-dimensional coordinate system. Of course, the above example is only a possible representation of the trajectory to be evaluated when the trajectory to be evaluated is represented in the two-dimensional coordinate system as an example. Here, the representation of the trajectory to be evaluated in other coordinate systems will not be given one by one.

[0030] In a specific implementation scenario, the angle between the first connecting line and the second connecting line can be calculated by cosine similarity. The three adjacent trajectory points are represented as P 1 ,P 2 ,P 3 For example, according to the trajectory coordinates of the trajectory points, the connection trajectory point P can be obtained 1 ,P 2 Vector representation of And connect the trajectory point P 2 ,P 3 Vector representation of Then we can get the angle θ between the two according to the calculation formula of cosine similarity:

[0031]

[0032] In the above formula (2), Both represent the magnitude of the vector, that is, the length of the first connecting line and the second connecting line. -1 Represents the inverse cosine function.

[0033] In a specific implementation scenario, when the sampling frequency is high, the lengths of the first connection line and the second connection line can be considered to be the same. Still taking the above example, it can be expressed as:

[0034]

[0035] In the above formula (3), Δs represents the length of the first connecting line and the second connecting line.

[0036] In a specific implementation scenario, after obtaining the angle between the first connecting line and the second connecting line, the triangle formed by the first track point, the second track point, and the third track point can be obtained, and as mentioned above, when the sampling frequency is high, the lengths of the first connecting line and the second connecting line can be considered the same, then the triangle can be considered an isosceles triangle. At the same time, the first track point, the second track point, the third track point, and the center of the circle where the three are located can also be connected to form an isosceles triangle, such as the first track point, the second track point and the center of the circle can be connected to form an isosceles triangle, the second track point, the third track point and the center of the circle can be connected to form an isosceles triangle, and the waist length of these two isosceles triangles is the radius, the side length is the aforementioned length Δs, and the angle between the waist and the base is θ / 2, so according to the cosine formula, the radius R can be obtained:

[0037]

[0038] On this basis, the inverse of the radius can be obtained as the curvature Curv of the trajectory to be evaluated at the second trajectory point:

[0039]

[0040] In one implementation scenario, after obtaining the curvature at each track point on the trajectory to be evaluated, a curvature score can be performed. Specifically, based on the maximum curvature of the target robot, several curvature intervals can be obtained, and each curvature interval does not overlap with each other, and based on the curvature interval where the track point on the trajectory to be evaluated is located, a sub-score of the track point is obtained, and then based on the sub-scores of each track point on the trajectory to be evaluated, a fusion is performed to obtain a first score of the smoothness of the trajectory to be evaluated. In the above method, the sub-score of the smoothness of the track point is obtained by the curvature interval where the curvature at the track point is located, and the sub-scores of each track point on the trajectory to be evaluated are fused to obtain the first score of the smoothness of the trajectory to be evaluated. The sub-scores at each track point can be comprehensively evaluated for smoothness, which helps to improve the accuracy of smoothness scoring in the curvature dimension.

[0041] In a specific implementation scenario, in order to obtain the curvature interval, several score values ​​sorted from small to large can be obtained first, and the maximum score value can be 1, and then the endpoint value of the curvature interval is obtained based on the product of the adjacent score values ​​and the limiting maximum curvature. For example, taking several score values ​​1 / 4, 1 / 2, and 1 sorted from small to large as an example, for the convenience of description, the limiting maximum curvature can be recorded as Curv p , we can get a curvature interval based on the adjacent fractional values ​​1 / 4 and 1 / 2 And based on the adjacent fractional values ​​1 / 2 and 1, another curvature interval is obtained Of course, the above examples are only several possible examples of curvature intervals, and do not limit other possible situations of curvature intervals. Other possible situations of curvature intervals will not be given one by one here. In the above method, a number of score values ​​are obtained in ascending order, and the maximum score value is 1, and then the endpoint values ​​of the curvature interval are obtained based on the product of the adjacent score values ​​and the maximum curvature limit, so that a number of non-overlapping curvature intervals can be set to facilitate the subsequent curvature scoring of the trajectory points.

[0042] In a specific implementation scenario, each curvature interval may be provided with a curvature score, and the endpoint values ​​of the curvature interval (such as an upper limit, a lower limit, etc.) may be correlated with the curvature score of the curvature interval. Exemplarily, the curvature score of the curvature interval may be negatively correlated with the endpoint value of the curvature interval, that is, the larger the endpoint value of the curvature interval, the smaller the curvature score of the curvature interval, and conversely, the smaller the endpoint value of the curvature interval, the larger the curvature score of the curvature interval. Alternatively, the curvature score of the curvature interval may also be positively correlated with the endpoint value of the curvature interval, and the correlation between the endpoint value of the curvature interval and the curvature score of the curvature interval is not limited here. In addition, the sub-score of the trajectory point may specifically be the curvature score of the curvature interval where the curvature of the trajectory point is located. Still including a number of curvature intervals and For example, the former can be set with a curvature score r 1 , the latter can be equipped with a curvature score r 2 , then the first score of the trajectory to be evaluated on smoothness can be expressed as:

[0043] K=n 1 × 1 +n 2 × 2 ……(6)

[0044] In the above formula (6), n 1 Indicates that the curvature is within the curvature interval The total number of trajectory points within n 2 Indicates that the curvature is within the curvature interval The total number of trajectory points within. It should be noted that the curvature score of the curvature interval may not be a fixed value, and may be customized according to actual needs. The specific value of the curvature score of the curvature interval is not limited here. As shown in the above formula (6), the sub-scores of each trajectory point on the trajectory to be evaluated can be fused by addition to obtain a first score of the smoothness of the trajectory to be evaluated. Of course, the fusion method of the sub-scores may not be limited to addition, but may also include but is not limited to weighting, etc. The fusion method of the sub-scores will not be given one by one here. In the above method, each curvature interval is respectively provided with a curvature score, and there is a correlation between the endpoint value of the curvature interval and the curvature score of the curvature interval, and the sub-score of the trajectory point is the curvature score of the curvature interval where the curvature of the trajectory point is located, which can reduce the complexity of obtaining the sub-score of the trajectory point as much as possible.

[0045] In one implementation scenario, the trajectory curve function of the trajectory to be evaluated can be obtained by performing cubic spline interpolation on the trajectory to be evaluated that satisfies the continuity of the second-order derivative. The specific process can refer to the technical details of the aforementioned cubic spline interpolation, which will not be repeated here. In addition, for the convenience of description, the trajectory curve function can be recorded as P(t). Of course, the above example is only a possible example of obtaining the trajectory curve function. The specific method of obtaining the trajectory curve function of the trajectory to be evaluated is not limited here, and examples are not given one by one. On this basis, the square of the second-order derivative of the trajectory curve function can be obtained to obtain the objective function, and then an integral operation is performed based on the objective function to obtain the strain energy of the trajectory curve function as the second score E of the trajectory to be evaluated regarding smoothness:

[0046]

[0047] In the above formula (7), P″(t) represents the second-order derivative of the trajectory curve function, [P″(t)] 2 In the above method, the square of the second-order derivative of the trajectory curve function is obtained to obtain the objective function, and then an integral operation is performed based on the objective function to obtain the strain energy of the trajectory curve function as the second score, and the strain energy of the curve can be used as an evaluation index of the curve smoothness.

[0048] Step S13: A final score of the trajectory to be evaluated regarding smoothness is obtained by fusing the first score and the second score regarding smoothness of the trajectory to be evaluated.

[0049] In an implementation scenario, the first score and the second score can be combined by adding, averaging, weighting, etc. to obtain a final score of the trajectory to be evaluated on smoothness. Taking the weighting of the first score and the second score to obtain the final score of the trajectory to be evaluated on smoothness as an example, the final score can be expressed as:

[0050] S=w 1 ×E+w2 ×K……(8)

[0051] In the above formula (8), w 1 ,w 2 Represents a weight factor. As a possible example, the weight factor may not be a fixed value, and may be set according to actual conditions. The specific value of the weight factor is not limited here.

[0052] In an implementation scenario, after obtaining the final score, the final score of the trajectory to be evaluated regarding smoothness can also be selected as the reward value of the target robot during the next trajectory planning, and the target robot can predict the planned trajectory based on the latest reward value (e.g., trajectory planning can be performed based on a reinforcement learning model), and move according to the planned trajectory to measure the actual motion trajectory of the target robot as the new trajectory to be evaluated of the target robot (e.g., the actual motion trajectory of the target robot when it moves according to the planned trajectory can be measured by the aforementioned measuring instrument to obtain a new trajectory to be evaluated). On this basis, the step of obtaining the trajectory to be evaluated of the target robot can be returned and iterated until the preset end condition is met. It should be noted that the preset end condition can be set according to the actual application needs. Exemplarily, in the case of optimizing the trajectory of the target robot as much as possible and performing trajectory optimization within its full motion cycle, the preset end condition can be set to the target robot stopping working, that is, the loop iteration is stopped until the target robot stops working, otherwise the iteration is repeated in this way; or, in the case of optimizing the motion trajectory of the target robot and taking into account the computational load, the preset end condition can be set to the final score being better than the scoring threshold for several consecutive times (such as three consecutive times, four consecutive times, etc.), that is, when it is detected that the final score is better than the scoring threshold for several consecutive times, it can be considered that the target robot has learned how to plan the desired motion trajectory through previous trajectory planning, and its motion trajectory can no longer be measured and evaluated. Of course, the above examples are only several possible examples of the preset end conditions, and the specific setting method of the preset end conditions is not limited here, and no examples are given one by one. In the above method, after obtaining the final score, the final score of the trajectory to be evaluated regarding smoothness is selected as the reward value of the target robot during the next trajectory planning, and the target robot predicts the planned trajectory based on the latest reward value, and moves according to the planned trajectory to measure the actual motion trajectory of the target robot as the new trajectory to be evaluated of the target robot, and then returns to the step of obtaining the trajectory to be evaluated of the target robot and iterates until the preset end condition is met. The trajectory evaluation can be continuously performed during the movement of the target robot to optimize the trajectory, which helps to continuously improve the smoothness of the motion trajectory of the target robot during each movement of the target robot.

[0053] The above scheme obtains the trajectory to be evaluated of the target robot, and then obtains a first score of the trajectory to be evaluated regarding smoothness based on the curvature of the trajectory points on the trajectory to be evaluated, and obtains a second score of the trajectory to be evaluated regarding smoothness based on the estimated trajectory curve function to be evaluated, and the first score and the second score of the trajectory to be evaluated regarding smoothness are merged to obtain a final score of the trajectory to be evaluated regarding smoothness. Therefore, the two mathematical indicators of curve curvature and curve function can be combined to comprehensively characterize the smoothness of the trajectory to be evaluated, and the smoothness of the robot motion trajectory can be evaluated as accurately as possible.

[0054] See also Figure 2 , Figure 2 It is a schematic diagram of the framework of an embodiment of the robot trajectory evaluation device of the present application. The robot trajectory evaluation device 20 includes: a trajectory acquisition module 21, a trajectory scoring module 22 and a scoring fusion module 23. The trajectory acquisition module 21 is used to acquire the trajectory to be evaluated of the target robot; the trajectory scoring module 22 is used to obtain the first score of the trajectory to be evaluated on the smoothness based on the curvature of the trajectory points on the trajectory to be evaluated, and obtain the second score of the trajectory to be evaluated on the smoothness based on the trajectory curve function of the trajectory to be evaluated; the scoring fusion module 23 is used to fuse the first score and the second score of the trajectory to be evaluated on the smoothness to obtain the final score of the trajectory to be evaluated on the smoothness.

[0055] In the above scheme, the robot trajectory evaluation device 20 obtains the trajectory to be evaluated of the target robot, and then obtains a first score of the smoothness of the trajectory to be evaluated based on the curvature of the trajectory points on the trajectory to be evaluated, and obtains a second score of the smoothness of the trajectory to be evaluated based on the estimated trajectory curve function to be evaluated, and obtains a final score of the smoothness of the trajectory to be evaluated by fusing the first score and the second score of the smoothness of the trajectory to be evaluated. Therefore, the two mathematical indicators of curve curvature and curve function can be combined to comprehensively characterize the smoothness of the trajectory to be evaluated, and the smoothness of the robot motion trajectory can be evaluated as accurately as possible.

[0056] In some disclosed embodiments, the trajectory scoring module 22 includes an interval acquisition submodule, which is used to obtain a number of curvature intervals based on the ultimate maximum curvature of the target robot; wherein the curvature intervals do not overlap with each other; the trajectory scoring module 22 includes a point scoring submodule, which is used to obtain a sub-score of a trajectory point based on the curvature interval in which the curvature of the trajectory point on the trajectory to be evaluated is located; the trajectory scoring module 22 includes a curve scoring submodule, which is used to fuse the sub-scores of each trajectory point on the trajectory to be evaluated to obtain a first score of the trajectory to be evaluated regarding smoothness.

[0057] In some disclosed embodiments, the interval acquisition submodule includes a score acquisition unit, which is used to obtain a number of score values ​​sorted from small to large; wherein the maximum score value is 1; the interval acquisition submodule includes an endpoint determination unit, which is used to obtain the endpoint value of the curvature interval based on the product of adjacent score values ​​and the limiting maximum curvature.

[0058] In some disclosed embodiments, each curvature interval is provided with a curvature score, the endpoint value of the curvature interval is correlated with the curvature score of the curvature interval, and the sub-score of the trajectory point is the curvature score of the curvature interval in which the curvature of the trajectory point is located.

[0059] In some disclosed embodiments, the robot trajectory evaluation device 20 includes a point selection module for acquiring three adjacent trajectory points on the trajectory to be evaluated, which are sequentially used as the first trajectory point, the second trajectory point and the third trajectory point; the robot trajectory evaluation device 20 includes an angle calculation module for obtaining the angle between the first connecting line and the second connecting line based on the trajectory coordinates of the first trajectory point, the trajectory coordinates of the second trajectory point and the trajectory coordinates of the third trajectory point; wherein the first connecting line is the connecting line between the first trajectory point and the second trajectory point, and the second connecting line is the connecting line between the second trajectory point and the third trajectory point; the robot trajectory evaluation device 20 includes a radius determination module for obtaining the radius of the target circle based on the angle and the length of any one of the first connecting line and the second connecting line; wherein the target circle is the circle in which the first trajectory point, the second trajectory point and the third trajectory point are located; the robot trajectory evaluation device 20 includes a curvature calculation module for obtaining the curvature of the second trajectory point based on the radius of the target circle.

[0060] In some disclosed embodiments, the trajectory scoring module 22 includes a function acquisition submodule for acquiring the square of the second-order derivative of the trajectory curve function to obtain the target function; the trajectory scoring module 22 includes a strain calculation submodule for performing an integral operation based on the target function to obtain the strain energy of the trajectory curve function as a second score.

[0061] In some disclosed embodiments, the robot trajectory evaluation device 20 includes a reward acquisition module, which is used to select the final score of the trajectory to be evaluated regarding smoothness as the reward value of the target robot during the next trajectory planning; wherein the target robot obtains the planned trajectory based on the latest reward value prediction, and moves according to the planned trajectory to measure the actual motion trajectory of the target robot as the new trajectory to be evaluated by the target robot; the robot trajectory evaluation device 20 includes a loop iteration module, which is used to return to the step of obtaining the trajectory to be evaluated of the target robot and iterate until a preset end condition is met.

[0062] In some disclosed embodiments, the target robot includes at least a chess-playing robot; and / or the target robot is provided with a robotic arm, and the trajectory to be evaluated is the end motion trajectory of the robotic arm; and / or the trajectory curve function is obtained by performing cubic spline interpolation on the trajectory to be evaluated that satisfies the continuity of the second-order derivative.

[0063] See also Figure 3 , Figure 3 : is a schematic diagram of the framework of an embodiment of an electronic device of the present application. The electronic device 30 includes at least a memory 31 and a processor 32 coupled to each other, the memory 31 stores at least program instructions, and the processor 32 is used to execute the program instructions to implement the steps in any of the above robot trajectory evaluation method embodiments. For details, please refer to the aforementioned disclosed embodiments, which will not be repeated here. As a possible example, the electronic device 30 may include but is not limited to a smart phone, a tablet computer, a server, etc., and the specific type of the electronic device 30 is not limited here.

[0064] Specifically, the processor 32 is used to control itself and the memory 31 to implement the steps in any of the above-mentioned robot trajectory evaluation method embodiments. The processor 32 can also be called a CPU (Central Processing Unit). The processor 32 may be an integrated circuit chip with signal processing capabilities. The processor 32 can also be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field-programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. In addition, the processor 32 can be implemented by an integrated circuit chip.

[0065] In the above scheme, the electronic device 30 obtains the trajectory to be evaluated of the target robot, and then obtains a first score of the smoothness of the trajectory to be evaluated based on the curvature of the trajectory points on the trajectory to be evaluated, and obtains a second score of the smoothness of the trajectory to be evaluated based on the estimated trajectory curve function to be evaluated, and the first score and the second score of the smoothness of the trajectory to be evaluated are merged to obtain a final score of the smoothness of the trajectory to be evaluated. Therefore, the two mathematical indicators of curve curvature and curve function can be combined to comprehensively characterize the smoothness of the trajectory to be evaluated, and the smoothness of the robot motion trajectory can be evaluated as accurately as possible.

[0066] See also Figure 4 , Figure 4It is a schematic diagram of the framework of an embodiment of the robot trajectory evaluation system of the present application. The robot trajectory evaluation system 40 includes: a measuring instrument 41, a target robot 42 and a data processing device 43. The measuring instrument 41 is used to measure the actual motion trajectory of the target robot 42. The measuring instrument 41 is connected to the data processing device 43 for communication. The data processing device 43 obtains the actual motion trajectory from the measuring instrument 41 as the trajectory to be evaluated, and the data processing device 43 is an electronic device in the above-mentioned electronic device embodiment. For details, please refer to the above-mentioned electronic device embodiment, which will not be repeated here. It should be noted that the measuring instrument 41 may include but is not limited to a laser tracker, a camera, etc., and the specific type of the measuring instrument 41 is not limited here.

[0067] In the above scheme, the robot trajectory evaluation system 40 includes: a measuring instrument 41, a target robot 42 and a data processing device 43. The measuring instrument 41 is used to measure the actual motion trajectory of the target robot 42. The measuring instrument 41 is communicatively connected with the data processing device 43. The data processing device 43 obtains the actual motion trajectory from the measuring instrument 41 as the trajectory to be evaluated. The data processing device 43 is an electronic device in the above electronic device embodiment, which can comprehensively characterize the smoothness of the trajectory to be evaluated by combining two mathematical indicators, namely, the curve curvature and the curve function, and can evaluate the smoothness of the robot motion trajectory as accurately as possible.

[0068] See also Figure 5 , Figure 5 1 is a schematic diagram of a framework of an embodiment of a computer-readable storage medium 50 of the present application. The computer-readable storage medium 50 stores program instructions 51 that can be executed by a processor, and the program instructions 51 are used to implement the steps in any of the above robot trajectory evaluation method embodiments.

[0069] In the above scheme, the computer-readable storage medium 50 obtains the trajectory to be evaluated of the target robot, and then obtains a first score of the smoothness of the trajectory to be evaluated based on the curvature of the trajectory points on the trajectory to be evaluated, and obtains a second score of the smoothness of the trajectory to be evaluated based on the estimated trajectory curve function to be evaluated, and the first score and the second score of the smoothness of the trajectory to be evaluated are merged to obtain a final score of the smoothness of the trajectory to be evaluated. Therefore, the two mathematical indicators of curve curvature and curve function can be combined to comprehensively characterize the smoothness of the trajectory to be evaluated, and the smoothness of the robot motion trajectory can be evaluated as accurately as possible.

[0070] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0071] The above description of various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other, and for the sake of brevity, they will not be repeated herein.

[0072] In the several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation described above is only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0073] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0074] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0075] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of each implementation method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

[0076] If the technical solution of this application involves personal information, the product using the technical solution of this application has clearly informed the personal information processing rules and obtained the individual's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using the technical solution of this application has obtained the individual's separate consent before processing the sensitive personal information, and at the same time meets the "explicit consent" requirement. For example, on personal information collection devices such as cameras, clear and prominent signs are set to inform that the personal information collection scope has been entered and personal information will be collected. If the individual voluntarily enters the collection scope, it is deemed that he or she agrees to the collection of his or her personal information; or on the device that processes personal information, the personal information processing rules are notified by obvious signs / information, and the individual's authorization is obtained through pop-up information or by asking the individual to upload his or her personal information; among them, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the type of personal information processed.

Claims

1. A robot trajectory evaluation method, characterized in that: include: Obtain the trajectory to be evaluated of the target robot; Based on the curvature of the trajectory points on the trajectory to be evaluated, a first score of the trajectory to be evaluated with respect to smoothness is obtained, and based on the trajectory curve function of the trajectory to be evaluated, a second score of the trajectory to be evaluated with respect to smoothness is obtained; A final score of the trajectory to be evaluated regarding smoothness is obtained by fusing the first score and the second score of the trajectory to be evaluated regarding smoothness.

2. The method according to claim 1, characterized in that The step of obtaining a first score of the trajectory to be evaluated regarding smoothness based on the curvature of the trajectory points on the trajectory to be evaluated includes: Based on the maximum curvature of the target robot, a plurality of curvature intervals are obtained; wherein the curvature intervals do not overlap with each other; Obtaining a sub-score of the trajectory point based on a curvature interval in which the curvature of the trajectory point on the trajectory to be evaluated is located; The sub-scores of the trajectory points on the trajectory to be evaluated are fused to obtain a first score of the trajectory to be evaluated regarding smoothness.

3. The method according to claim 2, characterized in that The method of obtaining a plurality of curvature intervals based on the maximum curvature limit of the target robot includes: Obtain a number of score values ​​sorted from small to large, wherein the maximum score value is 1; The endpoint values ​​of the curvature interval are obtained based on the products of the adjacent fractional values ​​and the limiting maximum curvature.

4. The method according to claim 2, characterized in that: Each of the curvature intervals is respectively provided with a curvature score, the endpoint value of the curvature interval is correlated with the curvature score of the curvature interval, and the sub-score of the trajectory point is the curvature score of the curvature interval in which the curvature of the trajectory point is located.

5. The method according to claim 1, characterized in that Before obtaining a first score of the trajectory to be evaluated regarding smoothness based on the curvature of the trajectory points on the trajectory to be evaluated, the method further includes: Acquire three adjacent trajectory points on the trajectory to be evaluated, and use them as the first trajectory point, the second trajectory point and the third trajectory point in sequence; Based on the trajectory coordinates of the first trajectory point, the trajectory coordinates of the second trajectory point and the trajectory coordinates of the third trajectory point, an angle between a first connecting line and a second connecting line is obtained; wherein the first connecting line is a connecting line between the first trajectory point and the second trajectory point, and the second connecting line is a connecting line between the second trajectory point and the third trajectory point; Based on the angle and the length of any one of the first connecting line and the second connecting line, the radius of the target circle is obtained; wherein the target circle is a circle where the first trajectory point, the second trajectory point and the third trajectory point are located together; Based on the radius of the target circle, the curvature of the second trajectory point is obtained.

6. The method according to claim 1, characterized in that The step of obtaining a second score of the trajectory to be evaluated regarding smoothness based on the trajectory curve function of the trajectory to be evaluated includes: Obtaining the square of the second-order derivative of the trajectory curve function to obtain the target function; An integral operation is performed based on the objective function to obtain the strain energy of the trajectory curve function as the second score.

7. The method according to claim 1, characterized in that After fusing the first score and the second score based on the smoothness of the trajectory to be evaluated to obtain a final score of the trajectory to be evaluated regarding smoothness, the method further includes: The final score of the trajectory to be evaluated on smoothness is selected as the reward value of the target robot in the next trajectory planning; wherein the target robot predicts the planned trajectory based on the latest reward value, and moves according to the planned trajectory, so as to measure the actual motion trajectory of the target robot as the new trajectory to be evaluated of the target robot; Return to the step of obtaining the trajectory to be evaluated of the target robot and iterate until a preset end condition is met.

8. The method according to any one of claims 1 to 7, characterized in that: The target robot at least includes a chess-playing robot; And / or, the target robot is provided with a mechanical arm, and the trajectory to be evaluated is a terminal motion trajectory of the mechanical arm; And / or, the trajectory curve function is obtained by performing cubic spline interpolation on the trajectory to be evaluated that satisfies the continuity of the second-order derivative.

9. A robot trajectory evaluation device, characterized in that: include: A trajectory acquisition module is used to obtain the trajectory to be evaluated of the target robot; A trajectory scoring module, configured to obtain a first score of the trajectory to be evaluated regarding smoothness based on the curvature of the trajectory points on the trajectory to be evaluated, and to obtain a second score of the trajectory to be evaluated regarding smoothness based on the trajectory curve function of the trajectory to be evaluated; The scoring fusion module is used to fuse the first score and the second score of the trajectory to be evaluated on the smoothness to obtain a final score of the trajectory to be evaluated on the smoothness.

10. An electronic device, characterized in that: The robot trajectory evaluation method comprises at least a memory and a processor coupled to each other, wherein the memory stores at least program instructions, and the processor is used to execute the program instructions to implement the robot trajectory evaluation method according to any one of claims 1 to 8.

11. A robot trajectory evaluation system, characterized in that: It includes a measuring instrument, a target robot and a data processing device, wherein the measuring instrument is used to measure the actual motion trajectory of the target robot, the measuring instrument is communicatively connected with the data processing device, the data processing device obtains the actual motion trajectory from the measuring instrument as the trajectory to be evaluated, and the data processing device is the electronic device described in claim 10.

12. A computer-readable storage medium, characterized in that: Program instructions that can be executed by a processor are stored, and the program instructions are used to implement the robot trajectory evaluation method according to any one of claims 1 to 8.

Images