Robot trajectory generation method and system

Abstract

The embodiment of the present application relates to the technical field of robots, and discloses a robot trajectory generation method and system, wherein the trajectory generation method comprises the following steps: receiving an actual trajectory point position at a current moment, which is recorded as a current position; determining a processed trajectory point position at the current moment based on a historical trajectory point position and the current position, which is recorded as a current processed position; and generating a robot virtual trajectory curve according to the current processed position.The scheme of the embodiment of the present application can inhibit or even eliminate high-frequency jitter, and improve trajectory quality.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of robot technology, and in particular to a robot trajectory generation method and system. BACKGROUND

[0002] In the application scenario of manual dragging robot teaching, the original trajectory point data generated by the operator due to inconsistent manual dragging speed rhythm often contains high-frequency jitter, noise and affects the trajectory quality due to different operator proficiency. These defects, if directly used to drive the robot, will cause the robot to move unstably and produce violent vibration, which not only affects the task completion quality, but also endangers the safety of equipment and personnel.

[0003] The prior art often uses a fixed low-pass filter to smooth the current trajectory, but the filtering parameters are static and do not refer to historical data, so the processed trajectory cannot adapt to the dynamic changes of the operation habits or movement speed of different operators, especially when processing high-speed and violent movement and low-speed and fine operation, it is difficult to balance smoothness and real-time performance at the same time, and lacks intelligence and robustness. SUMMARY

[0004] To address the defects, the embodiments of the present application disclose a robot trajectory generation method and system, which can suppress or even eliminate high-frequency jitter and improve trajectory quality.

[0005] The first aspect of the embodiments of the present application discloses a robot trajectory generation method, comprising:

[0006] receiving an actual trajectory point position at a current time, denoted as a current position;

[0007] determining a processed trajectory point position at the current time based on the historical trajectory point position and the current position, denoted as a current processed position, which specifically comprises:

[0008] For any trajectory point , the current processed position is:

[0009]

[0010] wherein, , , are the coordinate values of the trajectory point in the X-axis, Y-axis, and Z-axis directions, is the actual trajectory point position of the trajectory point at the t-th time, i.e. the current position, and are the actual trajectory point positions of the trajectory point at the (t-1)-th time and the (t-2)-th time, respectively, , , are respectively a first weight, a second weight and a third weight, and:

[0011]

[0012]

[0013]

[0014] wherein, , are respectively a maximum value and a minimum value of the set first weight, , are respectively a maximum speed value and a minimum speed value of the set robot, and b is a constant, which can be set to improve the anti-disturbance ability of the robot, is a trajectory point P j a velocity at the t-th moment, and:

[0015]

[0016] wherein, is a Euclidean distance between and ; is a sampling period;

[0017] generating a robot virtual trajectory curve according to the current processing position.

[0018] In the embodiment of the application, a speed-sensitive weight adjustment mechanism is introduced, which is especially suitable for a drag teaching scene of an unskilled operator, and can reduce the historical weight when moving at high speed and increase the historical weight when moving at low speed, thereby solving the phase distortion problem in the variable speed scene.

[0019] When the robot is detected to move at high speed, the weight of the current position is automatically increased , so that the filter bandwidth is increased and the lag is reduced, and the robot can respond to the instruction change of the operator more quickly, thereby avoiding the phenomenon of not being able to follow or motion trailing in high dynamic motion, and reducing the lag.

[0020] When low-speed operation or a tendency to stop is performed, the weight of the current position is automatically reduced , and the historical data is relied on instead, so that the filtering strength can be greatly improved, the slight jitter can be effectively suppressed or even eliminated, the smoothness is enhanced, and the robot end performs abnormally stably.

[0021] As an optional implementation, in the first aspect of the embodiment of the present application, generating the robot virtual trajectory curve according to the current processing position comprises:

[0022] determining the joint angles according to the current processing position;

[0023] calculating the end pose according to the joint angles;

[0024] generating the robot virtual trajectory curve according to the end pose.

[0025] By introducing inverse kinematics to solve the joint angles, it is ensured that each smoothed pose point must correspond to a set of feasible joint angles, thereby avoiding the danger of unreachable poses or configurations close to singular points in advance, and then verifying and visualizing through forward kinematics, a virtual trajectory is generated which is both smooth and fully complies with the kinematic constraints of the robot itself.

[0026] As an optional implementation, in the first aspect of the embodiment of the present application, determining the joint angles according to the current processing position comprises:

[0027] determining the joint angles according to the current processing position through inverse kinematics;

[0028] calculating the end pose according to the joint angles, comprising:

[0029] calculating the end pose through forward kinematics equations:

[0030]

[0031] wherein, is the end pose, is the joint angle of the i-th joint; is the homogeneous transformation matrix of the i-th joint;

[0032] generating the robot virtual trajectory curve according to the end pose, comprising:

[0033] generating the end effector trajectory curve of the robot according to the end pose:

[0034]

[0035] wherein, is the end effector trajectory curve, and are the start time and the end time of the trajectory generation, respectively;

[0036] displaying the end effector trajectory curve on the operation interface.

[0037] The embodiment of the present application binds the filtering output and the kinematics model depth, verifies the trajectory feasibility through forward kinematics, and visualizes the virtual trajectory to assist in real-time deviation correction. The operator can observe the final effect after the system processing in real time, thereby being able to more confidently and accurately perform the teaching, and facilitating offline debugging and program verification, and reducing the operation threshold and the dependence on proficiency.

[0038] As an optional implementation, in the first aspect of the embodiment of the present application, the method further comprises:

[0039] Real-time acquisition of acceleration of any trajectory point of the robot;

[0040] When the acceleration is greater than a preset acceleration value, the robot is controlled to be urgently stopped or an alarm signal is sent.

[0041] The embodiment of the present application introduces a proactive safety protection layer, significantly improves the functional safety level of the whole system. Real-time monitoring of acceleration is the last and most critical insurance for filtering effect. Even in the most extreme case, the acceleration sensor can capture abnormal mutations in the first time. The system can trigger emergency stop within milliseconds before the potential danger occurs, and kill the risk in the embryonic state.

[0042] As an optional implementation, in the first aspect of the embodiment of the present application, the method further comprises:

[0043] Saving one or more groups of virtual trajectory curves of the robot to form teaching data;

[0044] Teaching or skill reproduction of other robots by using the teaching data.

[0045] Through the teaching data multiplexing mode, the digitization, standardization and assetization of operation skills can be realized. By saving the optimized virtual trajectory as teaching data, it becomes a replicable and spreadable digital asset. On the one hand, ordinary workers can call the teaching data to complete high-quality work; on the other hand, the level difference between different operators and the state fluctuation of the same operator are eliminated, and when applied to industrial production, it can ensure that each product is processed under an absolute and optimal trajectory. In addition, the operation process can be quickly copied and uniformly upgraded, greatly saving time and cost.

[0046] The second aspect of the embodiment of the present application discloses a robot trajectory generation system, comprising:

[0047] A receiving unit is configured to receive an actual trajectory point position at a current time, denoted as a current position;

[0048] The computing unit is configured to determine a processed trajectory point position at a current time based on a historical trajectory point position and a current position, denoted as a current processed position, and specifically includes:

[0049] For any trajectory point , the current processed position is:

[0050]

[0051] wherein, , , are coordinate values of the trajectory point in the X-axis, Y-axis, and Z-axis directions, is an actual trajectory point position of the trajectory point at the t-th time, i.e., the current position, and are actual trajectory point positions of the trajectory point at the (t-1)-th time and the (t-2)-th time, , , are a first weight, a second weight, and a third weight, respectively, and:

[0052]

[0053]

[0054]

[0055] wherein, , are a maximum value and a minimum value of the first weight respectively, , are a maximum speed value and a minimum speed value of the robot respectively, and b is a constant, which can be set to improve the anti-disturbance capability of the robot, is an actual trajectory point position of the trajectory point P j at the t-th time, and:

[0056]

[0057] wherein, is a Euclidean distance between and ; is a sampling period;

[0058] The generating unit is configured to generate a virtual trajectory curve of the robot according to the current processed position.

[0059] The embodiment of the present application uses a filtering algorithm to process the current position information in combination with historical trajectory information, provides a reliable conversion path from rough and unreliable dragging teaching to smooth, stable and executable automatic trajectory for the robot, and fundamentally solves the safety hazards and quality defects when the original trajectory data is directly used.

[0060] The third aspect of the embodiment of the present application discloses an electronic device, comprising: a memory storing executable program code; a processor coupled with the memory; the processor invokes the executable program code stored in the memory, and is used for executing the robot trajectory generation method disclosed in the first aspect of the embodiment of the present application.

[0061] The fourth aspect of the embodiment of the present application discloses a computer readable storage medium storing a computer program, wherein the computer program causes a computer to execute the robot trajectory generation method disclosed in the first aspect of the embodiment of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort on the basis of these drawings.

[0063] Figure 1 is a flowchart of the robot trajectory generation method disclosed by the embodiment of the present application;

[0064] Figure 2 is a flowchart of generating a virtual trajectory curve of the robot disclosed by the embodiment of the present application;

[0065] Figure 3 is a structural schematic diagram of a robot trajectory generation system provided by the embodiment of the present application;

[0066] Figure 4 is a structural schematic diagram of an electronic device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0067] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort belong to the protection scope of the present application.

[0068] It should be noted that the terms first, second, third, fourth, etc. in the specification and claims of the present application are used to distinguish different objects, and are not used to describe a specific order. The terms of the embodiments of the present application include and have as well as any deformation thereof, and are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to the clearly listed steps or units, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0069] Embodiment one

[0070] Please refer to Figure 1 , Figure 1 is a flowchart of the robot trajectory generation method disclosed by the embodiments of the present application. Wherein, the execution subject of the method described in the embodiments of the present application is composed of software or / and hardware, which can receive relevant information through wired or / and wireless mode, and can send certain instructions. Of course, it can also have certain processing function and storage function. The execution subject can control multiple devices, such as remote physical server or cloud server and related software, or local host or server and related software for related operation of devices placed in certain place, etc. In some scenarios, it can also control multiple storage devices, which can be placed in the same place or different places.

[0071] As Figure 1 shown, the robot trajectory generation method comprises the following steps:

[0072] S110, receiving the actual trajectory point position at the current time, denoted as the current position.

[0073] The collection of trajectory points can be realized by encoder or related sensor such as hall element on robot executor, or by visual sensor such as binocular camera, etc. Here, the collection method is not limited.

[0074] The actual trajectory points at each position are collected at the same sampling frequency, wherein the actual trajectory point position at the current time is denoted as the current position, the trajectory point position at the previous time is denoted as the historical trajectory point position, and the data of each historical trajectory point position is saved. Here, the saved historical trajectory point position can be the actually collected trajectory point position, or the trajectory point position after step S120 processing.

[0075] S120, determining the processed trajectory point position at the current time based on the historical trajectory point position and the current position, denoted as the current processed position.

[0076] The embodiment of the present application is mainly aimed at the drag teaching application scene, in which the problem of inconsistent speed rhythm of the operator manually dragging easily affects the trajectory quality. In order to improve the trajectory quality and achieve better visual effect, the position of the trajectory point is subjected to smoothing filtering processing in the embodiment of the present application, so as to suppress or even eliminate high-frequency jitter.

[0077] There are various ways of smoothing filtering processing. In the embodiment of the present application, the historical trajectory point position is combined, instead of directly inputting the current position data into the corresponding filter to filter out high-frequency signals. Compared with the direct high-frequency filtering method, the smoothing filtering processing effect is better when the historical trajectory point position is combined.

[0078] Specifically, the direct high-frequency filtering is to forcibly filter out high-frequency signals in the frequency domain. The higher the order of the filter is, the lower the cutoff frequency is, the more serious the lag is, and the signal shape is distorted. The filtering by combining the historical trajectory point position is to smooth in the time domain by using weighted average, which can accurately balance the real-time performance and smoothness by adjusting the weight. The direct high-frequency filtering makes the signal edge become "smooth", which causes the steep rising edge / falling edge to become inclined and seriously distorted. The filtering by combining the historical trajectory point position retains the overall shape and trend of the original signal, and especially can well maintain the edge of the step signal.

[0079] Moreover, in the robot context, these noises may also come from the measurement error of the joint encoder, the slight jitter of the transmission mechanism, and the high-frequency oscillation of the current loop control, etc. The filtering of high-frequency noise by combining the historical trajectory point position is to obtain the smooth and ideal trajectory that the system expects to execute.

[0080] As an implementation mode, the second-order Butterworth filter core can be used to realize efficient noise suppression with fixed weight, which has low computational complexity, meets the real-time control requirement, and is very suitable for embedded systems with high real-time requirement or robot scenes requiring high-frequency control.

[0081] Specifically,

[0082] For any trajectory point , the current processing position is:

[0083]

[0084] Among them, , , are the coordinate values of the trajectory point in the X-axis, Y-axis, and Z-axis directions, is the actual trajectory point position of the trajectory point at the t-th moment, i.e. the current position, and are the coordinate values of the trajectory point are the actual trajectory point positions at the t-1th moment and the t-2th moment, , , are the first weight, the second weight and the third weight, respectively, and .

[0085] By giving the highest weight to the current position and the second highest weight to the historical data, for example, the first weight can be set as 0.5, the second weight as 0.3 and the third weight as 0.2, the high-frequency components introduced by physiological hand tremor of the operator or sensor noise can be effectively filtered out. At the same time, since the depth of dependence on historical data is limited, the phase lag introduced is extremely small, and the real-time following of the robot movement can be completely guaranteed, and the dull feeling of operation caused by excessive smoothing can be avoided. , ,

[0086] As another embodiment, a speed-sensitive weight adjustment mechanism is introduced to form an adaptive weighted filtering method, which is especially suitable for the drag teaching scene of an unskilled operator. The historical weight can be reduced at high speed and increased at low speed to solve the phase distortion problem in the variable speed scene.

[0087] Specifically:

[0088] For any trajectory point , the current processing position is:

[0089]

[0090] wherein, , , are the coordinate values of the trajectory point in the X-axis, Y-axis and Z-axis directions, is the actual trajectory point position at the tth moment, i.e. the current position, and are the actual trajectory point positions at the t-1th moment and the t-2th moment, , , are the first weight, the second weight and the third weight, respectively, and:

[0091]

[0092]

[0093] ​​​

[0094] wherein, , are the maximum and minimum values of the first weight set respectively, , are the maximum and minimum values of the robot speed set respectively, and b is a constant, which can be set to improve the anti-disturbance ability of the robot, is the trajectory point P j the velocity at the t-th moment, and:

[0095]

[0096] wherein, is the Euclidean distance between and ; is the sampling period.

[0097] When the high-speed motion of the robot is detected, the weight of the current position is automatically increased , for example, to the maximum value of 0.8, so that the filter bandwidth is increased and the hysteresis is reduced, and the robot can respond to the operator's instruction change more quickly, avoiding the phenomenon of not being able to follow or motion trailing in high dynamic motion, and reducing the hysteresis.

[0098] When low-speed operation or tend to stop, the weight of the current position is automatically reduced , for example, to the minimum value of 0.3, and instead more dependent on historical data, which can greatly improve the filtering strength, effectively suppress or even eliminate the slight jitter, enhance the smoothness, and make the robot end perform more stably.

[0099] In other embodiments, one or more groups of robot virtual trajectory curves can also be saved to form teaching data, so that they become replicable and propagable digital assets. Using these teaching data, other robots can be taught or skill reproduced, realizing rapid replication and unified upgrade of production process, greatly saving time and cost.

[0100] In other embodiments, in order to guarantee the smoothing filtering effect and avoid danger, the acceleration can be limited in a certain range, i.e., the acceleration is limited in a certain range.

[0101] Exemplarily, the acceleration of any trajectory point of the robot is acquired in real time ; when the acceleration is greater than a preset acceleration value , the robot is controlled to stop or an alarm signal is sent.

[0102] Real-time monitoring of acceleration is the last and most critical insurance of filtering effect, even in the most extreme cases, the acceleration sensor can first capture abnormal mutations. The system can trigger emergency shutdown within milliseconds before potential danger occurs, and kill the risk in its infancy.

[0103] S130, generating a robot virtual trajectory curve according to the current processing position.

[0104] The embodiment of the application binds the filtering output and the kinematic model depth, verifies the trajectory feasibility through forward kinematics, and visualizes the virtual trajectory to assist real-time correction. The operator can observe the final effect of the operation after the system processing in real time, thereby being able to more confidently and accurately demonstrate teaching, and facilitating offline debugging and program verification, reducing the operation threshold and dependence on proficiency.

[0105] Please refer to Figure 2 The specific steps can include the following steps:

[0106] S131, determining the joint angles according to the current processing position.

[0107] Determining the joint angles according to the current processing position is achieved through inverse kinematics, and each smooth pose point must correspond to a set of feasible joint angles by introducing inverse kinematics to solve the joint angles, thereby avoiding the danger of unreachable poses or adjacent singular points in advance.

[0108] S132, calculating the end pose according to the joint angles.

[0109] The end pose can be calculated according to the joint angles through the forward kinematics equation:

[0110]

[0111] wherein, is the end pose, is the joint angle of the i-th joint; is the homogeneous transformation matrix of the i-th joint.

[0112] S133, generating a robot virtual trajectory curve according to the end pose.

[0113] Based on the end pose of step S132, the end effector trajectory curve of the robot can be generated:

[0114]

[0115] wherein, is the end effector trajectory curve, and respectively are a start time and an end time of trajectory generation;

[0116] The verification and visualization through forward kinematics generate a virtual trajectory which is smooth and fully complies with the kinematic constraints of the robot itself, and the end effector trajectory curve can also be displayed in real time on the operation interface.

[0117] The embodiment of the present application uses a filtering algorithm to process the current position information in combination with historical trajectory information, thereby providing a reliable conversion path from rough and unreliable dragging teaching to smooth, stable and executable automatic trajectory for the robot, and fundamentally solving the safety hazards and quality defects when the original trajectory data is directly used.

[0118] Embodiment two

[0119] Please refer to Figure 3 , Figure 3 is a structural schematic diagram of the robot trajectory generation system disclosed by the embodiment of the present application. As shown in Figure 3 , the robot trajectory generation system can include:

[0120] The receiving unit 210 is configured to receive an actual trajectory point position at a current time, denoted as a current position;

[0121] The computing unit 220 is configured to determine a processed trajectory point position at the current time based on the historical trajectory point position and the current position, denoted as a current processed position;

[0122] The generating unit 230 is configured to generate a virtual trajectory curve of the robot according to the current processed position.

[0123] Preferably, the computing unit 220 can include:

[0124] For any trajectory point , the current processed position is:

[0125]

[0126] wherein, , , are coordinate values of the trajectory point in X-axis, Y-axis and Z-axis directions, is an actual trajectory point position of the trajectory point at the t time, i.e., the current position, and are actual trajectory point positions of the trajectory point at the t-1 time and the t-2 time, , , are respectively a first weight, a second weight and a third weight, and .

[0127] The computing unit 220 can also include:

[0128] For any trajectory point its current processing position is:

[0129]

[0130] wherein, , , are respectively coordinate values of the trajectory point in the X-axis, Y-axis and Z-axis directions, is the actual trajectory point position of the trajectory point at the t-th moment, i.e. the current position, and are respectively the actual trajectory point positions of the trajectory point at the (t-1)-th moment and the (t-2)-th moment, , , are respectively a first weight, a second weight and a third weight, and:

[0131]

[0132]

[0133]

[0134] wherein, , are respectively a maximum value and a minimum value of the first weight set, , are respectively a maximum speed value and a minimum speed value of the robot set, and b is a constant, is the velocity of the trajectory point P j at the t-th moment, and:

[0135]

[0136] wherein, is the Euclidean distance between and ; is a sampling period.

[0137] Preferably, the generating unit 230 can include:

[0138] determining the respective joint angles by inverse kinematics based on the current processing position;

[0139] Calculate the end pose by the forward kinematics equation:

[0140]

[0141] wherein, is the end pose, is the joint angle of the i th joint; is the homogeneous transformation matrix of the i th joint;

[0142] Generate the end effector trajectory curve of the robot according to the end pose:

[0143]

[0144] wherein, is the end effector trajectory curve, and are the start time and the end time of the trajectory generation, respectively.

[0145] Preferably, the system can further include an amplitude limiting unit for acquiring the acceleration of any trajectory point of the robot in real time; and when the acceleration is greater than a preset acceleration value, controlling the robot to stop urgently or issuing an alarm signal.

[0146] Preferably, the system can further include a multiplexing unit for saving one or more groups of robot virtual trajectory curves to form teaching data, and using the teaching data to teach or skill reproduce other robots.

[0147] Embodiment three

[0148] Please refer to Figure 4 , Figure 4 is a structural schematic diagram of an electronic device disclosed by the embodiment of the present application. The electronic device can be a computer, a server, etc. Of course, under certain circumstances, it can also be a smart device such as a mobile phone, a tablet computer, and a monitoring terminal, and an image acquisition device with processing function. As shown in Figure 4 , the electronic device can include:

[0149] a memory 310 storing executable program codes;

[0150] a processor 320 coupled with the memory 310;

[0151] The processor 320 calls the executable program codes stored in the memory 310 to execute part or all of the steps in the robot trajectory generation method in the embodiment one.

[0152] The embodiment of the present application discloses a computer readable storage medium which stores a computer program, wherein the computer program causes a computer to execute part or all steps in the robot trajectory generation method in the embodiment one.

[0153] The embodiment of the present application also discloses a computer program product, wherein when the computer program product is run on a computer, the computer program product causes the computer to execute part or all steps in the robot trajectory generation method in the embodiment one.

[0154] The embodiment of the present application also discloses an application publishing platform, wherein the application publishing platform is used for publishing a computer program product, wherein when the computer program product is run on a computer, the computer program product causes the computer to execute part or all steps in the robot trajectory generation method in the embodiment one.

[0155] In various embodiments of the present application, it should be understood that the size of the serial number of the processes does not mean the inevitable sequence of execution, and the execution sequence of the processes should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

[0156] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, i.e. they may be located in one place, or they may be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment of the present application.

[0157] In addition, each functional unit in the embodiments of the present application can be integrated in one processing unit, or each unit can exist physically independently, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of software functional unit.

[0158] The integrated unit, if realized in the form of software functional unit and sold or used as an independent product, can be stored in a computer accessible memory. Based on such understanding, the technical solutions of the present application essentially or the part of the prior art that makes contributions or the whole or part of the technical solutions can be embodied in the form of software product, which is stored in a memory and includes a plurality of steps for causing a computer device (which can be a personal computer, a server or a network device, and specifically can be a processor in the computer device) to execute the method steps of the embodiments of the present application.

[0159] In the embodiments provided in the present application, it should be understood that B corresponding to A means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean that B is determined only according to A, but B can also be determined according to A and / or other information.

[0160] A person of ordinary skill in the art can understand that part or all of the steps in the various methods of the embodiments can be completed by instructing the relevant hardware by a program, and the program can be stored in a computer readable storage medium, including Read-Only Memory (ROM), Random Access Memory (RAM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), One-time Programmable Read-Only Memory (OTPROM), Electrically-Erasable Programmable Read-Only Memory (EEPROM), Compact Disc Read-Only Memory (CD-ROM) or other optical disk memories, magnetic disk memories, magnetic tape memories, or any other computer readable medium capable of carrying or storing data.

[0161] The robot trajectory generation method and system disclosed in the embodiments of the present application are described in detail above, and the principles and implementation manners of the present application are described by applying specific examples in this paper. The above description of the embodiments is only used to help understand the method of the present application and its core idea; at the same time, for those skilled in the art, according to the idea of the present application, the specific implementation manner and application range will be changed, and the above description should not be understood as a limitation of the present application.

Claims

1. A robot trajectory generation method characterized by, The method comprises the following steps: receiving an actual trajectory point position at a current time, denoted as a current position; determining a processed trajectory point position at the current time based on a historical trajectory point position and the current position, denoted as a current processed position, which specifically comprises: For any trajectory point its current processing position is: in, , , These are the trajectory points. The coordinate values ​​in the X, Y, and Z axes. For trajectory points The actual trajectory point position at time t, i.e., the current position. and These are the trajectory points. The actual trajectory point positions at time t-1 and time t-2 , , They are the first weight, the second weight, and the third weight, respectively, and: wherein, , are a maximum and a minimum value of a set first weight, respectively, , are a maximum and a minimum speed value of the robot, respectively, and b is a constant, is a trajectory point P j a velocity at the t-th time instant, and: wherein is and the Euclidean distance between is the sampling period; generating a robot virtual trajectory curve according to the current processed position.

2. The robot trajectory generation method of claim 1, wherein, The method of generating a robot virtual trajectory curve according to the current processed position comprises: determining joint angles according to the current processed position; calculating an end pose according to the joint angles; generating a robot virtual trajectory curve according to the end pose.

3. The robot trajectory generation method of claim 2, wherein, The method of determining joint angles according to the current processed position comprises: determining the joint angles through inverse kinematics based on the current processed position; The method of calculating an end pose according to the joint angles comprises: calculating the end pose through a forward kinematics equation: wherein, is the end pose, is the joint angle of the ith joint; is the homogeneous transformation matrix of the ith joint; The method of generating a robot virtual trajectory curve according to the end pose comprises: generating an end effector trajectory curve of the robot according to the end pose: wherein, is an end effector trajectory curve, and are a start time and an end time of trajectory generation, respectively; displaying the end effector trajectory curve on an operation interface.

4. The robot trajectory generation method of any one of claims 1-3, wherein, The method further comprises: obtaining acceleration of any trajectory point of the robot in real time; when the acceleration is greater than a preset acceleration value, controlling the robot to stop or sending an alarm signal.

5. The robot trajectory generation method of any one of claims 1-3, wherein, The method further comprises: saving one or more sets of robot virtual trajectory curves to form teaching data; using the teaching data to teach or skill-reproduce other robots.

6. A robot trajectory generation system, characterized by, The method comprises the following steps: a receiving unit configured to receive an actual trajectory point position at a current time, denoted as a current position; a calculating unit configured to determine a processed trajectory point position at the current time based on a historical trajectory point position and the current position, denoted as a current processed position, which specifically comprises: For any trajectory point its current processing position is: in, , , These are the trajectory points. The coordinate values ​​in the X, Y, and Z axes. For trajectory points The actual trajectory point position at time t, i.e., the current position. and These are the trajectory points. The actual trajectory point positions at time t-1 and time t-2 , , They are the first weight, the second weight, and the third weight, respectively, and: wherein, , are a maximum and a minimum value of a set first weight, respectively, , are a maximum and a minimum speed value of the robot, respectively, b is a constant, is a trajectory point P j a velocity at the t-th time instant, and: wherein is and the Euclidean distance between is the sampling period; a generating unit configured to generate a robot virtual trajectory curve according to the current processed position.

7. An electronic device, comprising: The method comprises the following steps: a memory storing executable program codes; a processor coupled with the memory; the processor invokes the executable program codes stored in the memory to execute the robot trajectory generation method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, wherein the computer program causes a computer to execute the robot trajectory generation method according to any one of claims 1 to 5.

Images