Intelligent motion control method and device, equipment, storage medium and product

Abstract

The invention discloses an intelligent motion control method, device and equipment, a storage medium and a product. The method comprises the following steps: acquiring environment state data and motion equipment state data; generating a first control instruction and a second control instruction by using an artificial intelligence algorithm according to the environment state data; generating a precise control instruction based on the motion equipment state data, the first control instruction, the second control instruction and a motion control algorithm; and issuing the precise control instruction to each servo driver for execution so as to complete motion control. According to the method, the precise control instruction is generated based on the motion equipment state data, the first control instruction, the second control instruction and the motion control algorithm, complex environment changes can be rapidly adapted, and the motion equipment is precisely controlled.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of intelligent control technology, and in particular, to an intelligent motion control method, device, equipment, storage medium and product. Background Art

[0002] With the development of science and technology, intelligence has become an important development direction for equipment in various fields, and the requirements for intelligent control of various sports equipment are becoming increasingly higher.

[0003] Traditional motion control methods, such as Model Predictive Control (MPC) algorithms, can achieve relatively accurate motion regulation under known models and stable working conditions. However, they are not well adapted to complex and changeable actual environments that are difficult to model. Summary of the invention

[0004] The present invention provides an intelligent motion control method, device, equipment, storage medium and product to solve the problem that traditional motion control methods cannot accurately perform motion control in complex and changeable environments.

[0005] According to one aspect of the present invention, there is provided an intelligent motion control method, comprising:

[0006] Obtain environmental status data and motion equipment status data;

[0007] Generate a first control instruction and a second control instruction using an artificial intelligence algorithm according to the environmental status data;

[0008] Generate a precise control instruction based on the motion device state data, the first control instruction and the second control instruction, and a motion control algorithm;

[0009] The precise control instructions are sent to each servo driver for execution to complete motion control.

[0010] According to another aspect of the present invention, there is provided an intelligent motion control system, including a perception module, a processing module, an instruction generation module, a motion control module, an instruction fusion module and an execution module;

[0011] The sensing module is used to collect environmental data and sports equipment data in real time;

[0012] The processing module is used to process the environmental data and the sports equipment data to obtain environmental status data and sports equipment status data;

[0013] The instruction generation module is used to generate a first control instruction and a second control instruction using an artificial intelligence algorithm according to the environmental state data;

[0014] The motion control module is used to generate a third control instruction through a motion control algorithm according to the motion device state data and the preset basic task instruction;

[0015] The instruction fusion module is used to fuse the first control instruction, the second control instruction and the third control instruction to generate a precise control instruction;

[0016] The execution module is used to execute the precise control instruction.

[0017] According to another aspect of the present invention, there is provided a sports device, the sports device comprising: at least one processor;

[0018] and a memory communicatively coupled to the at least one processor;

[0019] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the intelligent motion control method described in any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the intelligent motion control method described in any embodiment of the present invention when executed.

[0021] According to another aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the intelligent motion control method according to any embodiment of the present invention is implemented.

[0022] The technical solution of the embodiment of the present invention obtains environmental status data and motion device status data; generates a first control instruction and a second control instruction using an artificial intelligence algorithm according to the environmental status data; generates a precise control instruction based on the motion device status data, the first control instruction and the second control instruction, and a motion control algorithm; and sends the precise control instruction to each servo driver for execution to complete motion control, thereby solving the problem that traditional motion control methods cannot accurately perform motion control in the face of complex and changeable environments, and achieving the beneficial effects of quickly adapting to complex environmental changes and accurately controlling motion equipment.

[0023] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 A schematic diagram of a flow chart of an intelligent motion control method provided in Embodiment 1 of the present invention;

[0026] Figure 2 A schematic diagram of a flow chart of an intelligent motion control method provided in Embodiment 2 of the present invention;

[0027] Figure 3 A schematic diagram of a flow chart of an intelligent motion control method provided in Embodiment 3 of the present invention;

[0028] Figure 4 A schematic diagram of the structure of an intelligent motion control system provided by Embodiment 4 of the present invention;

[0029] Figure 5 A schematic diagram of the structure of an intelligent motion control system provided in Embodiment 5 of the present invention;

[0030] Figure 6 The present invention is a schematic diagram of the structure of a motion device of an intelligent motion control method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only an embodiment of a part of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work should belong to the scope of protection of the present invention. It should be understood that the various steps recorded in the method implementation of the present invention can be performed in different orders and / or in parallel. In addition, the method implementation may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0032] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0033] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0034] It should be noted that the modifications of "one" and "plurality" mentioned in the present invention are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0035] The names of the messages or information exchanged between multiple devices in the embodiments of the present invention are only used for illustrative purposes, and are not used to limit the scope of these messages or information.

[0036] Embodiment 1

[0037] Figure 1 A flow chart of an intelligent motion control method provided in Embodiment 1 of the present invention is applicable to the case of intelligently controlling motion equipment. The method can be executed by an intelligent motion control device, wherein the device can be implemented by software and / or hardware and is generally integrated on the motion equipment. In this embodiment, the motion equipment includes but is not limited to: robots, self-driving vehicles, intelligent industrial equipment, intelligent warehousing equipment and many other equipment that require precise motion control.

[0038] like Figure 1 As shown, an intelligent motion control method provided by Embodiment 1 of the present invention includes the following steps:

[0039] S110, acquiring environmental status data and sports equipment status data.

[0040] The environmental status data may include temperature, humidity, obstacle information, road surface information, weather information, etc. The environmental status data may be acquired through a variety of sensors, including visual sensors, auditory sensors, tactile sensors, and inertial sensors.

[0041] The motion device state data can be understood as the motion state information of the motion device itself, such as walking state, stop state, turning state, speed, acceleration, turning direction and turning angle, etc. The motion device state data can be obtained from the main controller of the motion device, for example, the motion state and motion parameters of the robot can be obtained from the main controller of the robot, and the motion state and motion parameters of the vehicle can be obtained from the main controller of the vehicle.

[0042] S120: Generate a first control instruction and a second control instruction using an artificial intelligence algorithm according to the environmental status data.

[0043] Among them, the artificial intelligence algorithm may include a reinforcement learning algorithm and an imitation learning algorithm. The first control instruction may be understood as a control instruction generated using the imitation learning algorithm, and the second control instruction may be understood as a control instruction generated using the reinforcement learning algorithm.

[0044] In this embodiment, based on expert demonstration data, through imitation learning algorithms, such as convolutional neural networks for environmental state data processing and recurrent neural networks for term sequence learning, action patterns and strategies are extracted to generate the first control instruction.

[0045] In this embodiment, a reinforcement learning algorithm is used to learn a strategy through the interaction between the motion device and the environment to obtain an optimized strategy, and a second control instruction is generated according to the optimized strategy.

[0046] S130, generating a precise control instruction based on the motion device state data, the first control instruction, the second control instruction, and a motion control algorithm.

[0047] The motion control algorithm may be a traditional motion control algorithm, such as a PID algorithm, a model predictive control (MPC) algorithm, a dynamics algorithm, a kinematics algorithm, etc. The motion control algorithm is used to generate preliminary control instructions.

[0048] In this embodiment, the precise control instruction is generated based on the motion device state data, the first control instruction and the second control instruction, and the motion control algorithm, including the following two schemes:

[0049] Solution 1: Generate a preliminary control instruction, and fuse the preliminary control instruction, the second control instruction, and the third control instruction to generate a precise control instruction;

[0050] Solution 2: Generate precise control instructions using a motion control algorithm based on motion device status data, a first control instruction, and a second control instruction.

[0051] The precise control instruction may be a position instruction, a speed instruction or a torque instruction.

[0052] S140, sending the precise control instruction to each servo driver for execution to complete motion control.

[0053] For example, each joint of an industrial robot requires precise motion control, and a servo drive can drive the motor to achieve flexible and accurate movements of the robot.

[0054] Among them, after each servo driver receives the precise control command, the encoder on the servo motor detects the actual position, speed and other information of the servo motor in real time, and transmits these feedback signals to the servo driver. The servo driver compares the received command signal with the feedback signal and calculates the error between the two. According to the size and direction of the error, the servo driver calculates the appropriate control amount through the internal control algorithm, and adjusts the voltage and current output to the servo motor to drive the motor to operate and gradually reduce the error until the set accuracy requirement is met.

[0055] An intelligent motion control method provided in the first embodiment of the present invention first obtains environmental status data and motion device status data; then generates a first control instruction and a second control instruction using an artificial intelligence algorithm based on the environmental status data; then generates a precise control instruction based on the motion device status data, the first control instruction and the second control instruction, and the motion control algorithm; and finally sends the precise control instruction to each servo driver for execution to complete motion control. This method generates precise control instructions based on the motion device status data, the first control instruction and the second control instruction, and the motion control algorithm, and can quickly adapt to complex environmental changes and precisely control motion devices.

[0056] Based on the above embodiment, a variant embodiment of the above embodiment is proposed. It should be noted that in order to make the description concise, only the differences from the above embodiment are described in the variant embodiment.

[0057] In one embodiment, obtaining environmental status data and sports device status data includes:

[0058] Obtain environmental data and motion equipment data collected by sensors;

[0059] The environmental data and the motion device data are processed to obtain environmental status data and motion device status data.

[0060] In this embodiment, the sensor may include a tactile sensor, an auditory sensor, a visual sensor, an inertial sensor, a temperature sensor, a speed sensor, an acceleration sensor, and the like.

[0061] Among them, tactile sensors may include force-torque sensors, pressure sensors, and slip sensors; auditory sensors may include microphones, electret microphones, ultrasonic sensors, acoustic emission sensors, laser Doppler vibrometers, etc.; visual sensors may include cameras, etc.; inertial sensors may include accelerometers, gyroscopes, magnetometers, inertial measurement units, and inertial navigation systems, etc.

[0062] In this embodiment, the collected environmental data and sports equipment data are subjected to preliminary processing such as filtering and feature extraction to obtain normalized environmental data, i.e., environmental status data, and normalized sports equipment data, i.e., sports equipment status data. The environmental data may include temperature, humidity, obstacle information, road surface information, and weather information, etc.; the sports equipment data may include the sports equipment's own motion status information, including speed, acceleration, direction, angle, etc.

[0063] In one embodiment, the artificial intelligence algorithm includes an imitation learning algorithm and a reinforcement learning algorithm, and the use of the artificial intelligence algorithm to generate the first control instruction and the second control instruction according to the environmental state data includes:

[0064] Determine whether the current environment meets the preset conditions based on the environmental state data and the demonstration data; if so, construct a behavior generation strategy based on the demonstration data using the imitation learning algorithm; generate a first control instruction based on the behavior generation strategy; obtain a new environmental state and reward signal fed back by the environment after the motion device interacts with the environment; based on the new environmental state and the reward signal, continuously update the strategy and related parameters through the reinforcement learning algorithm to obtain an optimized strategy; generate a second control instruction based on the optimized strategy.

[0065] Furthermore, determining whether the current environment meets the preset conditions based on the environmental status data and the expert demonstration data includes: performing similarity calculation on the environmental status data and the demonstration scene data in the expert demonstration data to obtain a similarity result; and determining whether the current environment meets the preset conditions based on the similarity result.

[0066] Among them, expert demonstration data refers to data generated by domain experts or experienced professionals through actual operations, demonstrations, etc. These data are generally considered to be of high quality and authority, and can be used to guide model training, algorithm optimization, and provide learning examples for novices. In robot motion planning and control, expert demonstration data is used to train robots to complete complex tasks. For example, in the robot's grasping task, the best grasping position, strength, angle and other data demonstrated by experts can enable the robot to learn efficient and accurate grasping strategies, and improve the accuracy and success rate of its operations.

[0067] Among them, if the similarity between the demonstration scene data and the environmental status data is equal to or higher than the preset value, it can be determined that the current environment meets the preset conditions; if the similarity between the demonstration scene data and the environmental status data is lower than the preset value, it can be determined that the current environment does not meet the preset conditions.

[0068] In this embodiment, the motion device extracts patterns and rules from the demonstrator's behavior sequence and constructs a strategy that can generate similar behaviors, namely, a behavior generation strategy; the motion device learns the mapping relationship between states and actions by selecting actions in various states, so as to make similar decisions in similar situations.

[0069] In this embodiment, the motion device continuously selects actions in the environment, and the environment generates new environmental states and reward signals according to the actions of the motion device. The motion device records information such as each state, action, reward, and next state to form experience data. According to the selected reinforcement learning algorithm, the collected experience data is used to update the strategy function or value function of the intelligent agent. The interaction process between the motion device and the environment is continuously repeated to collect more experience data, and the strategy function or value function is continuously updated until the performance of the intelligent agent reaches a satisfactory level or reaches a preset number of training steps to obtain an optimized strategy.

[0070] Embodiment 2

[0071] Figure 2 This is a flow chart of an intelligent motion control method provided by the second embodiment of the present invention. The second embodiment is optimized on the basis of the above embodiments. For details not yet provided in this embodiment, please refer to the first embodiment.

[0072] like Figure 2 As shown, an intelligent motion control method provided by Embodiment 2 of the present invention comprises the following steps:

[0073] S210: Acquire environmental status data and sports equipment status data.

[0074] S220: Generate a first control instruction and a second control instruction using an artificial intelligence algorithm according to the environmental status data.

[0075] S230: Generate a third control instruction through a motion control algorithm according to the motion device state data and the preset basic task instruction.

[0076] The basic task instruction may be understood as an instruction for the desired motion state of the motion device. For example, the basic task instruction may be for the motion device to move forward at a speed of 20 m / min.

[0077] Exemplarily, the motion control algorithm is MPC, which is based on the system's prediction model and determines the control input through continuous online optimization. It includes the following steps:

[0078] 1. At each sampling moment, the state data of the motion device is used as an initial condition to predict the behavior of the motion device in a future limited time domain;

[0079] 2. Based on the prediction results and basic task instructions, solve a finite time domain optimization problem to obtain a set of future control sequences, but only the first control quantity will be applied to the motion device;

[0080] 3. At the next sampling moment, repeat the above process and perform prediction and optimization based on the new motion device status data.

[0081] S240: Fusing the first control instruction, the second control instruction, and the third control instruction to generate a precise control instruction.

[0082] Furthermore, the first control instruction, the second control instruction and the third control instruction are fused to generate a precise control instruction, including: dynamically adjusting the fusion ratio of the first control instruction, the second control instruction and the third control instruction according to preset factors; and fusing the first control instruction, the second control instruction and the third control instruction according to the fusion ratio to generate a precise control instruction.

[0083] Among them, the preset factors may include the complexity of the current environment, the urgency of the task, and weather conditions.

[0084] The preset factors are used as weights, and the fusion ratios among the first control instruction, the second control instruction and the third control instruction are dynamically adjusted according to the weights.

[0085] Exemplarily, in a stable and simple environment, the third control instruction is dominant, that is, the fusion ratio of the third control instruction is relatively large; in a new environment and when there is a demonstration to refer to, the fusion ratio of the first control instruction is increased; in a complex and changeable environment without prior experience, the fusion ratio of the second control instruction is increased to ensure that the sports equipment can flexibly respond to various environments.

[0086] S250, sending the precise control instruction to each servo driver for execution to complete motion control.

[0087] The second embodiment of the present invention provides an intelligent motion control method, which embodies the process of generating precise control instructions based on the motion device state data, the first control instruction and the second control instruction, and the motion control algorithm. The method can improve the working efficiency, reliability and intelligent control level of the motion device.

[0088] Embodiment 3

[0089] Figure 3 This is a flow chart of an intelligent motion control method provided by the third embodiment of the present invention. The third embodiment is optimized on the basis of the above embodiments. For details not yet detailed in this embodiment, please refer to the first and second embodiments.

[0090] like Figure 3 As shown, an intelligent motion control method provided by Embodiment 3 of the present invention includes the following steps:

[0091] S310: Obtain environmental status data and sports equipment status data.

[0092] S320: Generate a first control instruction and a second control instruction using an artificial intelligence algorithm according to the environmental status data.

[0093] S330, inputting the motion device state data, the first control instruction and the second control instruction into a motion controller.

[0094] S340, using the motion controller to generate precise control instructions using a motion control algorithm.

[0095] Exemplarily, using the MPC algorithm to generate precise control instructions includes: determining set performance indicators based on a first control instruction and a second control instruction; at each sampling moment, using the motion device state data as an initial condition to predict the behavior of the motion device in a future finite time domain; solving a finite time domain optimization problem based on the prediction results and the set performance indicators to obtain a set of future control sequences, but only the first control amount will be applied to the motion device; at the next sampling moment, repeating the above process, and re-predicting and optimizing based on the new motion device state data.

[0096] S350, sending the precise control instruction to each servo driver for execution to complete motion control.

[0097] The third embodiment of the present invention provides an intelligent motion control method, which specifically generates precise control instructions based on the motion device state data, the first control instruction and the second control instruction, and the motion control algorithm. The method can improve the working efficiency, reliability and intelligent control level of the motion device.

[0098] Embodiment 4

[0099] Figure 4 This is a structural schematic diagram of an intelligent motion control system provided in Example 4 of the present invention. The intelligent motion control system can be applied to situations where motion equipment is intelligently controlled, wherein the intelligent motion control system can be implemented by software and / or hardware and is generally integrated on the motion equipment.

[0100] like Figure 4 As shown, the intelligent motion control system includes: a perception module 110 , a processing module 120 , an instruction generation module 130 , a motion control module 140 , an instruction fusion module 150 and an execution module 160 .

[0101] A sensing module 110, for collecting environmental data and sports equipment data in real time;

[0102] A processing module 120, configured to process the environment data and the sports equipment data to obtain environment status data and sports equipment status data;

[0103] An instruction generation module 130, for generating a first control instruction and a second control instruction using an artificial intelligence algorithm according to the environmental state data;

[0104] The motion control module 140 is used to generate a third control instruction through a motion control algorithm according to the motion device state data and the preset basic task instruction;

[0105] An instruction fusion module 150, configured to fuse the first control instruction, the second control instruction and the third control instruction to generate a precise control instruction;

[0106] The execution module 160 is used to execute the precise control instruction.

[0107] In this embodiment, the device first collects environmental data and motion equipment data in real time through the perception module 110; secondly, the processing module 120 processes the environmental data and motion equipment data to obtain environmental status data and motion equipment status data; then, the instruction generation module 120 generates a first control instruction and a second control instruction based on the environmental status data using an artificial intelligence algorithm; the motion control module 130 generates a third control instruction through a motion control algorithm based on the motion equipment status data and preset basic task instructions; then, the instruction fusion module 140 fuses the first control instruction, the second control instruction and the third control instruction to generate a precise control instruction; finally, the execution module 150 executes the precise control instruction.

[0108] This embodiment provides an intelligent motion control system, which can utilize this method to improve the working efficiency, reliability and intelligent control level of sports equipment.

[0109] Furthermore, the artificial intelligence algorithm includes an imitation learning algorithm and a reinforcement learning algorithm, and the instruction generation module 120 includes:

[0110] A determination unit, used to determine whether the current environment meets the preset conditions according to the environmental status data and the demonstration data;

[0111] a construction unit, configured to, if yes, construct a behavior generation strategy using the imitation learning algorithm according to the demonstration data;

[0112] A first generating unit, configured to generate a first control instruction according to the behavior generating strategy;

[0113] An acquisition unit, used for acquiring a new environment state and a reward signal fed back by the environment after the sports device interacts with the environment;

[0114] An updating unit, configured to continuously update the strategy and related parameters through the reinforcement learning algorithm according to the new environment state and the reward signal to obtain an optimized strategy;

[0115] The second generating unit is used to generate a second control instruction according to the optimization strategy.

[0116] Based on the above technical solution, the determination unit is specifically used to: perform similarity calculation on the environmental state data and the demonstration scene data in the expert demonstration data to obtain a similarity result; and determine whether the current environment meets the preset conditions according to the similarity result.

[0117] Furthermore, the fusion module 140 includes:

[0118] an adjusting unit, configured to dynamically adjust a fusion ratio of the first control instruction, the second control instruction, and the third control instruction according to a preset factor;

[0119] A fusion unit is used to fuse the first control instruction, the second control instruction and the third control instruction according to the fusion ratio to generate a precise control instruction.

[0120] The above-mentioned intelligent motion control device can execute the intelligent motion control method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0121] Embodiment 5

[0122] Figure 5 This is a structural schematic diagram of an intelligent motion control system provided in Example 5 of the present invention. The intelligent motion control system can be applied to situations where motion equipment is intelligently controlled, wherein the intelligent motion control system can be implemented by software and / or hardware and is generally integrated on the motion equipment.

[0123] like Figure 5 As shown, the intelligent motion control system includes: a perception module 210 , a processing module 220 , a first generation module 230 , a second generation module 240 and an execution module 250 .

[0124] A sensing module 210 is used to collect environmental data and sports equipment data in real time;

[0125] A processing module 220, configured to process the environment data and the sports equipment data to obtain environment status data and sports equipment status data;

[0126] A first generating module 230, for generating a first control instruction and a second control instruction using an artificial intelligence algorithm according to the environmental state data;

[0127] A second generating module 240 is used to input the motion device state data, the first control instruction and the second control instruction into a motion controller, and generate a precise control instruction by using a motion control algorithm through the motion controller;

[0128] The execution module 250 is used to execute the precise control instruction.

[0129] In this embodiment, the device first collects environmental data and motion equipment data in real time through the perception module 210, and then processes the environmental data and motion equipment data through the processing module 220 to obtain environmental status data and motion equipment status data; then, the first generation module 230 uses an artificial intelligence algorithm to generate a first control instruction and a second control instruction based on the environmental status data; then, the motion equipment status data, the first control instruction and the second control instruction are input into the motion controller through the second generation module 240, and the motion controller uses the motion control algorithm to generate a precise control instruction; finally, the execution module 250 executes the precise control instruction.

[0130] This embodiment provides an intelligent motion control system, which can utilize this method to improve the working efficiency, reliability and intelligent control level of sports equipment.

[0131] Furthermore, the artificial intelligence algorithm includes an imitation learning algorithm and a reinforcement learning algorithm, and the first generation module 220 includes:

[0132] A determination unit, used to determine whether the current environment meets the preset conditions according to the environmental status data and the demonstration data;

[0133] a construction unit, configured to, if yes, construct a behavior generation strategy using the imitation learning algorithm according to the demonstration data;

[0134] A first generating unit, configured to generate a first control instruction according to the behavior generating strategy;

[0135] An acquisition unit, used for acquiring a new environment state and a reward signal fed back by the environment after the sports device interacts with the environment;

[0136] An updating unit, configured to continuously update the strategy and related parameters through the reinforcement learning algorithm according to the new environment state and the reward signal to obtain an optimized strategy;

[0137] The second generating unit is used to generate a second control instruction according to the optimization strategy.

[0138] Based on the above technical solution, the determination unit is specifically used to: perform similarity calculation on the environmental state data and the demonstration scene data in the expert demonstration data to obtain a similarity result; and determine whether the current environment meets the preset conditions according to the similarity result.

[0139] The above-mentioned intelligent motion control device can execute the intelligent motion control method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0140] Embodiment 6

[0141] Figure 6 The schematic diagram of the structure of the motion device 10 that can be used to implement the embodiment of the present invention is shown. The motion device includes, but is not limited to, robots, self-driving vehicles, intelligent industrial equipment, intelligent storage equipment and many other devices that require precise motion control. The components shown herein, their connections and relationships, and their functions are only for example, and are not intended to limit the implementation of the present invention described and / or required herein.

[0142] like Figure 6 As shown, the sports device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the sports device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0143] A number of components in the sports device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the sports device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0144] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as an intelligent motion control method.

[0145] In some embodiments, an intelligent motion control method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the motion device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps in the intelligent motion control method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform an intelligent motion control method in any other appropriate manner (e.g., by means of firmware).

[0146] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0147] In some embodiments, an intelligent motion control method can be implemented as a computer program, which is invisibly included in a computer program product. When the computer program is executed by a processor, an intelligent motion control method of the present invention is implemented. The computer program product can be understood as a software product that mainly implements its solution through a computer program. The computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, partially on the machine as an independent software package and partially on a remote machine, or completely on a remote machine or server.

[0148] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer 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 foregoing.

[0149] To provide interaction with a user, the systems and techniques described herein may be implemented on a sports device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the sports device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0150] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0151] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0152] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0153] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent motion control method, characterized in that: The method comprises: Obtain environmental status data and motion equipment status data; Generate a first control instruction and a second control instruction using an artificial intelligence algorithm according to the environmental status data; Generate a precise control instruction based on the motion device state data, the first control instruction and the second control instruction, and a motion control algorithm; The precise control instructions are sent to each servo driver for execution to complete motion control.

2. The method according to claim 1, characterized in that The step of obtaining the environmental status data and the motion device status data includes: Obtain environmental data and motion equipment data collected by sensors; The environmental data and the motion device data are processed to obtain environmental status data and motion device status data.

3. The method according to claim 1, characterized in that The artificial intelligence algorithm includes an imitation learning algorithm and a reinforcement learning algorithm. The method of generating the first control instruction and the second control instruction using the artificial intelligence algorithm according to the environmental state data includes: Determine whether the current environment meets the preset conditions according to the environmental status data and the demonstration data; If so, constructing a behavior generation strategy using the imitation learning algorithm based on the demonstration data; generating a first control instruction according to the behavior generation strategy; Acquire a new environment state and reward signal fed back by the environment after the sports device interacts with the environment; According to the new environment state and the reward signal, the strategy and related parameters are continuously updated by the reinforcement learning algorithm to obtain an optimized strategy; A second control instruction is generated according to the optimization strategy.

4. The method according to claim 3, characterized in that The determining whether the current environment meets the preset conditions according to the environmental status data and the expert demonstration data includes: Performing similarity calculation on the environmental state data and the demonstration scene data in the expert demonstration data to obtain a similarity result; Determine whether the current environment meets the preset condition according to the similarity result.

5. The method according to claim 1, characterized in that: The generating of the precise control instruction based on the motion device state data, the first control instruction and the second control instruction, and the motion control algorithm comprises: Generate a third control instruction through a motion control algorithm according to the motion device state data and the preset basic task instruction; The first control instruction, the second control instruction and the third control instruction are integrated to generate a precise control instruction.

6. The method according to claim 5, characterized in that The fusing the first control instruction, the second control instruction and the third control instruction to generate a precise control instruction includes: Dynamically adjusting the fusion ratio of the first control instruction, the second control instruction and the third control instruction according to preset factors; The first control instruction, the second control instruction and the third control instruction are fused according to the fusion ratio to generate a precise control instruction.

7. The method according to claim 1, characterized in that The generating of the precise control instruction based on the motion device state data, the first control instruction and the second control instruction, and the motion control algorithm comprises: inputting the motion device state data, the first control instruction and the second control instruction into a motion controller; The motion controller generates precise control instructions using a motion control algorithm.

8. An intelligent motion control system, characterized in that: The system includes a perception module, a processing module, an instruction generation module, a motion control module, an instruction fusion module and an execution module; The sensing module is used to collect environmental data and sports equipment data in real time; The processing module is used to process the environmental data and the sports equipment data to obtain environmental status data and sports equipment status data; The instruction generation module is used to generate a first control instruction and a second control instruction using an artificial intelligence algorithm according to the environmental state data; The motion control module is used to generate a third control instruction through a motion control algorithm according to the motion device state data and the preset basic task instruction; The instruction fusion module is used to fuse the first control instruction, the second control instruction and the third control instruction to generate a precise control instruction; The execution module is used to execute the precise control instruction.

9. A sports equipment, characterized in that: The sports equipment includes: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the intelligent motion control method described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the intelligent motion control method according to any one of claims 1 to 7 when executed.

11. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the intelligent motion control method according to any one of claims 1 to 7.

Images