Adaptive control method, device, equipment and storage medium

Abstract

The present disclosure relates to an adaptive control method, apparatus, device and storage medium, wherein the method comprises: in case it is determined that the execution device cannot execute a first control instruction, obtaining the control purpose of the first control instruction; obtaining a second control instruction that can achieve the control purpose; simulating the execution process of the second control instruction in a digital space; constructing a digital environment in the digital space based on the environmental information; determining the conflict between the digital environment and the execution process of the second control instruction, optimizing the execution process of the second control instruction to avoid the conflict; generating a target instruction based on the optimized execution process. The above method avoids the situation where the instruction cannot be executed, greatly improves the adaptability of the execution device, and enhances the robustness of the execution device.

Description

Technical Field

[0001] The present disclosure relates to the field of automatic control, and in particular, to an adaptive control method, device, equipment and storage medium. Background Art

[0002] In the control of the execution device, it is necessary to drive multiple modules of the execution device to complete a series of control instructions. For example, in the control of the robot, it is necessary to drive the motion controller of each joint of the robot or functional modules such as sensors, cameras, etc. to control the robot to complete a series of control instructions. Summary of the invention

[0003] Based on the above technical problems, the purpose of the present disclosure is to provide an adaptive control method, device, equipment and storage medium.

[0004] According to a first aspect of an embodiment of the present disclosure, an adaptive control method is provided, the method comprising: in case it is determined that an execution device cannot execute a first control instruction, obtaining a control purpose of the first control instruction; obtaining a second control instruction that can achieve the control purpose; simulating the execution process of the second control instruction in a digital space; constructing a digital environment in the digital space based on the environmental information; determining a conflict between the digital environment and the execution process of the second control instruction, optimizing the execution process of the second control instruction to avoid the conflict; and generating a target instruction based on the optimized execution process.

[0005] Optionally, obtaining a second control instruction capable of achieving the control purpose includes: inputting the control purpose, an associated control unit, and a fault condition of the associated control unit into an instruction generation model to generate a second control instruction, wherein the associated control unit is a control unit associated with the control purpose.

[0006] Optionally, the digital space is generated through digital twin technology.

[0007] Optionally, the method also includes: obtaining the first control instruction; obtaining the environmental information and the fault conditions of all control units of the execution device; generating an execution process of the first control instruction based on the first control instruction and the environmental information; and judging whether the execution process of the first control instruction can be executed based on the fault conditions of all control units.

[0008] Optionally, judging whether the execution process can be executed based on the fault conditions of all the control units includes: when any control unit used in the execution process is in a fault state, judging that the execution process of the first control instruction cannot be executed.

[0009] Optionally, the execution device is a robot, the control unit includes a motion controller of the robot, and the method further includes: obtaining the first control instruction, the control instruction is used to drive the robot to complete a specified action in a physical space; obtaining the environmental information and the fault conditions of all motion controllers; generating an execution process of the first control instruction based on the first control instruction and the environmental information; and judging whether the execution process of the first control instruction can be executed based on the fault conditions of all motion controllers.

[0010] Optionally, the control purpose is a robot action target, and obtaining a second control instruction that can achieve the control purpose includes: inputting the robot action target, an associated motion controller, and a fault condition of the associated motion controller into an instruction generation model to generate a second control instruction, and the associated motion controller is a motion controller that has an action association with the robot action target.

[0011] According to a second aspect of an embodiment of the present disclosure, an adaptive control device is provided, the device comprising: a first acquisition module, for acquiring the control purpose of the first control instruction when it is determined that the execution device cannot execute the first control instruction; a second acquisition module, for acquiring a second control instruction that can achieve the control purpose; a simulation module, for simulating the execution process of the second control instruction in a digital space; a construction module, for constructing a digital environment in the digital space based on the environmental information; an optimization module, for determining a conflict between the digital environment and the execution process of the second control instruction, and optimizing the execution process of the second control instruction to avoid the conflict; and a generation module, for generating a target instruction based on the optimized execution process.

[0012] According to a third aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, characterized in that when the program is executed by a processor, the adaptive control method provided by the first aspect of the present disclosure is implemented.

[0013] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, characterized in that it includes: a memory on which a computer program is stored; and a processor for executing the computer program in the memory to implement the adaptive control method provided by the first aspect of the present disclosure.

[0014] Through the above technical solution, when it is determined that the execution device cannot execute the first control instruction, a second control instruction that can achieve the control purpose is regenerated, and the second control instruction is optimized to generate a target instruction, thereby avoiding the situation where the instruction cannot be executed, greatly improving the adaptability of the execution device, and enhancing the robustness of the execution device.

[0015] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0017] Figure 1 The figure is a flow chart of an adaptive control method according to an exemplary embodiment.

[0018] Figure 2 It is a block diagram of an adaptive control device according to an exemplary embodiment.

[0019] Figure 3 It is a block diagram of an electronic device according to an exemplary embodiment.

[0020] Figure 4 is a block diagram of another electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0021] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0022] It should be noted that all actions of acquiring signals, information or data in the present disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the device is located and with the authorization given by the owner of the corresponding device.

[0023] There are at least the following problems in the related art: when a module involved in the control process of the execution device fails, it will cause control failure. For example, when a shutdown controller or functional module fails, it will cause the movement or operation of the robot to fail.

[0024] In response to the above problems, the inventor proposes that when the execution device determines that the issued instructions cannot be completed according to the current operating status of the device, avoidance measures can be effectively taken to complete the issued instructions. Based on this, the present application proposes an adaptive control method. When it is determined that the execution device cannot execute the first control instruction, a second control instruction that can achieve the control purpose is regenerated, and the second control instruction is optimized to generate a target instruction, thereby avoiding the situation where the instruction cannot be executed, greatly improving the adaptability of the execution device, and enhancing the robustness of the execution device.

[0025] Figure 1 is a flow chart of an adaptive control method according to an exemplary embodiment. Figure 1 As shown, the following steps are included.

[0026] Step S110: When it is determined that the execution device cannot execute the first control instruction, a control purpose of the first control instruction is obtained.

[0027] Execution equipment refers to some automatic control equipment such as automatic delivery equipment, sweeping robots, patrol robots, cleaning robots, etc. Execution equipment can complete tasks according to preset plans or programs.

[0028] Before issuing a control instruction for execution, determine whether the execution device can successfully execute the control instruction (this application refers to the instruction that cannot be completed as the first control instruction). If the first control instruction cannot be executed, obtain the control purpose of the first control instruction, which refers to the task or goal of the instruction. For example, for a control instruction of a service robot "use the right arm to take a glass of water", the control purpose of the instruction is "take a glass of water".

[0029] Optionally, the method also includes: obtaining the first control instruction; obtaining the environmental information and the fault conditions of all control units of the execution device; generating an execution process of the first control instruction based on the first control instruction and the environmental information; and judging whether the execution process of the first control instruction can be executed based on the fault conditions of all control units.

[0030] In one embodiment of the present application, a method for determining that the first instruction cannot be executed is:

[0031] A control instruction is obtained, where the control instruction may come from outside or inside the execution device.

[0032] After obtaining the control instruction, the environmental information around the execution device and the fault conditions of all control units of the execution device are obtained. The environmental information includes the objects and their properties around the execution device. For example, for the automatic delivery device, after sensing that the user has entered the seat, a control instruction is generated: "Use the display screen to prompt the user to order food." After obtaining the instruction, the automatic delivery device uses a perception module, such as an optical camera module, infrared sensor, etc., to scan the surrounding environment to obtain environmental information. The environmental information represents the space around the automatic delivery device, such as the ground, spatial distance, obstacles, etc. The control unit refers to the control module in the execution device, such as sensors, display screens, etc. The automatic delivery device uses a detection module to detect the fault conditions of all its control units and obtain the fault conditions of all control units.

[0033] Generate the execution process of the first control instruction based on the control instruction and the environmental information. The execution device generates a control instruction group in combination with the control instruction and the environmental information. The control instruction group is a control array along the time axis, which represents the process of completing the control instruction. For example, after the automatic delivery device obtains the completion environmental information and fault conditions, for the control instruction of "using the display screen to prompt the user to order food", the execution process is generated in combination with the environmental information: approach the user and light up the screen. The control instruction group of this control process includes: "move forward 5 meters", "turn left", and "light up the screen".

[0034] The execution device determines whether the execution process of the first control instruction can be executed based on the fault conditions of all the control units obtained, such as obtaining the control units involved in the execution process of the first control instruction, and determining whether the key units in the control units involved are faulty. The key units are pre-designated. When the key units fail, it is determined that the control process of the instruction cannot be executed.

[0035] Optionally, judging whether the execution process can be executed based on the fault conditions of all the control units includes: when any control unit used in the execution process is in a fault state, judging that the execution process of the first control instruction cannot be executed.

[0036] If any control unit used in the execution process is in a faulty state, the execution process cannot be executed. For example, the automatic delivery equipment searches for the control unit required by the control instruction group: forward wheels, steering mechanism, and screen, and then determines whether the above control units are faulty based on the fault conditions of all control units. If the fault condition reflects a screen fault, the automatic delivery equipment determines that the screen fault is present, then the control process of the instruction cannot be carried out and the control instruction cannot be executed.

[0037] Optionally, the execution device is a robot, the control unit includes a motion controller of the robot, and the method further includes: obtaining the first control instruction, which is used to drive the robot to complete a specified action in a physical space; obtaining the environmental information and the fault conditions of all motion controllers; generating an execution process of the first control instruction based on the first control instruction and the environmental information; and judging whether the execution process of the first control instruction can be executed based on the fault conditions of all motion controllers.

[0038] In one embodiment of the present application, the execution device is a robot, and the control unit is a motion controller of each joint of the robot. In some control processes, the control unit also includes the functional modules of the robot (such as sensors, cameras, etc.). The robot obtains control instructions, and the control instructions are used to drive the robot to complete a specified action in the physical space, such as "use the right robotic arm to grab a glass of water". The physical space refers to the real world where the robot is located.

[0039] After the robot determines that it cannot execute the control command, it downloads environmental information from the server or scans through its own equipment to obtain the environmental information. The environmental information can be: whether there are obstacles that affect the movement of the equipment during the operation of the robot equipment, and then check the fault status of the motion controller of each joint, or obtain the fault status of the motion controller based on the stored maintenance table.

[0040] The robot generates the execution process of the first control instruction based on the control instruction and environmental information, such as planning the motion trajectory of the robot arm based on the obstacle information, and generating a control array based on the motion trajectory. The control array is a series of control instructions along time, driving the joint controller to realize the motion trajectory.

[0041] The robot obtains the joint controllers involved in the control array, and determines whether there is a fault in the joint controllers involved based on the fault status. For example, if there is a fault in the motion controller of the right arm joint, the machine determines that there is a fault in the motion controller of the arm joint based on the fault status, and then determines that the execution process of the control execution cannot be completed and the control instruction cannot be completed.

[0042] Step S120, obtaining a second control instruction that can achieve the control purpose.

[0043] Based on the control purpose, other control instructions other than the first control instruction that can achieve the control purpose are obtained. This application refers to this type of control instruction as a second control instruction.

[0044] For example, you can create associated instructions for the control purpose in advance, and when a certain instruction cannot be executed, find other instructions based on the associated relationship. For example, for automatic delivery equipment, the control purpose of "prompting users to order food" is associated with the instructions "display screen display", "voice prompt", and "call waiter". When the control instruction of "using the display screen to prompt users to order food" cannot be completed, obtain the control purpose of "prompting users to order food" and find the instructions "voice prompt" and "call waiter" based on the associated relationship, and select any one of them.

[0045] Optionally, obtaining a second control instruction capable of achieving the control purpose includes: inputting the control purpose, an associated control unit, and a fault condition of the associated control unit into an instruction generation model to generate a second control instruction, wherein the associated control unit is a control unit associated with the control purpose.

[0046] In one embodiment of the present application, the method for acquiring the second control instruction may be:

[0047] The control purpose, associated control units, and the fault conditions of the associated control units are input into the instruction generation model. The associated control unit refers to the control unit associated with the control purpose, such as all control units required to be used in the execution process of the control instruction. The instruction generation model is a pre-trained model, and its training process can be: use the training set to train the initial model, and each sample in the training data includes: training data: control purpose, all control units associated with the control purpose, some units in the control unit have fault marks, marking data: a control instruction that can achieve the control purpose without using the marked control unit, the initial model can be a pre-trained deep learning model such as transform (converter), etc., set hyperparameters, and use the training set to train the initial model until the model converges. The trained instruction generation model can evaluate the control unit that can be replaced in the execution process of realizing the control purpose of the first control instruction, and combine the current executable control unit to generate a new second control instruction to finally complete the first control instruction issued by the user.

[0048] The instruction generation model can make predictions based on the control purpose, the associated control units and their fault conditions, and generate new control instructions, namely second control instructions, which can drive the execution device to achieve the control purpose without using the faulty control unit.

[0049] Optionally, the control purpose is a robot action target, and obtaining a second control instruction that can achieve the control purpose includes: inputting the robot action target, an associated motion controller, and a fault condition of the associated motion controller into an instruction generation model to generate a second control instruction, and the associated motion controller is a motion controller that has an action association with the robot action target.

[0050] In one embodiment of the present application, the execution device is a robot, and the control purpose is the action target of the robot. For example, the control instruction is "use the right robotic arm to grab a glass of water". The control purpose can be "a glass of water" or "grab a glass of water". The associated motion controller is a motion controller that has an action association with the robot action target. For example, for the control purpose "grab a glass of water", the associated motion controller is the motion controller of all joints that are associated with the grabbing action. The associated motion controller is marked as a fault, so that the faulty motion controller is marked, such as marking the motion controller of the right arm joint, and the control purpose "grab a glass of water" and the marked motion controller are input into the instruction generation model. The instruction generation model generates a new control instruction, that is, a second control instruction, such as "use the left robotic arm to grab a glass of water". The generated second control instruction can drive a replaceable motion controller to replace the damaged motion controller module to complete the issued instruction.

[0051] Step S130, simulating the execution process of the second control instruction in the digital space.

[0052] Step S140: constructing a digital environment in the digital space according to the environmental information.

[0053] Step S150, determining the conflict between the digital environment and the execution process of the second control instruction, and optimizing the execution process of the second control instruction to avoid the conflict.

[0054] After obtaining the second control instruction, it is also necessary to simulate the execution process of the instruction in the digital space, where the digital space refers to the virtual space corresponding to the physical space where multiple devices are located. The physical space refers to the real world, and the digital space can be mapped into the physical space through physical and mathematical models. The environmental information is mapped into the digital space to construct a digital environment, such as uploading the environmental information into the digital twin system, and the digital twin system maps obstacles into the digital space and constructs obstacles in the digital space.

[0055] The execution process of the second control instruction is optimized in the digital space according to the environmental information. The execution process of the second control instruction is simulated in the digital space, such as for the second control instruction "use the left robotic arm to grab a glass of water", the execution trajectory of the instruction is simulated in the digital space.

[0056] In the digital space, it is determined whether the spatial trajectory of the second control instruction touches or approaches an obstacle. If so, it indicates that there is a conflict between the environment and the execution process of the second control instruction. The execution trajectory of the second control instruction is optimized so that the optimized execution trajectory can bypass the obstacle and avoid the conflict.

[0057] Optionally, the digital space is generated through digital twin technology.

[0058] Digital twins are generated by mapping physical space through digital twin technology. Digital twins are the mapping of the structure, state, behavior, function and performance of complex physical systems such as industrial products, manufacturing systems and cities into a digital virtual world. Through real-time sensing, connection mapping, precise analysis and immersive interaction, physical systems are portrayed, predicted and controlled to achieve virtual-real integration of complex systems, so that all elements, processes and value chains of the system can achieve maximum closed-loop optimization. The essence of digital twins is to establish a virtual digital mirror of the physical system in the real world, which runs through the entire life cycle of the physical system and evolves dynamically with the physical system.

[0059] Step S160, generating target instructions according to the optimized execution process.

[0060] A control instruction, ie, a target instruction, is generated according to the optimized execution process in the digital space.

[0061] For example, a control array is generated according to the optimized execution trace, and the control array is used as the target instruction.

[0062] Through the above-mentioned adaptive control method, when it is determined that the execution device cannot execute the first control instruction, a second control instruction that can achieve the control purpose is regenerated, and the second control instruction is optimized to generate a target instruction, thereby avoiding the situation where the instruction cannot be executed, greatly improving the adaptability of the execution device, and enhancing the robustness of the execution device.

[0063] Figure 2 is a block diagram of an adaptive control device according to an exemplary embodiment. Figure 2 As shown, the device comprises:

[0064] A first acquisition module 210, configured to acquire a control purpose of the first control instruction when it is determined that the execution device cannot execute the first control instruction;

[0065] A second acquisition module 220, used to acquire a second control instruction capable of achieving the control purpose;

[0066] A simulation module 230, configured to simulate the execution process of the second control instruction in a digital space;

[0067] A construction module 240, configured to construct a digital environment in a digital space according to the environment information;

[0068] An optimization module 250, configured to determine a conflict between the digital environment and the execution process of the second control instruction, and optimize the execution process of the second control instruction to avoid the conflict;

[0069] The generation module 260 is used to generate target instructions according to the optimized execution process.

[0070] Optionally, the second acquisition module is specifically used to input the control purpose, the associated control unit, and the fault condition of the associated control unit into an instruction generation model to generate a second control instruction, and the associated control unit is a control unit associated with the control purpose.

[0071] Optionally, the device further comprises:

[0072] A third acquisition module, used to acquire the first control instruction;

[0073] A fourth acquisition module, used to acquire the environmental information and the fault conditions of all control units of the execution device;

[0074] An execution process generating module, used for generating an execution process of the first control instruction according to the first control instruction and the environmental information;

[0075] A judgment module is used to judge whether the execution process of the first control instruction can be executed according to the fault conditions of all the control units.

[0076] Optionally, the judgment module is specifically used to: when any control unit used in the execution process is in a fault state, determine that the execution process of the first control instruction cannot be executed.

[0077] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0078] Figure 3 FIG. 1 is a block diagram of an electronic device 300 according to an exemplary embodiment. Figure 3 As shown, the electronic device 300 may include: a processor 301 , a memory 302 . The electronic device 300 may also include one or more of a multimedia component 303 , an input / output (I / O) interface 304 , and a communication component 305 .

[0079] The processor 301 is used to control the overall operation of the electronic device 300 to complete all or part of the steps in the above-mentioned adaptive control method. The memory 302 is used to store various types of data to support the operation of the electronic device 300, and these data may include, for example, instructions for any application or method used to operate on the electronic device 300, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 303 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 302 or sent through the communication component 305. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 304 provides an interface between the processor 301 and other interface modules, and the other interface modules may be keyboards, mice, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 305 is used for wired or wireless communication between the electronic device 300 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or a combination of one or more of them, is not limited here. Therefore, the corresponding communication component 305 may include: Wi-Fi module, Bluetooth module, NFC module, etc.

[0080] In an exemplary embodiment, the electronic device 300 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned adaptive control method.

[0081] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned adaptive control method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 302 including program instructions, and the above-mentioned program instructions can be executed by the processor 301 of the electronic device 300 to complete the above-mentioned adaptive control method.

[0082] Figure 4 4 is a block diagram of an electronic device 400 according to an exemplary embodiment. For example, the electronic device 400 may be provided as a server. Figure 4 The electronic device 400 includes a processor 422, which may be one or more, and a memory 432 for storing a computer program executable by the processor 422. The computer program stored in the memory 432 may include one or more modules each corresponding to a set of instructions. In addition, the processor 422 may be configured to execute the computer program to perform the above-mentioned adaptive control method.

[0083] In addition, the electronic device 400 may further include a power supply component 426 and a communication component 450. The power supply component 426 may be configured to perform power management of the electronic device 400, and the communication component 450 may be configured to implement communication of the electronic device 400, for example, wired or wireless communication. In addition, the electronic device 400 may further include an input / output (I / O) interface 458. The electronic device 400 may operate based on an operating system stored in the memory 1932, such as Windows Server 2008. TM , Mac OSX TM , Unix TM , Linux TM etc.

[0084] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by the processor, the steps of the above-mentioned adaptive control method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 432 including program instructions, and the above-mentioned program instructions can be executed by the processor 422 of the electronic device 400 to complete the above-mentioned adaptive control method.

[0085] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program executable by a programmable device. The computer program has a code portion for executing the above-mentioned adaptive control method when executed by the programmable device.

[0086] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0087] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0088] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. An adaptive control method, characterized in that: The method comprises: In the case where it is determined that the execution device cannot execute the first control instruction, obtaining a control purpose of the first control instruction; Acquire a second control instruction capable of achieving the control purpose; Simulating the execution process of the second control instruction in a digital space; Constructing digital environment in digital space based on environmental information; Determining a conflict between the digital environment and the execution process of the second control instruction, and optimizing the execution process of the second control instruction to avoid the conflict; Generate target instructions based on the optimized execution process.

2. The method according to claim 1, characterized in that: The obtaining of a second control instruction capable of achieving the control purpose includes: The control purpose, the associated control unit, and the fault condition of the associated control unit are input into an instruction generation model to generate a second control instruction, and the associated control unit is a control unit associated with the control purpose.

3. The method according to claim 1, characterized in that: The digital space is generated through digital twin technology.

4. The method according to claim 1, characterized in that: The method further comprises: Acquire the first control instruction; Acquire the environmental information and the fault conditions of all control units of the execution device; generating an execution process of the first control instruction according to the first control instruction and the environmental information; Whether the execution process of the first control instruction can be executed is judged according to the fault conditions of all control units of the execution device.

5. The method according to claim 4, characterized in that: The determining whether the execution process can be executed according to the fault conditions of all control units of the execution device includes: When any control unit used in the execution process is in a fault state, it is determined that the execution process of the first control instruction cannot be executed.

6. The method according to claim 1, characterized in that: The execution device is a robot, the control unit of the execution device includes a motion controller of the robot, and the method further includes: Obtaining the first control instruction, where the control instruction is used to drive the robot to complete a specified action in a physical space; Obtaining the environmental information and the fault conditions of all motion controllers; generating an execution process of the first control instruction according to the first control instruction and the environmental information; Whether the execution process of the first control instruction can be executed is determined according to the fault conditions of all the motion controllers.

7. The method according to claim 6, characterized in that: The control purpose is a robot motion target, and the obtaining of a second control instruction capable of achieving the control purpose includes: The robot action target, the associated motion controller, and the fault condition of the associated motion controller are input into the instruction generation model to generate a second control instruction. The associated motion controller is a motion controller that has an action association with the robot action target.

8. An adaptive control device, characterized in that: The device comprises: A first acquisition module, configured to acquire a control purpose of the first control instruction when it is determined that the execution device cannot execute the first control instruction; A second acquisition module, used to acquire a second control instruction capable of achieving the control purpose; A simulation module, used for simulating the execution process of the second control instruction in a digital space; A construction module, used for constructing a digital environment in a digital space according to the environment information; an optimization module, used for determining a conflict between the digital environment and the execution process of the second control instruction, and optimizing the execution process of the second control instruction to avoid the conflict; The generation module is used to generate target instructions according to the optimized execution process.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.

10. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 7.

Images