Six-dimensional force sensor-based intelligent decision-making control method and system for body

Abstract

The invention provides a body intelligent decision control method and system based on a six-dimensional force sensor, and belongs to the technical field of body intelligence. The method comprises the steps that in the process that a mechanical arm executes a task execution state, the six-dimensional force sensor collects a stress signal of an end effector of the mechanical arm in real time; extracting a vertical direction force from the stress signal; according to the force in the vertical direction, the mass of an object grabbed by the mechanical arm is calculated in real time; and the state of the mechanical arm is judged in real time according to the mass of the object grabbed by the mechanical arm and the mechanical arm motion planning instruction, the mechanical arm motion planning instruction is completed according to the state of the mechanical arm, and the next mechanical arm motion planning instruction is executed again. The load mass of the mechanical arm can be accurately measured, and the defects that an existing intelligent system with a body is poor in precision and lags in response are powerfully overcome.

Description

Technical Field

[0001] The present invention belongs to the field of embodied intelligence technology, and specifically relates to an embodied intelligence decision-making control method and system based on a six-dimensional force sensor. Background Art

[0002] In today's era of rapid technological development, embodied intelligence, as a cutting-edge direction in the field of artificial intelligence with great potential and challenges, aims to give intelligent entities the comprehensive capabilities of accurate perception, efficient decision-making, and flexible action in real physical environments, thereby achieving smooth interaction with the surrounding environment.

[0003] In the technological landscape of embodied intelligence, accurate force perception plays a key role in enabling intelligent entities to perform tasks. Six-axis force sensors, as key components of force sensing, can measure force and torque components in three directions and are widely used in numerous scenarios, including industrial production and robotic operations. For example, in industrial manufacturing, robotic arms utilize six-axis force sensors to perform complex assembly and material handling tasks, adjusting their movements based on force feedback to ensure operational precision.

[0004] However, current embodied intelligence applications based on six-dimensional force sensors have significant drawbacks. For one thing, the measurement accuracy of existing six-dimensional force sensors is easily affected by environmental factors such as temperature fluctuations and electromagnetic interference, leading to deviations in the measurement data and, in turn, misjudging the forces applied to the intelligent entity. When a robotic arm grasps objects of varying materials and shapes, inaccuracies in the force sensors often result in inappropriate gripping force. A tight grip can damage the object, while a loose grip can render the grip unstable.

[0005] Furthermore, in complex operations, there's a lack of efficient algorithms to accurately translate the data collected by six-dimensional force sensors into a judgment of an object's state. For example, when a robotic arm assembles parts, even if the six-dimensional force sensor captures force and torque information, algorithmic limitations make it difficult to accurately determine whether the part has been correctly installed and whether the required assembly force has been achieved. This makes it difficult to ensure assembly quality, impacting production efficiency and product quality.

[0006] Furthermore, in embodied intelligence systems, the ability to determine whether a model has successfully completed a given action is crucial. Within its architecture, behavioral execution and judgment and decision-making capabilities are analogous to the human cerebellum and cerebrum, respectively, and their coordinated operation is crucial. However, existing six-dimensional force sensor technology has shortcomings in determining action completion. Even if an action can be executed based on force feedback, it is impossible to determine with certainty whether the action meets the intended goal, significantly limiting the overall effectiveness of the system. These issues are further amplified in large-scale application scenarios such as industrial production, severely hindering the practical promotion and application of embodied intelligence. Summary of the invention

[0007] In view of the deficiencies of the prior art, the present application proposes a method and system for embodied intelligent decision-making control based on a six-axis force sensor.

[0008] In a first aspect, the present application proposes a method for embodied intelligent decision-making control based on a six-axis force sensor, including:

[0009] Step S1: Generate a manipulator motion planning instruction according to a preset task target;

[0010] Step S2: Drive the manipulator into a task execution state according to the manipulator motion planning instruction;

[0011] Step S3: During the process of the manipulator executing the task execution state, the six-axis force sensor continuously collects the force signal of the end effector of the manipulator;

[0012] Step S4: Extract the vertical force from the force signal;

[0013] Step S5: According to the vertical force, calculate the mass of the object grasped by the manipulator in real time;

[0014] Step S6: According to the mass of the object grasped by the manipulator and the manipulator motion planning instruction, judge the state of the manipulator in real time, and according to the state of the manipulator, complete the manipulator motion planning instruction, and return to Step S1 to execute the next manipulator motion planning instruction.

[0015] According to the vertical force, calculate the mass of the object grasped by the manipulator in real time, and the calculation formula is as follows:

[0016] ;

[0017] where m is the mass of the object grasped by the manipulator, is the vertical force, is the self-gravity of the manipulator, is the offset generated by other interference forces, is the gravitational acceleration, is the acceleration in other directions except the direction of the end movement of the manipulator during the movement of the manipulator.

[0018] The state of the manipulator includes: the manipulator pick-up state, the manipulator idle state, and the manipulator drop state.

[0019] The real-time judgment of the state of the manipulator according to the mass of the object grasped by the manipulator and the manipulator motion planning instruction, and the completion of the manipulator motion planning instruction according to the state of the manipulator include:

[0020] When the robotic arm motion planning instruction is a grasping instruction, if the mass of the object grasped by the robotic arm jumps from a zero value with tolerance to a value greater than the material standard weight with tolerance, it is determined that the robotic arm has successfully grasped the material, and the robotic arm enters the picking-up state; if the mass of the object grasped by the robotic arm does not jump from a zero value with tolerance to a value greater than the material standard weight with tolerance, it is determined that the robotic arm has not successfully grasped the material, then the position parameters and force parameters of the gripper of the robotic arm are adjusted, and the process returns to step S1 to regenerate the robotic arm motion planning instruction and perform the grasping again.

[0021] The method of judging the state of the robotic arm in real time according to the mass of the object grasped by the robotic arm and the robotic arm motion planning instruction, and completing the robotic arm motion planning instruction according to the state of the robotic arm includes:

[0022] When the robotic arm motion planning instruction is a placing instruction, if the mass of the object grasped by the robotic arm drops from the effective grasping weight to a zero value with tolerance, it is determined that the material has been successfully placed by the robotic arm, and the robotic arm enters the placing state; if the mass of the object grasped by the robotic arm does not drop from the effective grasping weight to a zero value with tolerance, it is determined that the material has not been successfully placed by the robotic arm, then the position parameters and force parameters of the gripper of the robotic arm are adjusted, and the process returns to step S1 to regenerate the robotic arm motion planning instruction and perform the placing again.

[0023] The method of judging the state of the robotic arm in real time according to the mass of the object grasped by the robotic arm and the robotic arm motion planning instruction, and completing the robotic arm motion planning instruction according to the state of the robotic arm includes:

[0024] In the case where no robotic arm motion planning instruction is generated, if the mass of the object grasped by the robotic arm fluctuates within a preset range of a zero value with tolerance within a preset time period, the robotic arm is in an idle state, and the process returns to step S1 to wait for the generation of the next robotic arm motion planning instruction.

[0025] The zero value with tolerance is an error range that fluctuates within 5% above and below the zero value; the material standard weight with tolerance is an error range that fluctuates within 5% above and below the material standard weight.

[0026] In a second aspect, the present application proposes an embodied intelligent decision control system based on a six-dimensional force sensor, including:

[0027] An instruction generation module, configured to generate a robotic arm motion planning instruction according to a preset task target;

[0028] A task execution module, configured to drive the robotic arm into a task execution state according to the robotic arm motion planning instruction;

[0029] A signal acquisition module, configured to collect in real time the force signals of the end effector of the robotic arm by a six-axis force sensor during the task execution state of the robotic arm;

[0030] A vertical force extraction module, configured to extract the vertical force from the force signals;

[0031] A mass calculation module, configured to calculate in real time the mass of the object grasped by the robotic arm according to the vertical force;

[0032] A state judgment module, configured to judge in real time the state of the robotic arm according to the mass of the object grasped by the robotic arm and the motion planning instruction of the robotic arm, and complete the motion planning instruction of the robotic arm according to the state of the robotic arm, and return to the instruction generation module to execute the next motion planning instruction of the robotic arm.

[0033] In a third aspect, the present application provides an electronic device, including: one or more processors, and a memory, where the memory is used to store instructions, and when the instructions are executed by the one or more processors, the one or more processors are caused to execute the described embodied intelligent decision control method based on a six-axis force sensor.

[0034] In a fourth aspect, the present application provides a computer-readable storage medium, which stores executable instructions, and when the instructions are executed, the processor is caused to execute the described embodied intelligent decision control method based on a six-axis force sensor.

[0035] Advantageous effects:

[0036] The present application provides an embodied intelligent decision control method and system based on a six-axis force sensor, which can accurately measure the load mass of the robotic arm, effectively making up for the drawbacks of poor accuracy and response lag in existing embodied intelligent systems. Description of the drawings

[0037] Figure 1 A flowchart of an embodied intelligent decision control method based on a six-axis force sensor according to an embodiment of the present application;

[0038] Figure 2 A schematic diagram of an embodied intelligent decision control process based on a six-axis force sensor according to an embodiment of the present application;

[0039] Figure 3 A schematic block diagram of an embodied intelligent decision control system based on a six-axis force sensor according to an embodiment of the present application. Detailed implementation manners

[0040] The following further describes in detail the specific implementation manners of the present application in conjunction with the drawings and embodiments.

[0041] Embodiment 1:

[0042] This embodiment proposes an embodied intelligent decision-making control method based on a six-axis force sensor, as follows Figure 1 , Figure 2 shown, including:

[0043] Step S1: Generate a manipulator motion planning instruction according to a preset task goal;

[0044] Step S2: Drive the manipulator into the task execution state according to the manipulator motion planning instruction;

[0045] In this embodiment, after the manipulator system is powered on, it completes hardware self-check (including six-axis force sensor calibration and status detection of each joint servo motor of the manipulator) and software initialization (loading control algorithms and communication protocol configuration). Subsequently, the embodied intelligent decision-making control system triggers the model inference module, generates an initial manipulator motion planning instruction based on a preset task goal (such as material handling, parts assembly), and drives the manipulator into the task execution state.

[0046] Step S3: During the process of the manipulator executing the task execution state, the six-axis force sensor continuously collects the force signal of the end effector of the manipulator;

[0047] In this embodiment, first, the six-axis force sensor is customized and calibrated. For the specific application scenario of the manipulator grasping an object, the sensor is calibrated under various working conditions. By measuring standard objects of known weight at different temperatures, humidities, and different grasping postures, a high-precision calibration model is established to ensure that the sensor can accurately measure the force in the vertical direction in a complex environment, and then accurately convert the object weight. The calibration process belongs to the prior art and will not be elaborated in this embodiment.

[0048] In this embodiment, during the process of the manipulator executing an action, the six-axis force sensor continuously collects the force and torque signals received by the end effector. Specifically, the sensor converts the three-dimensional force and three-dimensional torque of the manipulator end in the Cartesian space into electrical signals through built-in sensitive elements such as strain gauges, and transmits them to the control system after amplification, filtering, and analog-to-digital conversion.

[0049] Step S4: Extract the vertical force from the force signal;

[0050] Specifically, in the Cartesian three-dimensional coordinate system, it is easy to extract the force in the vertical direction from the force signal.

[0051] Step S5: According to the vertical force, calculate the mass of the object grasped by the manipulator in real time. The calculation formula is as follows:

[0052] ;

[0053] where m is the mass of the object grasped by the manipulator, is the vertical force, is the self - gravity of the robotic arm, is the offset caused by other interference forces, is the gravitational acceleration, During the movement of the robotic arm, it is the acceleration in directions other than the direction of the movement of the end of the robotic arm.

[0054] In this embodiment, for weight calculation, the vertical force is extracted and a dedicated weight calculation algorithm is designed. Based on the vertical force component measured by the six - axis force sensor, combined with the gravitational acceleration and the robotic arm structure parameters (such as the length of the force arm, etc., used to correct the measured value of the force), the weight of the object is calculated through an accurate mathematical formula.

[0055] The method of this embodiment can quickly and accurately obtain the weight of the object, ensuring both real - time performance and meeting the requirements of measurement accuracy.

[0056] Step S6: According to the mass of the object grasped by the robotic arm and the robotic arm motion planning instruction, real - time judge the state of the robotic arm. According to the state of the robotic arm, complete the robotic arm motion planning instruction, and return to step S1 to execute the next robotic arm motion planning instruction.

[0057] The state of the robotic arm includes: the robotic arm picking - up state, the robotic arm idle state, and the robotic arm putting - down state.

[0058] The real - time judgment of the state of the robotic arm according to the mass of the object grasped by the robotic arm and the robotic arm motion planning instruction, and the completion of the robotic arm motion planning instruction according to the state of the robotic arm includes:

[0059] When the robotic arm motion planning instruction is a grasping instruction, if the mass of the object grasped by the robotic arm jumps from a zero value with tolerance to a value greater than the material standard weight with tolerance, it is determined that the robotic arm has successfully grasped the material, and the robotic arm enters the picking - up state; if the mass of the object grasped by the robotic arm does not jump from a zero value with tolerance to a value greater than the material standard weight with tolerance, it is determined that the robotic arm has not successfully grasped the material, then adjust the position parameters and force parameters of the gripper of the robotic arm, return to step S1, regenerate the robotic arm motion planning instruction, and perform grasping again.

[0060] The real - time judgment of the state of the robotic arm according to the mass of the object grasped by the robotic arm and the robotic arm motion planning instruction, and the completion of the robotic arm motion planning instruction according to the state of the robotic arm includes:

[0061] When the robotic arm motion planning instruction is a put-down instruction, if the mass of the object grasped by the robotic arm drops from the effective grasping weight to zero with a tolerance, it is determined that the material has been successfully placed by the robotic arm, and the robotic arm enters the put-down state; if the mass of the object grasped by the robotic arm does not drop from the effective grasping weight to zero with a tolerance, it is determined that the material has not been successfully placed by the robotic arm, then adjust the position parameters and force parameters of the gripper of the robotic arm, return to step S1, regenerate the robotic arm motion planning instruction, and perform the put-down again.

[0062] The method of determining the state of the robotic arm in real time according to the mass of the object grasped by the robotic arm and the robotic arm motion planning instruction, and completing the robotic arm motion planning instruction according to the state of the robotic arm includes:

[0063] In the case where no robotic arm motion planning instruction is generated, if the mass of the object grasped by the robotic arm fluctuates within a preset range of zero with a tolerance within a preset time period, the robotic arm is in an idle state, and return to step S1 to wait for the generation of the next robotic arm motion planning instruction.

[0064] In this embodiment, the control system compares the calculated weight with a preset threshold and performs state judgment:

[0065] In the case where the robotic arm motion planning instruction is a grasping instruction, the determination of the pick-up state: if the weight jumps from near zero to greater than the standard weight of the material (considering the measurement error, set as the tolerance), it is determined that the robotic arm has successfully grasped the material and enters the "pick-up state".

[0066] In the case where the robotic arm motion planning instruction is a put-down instruction, the determination of the put-down state: if the weight drops from the effective grasping weight value to near zero, it is determined that the material has been successfully placed and enters the "put-down state".

[0067] In the case where no robotic arm motion planning instruction is generated, the determination of the idle state: if the weight always fluctuates near zero (the pick-up or put-down determination conditions are not triggered) and the robotic arm has no motion instruction executed, it is determined to be in the "idle state".

[0068] Establish a grasping state feedback mechanism. When the grasping state is determined by weight comparison, the six-axis force sensor timely feeds back the grasping state information (success or failure) to the robotic arm control system. According to the feedback information, if the grasping is successful, the control system continues to perform subsequent operations; if the grasping fails, the control system adjusts parameters such as the position and force of the robotic arm gripper and performs the grasping attempt again.

[0069] Enables linkage with other equipment. In scenarios such as industrial production, the gripping status information from the six-dimensional force sensor can be linked with other equipment on the production line. For example, if the robotic arm successfully grasps a material, subsequent equipment on the production line can automatically start and proceed to the next processing operation. If the grasp fails, the production line is paused, avoiding subsequent production problems caused by incorrect material grasping and improving the reliability and efficiency of the entire production system.

[0070] Regardless of whether the robotic arm is in the "pickup" state, "placement" state, or "idle" state, as long as the complete task logic is met (for example, completing the transfer and placement of materials from station A to station B), the control system determines that the task is complete. At this point, it sends a command to return the robotic arm to a safe position (such as the initial stop), shuts down the model inference process, and the six-axis force sensor enters low-power monitoring mode. The entire task process is terminated and the next task is triggered.

[0071] The main thing to note is: if data abnormalities occur in the state judgment link (such as six-dimensional force sensor signal jumps, weight calculation results exceed the physically reasonable range), the control system triggers the exception handling mechanism: first, data filtering and recalculation are performed. If the calculation is still abnormal after three consecutive times, the robot arm action is suspended, and an error is reported through the human-machine interface, prompting manual inspection of the sensor connection, material status, etc. to ensure the reliability of the system operation.

[0072] The zero value with tolerance is an error range of 5% above and below the zero value; the standard weight of the material with tolerance is an error range of 5% above and below the standard weight of the material.

[0073] In this embodiment, a comparison and judgment algorithm needs to be constructed. The calculated weight of the object is compared with the preset actual mass of the object. A reasonable weight error tolerance range is set. When the calculated weight is within the error range of the actual mass, it is judged that the robot arm gripper has completely picked up the object; if the calculated weight is significantly less than the actual mass, it is judged that the gripper is incomplete. For example, the error range is set to ±5% of the actual mass. When When , it is determined that the crawl is successful, among which, The standard weight of the material.

[0074] This embodiment proposes an embodied intelligent decision-making and control method based on a six-dimensional force sensor. Compared with the traditional method of determining the completion of an action, the six-dimensional force sensor-based determination technology adopted in this embodiment has significant advantages. Traditional methods have drawbacks such as poor accuracy and delayed response in embodied intelligent systems, making it difficult to accurately determine whether an action is completed. In sharp contrast, the solution of this embodiment can accurately measure the load mass of the robotic arm, effectively making up for the many shortcomings of existing embodied intelligent systems in determining the completion of an action.

[0075] In the precision assembly scenario of industrial production, with its precise load mass determination ability, it can ensure that each component is accurately stressed during the assembly process, greatly improving the assembly accuracy, effectively reducing the defective rate, and significantly enhancing the production efficiency and product quality. In the medical field, surgical assistance robots can accurately perceive the forces between instruments and tissues with the help of this technology, precisely control movements, providing a solid guarantee for the accuracy and safety of surgeries, and assisting doctors in completing more complex and delicate surgical operations. In the service industry, robots providing personalized services use this solution to accurately determine the grasping state based on the force feedback when grasping different items, and thus flexibly and accurately complete various service tasks, greatly improving the service quality and user experience.

[0076] Embodiment 2:

[0077] This embodiment proposes an embodied intelligent decision control system based on a six-axis force sensor, as Figure 3 shown, including: an instruction generation module, a task execution module, a signal acquisition module, a vertical force extraction module, a mass calculation module, and a state judgment module;

[0078] The instruction generation module is connected to the task execution module, the task execution module is connected to the signal acquisition module, the signal acquisition module is connected to the vertical force extraction module, the vertical force extraction module is connected to the mass calculation module, the mass calculation module is connected to the state judgment module, and the state judgment module is connected to the instruction generation module;

[0079] The instruction generation module is used to generate a manipulator motion planning instruction according to a preset task target;

[0080] The task execution module is used to drive the manipulator into the task execution state according to the manipulator motion planning instruction;

[0081] The signal acquisition module is used to collect the force signal of the end effector of the manipulator in real time by the six-axis force sensor during the process of the manipulator executing the task execution state;

[0082] The vertical force extraction module is used to extract the vertical force from the force signal;

[0083] The mass calculation module is used to calculate the mass of the object grasped by the manipulator in real time according to the vertical force;

[0084] The state judgment module is used to judge the state of the manipulator in real time according to the mass of the object grasped by the manipulator and the manipulator motion planning instruction, and complete the manipulator motion planning instruction according to the state of the manipulator, and return to the instruction generation module to execute the next manipulator motion planning instruction.

[0085] Embodiment 3:

[0086] This embodiment provides an electronic device, including: one or more processors, and a memory. The memory is used to store instructions, and when the instructions are executed by the one or more processors, the one or more processors are caused to execute the described embodied intelligent decision-making control method based on a six-axis force sensor.

[0087] The electronic device can be a mobile phone, a computer, a tablet computer, etc., including a memory and a processor. A computer program is stored on the memory, and when the computer program is executed by the processor, it implements an embodied intelligent decision-making control method based on a six-axis force sensor as described in the embodiment. It can be understood that the electronic device may further include an input / output (I / O) interface and a communication component.

[0088] Among them, the processor is used to execute all or part of the steps in the described embodied intelligent decision-making control method based on a six-axis force sensor in the above embodiment. The memory is used to store various types of data, which may include, for example, instructions of any application program or method in the electronic device, as well as data related to the application program.

[0089] The processor can be implemented by an application specific integrated circuit (ASIC), a digital signal processor (DSP), a programmable logic device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller, a microprocessor, or other electronic components, and is used to execute the described embodied intelligent decision-making control method based on a six-axis force sensor in the above embodiment.

[0090] Embodiment 4:

[0091] This embodiment provides a computer-readable storage medium that stores executable instructions. When the instructions are executed and implemented in the form of a software functional unit and sold or used as an independent product, they can be stored in a computer-readable storage medium.

[0092] The computer software product is stored in a storage medium and includes several instructions to cause a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the described embodied intelligent decision-making control method based on a six-axis force sensor in various embodiments of the present application.

[0093] The foregoing storage medium includes: flash memory, hard disk, multimedia card, card-type memory (e.g., SD (Secure Digital Memory Card) or DX (abbreviation for Memory Data Register, MDR), memory data register, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, server, APP (abbreviation for Application, application software) application store, and various other media that can store program verification codes. A computer program is stored thereon, and when the computer program is executed by a processor, each step of the foregoing method for embodied intelligent decision-making control based on a six-axis force sensor can be implemented.

[0094] Each embodiment in this application is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the key point of each embodiment is to illustrate the differences from other embodiments.

[0095] The protection scope of this application is not limited to the above embodiments. Obviously, those skilled in the art can make various changes and deformations to the present disclosure without departing from the scope and spirit of the present disclosure. If these changes and deformations fall within the scope of the claims of the present disclosure and their equivalent technologies, the intention of the present disclosure also includes these changes and deformations.

Claims

1. An embodied intelligent decision-making control method based on a six-axis force sensor, characterized in that Including: Step S1: Generate a manipulator motion planning instruction according to a preset task target; Step S2: Drive the manipulator into a task execution state according to the manipulator motion planning instruction; Step S3: During the process of the manipulator executing the task execution state, a six-axis force sensor collects the force signal of the end effector of the manipulator in real time; Step S4: Extract the vertical force from the force signal; Step S5: According to the vertical force, calculate the mass of the object grasped by the manipulator in real time; Step S6: According to the mass of the object grasped by the manipulator and the manipulator motion planning instruction, judge the state of the manipulator in real time. According to the state of the manipulator, complete the manipulator motion planning instruction, return to Step S1, and execute the next manipulator motion planning instruction.

2. The method for embodied intelligent decision-making control based on a six-axis force sensor according to claim 1, wherein According to the vertical force, calculate the mass of the object grasped by the manipulator in real time. The calculation formula is as follows: ； where m is the mass of the object grasped by the robotic arm, is the force in the vertical direction, is the self-weight of the robotic arm, is the offset caused by other interfering forces, is the acceleration due to gravity, is the acceleration in other directions except the direction of the end of the robotic arm during the movement of the robotic arm.

3. A method for embodied intelligent decision-making control based on a six-axis force sensor according to claim 1, characterized in that, The states of the manipulator include: the manipulator pick-up state, the manipulator idle state, and the manipulator drop state.

4. The embodied intelligent decision-making control method based on a six-axis force sensor according to claim 3, wherein, The real-time judgment of the state of the manipulator according to the mass of the object grasped by the manipulator and the manipulator motion planning instruction, and the completion of the manipulator motion planning instruction according to the state of the manipulator include: When the manipulator motion planning instruction is a grasping instruction, if the mass of the object grasped by the manipulator jumps from a zero value with tolerance to a value greater than the material standard weight with tolerance, it is determined that the manipulator has successfully grasped the material, and the manipulator enters the pick-up state; if the mass of the object grasped by the manipulator does not jump from a zero value with tolerance to a value greater than the material standard weight with tolerance, it is determined that the manipulator has not successfully grasped the material, then adjust the position parameters and force parameters of the gripper of the manipulator, return to Step S1, regenerate the manipulator motion planning instruction, and perform grasping again.

5. The embodied intelligent decision-making control method based on a six-axis force sensor according to claim 3, wherein The real-time judgment of the state of the manipulator according to the mass of the object grasped by the manipulator and the manipulator motion planning instruction, and the completion of the manipulator motion planning instruction according to the state of the manipulator include: When the manipulator motion planning instruction is a dropping instruction, if the mass of the object grasped by the manipulator drops from the effective grasping weight to a zero value with tolerance, it is determined that the material has been successfully placed by the manipulator, and the manipulator enters the drop state; if the mass of the object grasped by the manipulator does not drop from the effective grasping weight to a zero value with tolerance, it is determined that the material has not been successfully placed by the manipulator, then adjust the position parameters and force parameters of the gripper of the manipulator, return to Step S1, regenerate the manipulator motion planning instruction, and perform dropping again.

6. The embodied intelligent decision-making control method based on a six-axis force sensor according to claim 3, wherein, The real-time judgment of the state of the manipulator according to the mass of the object grasped by the manipulator and the manipulator motion planning instruction, and the completion of the manipulator motion planning instruction according to the state of the manipulator include: In the case where no manipulator motion planning instruction is generated, if the mass of the object grasped by the manipulator fluctuates within a preset range of a zero value with tolerance within a preset time period, the manipulator is in an idle state, and return to Step S1 to wait for the generation of the next manipulator motion planning instruction.

7. A method for embodied intelligent decision-making control based on a six-axis force sensor according to claim 4, characterized in that The zero value with tolerance is an error range that fluctuates up and down around the zero value by 5%; the material standard weight with tolerance is an error range that fluctuates up and down around the material standard weight by 5%.

8. An embodied intelligent decision-making control system based on a six-axis force sensor, characterized in that, Including: An instruction generation module for generating a manipulator motion planning instruction according to a preset task target; A task execution module for driving the manipulator into a task execution state according to the manipulator motion planning instruction; A signal acquisition module for the six-axis force sensor to collect the force signal of the end effector of the manipulator in real time during the process of the manipulator executing the task execution state; A vertical force extraction module for extracting the vertical force from the force signal; A mass calculation module for calculating the mass of the object grasped by the manipulator in real time according to the vertical force; A state judgment module for judging the state of the manipulator in real time according to the mass of the object grasped by the manipulator and the manipulator motion planning instruction, completing the manipulator motion planning instruction according to the state of the manipulator, and returning to the instruction generation module to execute the next manipulator motion planning instruction.

9. An electronic device, characterized in that, Comprising: One or more processors, and a memory for storing instructions, which when executed by the one or more processors cause the one or more processors to execute a method for embodied intelligent decision-making control based on a six-axis force sensor according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores executable instructions, which when executed cause the processor to execute a method for embodied intelligent decision-making control based on a six-axis force sensor according to any one of claims 1 to 7.

Images