Robot track synchronization control method

Abstract

The invention relates to a robot track synchronization control method. According to the technical scheme, efficient collection and over-distance transmission of neural signals are achieved through the quantum entanglement technology, the brain movement intention is analyzed in combination with a high-sensitivity sensor and an intelligent algorithm, an instruction is transmitted to a robot power driving system through a low-delay communication architecture, and real-time synchronization of man-machine tracks is achieved through a two-way feedback system. Meanwhile, the movement flexibility of the robot is improved by adopting a lightweight design, the problems of high delay, low precision, poor interaction experience and the like in traditional man-machine synchronous control are solved, and the method can be widely applied to the fields of exoskeleton robots, industrial collaborative robots, rehabilitation medical robots and the like. The method has the advantages of being low in delay, high in precision, capable of improving interaction experience and wide in application range.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of robot control, and relates to a robot trajectory synchronous control method. BACKGROUND

[0002] With the development of human-computer interaction technology, the trajectory synchronous control of robots and human bodies has become a research hotspot. Traditional human-computer synchronous methods mostly rely on mechanical sensors (such as electromyographic sensors and posture sensors) or manual operation instructions, and have problems such as high response delay, low intention recognition accuracy, and poor synchronicity.

[0003] In the aspect of neural signal acquisition, existing brain-computer interface technologies mostly use non-invasive devices such as EEG and fNIRS or invasive electrodes, and the signal resolution is limited and easily interfered by noise. The signal analysis relies on traditional calculation methods, and the processing efficiency is low, which is difficult to meet the real-time synchronous demand. In the field of communication and control, traditional methods rely on cloud computing and 4G and below communication technologies, and due to high transmission delay and weak local processing capability, the response of robots is lagged. In addition, existing robot power systems mostly have problems such as heavy structure, insufficient joint flexibility, and single feedback mechanism, which affect the naturalness and accuracy of human-robot collaboration.

[0004] The development of quantum technology provides a new possibility for solving the above problems. The non-locality of quantum entanglement can realize real-time transmission of signals over a distance, and the parallel processing capability of quantum computing can improve the neural signal analysis efficiency. Therefore, the combination of quantum technology and brain-computer interface and robot control is expected to break through the bottleneck of traditional technology and realize higher-precision human-robot trajectory synchronization.

[0005] Therefore, the application provides a robot trajectory synchronous control method to solve the above problems. SUMMARY

[0006] In view of the problems existing in the prior art, the application discloses a robot trajectory synchronous control method, which comprises the following steps:

[0007] Step 1: neural signal acquisition and trajectory intention analysis, the neural signal of the motor cortex of the user's brain is acquired through a wearable neural signal acquisition device, and after quantum encoding, the neural signal is transmitted to the robot end through a quantum entanglement channel, and then the motion trajectory intention of the user is analyzed through a quantum computing module combined with a deep learning algorithm, and converted into an initial trajectory control instruction;

[0008] Step 2: low-delay instruction transmission and optimization, the initial trajectory control instruction is transmitted to the edge computing module of the robot end by using 5G / 6G communication technology, and the initial trajectory control instruction is locally optimized by edge computing;

[0009] Step 3: Robot trajectory execution and drive control, the bionic joint structure of the robot drives the joint movement through a servo motor or a hydraulic drive according to the optimized trajectory instruction, simulates the human motion trajectory, and the joint and support structure of the robot are made of carbon fiber composite material or magnesium-aluminum alloy;

[0010] Step 4: Two-way feedback and trajectory correction, the motion environment information and the execution end state are collected through the sensors at the robot end, presented to the user through the VR glasses, and the deviation between the user's intended trajectory and the actual execution trajectory of the robot is compared based on the quantum entangled neural bridge established by the implanted neural chip, and the trajectory instruction is dynamically corrected.

[0011] As a preferred scheme of the present application, the wearable neural signal acquisition device in step 1 is a Neuro flexible brain ring containing high-density EEG electrodes and fNIRS sensors or an invasive brain-computer interface device containing Utah array electrodes.

[0012] As a preferred scheme of the present application, the deep learning algorithm in step 1 is a convolutional neural network (CNN) for filtering noise in neural signals and identifying motion intention.

[0013] As a preferred scheme of the present application, the edge computing module in step 2 is deployed at the robot end for local rapid processing of the initial trajectory control instruction, reducing dependence on the cloud.

[0014] As a preferred scheme of the present application, the bionic joint structure in step 3 includes hip joints, knee joints, ankle joints, elbow joints, finger joints, back spines and shoulder joints, each joint is provided with a high-precision ball screw or a harmonic reducer.

[0015] As a preferred scheme of the present application, the servo motor in step 3 is a low-inertia permanent magnet synchronous servo motor, and the hydraulic drive is used to provide driving force in heavy load scenarios.

[0016] As a preferred scheme of the present application, the sensors in step 4 include visual sensors, force sensors and functional near-infrared spectroscopy (fNIRS) sensors, which are used to collect motion environment information, execution end stress state and real-time response of user's brain motor cortex, respectively.

[0017] As a preferred scheme of the present application, the dynamic correction of the trajectory instruction in step 4 is realized through a deep learning algorithm to reduce the deviation between the user's intended trajectory and the actual execution trajectory of the robot.

[0018] As a preferred scheme of the present application, the quantum entanglement channel is formed by connecting the user's neural signal quantum encoding with the pre-set entangled particles at the robot end, realizing the super-distance instant transmission of neural signals.

[0019] As a preferred embodiment of the present invention, the 5G / 6G communication technology is used to ensure that the transmission delay of trajectory control commands is controlled within the millisecond level.

[0020] The beneficial effects of this invention are:

[0021] Real-time transmission of neural signals is achieved through quantum entanglement technology. Combined with quantum computing and deep learning algorithms, the intention is quickly interpreted, and the trajectory synchronization delay is compressed to the nanosecond level, which greatly improves the synchronization accuracy.

[0022] It adopts a low-latency communication architecture that combines 5G / 6G with edge computing, and is equipped with a high-torque, low-inertia drive system to ensure the robot's rapid response to trajectory commands;

[0023] Bionic joint design and the application of lightweight materials enable robots to accurately mimic complex human movement trajectories and adapt to diverse scenario requirements;

[0024] The two-way feedback system uses VR real-time imaging and quantum neural bridging to allow users to perceive the robot's status in real time, forming a closed-loop control and improving the naturalness and comfort of human-machine collaboration. Attached Figure Description

[0025] Figure 1 This is a flowchart of the overall system of the present invention; Detailed Implementation

[0026] Example 1

[0027] like Figure 1 As shown, the robot trajectory synchronization control method of the present invention is applied to a lower limb exoskeleton robot to help patients with limb movement disorders achieve synchronized walking trajectories. The technical solution adopted includes the following steps:

[0028] Step 1: Neural Signal Acquisition and Analysis

[0029] Users wear the Neuro flexible brain ring, which has 128 channels of high-density EEG electrodes and fNIRS sensors to collect neural signals from the brain's motor cortex that control lower limb walking.

[0030] After being quantum encoded, the signal establishes a long-distance transmission channel with the entangled particles at the end of the exoskeleton robot and is transmitted to the robot's HiQ quantum simulator.

[0031] The quantum simulator analyzes signal features through parallel processing and filters noise such as electromyography interference using CNN deep learning algorithms. It identifies walking intentions such as "stepping", "lifting the leg", and "landing", and converts them into trajectory angle sequence instructions for the hip, knee and ankle joints (such as hip flexion angle 30° → knee extension angle 15°, etc.).

[0032] Step 2: Command Transmission and Optimization

[0033] The trajectory instruction is transmitted to the edge computing module of the exoskeleton robot through the 6G communication network assistance, and the edge computing unit optimizes the trajectory angle sequence based on the height, weight and other parameters of the patient (such as adjusting the step length to 50 cm, adapting to the patient's physical condition);

[0034] The optimized instruction is controlled within 5ms, ensuring real-time matching with the patient's walking intention.

[0035] Step 3: Trajectory execution

[0036] The hip joint, knee joint and ankle joint of the exoskeleton robot adopt a modular bionic structure, and the joint drive selects a servo motor with a torque of 200N·m, which is matched with a harmonic reducer. According to the trajectory instruction, the joint motion is controlled: the hip joint completes the motion of 30° flexion→20° extension within 0.5s, the knee joint synchronously completes the coordinated action of 15° extension→45° flexion, simulating the normal walking trajectory;

[0037] The joint support adopts carbon fiber composite material, and the overall weight is controlled within 3kg, reducing the burden of the patient.

[0038] Step 4: Two-way feedback and correction

[0039] The pressure sensor of the exoskeleton foot collects landing force data, which is displayed to the patient in real time through the VR glasses, and the fNIRS monitors the feedback signal of the patient's brain to the trajectory execution;

[0040] If the patient intends to take a big step but the robot step is insufficient, the quantum neural bridge system detects the deviation and corrects the trajectory instruction through a deep learning algorithm, adjusts the hip joint flexion angle to 35°, and increases the step length to 60cm, realizing the precise synchronization of the walking trajectory.

[0041] Example 2

[0042] As shown in Figure 1 The robot trajectory synchronization control method provided by the application is applied to a dual-arm collaborative robot, cooperates with a worker to complete precision part assembly, realizes hand operation trajectory synchronization, and adopts the technical scheme comprising the following steps:

[0043] Step 1: Neural signal acquisition and analysis

[0044] The worker wears an invasive Utah array electrode (containing 100 neuron contacts) to accurately obtain the neural signals of arm and finger movement;

[0045] The signal is transmitted to the quantum computing unit of the collaborative robot after quantum encoding, and the assembly intentions such as "grabbing", "rotating" and "placing" are analyzed to convert into three-dimensional trajectory coordinate instructions of the shoulder joint, elbow joint and finger joint;

[0046] Step 2: Instruction transmission and optimization

[0047] The instruction is transmitted to the robot edge node through 5G slicing technology. The edge computing module combines the part size (such as a bolt with a diameter of 5 mm) and the assembly accuracy requirement (±0.01 mm) to optimize the motion trajectory speed of the finger joint (such as 5 mm / s);

[0048] Step 3: Trajectory execution

[0049] The robot arm joint adopts a hydraulic driver (providing a driving force of 500 N), and the finger joint adopts a servo motor (control accuracy ±0.005°). According to the optimized trajectory instruction, the bolt is grabbed, aligned with the screw hole, and rotated and tightened, and the trajectory error is controlled within ±0.008 mm;

[0050] Step 4: Two-way feedback and correction

[0051] The visual sensor at the end of the robot captures the assembly process in real time, which is fed back to the worker through the VR glasses, and the force sensor detects the tightening torque.

[0052] If the worker intends to increase the tightening force, the quantum neural bridge system detects the change in brain signals and immediately corrects the trajectory instruction to increase the hydraulic drive pressure, ensuring the assembly quality.

[0053] The electrical connection method or structure not described in detail in this paper is prior art.

[0054] Although the specific embodiments of the present application have been described in detail above, the present application is not limited to the above embodiments. Within the knowledge possessed by those skilled in the art, various changes can be made without departing from the spirit of the present application, and modifications or deformations without creative labor are still within the protection scope of the present application.

Claims

1. A robot trajectory synchronization control method, characterized in that, Includes the following steps: Step 1: Neural signal acquisition and trajectory intention analysis. The neural signals of the user's motor cortex are acquired through a wearable neural signal acquisition device, and after quantum encoding, they are transmitted to the robot through a quantum entanglement channel. The user's movement trajectory intention is then analyzed by a quantum computing module combined with a deep learning algorithm and converted into initial trajectory control commands. Step 2: Low-latency command transmission and optimization. 5G / 6G communication technology is used to transmit the initial trajectory control command to the edge computing module on the robot. The initial trajectory control command is then localized and optimized through edge computing. Step 3: Robot trajectory execution and drive control. The robot's bionic joint structure drives the joint movement through servo motors or hydraulic actuators according to the optimized trajectory instructions, simulating the human body's movement trajectory. The robot's joints and support structure are made of carbon fiber composite materials or magnesium-aluminum alloy. Step 4: Two-way feedback and trajectory correction. The robot's sensors collect motion environment information and execution status, which are presented to the user through VR glasses. At the same time, based on the quantum entanglement neural bridge established by the implanted neural chip, the deviation between the user's intended trajectory and the robot's actual execution trajectory is compared, and the trajectory command is dynamically corrected.

2. The robot trajectory synchronization control method according to claim 1, characterized in that: The wearable neural signal acquisition device mentioned in step 1 is a Neuro flexible brain ring containing high-density EEG electrodes and fNIRS sensors or an invasive brain-computer interface device containing Utah array electrodes.

3. The robot trajectory synchronization control method according to claim 1, characterized in that: The deep learning algorithm mentioned in step 1 is a convolutional neural network (CNN), which is used to filter noise in neural signals and identify motion intentions.

4. The robot trajectory synchronization control method according to claim 1, characterized in that: The edge computing module described in step 2 is deployed on the robot to perform localized and rapid processing of initial trajectory control commands, reducing reliance on the cloud.

5. The robot trajectory synchronization control method according to claim 1, characterized in that: The bionic joint structure described in step 3 includes hip joints, knee joints, ankle joints, elbow joints, finger joints, spine and shoulder joints, and each joint is equipped with a high-precision ball screw or harmonic reducer.

6. The robot trajectory synchronization control method according to claim 1, characterized in that: The servo motor mentioned in step 3 is a low-inertia permanent magnet synchronous servo motor, and the hydraulic drive is used to provide driving force in heavy-load scenarios.

7. The robot trajectory synchronization control method according to claim 1, characterized in that: The sensors mentioned in step 4 include a visual sensor, a force sensor, and a functional near-infrared spectroscopy (fNIRS) sensor, which are used to collect information on the motion environment, the force state of the actuator, and the real-time response of the user's motor cortex, respectively.

8. The robot trajectory synchronization control method according to claim 1, characterized in that: The dynamic trajectory correction command mentioned in step 4 is implemented through a deep learning algorithm to reduce the deviation between the user's intended trajectory and the robot's actual execution trajectory.

9. The robot trajectory synchronization control method according to claim 1, characterized in that: The quantum entanglement channel is formed by connecting the user's neural signals, which are quantum encoded, with entangled particles preset on the robot, thereby enabling real-time transmission of neural signals over long distances.

10. A robot trajectory synchronization control method according to claim 1, characterized in that: The 5G / 6G communication technology is used to ensure that the transmission delay of trajectory control commands is controlled within milliseconds.

Images