Control method and path control method of on-site sales robot

Abstract

The invention provides a control method of an on-site sales robot, and the method comprises the steps that an acquisition module carries out the signal acquisition in an interest region, the interest region is an interest region related to motor imagery, and transmits an acquired signal to a signal processing module; the signal processing module converts the collected signal into a digital signal through an analog-to-digital converter; preprocessing the converted digital signals by using an AI large model, and extracting high-order features and modes of the signals; carrying out discrete wavelet transform-based feature extraction on the signal; performing mode recognition on the signal according to the extracted features to obtain a motion instruction of the user to the on-site sales robot; wirelessly transmitting a motion instruction of a user to the on-site sales robot to a single chip microcomputer on the on-site sales robot through a wireless interface; and the single chip microcomputer on the sales robot sends control information to the driving circuit board according to the motion instruction, so that the single chip microcomputer on the sales robot controls the sales robot to move.

Description

Technical Field

[0001] The present invention relates to the field of automation technology, and in particular to a control method and a path control method of an on-site sales robot. Background Art

[0002] With the continuous development of science and technology, robots are increasingly used in the commercial field. In the real estate sales industry, the current position is sensed by the sensor device installed inside the sales robot. The obstacle avoidance parameters are obtained based on the various obstacle data obtained by image recognition technology and the target point position data to avoid the obstacles, and then the optimal path from the current position to the target position is planned. Unmanned driving technology and the control of the movement of sliding objects with thoughts have infinite prospects. The integration of the two will surely become a new outlet and usher in an explosive period in the future. The control of the movement of sliding objects with thoughts is widely used in medical care, health, game entertainment and smart home. It can be concluded that in the near future, it will enter our lives.

[0003] In the prior art, when a remote-controlled on-site sales robot is in motion, the user needs to hold a remote control to control the operation of the on-site sales robot. There are too many accessories that are inconvenient to carry. If the user can control the operation of the on-site sales robot through his own thoughts, the user can control the on-site sales robot at will. The user does not need to hold a remote control during the driving process of the on-site sales robot, which improves the convenience of operation of the on-site sales robot and can also avoid the problem of being unable to control the operation of the on-site sales robot due to the loss of the remote control. Although the existing on-site sales robots have solved the planning of the driving path to a certain extent, there are some problems in path control, such as unreasonable path planning, poor obstacle avoidance ability, lack of path planning to avoid obstacles from the current position to the target position, lack of obstacle avoidance parameters obtained through multiple obstacle data values ​​to control the speed of the on-site sales robot when it encounters obstacles, which affects the robot's work efficiency and customer experience. Summary of the invention

[0004] The present invention provides a control method and a path control method for an on-site sales robot, which enable the user to freely control the on-site sales robot with his / her thoughts.

[0005] On the one hand, the present application provides a control method for an on-site sales robot, the method comprising: signal acquisition: an acquisition module performs signal acquisition in an area of ​​interest, the area of ​​interest being an area of ​​interest related to motor imagination, and sends the acquired signal to a signal processing module; signal conversion: the signal processing module converts the acquired signal into a digital signal through an analog-to-digital converter; AI large model preprocessing: the signal processing module uses the AI ​​large model to preprocess the converted digital signal to extract high-order features and patterns of the signal; feature extraction: the signal processing module performs feature extraction based on discrete wavelet transform on the signal; pattern recognition: pattern recognition is performed on the signal according to the extracted features to obtain motion instructions that the user wants to control the on-site sales robot; wireless transmission: the signal processing module wirelessly transmits the motion instructions that the user wants to control the on-site sales robot to the single-chip microcomputer on the on-site sales robot through a wireless interface; motion control: the single-chip microcomputer on the on-site sales robot sends control information to the driving circuit board according to the motion instructions, so that the single-chip microcomputer on the on-site sales robot controls the movement of the on-site sales robot.

[0006] Optionally, the method further comprises: the signal processing module processes the digital signal; each input sample of the digital signal x[n] enters the digital filter in sequence, and the output y[n] of the digital filter at any time is a simple weighted sum of current and past sample inputs:

[0007]

[0008] x[nL] is the Lth past input sample, y[nL] is the Lth past output sample, b L 、a L are the scale weights of each input sample and output sample, M and N are the number of input sample weights and output sample weights used by the filter, respectively; by adjusting the length of the filter and the weights assigned to consecutive samples, the signal frequency in a specific frequency range will be amplified, attenuated, retained or disappear.

[0009] Optionally, the method further includes: discrete wavelet transform is to discretize c as a scale factor and d as a translation factor, and the discrete wavelet transform of the signal f(t) is:

[0010]

[0011] ψ j,k (t) is the discretized wavelet function, which is the kth low-frequency component of the jth layer;

[0012] The discrete wavelet transform is a uniformly discretized time series. The discrete wavelet transform DWTx(m,n) of the signal x(t) is defined as:

[0013]

[0014] Where m is the scale factor, n is the expansion factor, ψ m,n (t) is the discretized wavelet function.

[0015] Optionally, the signal processing module extracts features of the signal based on discrete wavelet transform, including: wavelet transform can realize frequency domain conversion of the signal, wavelet transform uses a basic wavelet as a scale transformation and time shift and then convolves with the signal to be analyzed, and the continuous wavelet transform CWTx(c, d) of the signal x(t) is defined as:

[0016]

[0017] Among them, CWTx(c,d) is the time-frequency feature map, x(t) is the electrical signal, c is the scale factor, d is the translation factor, is the wavelet basis function under the translation factor d and the scale factor c, φ(t) is the basic wavelet (or mother wavelet), which can be a real signal or a complex signal; the non-zero real number c is the scale factor, which is the parameter for scaling the basic wavelet φ(t) on the time axis; the larger the c, the smaller the scale, the more the corresponding wavelet φ(t / c) is stretched in the time domain and the more compressed in the frequency domain, the time translation parameter d, different d values ​​indicate that the wavelet moves to different positions along the time axis.

[0018] Optionally, the method further comprises: processing the motor imagery electrical signal in the discrete domain by using continuous wavelet transform, discretizing the transform, and processing as follows: cj=2 j ,d j,k =k*2 j , where c is the scale factor and d is the translation factor. The continuous wavelet transform maps the signal from one-dimensional space to two-dimensional space, discretizes the scale factor c and the time-shift parameter d, and uses the wavelet transform values ​​at certain discrete points on the time-scale plane to characterize the signal, realizing the feature extraction of the frequency band of interest, and discretizes the scale by an integer power of a constant 2, that is, c=2^j,j∈Z.

[0019] Optionally, the method further comprises:

[0020] When the user imagines the left hand moving, the energy in the right hemisphere decays, which is manifested as the ERD phenomenon of correlated desynchronization, and the energy in the left hemisphere increases, which is manifested as the ERS phenomenon of correlated synchronization. The quantification method of ERD / ERS is: E represents the energy value of the EEG signal of a certain frequency band at a certain electrode after motor imagery; R represents the energy value of the EEG signal of a certain frequency band at a certain electrode before motor imagery; when ERD / ERS is a positive value, the energy increases after motor imagery and the ERS phenomenon occurs; when ERD / ERS is a negative value, the energy attenuates after motor imagery and the ERD phenomenon occurs.

[0021] Optionally, the method further includes: detecting the ERD / ERS value of the electrode and performing pattern recognition on the signal to obtain the motion instruction that the user wants to give to the on-site sales robot; when the ERD / ERS value of the left hemisphere electrode is detected to be a positive value, the energy of the left hemisphere increases and the energy of the right hemisphere decreases, and it is concluded that the user is imagining a left-hand movement, thereby recognizing that the motion instruction that the user wants to give to the on-site sales robot is to move to the left; when the ERD / ERS value of the right hemisphere electrode is detected to be a positive value, the energy of the right hemisphere increases and the energy of the left hemisphere decreases, and it is concluded that the user is imagining a right-hand movement, thereby recognizing that the motion instruction that the user wants to give to the on-site sales robot is to move to the right.

[0022] Optionally, the single-chip microcomputer on the on-site sales robot sends control information to the driving circuit board according to the motion instruction, so that the single-chip microcomputer on the on-site sales robot controls the movement of the on-site sales robot, including: when the frequency of the pulse width modulation (PWM) signal sent by the single-chip microcomputer to the driving circuit board is 14-30Hz, the motors driving the left and right wheels of the on-site sales robot rotate in the same direction and at the same speed, and the on-site sales robot moves forward; when the frequency of the pulse width modulation signal sent by the single-chip microcomputer to the driving circuit board is 30-40Hz, the left wheel motor of the on-site sales robot is The left wheel motor of the on-site sales robot rotates in the opposite direction, and the right wheel motor rotates in the opposite direction, the two wheels form a differential, and the on-site sales robot moves to the right; when the single-chip microcomputer sends the control information to the drive circuit board with a pulse width modulation signal frequency of 8-13Hz, the left wheel motor of the on-site sales robot rotates in the opposite direction, and the right wheel motor rotates forward, the two wheels also form a differential, and the on-site sales robot moves to the left; when the single-chip microcomputer sends the control information to the drive circuit board with a pulse width modulation signal frequency of 1-3Hz, the left and right wheel motors of the on-site sales robot stop rotating at the same time, and due to the action of the reduction gearbox, the on-site sales robot stops moving quickly.

[0023] Optionally, after the single-chip microcomputer on the on-site sales robot sends control information to the driving circuit board according to the motion instruction, so that the single-chip microcomputer on the on-site sales robot controls the movement of the on-site sales robot, the method further includes: a feedback module for testing the physiological signal of the user, if the feedback is a joyful emotion, the mode in which the single-chip microcomputer controls the movement of the on-site sales robot is correct; if the feedback is a frustrated emotion, the mode in which the single-chip microcomputer controls the movement of the on-site sales robot is wrong; the feedback module sends an error report to the single-chip microcomputer, and the single-chip microcomputer sends a braking movement instruction to the driving circuit board, so that the single-chip microcomputer controls the braking movement of the on-site sales robot; when the single-chip microcomputer controls the movement of the on-site sales robot correctly, the user expresses a joyful emotion feedback recognition result; when the single-chip microcomputer controls the movement of the on-site sales robot incorrectly, the user expresses a frustrated emotion feedback recognition result; by calculating the multi-dimensional information between the EEG leads to obtain the asymmetric feature ASI, it can effectively determine whether an emotion occurs:

[0024]

[0025] in, Refers to the information of the left brain signal X flowing to the right brain signal Y. Similarly Indicates the information flow from Y to X; S f is the total amount of two-way information; S n Refers to the flow of information when no emotions occur.

[0026] A second aspect of the present invention provides a path control method for an on-site sales robot, comprising the following steps:

[0027] S1: A global map is stored in the sales robot in advance, the map is divided into multiple areas, the center point of each area is recorded as A, B, C, D, E and F target points, and the system receives request information containing node ID sent from the outside;

[0028] S2: sense the current position through the sensor device installed inside the sales robot, mark the current position coordinates of the sales robot as the starting coordinates, parse the node ID in the request information, determine the marked coordinate position information corresponding to the node ID according to the preset coordinate system, and record the path from the starting coordinates to the target coordinates as the optimal path;

[0029] S3: The image acquisition device installed on the sales robot captures images of the surrounding environment in real time, detects the location information of obstacles from the image through the Yolo target detection algorithm, converts the obstacle information in the image into coordinates in a two-dimensional coordinate system, and marks the coordinate position, length and width of the obstacle on the map. Obstacle avoidance parameters are obtained based on the obstacle coordinates and the initial coordinate distance, the minimum safety distance and the obstacle length and width;

[0030] S4: The deceleration value of the sales robot is obtained according to the difference between the current speed of the sales robot and the target speed of the sales robot, and the deceleration value of the sales robot caused by the turning is obtained by multiplying the adjustment coefficient by the difference between the current speed and the linear speed, and the final deceleration value is added to decelerate and avoid obstacles;

[0031] S5: By comparing the distance value between the current position of the sales robot and the target node with the preset distance value, it is determined whether the target node has been reached according to the comparison result.

[0032] As a further solution of the present invention: Step S1 comprises the following steps:

[0033] A global map is created through synchronous positioning and map building technology, and the map is divided into multiple areas. The central position inside each area is marked as multiple target points, including target points A, B, C, D, E and F, which are stored inside the sales robot for record. The system receives request information containing node IDs sent from the outside; among them, the node IDs include point A of the reception desk, point B of the model display area, point C of the model room entrance, point D of the negotiation area, point E of the signing area, and point F of the rest area.

[0034] As a further solution of the present invention: the step S2 comprises the following steps:

[0035] The current position is sensed by the sensor device installed inside the sales robot, and the coordinates of the current position of the sales robot are marked as the starting coordinates. The robot parses the received request information and extracts the node ID therein, and constructs a preset two-dimensional plane coordinate system through the map structure. According to the parsed node ID, the corresponding marked coordinate position information is searched in the preset coordinate system, and the node ID is matched with the coordinate position one by one. According to the starting point coordinates and the target point coordinates, the path planning algorithm is used to obtain the optimal path from the starting coordinates to the target coordinates; wherein the node IDs are A, B, C, D, E, F and O points, and the corresponding coordinates are the target point A (X A , Y A ), point B (X B , Y B ), point C (X C , Y C ), point D (X D , Y D ), point E (X E , Y E ) and point F (X F , Y F ) and the starting point O (X O , Y O ).

[0036] As a further solution of the present invention: according to the coordinates of the starting point and the coordinates of the target point, a path planning algorithm is used to calculate the optimal path from the coordinates of the starting point to the coordinates of the target point, including the following steps:

[0037] The path planning algorithm is used to search for the path from the current position to the target point. During the search process, the path planning algorithm will evaluate the map data and the distance values ​​between different nodes to find the optimal path. When obstacles are detected during the detection process, the map is updated and the optimal path is replanned.

[0038] As a further solution of the present invention: Step S3 comprises the following steps:

[0039] The image acquisition device installed on the sales robot captures images of the surrounding environment in real time, pre-processes the collected images, extracts the size and shape features of obstacles from the pre-processed images, and uses deep learning algorithms to classify and identify the extracted features. After identifying the obstacles, the Yolo target detection algorithm is used to detect the location information of the obstacles from the image. The spatial geometric transformation converts the obstacle information in the image into coordinates in a two-dimensional coordinate system. The grid method is used to update the environment map inside the robot, and the coordinate position, length and width of the obstacles are marked in the map. Obstacle avoidance parameters are obtained through the obstacle coordinates and the initial coordinate distance, the minimum safety distance and the obstacle length and width. The speed of the robot is adjusted to assist the sales robot in positioning and avoiding obstacles during movement.

[0040] Obstacle avoidance parameter calculation formula is obtained based on obstacle coordinates and initial coordinate distance, minimum safety distance, obstacle length and width:

[0041]

[0042] Where Distance2 is the distance between the obstacle coordinates and the initial coordinates, Distance1 is the minimum safe distance, (X O , Y O ) is the coordinate of the starting point O, (X Z , Y Z ) is the obstacle coordinate, denoted as point G; avoidance parameter is the calculated value of obstacle avoidance parameter, L Z is the length of the obstacle, W Z is the width of the obstacle;

[0043] If the calculated value of the obstacle avoidance parameter is a positive number, the sales robot can pass safely without slowing down; if the calculated value of the obstacle avoidance parameter is a negative number, the sales robot needs to slow down and turn the angle to avoid the obstacle.

[0044] As a further solution of the present invention: the step S4 comprises the following steps:

[0045] The calculation formula for safe braking distance at the current speed is:

[0046]

[0047] Wherein, Distance3 is the calculated value of the safe braking distance, V is the current speed of the sales robot, a is the maximum deceleration of the sales robot, T is the robot reaction time, g is the acceleration of gravity, and μ is the friction coefficient between the sales robot and the ground;

[0048] The target speed value calculation formula is obtained based on the sales robot's maximum deceleration value and minimum safety distance deceleration value:

[0049]

[0050] Among them, V target is the target speed, a is the maximum deceleration of the sales robot, T is the robot reaction time, and Distance1 is the minimum safety distance value;

[0051] The sales robot deceleration value calculation formula is obtained based on the difference between the sales robot's current speed and the sales robot's target speed:

[0052] V s =VV target

[0053] Among them, V target is the target speed, V is the current speed of the sales robot, V s Slowdown value for sales robot;

[0054] Multiply the adjustment coefficient by the difference between the current speed and the linear speed to get the turning deceleration value of the sales robot caused by turning. The turning deceleration value calculation formula is:

[0055]

[0056] Where R is the wheel radius of the sales robot, V is the current speed of the sales robot, t is the time change, α is the deceleration value adjustment coefficient, π is the circumference, V z Calculate the value for the steering deceleration value;

[0057] Final deceleration value calculation formula:

[0058] V final =V s +V z

[0059] Among them, V s is the deceleration value, V zis the calculated value of the steering deceleration value, V final is the final deceleration value.

[0060] As a further solution of the present invention: the step S5 comprises the following steps:

[0061] By comparing the distance value between the current position of the sales robot and the target node with the preset distance value, it is determined whether the target node has been reached based on the comparison result; if the distance value between the sales robot and the target node is greater than 0.3 meters, the sales robot has not reached the target node and needs to continue moving towards the target point; if the distance value between the sales robot and the target node is less than or equal to 0.3 meters, the sales robot has reached the target node and performs the corresponding task according to the information of different node IDs; after completing the task, the sales robot begins to receive new task instructions to replan the path and execute the task.

[0062] The present invention uses a path planning algorithm to perform corresponding evaluations based on map data and distance values ​​between different nodes to find the optimal path to the target point. When an obstacle is detected during the detection process, the map is updated and the optimal path to avoid the obstacle is planned, thereby achieving normal operation of the robot and avoiding the occurrence of potential risks. The present invention uses an image acquisition device to capture images of the surrounding environment in real time, extracts the size and shape features of the obstacle after preprocessing, and classifies and identifies the extracted features through a deep learning algorithm, thereby achieving accurate identification of the type of obstacle. The present invention uses the Yolo target detection algorithm to detect the position information of the obstacle from the image, uses spatial geometric transformation to convert the obstacle information in the image into coordinates in a two-dimensional coordinate system, obtains obstacle avoidance parameters through the obstacle coordinates and the initial coordinate distance, the minimum safe distance, and the length and width of the obstacle, and adjusts the speed of the robot, thereby achieving the sales robot's positioning and timely avoidance of obstacles during movement. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings of the embodiments are briefly introduced below. Obviously, the drawings in the following description only relate to some embodiments of the present invention, but are not intended to limit the present invention.

[0064] Figure 1 A flow chart of a control method for an on-site sales robot provided in an embodiment of the present application;

[0065] Figure 2 A flow chart of a control method of an on-site sales robot provided in yet another embodiment of the present application;

[0066] Figure 3 A system framework diagram for controlling an on-site sales robot provided in an embodiment of the present application;

[0067] Figure 4 A flowchart of interactions between a system framework for controlling an on-site sales robot provided in an embodiment of the present application;

[0068] Figure 5 A schematic diagram of physical interaction for controlling an on-site sales robot provided in an embodiment of the present application;

[0069] Figure 6 A flow chart of a path control method for an on-site sales robot provided in an embodiment of the present application. DETAILED DESCRIPTION

[0070] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0071] This application proposes a control method and system for a field sales robot. The control system includes a signal processing device and a single-chip microcomputer installed on the field sales robot. This document aims to exchange information between the signal processing device and the single-chip microcomputer on the field sales robot, and then the single-chip microcomputer controls the motion mode and motion trajectory of the field sales robot. The control system includes an acquisition module to acquire signals; the signal processing module uses an AI large model to pre-process the converted digital signal to extract the high-order features and patterns of the signal; the signal processing module extracts features of the signal based on discrete wavelet transform; the signal is pattern-recognized according to the extracted features to obtain the motion instructions that the user wants to the field sales robot; the motion instructions that the user wants to the field sales robot are wirelessly transmitted to the single-chip microcomputer on the field sales robot through a wireless interface; the single-chip microcomputer on the field sales robot sends control information to the driver circuit board according to the motion instructions, thereby controlling the movement of the field sales robot.

[0072] Motor imagery refers to the process of imagining the movement of a part of the body without actually producing obvious movements. The basis for the generation of motor imagery electrical signals is the event-related synchronization / desynchronization phenomenon. The process of motor imagery can activate certain areas of the brain, causing the energy of some specific electrical signals to increase or decrease. For example, when people imagine their left arm moving, but the left arm does not actually move, the brain will generate an electrical signal to execute the left arm movement.

[0073] The field sales robot in this application can be a mobile terminal device such as an intelligent robot, a mobile payment device, an intelligent navigation dog, etc. Optionally, in the application scenario of this application, when the field sales robot is a field sales robot, when the marketer is selling real estate, the salesperson can control the movement mode and movement direction of the field sales robot through thoughts, and control the field sales robot to actively walk towards the customer to explain the real estate information to the customer.

[0074] Embodiment 1

[0075] like Figure 1 The flowchart of a control method of a field sales robot provided by an embodiment of the present application is shown. The embodiment of the present application proposes a method for controlling a field sales robot based on motor imagery, and the method comprises the following steps:

[0076] Step 101, signal acquisition: the acquisition module performs signal acquisition in the region of interest, which is the region of interest related to motor imagery, and sends the acquired signal to the signal processing module.

[0077] The signals of the user's different motor imagination actions are collected and detected, and the signals are divided into several bands according to the frequency, including α wave, β wave, γ wave, and θ wave.

[0078] α wave: The frequency range is 8-13Hz, and the amplitude is 20-100μV. This wave band is closely related to human movement imagination and actual movement. β wave: The frequency range is 14-30Hz, and the amplitude is 5-20μV. It often appears when humans are thinking about problems or are suddenly stimulated by the outside world. The appearance of β wave is often accompanied by strong emotional states such as fear, excitement, and excitement. θ wave: The frequency range is 4-7Hz, and the amplitude is 20-150μV. It often appears when adults feel slightly sleepy or extremely relaxed. δ wave: The frequency range is 0.5-3Hz, and the amplitude is 20-200μV. It often appears when humans are in a deep sleep state or dizzy and comatose.

[0079] The sampling frequency of the acquisition module can be 128Hz, and the acquisition module includes a signal generator, a photomultiplier tube, an amplifier, and an analog-to-digital converter. The signal generator includes a detection electrode and a reference electrode, and each detection electrode is connected to the input of a differential amplifier. The signal reflects the superposition of postsynaptic potentials generated by the collected neurons. Functional magnetic resonance imaging obtains electrical signals through changes in blood flow during neuronal activity. Functional infrared imaging is similar, but it measures changes in blood oxygen levels. Magnetoencephalography uses instruments such as superconducting quantum interference devices to measure changes in magnetic fields caused by electrical signals.

[0080] Optionally, the collected signal is composed of N mixed signals, which are represented as a two-dimensional matrix x(t), where the rows of the matrix represent the signals of each channel and the columns represent the sampling points, x(t) = [x1(t), x2(t), x3(t), ..., x N (t)] T , the unknown source signal a(t)=[a1(t),a2(t),a3(t),...,a N (t)] T , the mixing mechanism of the unknown signal is represented by matrix B, and the collected original signal is represented by the unknown signal source a(t), then x(t)=Ba(t), the unknown signal is mixed by matrix B to obtain the collected signal x(t), and each column in matrix B represents the spatial distribution of an independent component on the electrode.

[0081] The system for controlling an on-site sales robot proposed in the present application also includes a signal recording module, which records the spike potential emitted by a single neuron collected by electrodes in the collection module. The spike potential generated by the neuron that is closer to the electrode has a greater amplitude deviation in the recorded signal.

[0082] The signal processing module processes the digital signal; each input sample of the digital signal x[n] enters the filter in turn, and the output y[n] of the digital filter at any time is a simple weighted sum of the current and past sample inputs:

[0083]

[0084] x[nL] is the Lth past input sample, y[nL] is the Lth past output sample, b L 、a L are the scale weights of each input sample and output sample, M and N are the number of input sample weights and output sample weights used by the filter, respectively; by adjusting the length of the filter and the weights assigned to consecutive samples, the signal frequency in a specific frequency range will be amplified, attenuated, retained or disappear.

[0085] The amplified signal passes through an anti-aliasing filter and is then digitized by an A / D (analog / digital) converter. By properly adjusting the length of the filter and the weights assigned to successive samples, the signal frequencies in a certain frequency range can be amplified, attenuated, retained, or eliminated.

[0086] Filters are divided into high-pass filters, low-pass filters, band-pass filters and notch filters. High-pass filters are used to remove low-frequency noise. Signals above a certain frequency can pass through, and signals below this frequency will be attenuated and filtered out. Therefore, high-pass filters will retain high-frequency EEG activities, such as beta waves and gamma waves. High-pass filters can improve the clarity of EEG signals. Low-pass filters are used to remove high-frequency noise. Signals below a certain frequency pass through, and the opposite is true for frequencies above. Band-pass filters refer to signals within a certain frequency range that can pass through, while frequencies below or above this range are removed. Signals outside this frequency range will be attenuated and filtered out, which is equivalent to performing high-pass filtering and low-pass filtering at the same time. Notch filtering refers to signals within a certain frequency range that will be attenuated and filtered out, while signals outside this frequency range will be retained. For example, it is used to remove interference caused by power line frequencies (such as 50Hz or 60Hz) and other frequency noise, which helps reduce the impact of power supply interference on EEG signals.

[0087] Step 102, signal conversion: the signal processing module converts the collected signal into a digital signal through an analog-to-digital converter.

[0088] Discrete wavelets consist of two functions: a scaling function and a wavelet function. The unit step function is used as the scaling function, and the wavelet function consists of an offset from the unit step function. Discrete wavelets are scaled only using a specific time scale; the scaling is usually a power of 2. Haar wavelet is a type of discrete wavelet, and the formula is as follows:

[0089]

[0090] As a type of digital filter, discrete wavelet transform can extract the characteristics of different frequency bands of electrical signals. Wavelets are used to divide the original electrical signals into five frequency bands: d1-d5, and the corresponding frequency bands are: 64-128Hz (d1), 32-64Hz (d2), 16-32Hz (d3), 8-16Hz (d4), and 4-8Hz (d5). The researchers calculated the signal energy and fluctuation index of the d3-d5 frequency band, and used support vector machines to build a discriminant model, ultimately achieving a sensitivity of 94.46% and a specificity of 95.26%.

[0091] Optionally, feature extraction includes: reducing signal noise and enhancing relevant characteristics through signal conditioning, extracting features from the conditioned signal, and using feature conditioning to appropriately prepare feature vectors for a feature conversion stage.

[0092] Optionally, data enhancement: After step 102, the method for controlling a field sales robot based on motor imagery further includes: adding Gaussian noise to the digital signal to enhance the data, and the distribution function is:

[0093] Gaussian distribution is also called normal distribution N(μ,δ 2 ), where μ and δ 2 are the expected value and variance of the Gaussian distribution.

[0094] Step 103, AI large model preprocessing: The signal processing module uses the AI ​​large model to preprocess the converted digital signal to extract the high-order features and patterns of the signal.

[0095] The AI ​​big model uses deep learning algorithms (such as convolutional neural networks or recurrent neural networks) to perform multi-level feature extraction and analysis on signals, thereby identifying characteristic signals related to motor imagery.

[0096] Specifically, extracting the high-order features of the signal includes the following steps: assuming that the probability density function of the random variable x(t) is f(x), and its first characteristic function is

[0097]

[0098] The first characteristic function Φ(ω) is the Fourier transform of the probability density function f(x). The second characteristic function Ψ(ω) is ψ(ω) = In[Φ(ω)];

[0099] The definition of high-order cumulant is that the k-order cumulant of the random variable x is the k-order derivative of its second characteristic function in situ, that is, C k =ψ (k) (ω) ω＝0 ;

[0100] The bispectrum is defined as the two-dimensional Fourier transform of the third-order cumulant,

[0101] is the frequency, For time delay Changshu, When , the signal is sliced ​​diagonally in the bispectrum, and the slice is used to obtain the frequency of the signal after removing the Gaussian white noise, that is, the frequency corresponding to the maximum value of the bispectrum.

[0102] Optionally, the formula for extracting high-order features of the signal is as follows:

[0103] ,in is the weight of the i-th neuron in layer L1 and the j-th neuron in layer L2, is the corresponding bias, k is the number of neurons, To extract the eigenvalues ​​of the high-order feature output layer L1 of the signal, is a one-dimensional feature.

[0104] Step 104, feature extraction: the signal processing module extracts features of the signal based on discrete wavelet transform.

[0105] Discrete wavelet transform is to discretize c as the scale factor and d as the translation factor. The discrete wavelet transform of the signal f(t) is:

[0106]

[0107] ψ j,k (t) is the discretized wavelet function, which is the kth low-frequency component of the jth layer;

[0108] The discrete wavelet transform is a uniformly discretized time series. The discrete wavelet transform DWTx(m,n) of the signal x(t) is defined as:

[0109]

[0110] Where m is the scale factor, n is the expansion factor, ψ m,n (t) is the discretized wavelet function.

[0111] The signal processing module extracts features of the signal based on discrete wavelet transform, including: wavelet transform can realize frequency domain conversion of the signal, and wavelet transform uses a basic wavelet as a scale transformation and time shift to convolve with the signal to be analyzed. The continuous wavelet transform CWTx(c, d) of the signal x(t) is defined as:

[0112]

[0113] Where φ(t) is the basic wavelet (or mother wavelet), which can be a real signal or a complex signal; common mother wavelets include Haar wavelet and Morlet wavelet, and the non-zero real number c is the scale factor, which is the parameter for scaling the basic wavelet φ(t) on the time axis; the larger the c, the smaller the scale, and the corresponding wavelet φ(t / c) is more stretched in the time domain and more compressed in the frequency domain. The real number d is the time shift parameter, and different d values ​​indicate that the wavelet moves to different positions along the time axis.

[0114] Optionally, the corresponding co-spatial mode eigenvector f(x) is obtained by the covariance logarithm, and the formula is as follows:

[0115]

[0116] Among them, Z j is the j-th row signal of the signal Z after the spatial filter, m is the characteristic parameter of the common spatial mode spatial filter, var(.) is the variance operator, and In(.) is the logarithm operator.

[0117] Optionally, continuous wavelet transform extracts the input signal according to different frequency bands, thereby achieving multi-scale decomposition to obtain corresponding frequency band signals, and finally achieving time-frequency domain decomposition of the original signal. Compared with Fourier transform, wavelet transform can pay more attention to the local characteristics of the signal and can better analyze the signal in the time-frequency domain.

[0118] Optionally, the method further comprises: processing the motor imagery electric signal in the discrete domain by using continuous wavelet transform, discretizing the transform, and processing as follows: cj=2 j ,d j,k =k*2 j , where c is the scale factor and d is the translation factor. The continuous wavelet transform maps the signal from one-dimensional space to two-dimensional space, discretizes the scale factor c and the time-shift parameter d, and uses the wavelet transform values ​​at certain discrete points on the time-scale plane to characterize the signal to achieve feature extraction of the frequency band of interest. The scale is discretized by an integer power of a constant 2, that is, c=2^j,j∈Z.

[0119] Continuous wavelet transform maps the signal from one-dimensional space to two-dimensional space, so much of the information contained is redundant. This allows the scale factor c and the time shift parameter d to be discretized, realizing feature extraction of the frequency band of interest.

[0120] Optionally, this step also includes extracting features of the signal in the time domain, frequency domain, time-frequency domain, and spatial domain.

[0121] The time domain function is transformed into the frequency domain function through Fourier transform.

[0122]

[0123] Time domain feature extraction is a relatively primitive technique that analyzes signals based on time, allowing us to quantify how the signal changes over time, which is particularly important in EEG signals because they are usually recorded over a period of multiple hours. Usually, windowing and segmentation of the signal is required for time domain feature extraction. Each window will extract a local feature, and researchers will be able to see how these features change over each window.

[0124] Frequency domain analysis techniques focus on extracting features from the sinusoidal signals that constitute the data, usually by converting from the time domain to the frequency domain before further analysis.

[0125] Optionally, the signal characteristics are optimized. Calculate each characteristic F of each frequency band i SU value between SU ​​and category C ic , and according to SU ic Then, according to each feature and category label SU icThe value range of λ% is used to select different thresholds, and the remaining feature dimensions and related recognition accuracy after feature screening are observed. The threshold selection formula is as follows:

[0126]

[0127] Among them, λ=10~90, δ is the threshold.

[0128] Step 105, pattern recognition: perform pattern recognition on the signal according to the extracted features to obtain the motion instructions that the user wants to control the on-site sales robot.

[0129] The motion modes of the on-site sales robot include: acceleration, braking, left turn, and right turn. The motion instructions of the on-site sales robot include: acceleration, braking, left turn, and right turn.

[0130] The SVM support vector machine with radial basis kernel function is used as the motor imagery EEG signal recognition classifier. The classification decision function is as follows:

[0131]

[0132] Among them, sgn(·) represents the sign function, a i * Indicates a i The optimal solution of b * represents the classification threshold, K(x,x i ) represents the kernel function, f(x) represents the classification function, x i represents the i-th sample, y i Represents the result label of the i-th sample, where the category of the classified sample x is determined by the positive or negative judgment of the classification function. The optimal channel of each sub-band is selected according to the characteristics of each individual and the characteristics of the frequency band signal, effectively avoiding the interference of non-explicit channel noise. Through the feature characterization method, the motor imagery EEG signal is extracted and optimized, thereby achieving effective characterization of the motor imagery EEG signal, and finally the support vector machine SVM classifier is used to realize the pattern recognition of the motor imagery EEG signal.

[0133] By imagining the movement of the left and right arms, the on-site sales robot can be controlled to turn left and right and walk. By imagining the movement of the tongue, the on-site sales robot can be controlled to brake. By imagining the movement of the left and right feet, the on-site sales robot can be controlled to move forward and backward. After determining that the on-site sales robot needs to turn right and walk, the user needs to imagine raising the right arm. The recognition module in the on-site sales robot recognizes the user's electrical signal and obtains a control instruction, and sends the control instruction to the control module to control the steering of the on-site sales robot's universal wheels.

[0134] When humans are stimulated by visual, auditory or tactile stimuli, specific functional areas of the cerebral cortex will be activated to analyze the stimuli and transmit relevant information, thereby accelerating the metabolic rate and blood flow rate. These physiological activities consume a lot of energy, resulting in a decrease in the amplitude of the corresponding EEG signal, that is, a decrease in the energy of a certain rhythm. This phenomenon is called event-related desynchronization ERD. On the contrary, when the brain is in a relaxed and peaceful state, the amplitude of the EEG signal of the relevant rhythm will increase significantly, and the energy will increase accordingly. This phenomenon is called event-related synchronization ERS. The electrode channels C3 and C4 for collecting EEG signals are located in the parietal lobe area of ​​the brain responsible for limb movement senses. Therefore, when the subject performs motor imagination of left and right hand movements, event-related desynchronization / synchronization will occur in the C3 and C4 areas of the cerebral cortex. Since the left and right hemispheres of the brain control opposite body movements respectively, when imagining left hand movements, for example, the energy of the EEG rhythm related to the right hemisphere cortex of the brain decays, which is manifested as the ERD phenomenon, while the energy of the EEG rhythm related to the left hemisphere cortex increases, which is manifested as the ERS phenomenon. The corresponding relationship between the ERD / ERS phenomenon and the imagined left and right hand movements on the C3 and C4 channels can be obtained as shown in the following table:

[0135] Imagination Task aisle ERD / ERS phenomenon Left Hand C3 ERS C4 ERD Right hand C3 ERS C4 ERD

[0136] When the user imagines moving his left hand, the energy in the right hemisphere decays, which is manifested as the correlated desynchronization (ERD) phenomenon; the energy in the left hemisphere increases, which is manifested as the correlated synchronization (ERS) phenomenon. The quantification method of ERD / ERS is as follows:

[0137] E represents the energy value of the EEG signal of a certain frequency band of a certain electrode after motor imagery; R represents the energy value of the EEG signal of a certain frequency band of a certain electrode before motor imagery. From the above formula, it can be concluded that when ERD / ERS is a positive value, it means that the energy increases after motor imagery, so the ERS phenomenon occurs; when ERD / ERS is a negative value, it means that the energy decays after motor imagery, so the ERD phenomenon occurs.

[0138] Optionally, by detecting the ERD / ERS value of the electrode, pattern recognition is performed on the signal to obtain the motion instruction that the user wants to control the field sales robot.

[0139] For example, when the ERD / ERS value of the left hemisphere C3 electrode is positive, the energy of the left hemisphere increases and the energy of the right hemisphere decreases, and the user imagines moving his left hand, thereby recognizing that the user wants to give the on-site sales robot an instruction to move to the left; when the ERD / ERS value of the right hemisphere electrode is positive, the energy of the right hemisphere increases and the energy of the left hemisphere decreases, and the user imagines moving his right hand, thereby recognizing that the user wants to give the on-site sales robot an instruction to move to the right.

[0140] Step 106, wireless transmission: the signal processing module wirelessly transmits the motion instructions that the user wants to use to control the on-site sales robot to the single-chip microcomputer on the on-site sales robot through the wireless interface.

[0141] The movement instructions that the user wants to give to the on-site sales robot: acceleration, braking, left turn or right turn, are wirelessly transmitted to the single chip microcomputer on the on-site sales robot.

[0142] The on-site sales robot can obtain information from the control system through wired or wireless connection. The above-mentioned wireless connection methods include but are not limited to 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or developed in the future.

[0143] The single-chip microcomputer is an STM32F microcontroller or an 89C51 microcontroller. The STM32F single-chip microcomputer has a high-gain inverting amplifier that constitutes an internal oscillator. Pins XTAL1 and XTAL2 are the input and output terminals of the amplifier, respectively, and are used to connect an external crystal oscillator. The STM32F single-chip microcomputer is high-level reset enabled. In the single-chip microcomputer minimum system design, it is necessary to ensure that the single-chip microcomputer can be reset when powered on. At the same time, when the system runs away during operation, the single-chip microcomputer can be reset by the corresponding button. Therefore, the single-chip microcomputer reset needs to have two reset modes: power-on reset and button reset.

[0144] Step 107, motion control: the single-chip microcomputer on the on-site sales robot sends control information to the driving circuit board according to the motion instruction, so that the single-chip microcomputer on the on-site sales robot controls the motion of the on-site sales robot.

[0145] Specifically, the single-chip microcomputer controls the steering and speed of the motor of the on-site sales robot. When the pulse width modulation (PWM) signal frequency of the single-chip microcomputer sending control information to the driving circuit board is 14-30Hz, the motors driving the left and right wheels of the on-site sales robot rotate in the same direction and at the same speed at the same time, and the on-site sales robot moves forward. After algorithm processing, the speed of the on-site sales robot is proportional to the strength of the signal. The stronger the signal strength, the faster the speed of the on-site sales robot. In order to play a role in safety protection, the maximum value of the motor speed control will be set, and when the signal jumps in different bands, the system will stop working immediately and the on-site sales robot will stop moving. When the pulse width modulation (PWM) signal frequency sent by the single-chip microcomputer is 40Hz, the left wheel motor of the on-site sales robot rotates forward, and the right wheel motor rotates reversely, the two wheels form a differential, and the on-site sales robot moves to the right. At this time, the strength of the signal is not proportional to the motor speed in the on-site sales robot, that is, in this band, the speed of the on-site sales robot turning is a uniform turning speed. When the PWM signal frequency sent by the single-chip microcomputer is 8-13Hz, the left wheel motor of the on-site sales robot rotates in the opposite direction, and the right wheel motor rotates in the forward direction, and the two wheels also form a differential speed, and the on-site sales robot moves to the left. At this time, the signal strength is not proportional to the motor speed of the on-site sales robot, that is, in this band, the speed of the on-site sales robot is also a uniform speed. When the PWM signal frequency sent by the single-chip microcomputer is 1-3Hz, the left and right wheel motors of the on-site sales robot stop rotating at the same time. Due to the effect of the reduction box, the on-site sales robot stops moving quickly.

[0146] In some implementations, sensors are arranged around the on-site sales robot, and the sensors detect the distance between the on-site sales robot and surrounding obstacles, and send the distance information to a single-chip microcomputer, which controls the movement of the on-site sales robot according to the distance information.

[0147] After step 107, the single-chip microcomputer on the on-site sales robot sends control information to the driving circuit board according to the motion instruction, so that the single-chip microcomputer on the on-site sales robot controls the movement of the on-site sales robot. The above method further includes:

[0148] The feedback module is used to test the user's physiological signals. If the feedback is joyful, the single-chip microcomputer controls the movement mode of the on-site sales robot correctly; if the feedback is frustrated, the single-chip microcomputer controls the movement mode of the on-site sales robot incorrectly; the feedback module sends an error report to the single-chip microcomputer, and the single-chip microcomputer sends a braking movement instruction to the driver circuit board, so that the single-chip microcomputer controls the braking movement of the on-site sales robot.

[0149] When the single-chip microcomputer controls the movement pattern of the on-site sales robot correctly, the user will express joyful emotions to feedback the recognition result; when the single-chip microcomputer controls the movement pattern of the on-site sales robot incorrectly, the user will express frustrated emotions to feedback the recognition result.

[0150] Optionally, by calculating the multi-dimensional information between EEG leads to obtain the asymmetry feature ASI, it can effectively determine whether emotions occur:

[0151]

[0152] in, Refers to the information of the left brain signal X flowing to the right brain signal Y. Similarly Indicates the information flow from Y to X; S f is the total amount of two-way information; S n Refers to the flow of information when no emotions occur.

[0153] Emotion recognition is performed by analyzing the characteristics of EEG signals displayed by people in different emotional states. Therefore, the first thing to do is to extract relevant features from the EEG signal data collected by our laboratory, so as to provide the original feature set for subsequent feature selection and classification recognition. Features are the basis and key of classification recognition. The quality of features directly affects the quality of classification recognition. The experiment first collects EEG signals of people in different emotional states through a physiological signal recorder; we directly calculate these data, and the calculated values ​​are called original features. Various statistical values ​​of EEG signals are calculated, and these original statistical values ​​are used as original features. According to the particularity and difference of EEG signals, the average energy of the β wave rhythm of EEG signals in the time domain and frequency domain is extracted.

[0154] Feature extraction of electrical signals: mean A of the electrical signal beta wave, standard deviation B of the electrical signal beta wave, minimum Min of the electrical signal beta wave, maximum Max of the electrical signal beta wave, ratio of the number of minimum values ​​of the electrical signal beta wave to the signal length min Ratio, ratio of the number of maximum values ​​of the electrical signal beta wave to the signal length max Ratio, average energy EnergyA of the electrical signal beta wave.

[0155]

[0156] Wherein, E represents the electrical signal data, and N represents the length of the electrical signal data.

[0157] The present application provides a control method for a field sales robot, which uses the electrical signals generated when the user imagines different movements as the control information source to intelligently control the movement mode of the field sales robot, thereby realizing the user's free control of the field sales robot with his mind. Through the above method, the deep learning ability of the AI ​​large model can be used to more accurately identify and process signals related to movement imagination, thereby realizing precise control of the field sales robot.

[0158] Embodiment 2

[0159] like Figure 2 The flowchart of a control method of a field sales robot provided by an embodiment of the present application is shown. Embodiment 2 of the present application proposes a method for controlling a field sales robot based on motor imagery, and the method comprises the following steps:

[0160] Step 201: The acquisition module acquires signals in an area of ​​interest, which is an area of ​​interest related to motor imagery, and sends the acquired signals to a signal processing module.

[0161] Step 202: The signal processing module converts the collected signal into a digital signal through an analog-to-digital converter.

[0162] Step 203: The signal processing module uses the AI ​​big model to pre-process the converted digital signal to extract the high-order features and patterns of the signal.

[0163] Step 204: The signal processing module performs feature extraction on the signal based on discrete wavelet transform.

[0164] Step 205: Perform pattern recognition on the signal based on the extracted features to obtain the motion instructions that the user wants to use to control the on-site sales robot.

[0165] Step 206: The signal processing module wirelessly transmits the motion instructions that the user wants to give to the on-site sales robot to the single-chip microcomputer on the on-site sales robot through the wireless interface.

[0166] Step 207: The single-chip microcomputer on the on-site sales robot sends control information to the driving circuit board according to the motion instruction, so that the single-chip microcomputer on the on-site sales robot controls the movement of the on-site sales robot.

[0167] Step 208, the feedback module is used to test the user's physiological signals. If the feedback is joyful, the single-chip microcomputer controls the movement mode of the on-site sales robot correctly.

[0168] Step 209 , if the feedback is of frustrated emotion, the single chip microcomputer controls the mode of the on-site sales robot's movement in error, the feedback module sends an error report to the single chip microcomputer, and jumps to step 207 .

[0169] In step 210, the single-chip microcomputer sends a braking movement instruction to the driving circuit board, so that the single-chip microcomputer controls the braking movement of the on-site sales robot.

[0170] Embodiment 3

[0171] like Figure 3 The system framework diagram of a control field sales robot provided by the embodiment of the present application is shown as follows: Figure 4 The interactive flow chart of the system framework for controlling a field sales robot provided by the embodiment of the present application is shown as follows: Figure 5 The illustrated embodiment of the present application provides a schematic diagram of a physical interaction for controlling an on-site sales robot. Embodiment 3 of the present application proposes a system for controlling an on-site sales robot, the system 300 comprising: an acquisition module 301, for acquiring signals in an area of ​​interest, the area of ​​interest being an area of ​​interest related to motor imagination, and sending the acquired signals to a signal processing module; the signal processing module 302, for converting the acquired signals into digital signals through an analog-to-digital converter, preprocessing the converted digital signals using an AI large model, extracting high-order features and patterns of the signals, the signal processing module performing feature extraction based on discrete wavelet transform on the signals; a recognition module 303, for performing pattern recognition on the signals according to the extracted features to obtain motion instructions that the user wants to use to control the on-site sales robot 307; a transmission module 304, for the signal processing module to transmit the signals to the on-site sales robot 307 via a wireless interface The motion instructions that the user wants to use to control the on-site sales robot 307 are wirelessly transmitted to the single-chip microcomputer on the on-site sales robot; the control module 305 is used for the single-chip microcomputer on the on-site sales robot to send control information to the driving circuit board according to the motion instructions, so that the single-chip microcomputer on the on-site sales robot controls the movement of the on-site sales robot; the feedback module 306 is used to test the user's physiological signals. If the feedback is a happy emotion, the single-chip microcomputer controls the movement mode of the on-site sales robot correctly; if the feedback is a depressed emotion, the single-chip microcomputer controls the movement mode of the on-site sales robot incorrectly; the feedback module sends an error report to the single-chip microcomputer, and the single-chip microcomputer sends a braking movement instruction to the driving circuit board, so that the single-chip microcomputer controls the braking movement of the on-site sales robot.

[0172] The acquisition module 301 may be a module independent of the control system 300 and sends the acquired signals to the control system 300 , or may be a module embedded in the control system, and the acquisition module 301 and the control system 300 are integrated.

[0173] Information can be transmitted between the field sales robot and the control system via wired or wireless connection.

[0174] The system for controlling an on-site sales robot provided in the above embodiment corresponds one-to-one to the control method for an on-site sales robot provided in the above embodiment. The system for controlling an on-site sales robot executes all steps of the method for controlling an on-site sales robot, which will not be repeated here.

[0175] Embodiment 4

[0176] An embodiment of the present application provides a control method for an on-site sales robot, which includes the following steps: establishing a coordinate system, determining the coordinates of multiple nodes in the coordinate system, obtaining the current position coordinates of the sales robot in real time, planning the path trajectory of the sales robot from the current position to multiple nodes, and the sales robot moving according to the planned path trajectory.

[0177] Establish a coordinate system and determine the coordinates of multiple nodes in the coordinate system. These nodes can include important locations in the sales area, such as product display areas, cash registers, etc. Obtain the current position coordinates of the sales robot in real time. Sensor technologies such as GPS and LiDAR can be used to accurately determine the position of the sales robot in the coordinate system. According to the coordinates of multiple nodes and the current position coordinates of the sales robot, plan the path trajectory of the sales robot from the current position to multiple nodes. The sales robot moves according to the planned path trajectory and updates its own position coordinates in real time so that it can adjust the path in time when encountering obstacles or other abnormal situations.

[0178] Optionally, the sales robot receives a request message sent by the node, the request message including a node ID; determines the coordinates of the node in the coordinate system according to the node ID in the request message, plans a path trajectory of the sales robot from the current position to the node, and the sales robot moves according to the planned path trajectory to reach the position of the node.

[0179] Embodiment 5

[0180] See also Figure 6 The present invention is a flow chart of a path control method of an on-site sales robot, and the path control method of the on-site sales robot includes the following steps:

[0181] S601: A global map is stored in the sales robot in advance, the map is divided into multiple areas, the center point of each area is recorded as A, B, C, D, E and F target points, and the system receives request information containing node ID sent from the outside.

[0182] S602: Sense the current position through the sensor device installed inside the sales robot, mark the current position coordinates of the sales robot as the starting coordinates, parse the node ID in the request information, determine the marked coordinate position information corresponding to the node ID according to the preset coordinate system, and record the path from the starting coordinates to the target coordinates as the optimal path.

[0183] S603: The image acquisition device installed on the sales robot is used to capture images of the surrounding environment in real time, and the position information of obstacles is detected from the image through the Yolo target detection algorithm. The obstacle information in the image is converted into coordinates in a two-dimensional coordinate system, and the coordinate position, length and width of the obstacle are marked in the map. Obstacle avoidance parameters are obtained according to the obstacle coordinates and the initial coordinate distance, the minimum safety distance and the obstacle length and width.

[0184] S604: The deceleration value of the sales robot is obtained according to the difference between the current speed and the target speed of the sales robot, and the adjustment coefficient is multiplied by the difference between the current speed and the linear speed to obtain the turning deceleration value of the sales robot caused by turning. The final deceleration value is added to decelerate and avoid obstacles.

[0185] S605: Compare the distance value between the current position of the sales robot and the target node with the preset distance value, and determine whether the target node has been reached based on the comparison result.

[0186] Specifically, a global map is pre-stored inside the sales robot, and the global map is divided into multiple areas, each area represents a specific task execution area, and the central position point of each area is marked and recorded as A, B, C, D, E and F target points, which serve as reference points for robot navigation and task execution; the sensor device is started to continuously monitor and record the current position information of the sales robot, and when a request message containing a node ID sent from the outside is received, the current position coordinates of the sales robot obtained by the sensor at this time are immediately marked as the starting coordinates, the node ID in the request message is parsed, and converted into a target point identifier recognizable by the system, and the coordinate position of the parsed node ID is found, and the starting coordinates, target coordinates and map data are input into In the selected path planning algorithm, the optimal path from the starting coordinates to the target coordinates is calculated; the image acquisition device is started to capture and record the image of the robot's surrounding environment, the coordinate information of the obstacles is extracted from the output results of the pre-trained Yolo target detection algorithm, and two-dimensional coordinate conversion is performed. The coordinate information of the obstacles is marked in the map data, and the obstacle avoidance parameters are calculated; the deceleration value of the sales robot is obtained according to the difference between the current speed of the sales robot and the target speed of the sales robot, and the adjustment coefficient is multiplied by the difference between the current speed and the linear speed to obtain the sales robot steering deceleration value caused by the steering, and the final deceleration value is added to decelerate; the distance value between the current position of the sales robot and the target node is compared with the preset distance value, and it is determined whether the target node has been reached according to the comparison result.

[0187] In one embodiment of the present invention, step S601 includes the following steps: creating a global map through synchronous positioning and map building technology, dividing the map into multiple areas, marking the central position within each area as multiple target points, including target points A, B, C, D, E and F, which are stored inside the sales robot for recording, and the system receives request information containing node ID sent from the outside; wherein the node ID includes point A of the reception desk, point B of the model display area, point C of the model room entrance, point D of the negotiation area, point E of the signing area, and point F of the rest area.

[0188] Specifically, a global map is pre-stored inside the sales robot, and the global map is divided into multiple areas. Each area represents a specific task execution area, and the central position point of each area is marked and recorded as target points A, B, C, D, E and F. These target points serve as reference points for robot navigation and task execution; the node IDs include point A for the reception desk, point B for the model display area, point C for the model room entrance, point D for the negotiation area, point E for the signing area, and point F for the rest area.

[0189] In one embodiment of the present invention, step S602 includes the following steps: sensing the current position by a sensor device installed inside the sales robot, marking the current position coordinates of the sales robot as the starting coordinates, the robot parses the received request information and extracts the node ID therein, constructs a preset two-dimensional plane coordinate system through a map structure, searches for the corresponding marked coordinate position information in the preset coordinate system according to the parsed node ID, matches the node ID with the coordinate position one by one, and uses a path planning algorithm to obtain the optimal path from the starting coordinates to the target coordinates according to the starting point coordinates and the target point coordinates; wherein the node IDs are A, B, C, D, E, F and O points, and the corresponding coordinates are the target point A point (X A , Y A ), point B (X B , Y B ), point C (X C , Y C ), point D (X D , Y D ), point E (X E , Y E ) and point F (X F , Y F ) and the starting point O (X O , Y O ).

[0190] Specifically, the sensor device installed inside the sales robot is started to continuously monitor and record the current position information of the sales robot. When a request message containing a node ID sent from the outside is received, the current position coordinates of the sales robot obtained by the sensor at this time are immediately marked as the starting coordinates, the node ID in the request message is parsed, and it is converted into a target point identifier recognizable by the system, and the coordinate position of the parsed node ID is found, and the starting coordinates, target coordinates and map data are input into the selected path planning algorithm to calculate the optimal path from the starting coordinates to the target coordinates; wherein the node IDs are A, B, C, D, E, F and O points, and the corresponding coordinates are the target point A point (X A , Y A ), point B (X B , Y B ), point C (X C , Y C ), point D (X D , Y D ), point E (X E , Y E ) and point F (X F , Y F ) and the starting point O (X O , Y O ).

[0191] In one embodiment of the present invention, a path planning algorithm is used to calculate the optimal path from the starting point coordinates to the target point coordinates based on the starting point coordinates and the target point coordinates, including the following steps: searching for a path from the current position to the target point through the path planning algorithm. During the search process, the path planning algorithm will evaluate and find the optimal path based on the map data and the distance values ​​between different nodes. When an obstacle is detected during the detection process, the map is updated and the optimal path is re-planned.

[0192] Specifically, the path planning algorithm is used to search for the path from the current position to the target point, and the coordinate position, length and width of the obstacles are marked in the pre-stored global map data structure. When a new obstacle is detected or an existing obstacle moves, the map data is updated in time, and the sales robot is replanned to have the optimal path from the current position to the target position and avoid obstacles.

[0193] In one embodiment of the present invention, step S603 includes the following steps: capturing images of the surrounding environment in real time through an image acquisition device installed on the sales robot, preprocessing the acquired images, extracting size and shape features of obstacles from the preprocessed images, classifying and identifying the extracted features using a deep learning algorithm, detecting the position information of the obstacles from the image through a Yolo target detection algorithm after identifying the obstacles, converting the obstacle information in the image into coordinates in a two-dimensional coordinate system through spatial geometric transformation, updating the environment map inside the robot using a grid method, and marking the coordinate position, length and width of the obstacles in the map, obtaining obstacle avoidance parameters through the obstacle coordinates and the initial coordinate distance, the minimum safety distance and the obstacle length and width, adjusting the speed of the robot, and assisting the sales robot in positioning and avoiding obstacles during movement; obtaining an obstacle avoidance parameter calculation formula based on the obstacle coordinates and the initial coordinate distance, the minimum safety distance, the obstacle length and width:

[0194]

[0195] Where Distance2 is the distance between the obstacle coordinates and the initial coordinates, Distance1 is the minimum safe distance, (X O , Y O ) is the coordinate of the starting point O, (X Z , Y Z ) is the obstacle coordinate, denoted as point G; avoidance parameter is the calculated value of obstacle avoidance parameter, L Z is the length of the obstacle, W Z is the width of the obstacle;

[0196] If the calculated value of the obstacle avoidance parameter is a positive number, the sales robot can pass safely without slowing down; if the calculated value of the obstacle avoidance parameter is a negative number, the sales robot needs to slow down and turn the angle to avoid the obstacle.

[0197] Specifically, an image acquisition device installed on the sales robot is used to capture images of the surrounding environment in real time, the acquired images are preprocessed, the size and shape features of the obstacles are extracted from the preprocessed images, and the extracted features are classified and identified using a deep learning algorithm. After the obstacle is identified, the position information of the obstacle is detected from the image using a Yolo target detection algorithm, and the coordinates of the center point in the image are obtained. The coordinates of the upper left and upper right corners of the bounding box are converted into coordinates in a two-dimensional coordinate system using spatial geometric transformation. The environment map inside the robot is updated using a grid method, and the coordinate position, length and width of the obstacle are marked in the map. The map data structure can be queried to find the map area closest to the current robot position, and the obstacle avoidance parameter is obtained through the obstacle coordinates and the initial coordinate distance, the minimum safety distance, and the obstacle length and width. If the calculated value of the obstacle avoidance parameter is a positive number, it means that the sales robot can pass safely without decelerating; if the calculated value of the obstacle avoidance parameter is a negative number, the sales robot needs to decelerate and turn the angle to avoid the obstacle; wherein, the minimum safety distance Distance1 is 12 meters.

[0198] In one embodiment of the present invention, the step S604 includes the following steps:

[0199] The calculation formula for safe braking distance at the current speed is:

[0200]

[0201] Wherein, Distance3 is the calculated value of the safe braking distance, V is the current speed of the sales robot, a is the maximum deceleration of the sales robot, T is the robot reaction time, g is the acceleration of gravity, and μ is the friction coefficient between the sales robot and the ground;

[0202] The target speed value calculation formula is obtained based on the sales robot's maximum deceleration value and minimum safety distance deceleration value:

[0203]

[0204] Among them, V target is the target speed, a is the maximum deceleration of the sales robot, T is the robot reaction time, and Distance1 is the minimum safety distance value;

[0205] The sales robot deceleration value calculation formula is obtained based on the difference between the sales robot's current speed and the sales robot's target speed:

[0206] V s =VV target

[0207] Among them, V target is the target speed, V is the current speed of the sales robot, V s Slowdown value for sales robot;

[0208] Multiply the adjustment coefficient by the difference between the current speed and the linear speed to get the turning deceleration value of the sales robot caused by turning. The turning deceleration value calculation formula is:

[0209]

[0210] Where R is the wheel radius of the sales robot, V is the current speed of the sales robot, t is the time change, α is the deceleration value adjustment coefficient, π is the circumference, V z Calculate the value for the steering deceleration value;

[0211] Final deceleration value calculation formula:

[0212] V final =V s +V z

[0213] Among them, V s is the deceleration value, V z is the calculated value of the steering deceleration value, V final is the final deceleration value.

[0214] Specifically, first calculate the distance between the current position of the robot and the nearest obstacle; determine whether obstacle avoidance measures need to be taken based on the preset minimum safety distance, and obtain the safe braking distance at the current speed through the current robot speed, maximum deceleration value, reaction time, gravity acceleration and the friction coefficient between the sales robot and the ground, where the gravity acceleration g is 9.8, the adjustment coefficient α is 0.8, the pi π is 3.14, and the friction coefficient μ is 0.5. The target speed value is obtained based on the maximum deceleration value and the minimum safety distance deceleration value of the sales robot. The target speed value is a speed that ensures that the robot can stop at a safe distance. The deceleration value of the sales robot is obtained by the difference between the current speed of the sales robot and the target speed of the sales robot. The steering deceleration value caused by steering is obtained by multiplying the adjustment coefficient by the difference between the current speed and the linear speed. The final deceleration value is obtained by adding the deceleration value and the steering deceleration value.

[0215] In one embodiment of the present invention, step S605 includes the following steps: comparing the distance value between the current position of the sales robot and the target node with the preset distance value, and judging whether the target node has been reached according to the comparison result; if the distance value between the sales robot and the target node is greater than 0.3 meters, the sales robot has not reached the target node and needs to continue to move towards the target point; if the distance value between the sales robot and the target node is less than or equal to 0.3 meters, the sales robot reaches the target node and performs the corresponding task according to the information of different node IDs; after completing the task, the sales robot starts to receive new task instructions to replan the path and execute the task.

[0216] Specifically, the distance value between the two points is obtained by the coordinate point of the current position of the sales robot and the coordinate point of the target node, a preset distance value is set to 0.3 meters, and the distance value between the two points is compared with the preset distance value. If the distance value between the current position of the sales robot and the target node is greater than 0.3 meters, it continues to move towards the target node; if the distance value between the current position of the sales robot and the target node is less than or equal to 0.3 meters, it starts to execute subsequent tasks; after the task is completed, it receives new task instructions to re-plan the path and execute the task.

[0217] The control method and path control method of a field sales robot provided in the embodiment of the present application solves the problem that the remote control field sales robot has too many accessories and is inconvenient to carry, and realizes the free control of the field sales robot by the user's mind. In the present application, when a marketer is selling real estate, the salesperson can control the movement mode and movement direction of the field sales robot by mind, and control the field sales robot to actively walk towards the customer to explain the real estate information to the customer, thereby improving the efficiency of the marketer in selling real estate and reducing a large amount of labor costs.

[0218] The above description is merely an exemplary embodiment of the present invention and is not intended to limit the protection scope of the present invention. The protection scope of the present invention is determined by the appended claims.

Claims

1. A control method for a field sales robot, It is characterized in that The method comprises: Signal acquisition: the acquisition module performs signal acquisition in the region of interest, which is a region of interest related to motor imagery, and sends the acquired signal to the signal processing module; Signal conversion: The signal processing module converts the collected signal into a digital signal through an analog-to-digital converter; AI big model preprocessing: The signal processing module uses the AI ​​big model to preprocess the converted digital signal and extract the high-order features and patterns of the signal; Feature extraction: the signal processing module performs feature extraction on the signal based on discrete wavelet transform; Pattern recognition: performing pattern recognition on the signal according to the extracted features to obtain the motion instructions that the user wants to control the field sales robot; Wireless transmission: the signal processing module wirelessly transmits the motion instructions that the user wants to use to control the on-site sales robot to the single-chip microcomputer on the on-site sales robot through a wireless interface; Motion control: The single-chip microcomputer on the on-site sales robot sends control information to the driving circuit board according to the motion instruction, so that the single-chip microcomputer on the on-site sales robot controls the movement of the on-site sales robot.

2. The method according to claim 1, It is characterized in that The method further comprises: the signal processing module processes the digital signal; Each input sample of the digital signal x[n] enters the digital filter in turn, and the output y[n] of the digital filter at any time is a simple weighted sum of the current and past sample inputs: x[nL] is the Lth past input sample, y[nL] is the Lth past output sample, b L 、a L are the scale weights of each input sample and output sample, respectively, M and N are the number of input sample weights and output sample weights used by the filter, respectively; By adjusting the length of the filter and the weights assigned to successive samples, the signal frequencies in a certain frequency range will be amplified, attenuated, preserved, or eliminated; The method further includes: discrete wavelet transform is to discretize c as a scale factor and d as a translation factor, and the discrete wavelet transform of the signal f(t) is: ψ j,k (t) is the discretized wavelet function, which is the kth low-frequency component of the jth layer; The discrete wavelet transform is a uniformly discretized time series. The discrete wavelet transform DWTx(m,n) of the signal x(t) is defined as: Where m is the scale factor, n is the expansion factor, ψ m,n (t) is the discretized wavelet function.

3. The method according to claim 1, It is characterized in that The signal processing module extracts features of the signal based on discrete wavelet transform, including: Wavelet transform can realize the frequency domain conversion of the signal. Wavelet transform uses a basic wavelet as a scale transformation and time shift to convolve with the signal to be analyzed. The continuous wavelet transform CWTx(c,d) of the signal x(t) is defined as: Among them, CWTx(c,d) is the time-frequency feature map, x(t) is the electrical signal, c is the scale factor, d is the translation factor, is the wavelet basis function under the translation factor d and the scale factor c, φ(t) is the basic wavelet (or mother wavelet), which can be a real signal or a complex signal; the non-zero real number c is the scale factor, which is the parameter for scaling the basic wavelet φ(t) on the time axis; the larger the c, the smaller the scale, and the corresponding wavelet φ(t / c) is more stretched in the time domain and more compressed in the frequency domain, the time translation parameter d, different d values ​​indicate that the wavelet moves to different positions along the time axis.

4. The method according to claim 1, It is characterized in that The method further comprises: processing the motor imagery electric signal in the discrete domain by using continuous wavelet transform, discretizing the transform, and processing as follows: cj=2 j ,d j,k =k*2 j , where c is the scale factor and d is the translation factor. The continuous wavelet transform maps the signal from one-dimensional space to two-dimensional space, discretizes the scale factor c and the time-shift parameter d, and uses the wavelet transform values ​​at certain discrete points on the time-scale plane to characterize the signal, so as to realize the feature extraction of the frequency band of interest, and discretizes the scale according to the integer power of the constant 2, that is, c=2^j,j∈Z; When the user imagines the left hand moving, the energy in the right hemisphere decays, which is manifested as the correlated desynchronization ERD phenomenon, and the energy in the left hemisphere increases, which is manifested as the correlated synchronization ERS phenomenon. The quantification method of ERD / ERS is: E represents the energy value of the EEG signal of a certain frequency band at a certain electrode after motor imagery; R represents the energy value of the EEG signal of a certain frequency band at a certain electrode before motor imagery; when ERD / ERS is a positive value, the energy increases after motor imagery and the ERS phenomenon occurs; when ERD / ERS is a negative value, the energy attenuates after motor imagery and the ERD phenomenon occurs.

5. The method according to claim 4, It is characterized in that The method further comprises: By detecting the ERD / ERS value of the electrode, pattern recognition is performed on the signal to obtain the movement instruction that the user wants to give to the field sales robot; When the ERD / ERS value of the left hemisphere electrode is detected to be positive, the energy of the left hemisphere increases and the energy of the right hemisphere decreases, and it is concluded that the user imagines moving his left hand, thereby recognizing that the movement instruction the user wants to give to the field sales robot is to move to the left; When the ERD / ERS value of the right hemisphere electrode is detected to be positive, the energy of the right hemisphere increases and the energy of the left hemisphere decreases, and it is concluded that the user imagines moving his right hand, thereby recognizing that the movement instruction the user wants to give to the on-site sales robot is to move to the right; The single chip microcomputer on the on-site sales robot sends control information to the driving circuit board according to the motion instruction, so that the single chip microcomputer on the on-site sales robot controls the movement of the on-site sales robot, including: When the frequency of the pulse width modulation (PWM) signal of the single-chip microcomputer sending the control information to the driving circuit board is 14-30Hz, the motors driving the left and right wheels of the on-site sales robot rotate in the same direction and at the same speed at the same time, and the on-site sales robot moves forward; when the frequency of the pulse width modulation signal of the single-chip microcomputer sending the control information to the driving circuit board is 30-40Hz, the left wheel motor of the on-site sales robot rotates forward, and the right wheel motor rotates reversely, the two wheels form a speed differential, and the on-site sales robot moves to the right; when the frequency of the pulse width modulation signal of the single-chip microcomputer sending the control information to the driving circuit board is 8-13Hz, the left wheel motor of the on-site sales robot rotates reversely, the right wheel motor rotates forward, the two wheels also form a speed differential, and the on-site sales robot moves to the left; when the frequency of the pulse width modulation signal of the single-chip microcomputer sending the control information to the driving circuit board is 1-3Hz, the left and right wheel motors of the on-site sales robot stop rotating at the same time, and due to the effect of the reduction gearbox, the on-site sales robot stops moving quickly.

6. The method according to claim 1, It is characterized in that After the single-chip microcomputer on the on-site sales robot sends control information to the driving circuit board according to the motion instruction, so that the single-chip microcomputer on the on-site sales robot controls the on-site sales robot to move, the method further includes: The feedback module is used to test the physiological signals of the user. If the feedback is a joyful emotion, the single-chip microcomputer controls the movement mode of the on-site sales robot correctly; if the feedback is a frustrated emotion, the single-chip microcomputer controls the movement mode of the on-site sales robot incorrectly; the feedback module sends an error report to the single-chip microcomputer, and the single-chip microcomputer sends a braking movement instruction to the driving circuit board, so that the single-chip microcomputer controls the braking movement of the on-site sales robot; When the single chip microcomputer controls the movement mode of the on-site sales robot correctly, the user expresses joy emotion feedback recognition result; when the single chip microcomputer controls the movement mode of the on-site sales robot incorrectly, the user expresses frustration emotion feedback recognition result; By calculating the multi-dimensional information between EEG leads, we can obtain the asymmetry feature ASI, which can effectively determine whether emotions occur: in, Refers to the information of the left brain signal X flowing to the right brain signal Y. Similarly Indicates the information flow from Y to X; S f is the total amount of two-way information; S n Refers to the flow of information when no emotions occur.

7. A path control method for a field sales robot, It is characterized in that The method comprises the following steps: S1: A global map is stored in the sales robot in advance, the map is divided into multiple areas, the center point of each area is recorded as A, B, C, D, E and F target points, and the system receives request information containing node ID sent from the outside; S2: sense the current position through the sensor device installed inside the sales robot, mark the current position coordinates of the sales robot as the starting coordinates, parse the node ID in the request information, determine the marked coordinate position information corresponding to the node ID according to the preset coordinate system, and record the path from the starting coordinates to the target coordinates as the optimal path; S3: The image acquisition device installed on the sales robot captures images of the surrounding environment in real time, detects the location information of obstacles from the image through the Yolo target detection algorithm, converts the obstacle information in the image into coordinates in a two-dimensional coordinate system, and marks the coordinate position, length and width of the obstacle on the map. Obstacle avoidance parameters are obtained based on the obstacle coordinates and the initial coordinate distance, the minimum safety distance and the obstacle length and width; S4: The deceleration value of the sales robot is obtained according to the difference between the current speed of the sales robot and the target speed of the sales robot, and the deceleration value of the sales robot caused by the turning is obtained by multiplying the adjustment coefficient by the difference between the current speed and the linear speed, and the final deceleration value is added to decelerate and avoid obstacles; S5: By comparing the distance value between the current position of the sales robot and the target node with the preset distance value, it is determined whether the target node has been reached according to the comparison result.

8. A path control method for an on-site sales robot according to claim 7, It is characterized in that The step S1 comprises the following steps: A global map is created through synchronous positioning and map building technology, and the map is divided into multiple areas. The central position of each area is marked as multiple target points, including A, B, C, D, E and F target points, which are stored inside the sales robot for recording. The system receives request information containing node ID sent from the outside; Among them, the node IDs include point A of the reception desk, point B of the model display area, point C of the model room entrance, point D of the negotiation area, point E of the signing area, and point F of the rest area; Described step S2, comprises the following steps: The current position is sensed by the sensor device installed inside the sales robot, and the coordinates of the current position of the sales robot are marked as the starting coordinates. The robot parses the received request information and extracts the node ID therein, and constructs a preset two-dimensional plane coordinate system through the map structure. According to the parsed node ID, the corresponding marked coordinate position information is searched in the preset coordinate system, and the node ID is matched with the coordinate position one by one. According to the starting point coordinates and the target point coordinates, the path planning algorithm is used to obtain the optimal path from the starting coordinates to the target coordinates; The node IDs are A, B, C, D, E, F and O, and the corresponding coordinates are the target point A (X A , Y A ), point B (X B , Y B ), point C (X C , Y C ), point D (X D , Y D ), point E (X E , Y E ) and point F (X F , Y F ) and the starting point O (X O , Y O ); According to the coordinates of the starting point and the target point, the path planning algorithm is used to calculate the optimal path from the starting point to the target point, including the following steps: The path planning algorithm is used to search for the path from the current position to the target point. During the search process, the path planning algorithm will evaluate the map data and the distance values ​​between different nodes to find the optimal path. When obstacles are detected during the detection process, the map is updated and the optimal path is replanned.

9. The path control method of a field sales robot according to claim 7, It is characterized in that The step S3 comprises the following steps: The image acquisition device installed on the sales robot captures images of the surrounding environment in real time, pre-processes the collected images, extracts the size and shape features of obstacles from the pre-processed images, and uses deep learning algorithms to classify and identify the extracted features. After identifying the obstacles, the Yolo target detection algorithm is used to detect the location information of the obstacles from the image. The spatial geometric transformation converts the obstacle information in the image into coordinates in a two-dimensional coordinate system. The grid method is used to update the environment map inside the robot, and the coordinate position, length and width of the obstacles are marked in the map. Obstacle avoidance parameters are obtained through the obstacle coordinates and the initial coordinate distance, the minimum safety distance and the obstacle length and width. The speed of the robot is adjusted to assist the sales robot in positioning and avoiding obstacles during movement. Obstacle avoidance parameter calculation formula is obtained based on obstacle coordinates and initial coordinate distance, minimum safety distance, obstacle length and width: Among them, Distance 2 Distance is the distance between the obstacle coordinates and the initial coordinates. 1 is the minimum safety distance value, (X O , Y O ) is the coordinate of the starting point O, (X Z , Y Z ) is the obstacle coordinate, denoted as point G; avoidance parameter is the calculated value of obstacle avoidance parameter, L Z is the length of the obstacle, W Z is the width of the obstacle; If the calculated value of the obstacle avoidance parameter is a positive number, the sales robot can pass safely without slowing down; If the calculated value of the obstacle avoidance parameter is a negative number, the sales robot needs to slow down and turn the angle to avoid the obstacle.

10. The path control method of a field sales robot according to claim 7, It is characterized in that The step S4 comprises the following steps: The calculation formula for safe braking distance at the current speed is: Among them, Distance 3 is the calculated value of the safe braking distance, V is the current speed of the sales robot, a is the maximum deceleration of the sales robot, T is the robot reaction time, g is the acceleration of gravity, and μ is the friction coefficient between the sales robot and the ground; The target speed value calculation formula is obtained based on the sales robot's maximum deceleration value and minimum safety distance: V target =2aT+DistaTnce 1 Among them, V target is the target speed, a is the maximum deceleration of the sales robot, T is the robot reaction time, Distance 1 is the minimum safety distance value; The sales robot deceleration value calculation formula is obtained based on the difference between the sales robot's current speed and the sales robot's target speed: V s =VV target Among them, V target is the target speed, V is the current speed of the sales robot, V s Slowdown value for sales robot; The adjustment coefficient is multiplied by the difference between the current speed and the linear speed to obtain the turning deceleration value of the sales robot caused by turning, and the calculation formula for the turning deceleration value is obtained: Where R is the wheel radius of the sales robot, V is the current speed of the sales robot, t is the time change, α is the deceleration value adjustment coefficient, π is the circumference, V z Calculate the value for the steering deceleration value; Final deceleration value calculation formula: V final =V s +V z Among them, V s is the deceleration value, V z is the calculated value of the steering deceleration value, V final is the final deceleration value; The step S5 comprises the following steps: By comparing the distance value between the current position of the sales robot and the target node with the preset distance value, it is determined whether the target node has been reached according to the comparison result; If the distance between the sales robot and the target node is greater than 0.3 meters, the sales robot has not reached the target node and needs to continue moving toward the target point; If the distance between the sales robot and the target node is less than or equal to 0.3 meters, the sales robot arrives at the target node and performs the corresponding task according to the information of different node IDs; After completing the task, the sales robot begins to receive new task instructions to replan the path and execute the task.

Images