Insect robot automatic obstacle avoidance and track recording system and method

Abstract

The invention discloses an insect robot automatic obstacle avoidance and track recording system and method, and belongs to the technical field of electronic information technology, computer science and technology and biological science and technology. The invention provides an insect robot automatic obstacle avoidance and track recording method and system based on a new generation of information technologies (including an integration technology, a sensor technology, wireless communication, a software technology and the like). The system has the advantages that real-time sensing of the surrounding environment of the insect robot can be achieved, obstacles in the environment can be automatically avoided, in addition, the movement track of the insect robot can be recorded, experimenters can monitor and analyze the movement of the insect robot through the system, and therefore the accuracy and efficiency of experiments are improved; from the long term, a new thought is provided for intelligent development of the insect robot.

Description

Technical Field

[0001] The invention belongs to electronic information technology, computer science and technology and biological science and technology, and specifically relates to an automatic obstacle avoidance and trajectory recording system and method for an insect robot. Background Art

[0002] Insect robots have great potential for application in disaster relief, industrial inspection, military reconnaissance, scientific investigation and special engineering due to their excellent movement ability, high flexibility and strong stealth. In particular, in earthquake ruins search and rescue, dangerous environment survey, confined space exploration and other scenes where personnel are difficult to reach or there are safety hazards, insect robots can effectively reduce personnel risks and significantly improve work efficiency. Controlling the movement behavior of insects through electrical stimulation and other methods has the advantages of low energy consumption, strong load capacity and good environmental adaptability. At present, domestic and foreign scholars' research on insect robots mainly focuses on stimulation methods, movement control and behavior analysis.

[0003] In the prior art, the control method of insect robots mainly relies on manual operation. Experimenters manually send control instructions by observing the movement state of insects. This method has the following problems: First, the real-time and accuracy of manual control are poor, and it is difficult to deal with emergencies in complex environments; second, insect robots lack the ability to autonomously perceive the environment and cannot effectively avoid obstacles; third, the recording and analysis methods of real-time motion trajectories are rarely used in insect robots, which is not conducive to the optimization of control strategies. In order to improve the environmental perception ability of insect robots, some researchers have tried to carry various sensors on the back of insects. However, due to the small size of insects and limited load capacity, traditional depth cameras, lidars and other equipment are large in size and heavy in weight, making them difficult to use in practice. In addition, most studies only focus on the realization of a single function, lacking a comprehensive solution that organically combines functions such as environmental perception, autonomous obstacle avoidance and trajectory recording.

[0004] Therefore, it is necessary to study an insect robot intelligent control system that integrates environmental perception, autonomous obstacle avoidance and trajectory recording functions. The system should have a lightweight environmental perception solution, an intelligent obstacle avoidance decision-making mechanism, accurate real-time trajectory recording function and a friendly human-computer interaction interface to improve the insect robot's motion control ability and experimental analysis efficiency in complex environments. Summary of the invention

[0005] In view of the above-mentioned technical problems existing in the prior art, the present invention proposes an insect robot automatic obstacle avoidance and trajectory recording system and method, which has a reasonable design, overcomes the shortcomings of the prior art, and has good effects.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] An automatic obstacle avoidance and trajectory recording system for an insect robot, comprising an environment perception module, a depth estimation module, an obstacle avoidance decision module, a wireless communication module, a control signal generation module, an image acquisition module, a motion trajectory recording module, and a host computer control display unit module;

[0008] The environment perception module is configured to obtain a first-person perspective image stream of the insect robot through a monocular camera mounted on a microcontroller on the back of the insect, and record the environment information;

[0009] A depth estimation module is configured to extract the image stream of the environment perception module, generate a real-time depth map using a deep learning algorithm, and obtain relative distance information between the insect robot and obstacles;

[0010] The obstacle avoidance decision module is configured to formulate an obstacle avoidance strategy based on the depth map generated by the depth estimation module and generate corresponding control instructions;

[0011] A wireless communication module is configured to realize wireless data transmission between various modules of the system to ensure the real-time transmission of instructions and data;

[0012] The control signal generating module is configured to receive corresponding instructions from the wireless communication module and generate corresponding control stimulation signals. The control signal generating module is connected to four output ports of the microcontroller, and each output port is respectively connected to a microelectrode pre-implanted in the insect body;

[0013] An image acquisition module is configured to use an industrial camera to capture a motion image of the insect robot and transmit the image data to a motion trajectory recording module;

[0014] A motion trajectory recording module is configured to process the image provided by the image acquisition module, record the motion trajectory based on the target tracking algorithm, and mark the corresponding identifiers for different control instructions on the trajectory;

[0015] The host computer control display unit module is configured to provide a human-computer interaction interface, display real-time video streams, depth maps and motion trajectory images, use communication protocols to achieve two-way data transmission between the microcontroller and the host computer, support switching between manual control and automatic obstacle avoidance functions, and set image, data, and waveform parameter storage options;

[0016] Furthermore, the environment perception module is configured to connect the microcontroller on the back of the insect robot to WiFi, and uses the camera module to obtain images, thereby enhancing the insect robot's ability to perceive the surrounding environment;

[0017] The microcontroller is arranged on the back of the insect robot, and a pin header is led out from the output port of the microcontroller, and the pin header is inserted into a female header fixed on the back of the insect;

[0018] The rib mother is fixed to the back of the insect through electrodes made of 0.16mm stainless steel needles with a length of 3-8mm. The rib mother is connected to its corresponding stimulation site through leads.

[0019] Furthermore, the depth estimation module adopts the Depth Anything V2 depth estimation model to visualize the depth map through the INFERNO color mapping scheme. The depth value reflects the distance of the obstacle from the insect robot. The larger the depth value, the closer the obstacle is.

[0020] Furthermore, the obstacle avoidance decision module divides the depth map into three areas: center, left and right. The minimum depth value of the center area is extracted to judge the obstacles ahead, and the average depth value of the left and right areas is calculated to determine the turning direction. When the minimum depth value of the center area is greater than the set threshold, the system determines that there is an obstacle ahead, and chooses to turn in the direction with a larger depth value by comparing the difference in the average depth values ​​of the left and right areas.

[0021] Furthermore, the wireless communication module realizes two-way communication between the microcontroller and the host computer based on the HTTP protocol, transmits video streams and control instructions through WiFi, sets a 5-second communication timeout protection mechanism, and adds time interval control when sending instructions to ensure the stability of control.

[0022] Furthermore, the stimulation signal generated by the control signal generating module is a square wave pulse signal with adjustable high and low level time and pulse number, wherein the high and low level time is 10ms, a pulse cycle is 20ms, and the pulse number is adjustable, thereby realizing the forward and steering control of the insect robot.

[0023] Furthermore, the image acquisition module uses an industrial camera to acquire images, adopts the Python programming language to implement image processing, obtains the original image data of the industrial camera through the MVSDK interface, and after image processing and buffer management, converts the data into a format that can be processed by OpenCV.

[0024] Furthermore, the motion trajectory recording module adopts the KCF algorithm to realize target tracking. The initial tracking target is determined by mouse selection. The system automatically draws a yellow boundary box to mark the target position, records the motion path with a red trajectory line, and uses marking symbols of different shapes and colors on the trajectory to represent different control instructions.

[0025] Furthermore, the host computer control display unit module is developed based on the PyQt5 framework, and uses multi-threaded processing of different algorithms to improve the system response speed, display the video stream, depth map, motion trajectory in real time, and provide switching options between manual control and automatic obstacle avoidance functions, and support recording interactive interface options.

[0026] In addition, the present invention also provides an automatic obstacle avoidance and trajectory recording method for an insect robot, which adopts the automatic obstacle avoidance and trajectory recording system for an insect robot as described above, and specifically comprises the following steps:

[0027] Step 1: The experimenter connects the system slave to the microelectrode pre-implanted in the insect, initializes the microcontroller and camera, configures the camera parameters and establishes a WiFi connection, collects the insect's first-person perspective image through the camera interface, and transmits the image data to the host computer for display via the wireless communication module;

[0028] Step 2: For the first-person video stream, the Depth Anything V2 depth estimation model is called to generate a depth map, and the INFERNO color mapping scheme is used for visualization. The depth value in the depth map reflects the relative distance between the obstacle and the insect robot;

[0029] Step 3: The obstacle avoidance decision module divides the depth map into three areas: center, left, and right. It extracts the minimum depth value in the center area to determine the obstacle ahead, calculates the average depth value of the left and right areas to determine the turning direction, and generates obstacle avoidance control instructions based on the depth value comparison results.

[0030] Step 4: The control command is sent to the microcontroller through the HTTP protocol. The control signal generation module selects the corresponding output port according to the received command, generates a pulse signal with a high and low level time of 10ms, and acts on different positions of the insect body through microelectrodes to achieve basic action control such as turning left, turning right, and moving forward. The response of the insect to the stimulus is monitored. When the response is found to be weakened, the user is prompted to adjust the stimulus parameters or change the stimulus waveform, and the stimulus fatigue is reduced by increasing the number of pulses.

[0031] Step 5: The industrial camera collects the overall motion picture of the insect robot in real time through the MVSDK interface. The image data is transmitted to the trajectory recording module after preprocessing. The KCF algorithm is used for target tracking and the target position information is updated in real time.

[0032] Step 6: The trajectory recording module draws a yellow bounding box on the image to mark the current position, uses a red line to record the motion trajectory, and marks the action position of the control command on the trajectory to establish a proportional mapping relationship between the actual position of the insect and the display interface. Each time a control command is sent, a different marking symbol is used on the trajectory to record the stimulus position, which is convenient for analyzing the control effect;

[0033] Step 7: The upper computer display control unit provides two control modes: manual and automatic. In manual mode, the experimenter can send control commands through the interface buttons. In automatic mode, the system automatically generates obstacle avoidance commands based on depth information to ensure the safe movement of the insect robot.

[0034] Step 8: The first-person perspective image, depth map, motion trajectory, control instructions, stimulation parameters and other information of the insect robot can be saved and recorded for experimental personnel to view and analyze, providing a basis for optimizing the control strategy.

[0035] Beneficial technical effects brought by the present invention:

[0036] The present invention realizes the real-time perception of the environment by the insect robot through a lightweight monocular camera combined with a depth estimation algorithm, overcoming the limitations of the traditional depth sensor, which is large in size and heavy in weight. The intelligent obstacle avoidance decision-making mechanism based on depth information enables the insect robot to have autonomous obstacle avoidance capabilities. At the same time, the system integrates an accurate trajectory recording function, and the experimenter can analyze and optimize the control effect. In addition, the multi-threaded parallel processing and a friendly human-computer interaction interface are used to improve the real-time and usability of the system. The present invention provides a complete set of intelligent control solutions for insect robots to improve their application capabilities in complex environments.

[0037] The present invention proposes an automatic obstacle avoidance and trajectory recording method and system for an insect robot based on a new generation of information technology (including integration technology, sensor technology, wireless communication, software technology, etc.); in effect, it can realize real-time perception of the surrounding environment of the insect robot and automatically avoid obstacles in the environment. In addition, it can record the movement trajectory of the insect robot. Experimenters can monitor and analyze the movement of the insect robot through the system, thereby improving the accuracy and efficiency of the experiment; in the long run, it provides a new idea for the intelligent development of insect robots. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 The present invention is a schematic diagram of an automatic obstacle avoidance and trajectory recording method for an insect robot and a flow chart of the method.

[0039] Figure 2 The present invention is a schematic diagram of the overall structure of an insect robot automatic obstacle avoidance and trajectory recording system and method.

[0040] Figure 3 It is a schematic diagram showing the motion track recording module of the present invention.

[0041] Figure 4 It is a schematic diagram of the structure of the host computer display control unit module of the present invention.

[0042] In the figure: 1-host computer control display unit module; 2-network port data transmission; 3-industrial camera; 4-camera bracket; 5-environmental obstacles; 6-electrodes implanted in insect body parts; 7-microcontroller; 8-Madagascar cockroach insect carrier; 9-insect back fixed motherboard; 10-experimental ground platform; 11-communication transmission signal; 12-wireless communication module; 13-track recording display screen; 14-forward instruction identifier; 15-left turn instruction identifier; 16-insect robot motion trajectory; 17-right turn instruction identifier; 18-host computer real-time video stream Display screen; 19-Real-time depth map display screen of the host computer; 20-Real-time trajectory recording screen of the host computer; 21-Left turn control button; 22-Forward control button; 23-Right turn control button; 24-Store video switch button; 25-Information storage switch button; 26-Depth control switch button; 27-Stimulation signal high level duration setting option; 28-Stimulation signal low level duration setting option; 29-Stimulation signal pulse number setting option; 30-Minimum depth value of the central area; 31-Average depth value of the left area; 32-Average depth value of the right area. DETAILED DESCRIPTION

[0043] The present invention is further described in detail below with reference to the accompanying drawings and specific embodiments:

[0044] Embodiment 1:

[0045] like Figure 1 , Figure 2 As shown, an automatic obstacle avoidance and trajectory recording system for an insect robot includes an environment perception module, a depth estimation module, an obstacle avoidance decision module, a wireless communication module, a control signal generation module, an image acquisition module, a motion trajectory recording module, and a host computer control display unit module;

[0046] The depth estimation module, obstacle avoidance decision module, wireless communication module, image acquisition module, motion trajectory recording module, and upper computer control display unit module are integrated in the host; the environment perception module and the control signal generation module are integrated in the slave. The slave is a microcontroller carried on the back of the insect robot, which can be easily disassembled during non-experimental time for easy operation. At the same time, the mother row 9 is fixed on the back of the insect. The electrode 6 implanted in the insect body part is made of 0.16mm stainless steel needle with a length of 3-8mm. The mother row is connected to the corresponding stimulation part through a lead wire, and the pin row is led out from the output port of the slave. The pin row is inserted into the mother row to achieve the generation and transmission of the stimulation signal to the stimulation part.

[0047] The microcontroller 7 uses XIAO ESP32S3 produced by Seeed Studio and is powered by a 3.7V rechargeable polymer lithium battery.

[0048] The environmental perception module uses an OV2640 camera with a maximum resolution of 1600×1200. It is connected to the microcontroller through an I2C interface to collect first-person images of insects in real time. The camera is fixed at the front end of the insect's back with a field of view of 60 degrees, which can clearly capture the environmental information in front.

[0049] The depth estimation module adopts the Depth Anything V2 depth estimation model, which is lightweight and can realize real-time reasoning on the GPU. The model input is a monocular RGB image and the output is a depth map, which is visualized using the INFERNO color mapping scheme, where dark colors represent long distances and light colors represent short distances. The depth value range is 0-10.

[0050] The obstacle avoidance decision module divides the depth map into three areas: center, left and right, and formulates an obstacle avoidance strategy by comparing the depth values ​​of each area. The center area (1 / 3 width × 1 / 3 height) is used to detect the environmental obstacle 5 in front, and the left and right areas (each 1 / 2 width) are used to determine the turning direction. When the minimum depth value of the center area is greater than the obstacle judgment threshold, the system determines that there is an obstacle in front; when the difference in the average depth value of the left and right areas is greater than the turning judgment threshold, the system chooses to turn in the direction with a larger depth value.

[0051] The wireless communication module 12 realizes data transmission between various modules of the system based on the HTTP protocol, transmits video streams and control instructions through WiFi, sets a 5-second communication timeout protection mechanism, and adds a 3.5-second time interval control when sending instructions to ensure the stability of the communication transmission signal 11. It supports a disconnection reconnection mechanism and can automatically restore the communication connection.

[0052] The stimulation signal generated by the control signal generating module is a square wave pulse signal with adjustable high and low level time and pulse number, wherein the high and low level time is 10ms, a pulse cycle is 20ms, and the pulse number can be adjusted according to the state of the insect robot. It is connected to the microelectrodes pre-implanted in the insect body through four output ports to realize basic action control such as turning left, turning right, and moving forward. In addition, a ground pin is led out and implanted in the insect body.

[0053] The image acquisition module uses a MadeVision industrial camera 3, and the camera and the computer are connected via a network port data transmission 2. The Python programming language is used to obtain the original image data with a resolution of 1280×720 through the MVSDK interface. After image processing and buffer management, the data is converted into a format that can be processed by OpenCV. The industrial camera is fixed above the experimental platform through a camera bracket 4 to capture the overall motion picture of the insect robot.

[0054] The motion track recording module is as follows: Figure 3As shown, the insect robot motion trajectory 16 can be displayed through the trajectory recording display screen 13, the KCF algorithm is used to achieve target tracking, the initial tracking target is determined by mouse selection, the system automatically draws a yellow boundary box to mark the target position, and the motion trajectory is recorded with a red line. Different shapes and colors of marking symbols are used on the trajectory to represent different control instructions: a yellow triangle represents a forward instruction identifier 14, a blue cross represents a left turn instruction identifier 15, and a green diamond represents a right turn instruction identifier 17.

[0055] The host computer controls the display unit module 1 as Figure 4 As shown, the color design is developed based on the PyQt5 framework, and multi-threaded processing of different algorithms is used to improve the system response speed. The interface layout adopts a three-screen parallel display mode, which is the host computer real-time video stream display screen 18, the host computer real-time depth map display screen 19, and the host computer real-time trajectory recording screen 20. Provide manual control and depth control switch buttons 26 to realize the switching option of the automatic obstacle avoidance function, support data recording and screen saving functions, and the interface also includes a depth information display area, which displays the minimum depth value in front and the average depth value of the left and right areas in real time. The manual control options include a left turn control button 21, a forward control button 22, and a right turn control button 23, and are provided with a stimulus signal high level duration setting option 27, a stimulus signal low level duration setting option 28, and a stimulus signal pulse number setting option 29. By adjusting different setting option parameters, the corresponding control instructions are triggered to realize left and right turn and acceleration instructions. The data recording and screen saving functions are realized by setting the video storage switch button 24 and the information storage switch button 25. The information recording can record the minimum depth value 30 of the central area, the average depth 31 of the left area, and the average depth value 32 of the right area in real time. The screen saving can store three real-time pictures for the experimenters to view, analyze and optimize the control strategy.

[0056] Embodiment 2:

[0057] On the basis of the above-mentioned embodiment 1, the present invention further provides an automatic obstacle avoidance and trajectory recording method for an insect robot, which is specifically described by taking a Madagascar cockroach insect carrier 8 as an example, and specifically comprises the following steps:

[0058] Step 1: The experimenter connects the system slave to the microelectrode pre-implanted in the body of the Madagascar cockroach, places it on the experimental ground platform 10, initializes the microcontroller and camera, configures the camera parameters and establishes a WiFi connection, collects the insect's first-person perspective image through the camera interface, and transmits the image data to the host computer for display via the wireless communication module;

[0059] Step 2: For the first-person video stream, the Depth Anything V2 depth estimation model is called to generate a depth map, and the INFERNO color mapping scheme is used for visualization. The depth value in the depth map reflects the relative distance between the obstacle and the cockroach robot;

[0060] Step 3: The obstacle avoidance decision module divides the depth map into three areas: center, left, and right. It extracts the minimum depth value in the center area to determine the obstacle ahead, calculates the average depth value of the left and right areas to determine the turning direction, and generates obstacle avoidance control instructions based on the depth value comparison results.

[0061] Step 4: The control command is sent to the microcontroller through the HTTP protocol. The control signal generation module selects the corresponding output port according to the received command, generates a pulse signal with a high and low level time of 10ms, and acts on different positions of the insect body through microelectrodes to achieve basic action control such as turning left, turning right, and moving forward. The response of the cockroach to the stimulus is monitored. When the response is found to be weakened, the experimenter is prompted to adjust the stimulus parameters or change the stimulus waveform, and the stimulus fatigue is reduced by increasing the number of pulses.

[0062] Step 5: The industrial camera collects the overall motion picture of the insect robot in real time through the MVSDK interface. The image data is transmitted to the trajectory recording module after preprocessing. The KCF algorithm is used for target tracking and the target position information is updated in real time.

[0063] Step 6: The trajectory recording module draws a yellow bounding box on the image to mark the current position, uses a red line to record the motion trajectory, and marks the action position of the control command on the trajectory to establish a proportional mapping relationship between the actual position of the insect and the display interface. Each time a control command is sent, a different marking symbol is used on the trajectory to record the stimulus position, which is convenient for analyzing the control effect;

[0064] Step 7: The upper computer display control unit provides two control modes: manual and automatic. In manual mode, the experimenter can send control instructions through the interface buttons. In automatic mode, the system automatically generates obstacle avoidance instructions based on the depth information to ensure that the cockroach robot automatically avoids obstacles in the environment.

[0065] Step 8: The cockroach robot's first-person perspective image, depth map, motion trajectory, control instructions, stimulation parameters and other information can be saved and recorded for experimenters to review and analyze, providing a basis for optimizing the control strategy.

[0066] This specific implementation can be widely used in various types of insect robot control research, and can also be applied to more animal robots for more behavioral analysis and exploration. This embodiment provides an insect robot automatic obstacle avoidance and trajectory recording method and system based on a new generation of information technology (including integration technology, sensor technology, wireless communication, software technology, etc.), which provides a basic method for the development of animal robot technology, promotes the application and development of biological robot technology in a variety of complex environments, and has broad application space and development potential.

[0067] Of course, the above description is not a limitation of the present invention, and the present invention is not limited to the above examples. Changes, modifications, additions or substitutions made by technicians in this technical field within the essential scope of the present invention should also fall within the protection scope of the present invention.

Claims

1. An automatic obstacle avoidance and trajectory recording system for an insect robot, characterized in that: It includes environment perception module, depth estimation module, obstacle avoidance decision module, wireless communication module, control signal generation module, image acquisition module, motion trajectory recording module, and host computer control display unit module; The environment perception module is configured to obtain the first-person perspective image stream of the insect robot through a monocular camera installed on the microcontroller on the back of the insect, and record the environment information; A depth estimation module is configured to extract the image stream of the environment perception module, generate a real-time depth map using a deep learning algorithm, and obtain relative distance information between the insect robot and obstacles; The obstacle avoidance decision module is configured to formulate an obstacle avoidance strategy based on the depth map generated by the depth estimation module and generate corresponding control instructions; A wireless communication module is configured to realize wireless data transmission between various modules of the system to ensure the real-time transmission of instructions and data; The control signal generating module is configured to receive corresponding instructions from the wireless communication module and generate corresponding control stimulation signals. The control signal generating module is connected to four output ports of the microcontroller, and each output port is respectively connected to a microelectrode pre-implanted in the insect body; An image acquisition module is configured to use an industrial camera to capture a motion image of the insect robot and transmit the image data to a motion trajectory recording module; A motion trajectory recording module is configured to process the image provided by the image acquisition module, record the motion trajectory based on the target tracking algorithm, and mark the corresponding identifiers for different control instructions on the trajectory; The host computer control display unit module is configured to provide a human-computer interaction interface, display real-time video streams, depth maps and motion trajectory images, use communication protocols to achieve two-way data transmission between the microcontroller and the host computer, support switching between manual control and automatic obstacle avoidance functions, and set image, data, and waveform parameter storage options.

2. The automatic obstacle avoidance and trajectory recording system for insect robots according to claim 1, characterized in that: The environmental perception module is configured with a microcontroller on the back of the insect robot to access WiFi and use a camera module to obtain images, thereby enhancing the insect robot's ability to perceive the surrounding environment. The microcontroller is arranged on the back of the insect robot, and a pin header is led out from the output port of the microcontroller, and the pin header is inserted into a female header fixed on the back of the insect; The rib mother is fixed to the back of the insect through electrodes made of 0.16mm stainless steel needles with a length of 3-8mm. The rib mother is connected to its corresponding stimulation site through leads.

3. The automatic obstacle avoidance and trajectory recording system for insect robots according to claim 1, characterized in that: The depth estimation module adopts the Depth Anything V2 depth estimation model and visualizes the depth map through the INFERNO color mapping scheme. The depth value reflects the distance of the obstacle from the insect robot. The larger the depth value, the closer the obstacle is.

4. The automatic obstacle avoidance and trajectory recording system for insect robots according to claim 1, characterized in that: The obstacle avoidance decision module divides the depth map into three areas: center, left and right. The minimum depth value in the center area is extracted to judge the obstacle ahead, and the average depth value of the left and right areas is calculated to determine the turning direction. When the minimum depth value in the center area is greater than the set threshold, the system determines that there is an obstacle ahead, and chooses to turn in the direction with a larger depth value by comparing the difference in the average depth values ​​of the left and right areas.

5. The automatic obstacle avoidance and trajectory recording system for insect robots according to claim 1, characterized in that: The wireless communication module realizes two-way communication between the microcontroller and the host computer based on the HTTP protocol, transmits video streams and control instructions through WiFi, sets a 5-second communication timeout protection mechanism, and adds time interval control when sending instructions to ensure the stability of control.

6. The automatic obstacle avoidance and trajectory recording system for insect robots according to claim 1, characterized in that: The stimulation signal generated by the control signal generation module is a square wave pulse signal with adjustable high and low level time and pulse number, where the high and low level time is 10ms, a pulse cycle is 20ms, and the pulse number can be adjusted to achieve forward and steering control of the insect robot.

7. The automatic obstacle avoidance and trajectory recording system for insect robots according to claim 1, characterized in that: The image acquisition module uses industrial cameras for image acquisition and uses the Python programming language to implement image processing. It obtains the original image data of the industrial camera through the MVSDK interface. After image processing and buffer management, the data is converted into a format that can be processed by OpenCV.

8. The automatic obstacle avoidance and trajectory recording system for insect robots according to claim 1, characterized in that: The motion trajectory recording module uses the KCF algorithm to achieve target tracking. The initial tracking target is determined by selecting the mouse. The system automatically draws a yellow boundary box to mark the target position, records the motion path with a red trajectory line, and uses marking symbols of different shapes and colors on the trajectory to represent different control instructions.

9. The automatic obstacle avoidance and trajectory recording system for insect robots according to claim 1, characterized in that: The host computer control display unit module is developed based on the PyQt5 framework. It uses multi-threaded processing of different algorithms to improve the system response speed, display video streams, depth maps, motion trajectories in real time, and provides switching options for manual control and automatic obstacle avoidance functions. It supports recording interactive interface options.

10. An automatic obstacle avoidance and trajectory recording method for an insect robot, characterized in that: The automatic obstacle avoidance and trajectory recording system for insect robots as claimed in claim 1 specifically comprises the following steps: Step 1: The experimenter connects the system slave to the microelectrode pre-implanted in the insect, initializes the microcontroller and camera, configures the camera parameters and establishes a WiFi connection, collects the insect's first-person perspective image through the camera interface, and transmits the image data to the host computer for display via the wireless communication module; Step 2: For the first-person video stream, the Depth Anything V2 depth estimation model is called to generate a depth map, and the INFERNO color mapping scheme is used for visualization. The depth value in the depth map reflects the relative distance between the obstacle and the insect robot; Step 3: The obstacle avoidance decision module divides the depth map into three areas: center, left, and right. The minimum depth value in the center area is extracted to determine the obstacle ahead. The average depth value in the left and right areas is calculated to determine the steering direction. The obstacle avoidance control command is generated based on the depth value comparison threshold. Step 4: The control command is sent to the microcontroller through the HTTP protocol. The control signal generation module selects the corresponding output port according to the received command, generates a pulse signal with a high and low level time of 10ms, and acts on different positions of the insect body through microelectrodes to achieve basic action control including turning left, turning right, and moving forward. The response of the insect to the stimulus is monitored. When the response is found to be weakened, the user is prompted to adjust the stimulus parameters or change the stimulus waveform, and the stimulus fatigue is reduced by increasing the number of pulses. Step 5: The industrial camera collects the overall motion picture of the insect robot in real time through the MVSDK interface. The image data is transmitted to the trajectory recording module after preprocessing. The KCF algorithm is used for target tracking and the target position information is updated in real time. Step 6: Use the trajectory recording module to draw a yellow bounding box on the image to mark the current position, use a red line to record the motion trajectory, and mark the action position of the control command on the trajectory to establish a proportional mapping relationship between the actual position of the insect and the display interface. Each time a control command is sent, a different marking symbol is used on the trajectory to record the stimulus position, which is convenient for analyzing the control effect; Step 7: The host computer display control unit provides two control modes: manual and automatic. In manual mode, the experimenter can send control commands through the interface buttons. In automatic mode, the system automatically generates obstacle avoidance commands based on depth information to ensure the safe movement of the insect robot. Step 8: Save and record the information including the insect robot's first-person perspective image, depth map, motion trajectory, control instructions and stimulation parameters for the experimenter to review and analyze, providing a basis for optimizing the control strategy.

Images