Remote control method and system for flight attitude of unmanned aerial vehicle

Abstract

The invention discloses an unmanned aerial vehicle flight attitude remote control method and system, and relates to the technical field of unmanned aerial vehicle flight control, a myoelectric arm ring is worn on the forearm of an operator, myoelectric signals of the operator during different preset gestures are collected, the myoelectric signals are processed to obtain feature vectors, and the feature vectors are used for obtaining the flight attitude of the unmanned aerial vehicle; a plurality of feature vectors representing different gestures are combined to obtain a feature vector template, the current feature vector is compared with the feature vector template, a mapping rule table is established, the current gesture is mapped into an unmanned aerial vehicle control instruction, an unmanned aerial vehicle control signal is determined, and the unmanned aerial vehicle control signal is sent to the unmanned aerial vehicle. According to the invention, gesture electromyographic signals of an operator are acquired through the electromyographic armlet, and a multilayer signal processing technology, an innovative dual verification mechanism and an emergency gesture design are adopted, so that the limitation of a traditional remote controller in the aspects of an operation mode and environmental adaptability is broken through; and a brand-new technical solution is provided for the control of the unmanned aerial vehicle.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle (UAV) flight control, and in particular to a method and system for remotely controlling the flight attitude of an UAV. Background Art

[0002] In recent years, with the advancement of science and technology and the promotion of military needs, drone technology has developed rapidly, and drones are playing an increasingly important role in the military field. In these applications, efficient and precise remote control plays a vital role in the quality and safety of drone missions. The existing drone control methods mainly rely on remote controls, which have the disadvantages of complex operation, slow response speed and poor anti-interference ability, making it difficult to meet the needs of rapid response and precise control in complex battlefield environments.

[0003] Therefore, the present invention proposes a method and system for remotely controlling the flight attitude of an unmanned aerial vehicle. Summary of the Invention

[0004] The technical problem solved by the present invention is that the existing drone control method mainly relies on remote controls, which have the disadvantages of complex operation, slow response speed and poor anti-interference ability, making it difficult to meet the needs of rapid response and precise control in complex battlefield environments.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: a method for remotely controlling the flight attitude of an unmanned aerial vehicle, comprising: Step S1: Wearing the myoelectric armband on the operator's forearm to collect the operator's electromyographic signals when performing different preset gestures; Step S2: Processing the electromyographic signal to obtain a feature vector, and combining multiple feature vectors representing different gestures to obtain a feature vector template; Step S3, calculating the current feature vector, comparing the current feature vector with the feature vector template, and identifying the current gesture; Step S4: establishing a mapping rule table, mapping the current gesture to a drone control instruction, and determining a drone control signal according to the drone control instruction; Step S5: Before sending the drone control signal to the drone, the control command is double-verified. When an abnormal situation occurs, different emergency gestures are used according to different abnormal situations.

[0006] As a preferred solution of the method for remotely controlling the flight attitude of a UAV according to the present invention, step S1 specifically includes: Wearing a myoelectric armband on the operator's forearm, wherein the myoelectric armband includes a plurality of myoelectric sensors; The myoelectric signals of the operator performing different preset gestures on the myoelectric sensor are collected, and the different preset gestures include fist clenching, stretching, flexing fingers, relaxing, raising the wrist, pressing the wrist, and emergency gestures.

[0007] As a preferred solution of the method for remotely controlling the flight attitude of a UAV according to the present invention, step S2 specifically includes: Processing the electromyographic signal to obtain a feature vector, combining multiple feature vectors representing different gestures to obtain a feature vector template, wherein the processing includes signal cleaning and extraction processing; The signal cleaning process includes using a bandpass filter to remove noise and interference of the electromyographic signal to obtain a first electromyographic signal, and rectifying and smoothing the first electromyographic signal to obtain a second electromyographic signal; The extraction process includes extracting multiple features from the second electromyographic signal that can distinguish the different preset gestures, screening out useful features from the multiple features using a filtering method, and combining the useful features to form a feature vector, wherein the multiple features include time domain features, frequency domain features, and time-frequency features; Each preset gesture is repeatedly executed and the electromyographic signals of each repeated preset gesture are collected. The electromyographic signals of each repeated preset gesture are subjected to signal cleaning and extraction processing to obtain multiple feature vectors representing different gestures. The multiple feature vectors representing different gestures constitute a feature vector template.

[0008] As a preferred solution of the method for remotely controlling the flight attitude of a UAV according to the present invention, step S3 specifically includes: The current electromyographic signal is collected, the signal cleaning process and the extraction process are performed on the current electromyographic signal, a current feature vector is determined, the current feature vector is compared with a feature vector template, and the current gesture is recognized.

[0009] As a preferred solution of the method for remotely controlling the flight attitude of a UAV according to the present invention, the comparison specifically includes: A similarity measurement method is used to calculate the similarity between the current feature vector and the feature vector template. If the similarity is greater than or equal to a first threshold, the gesture corresponding to the feature vector template is the current gesture.

[0010] As a preferred solution of the method for remotely controlling the flight attitude of a drone according to the present invention, step S4 specifically includes: A mapping rule table is established according to different preset gestures, wherein the mapping rule table includes a fist corresponding to a drone take-off command, a stretching corresponding to a drone landing command, a finger bending corresponding to a drone left flight command, a relaxation corresponding to a drone right flight command, a wrist raising corresponding to a drone acceleration command, a wrist pressing corresponding to a drone deceleration command, and an emergency gesture corresponding to a drone preset safety command. The current gesture is mapped to a drone control command, and the drone control signal is determined according to the drone control command.

[0011] As a preferred solution of the method for remotely controlling the flight attitude of a drone according to the present invention, step S5 specifically includes: Before sending the drone control signal to the drone, the control command is double-verified. The double verification includes the initial verification of the control command and the secondary confirmation of the control command. When an abnormal situation occurs, different emergency gestures are used according to different abnormal situations. When the operator performs the emergency gesture, the drone immediately executes the preset safety instructions. The different abnormal situations include the drone needing to make an emergency landing, the drone needing to hover urgently, the drone's GPS signal being lost, and the drone's low battery warning.

[0012] As a preferred solution of the method for remotely controlling the flight attitude of a UAV according to the present invention, the control instruction initial verification and control instruction secondary confirmation specifically include: Control command initial verification: Verify whether the control command corresponds to the gesture in the mapping rule table and whether the control command matches the current state of the drone, including flight mode, flight altitude, and drone battery level. If the control command passes the initial verification, the control command will be confirmed again. Second confirmation of control instructions: For key control instructions, the operator performs the preset gesture again after performing the preset gesture.

[0013] As a preferred solution of the method for remotely controlling the flight attitude of a drone according to the present invention, the method of using different emergency gestures according to different abnormal situations specifically includes: Drone needs to make an emergency landing: Clench your fist twice in quick succession; The drone needs to hover urgently: quickly cross your arms over your chest; Drone GPS signal lost: Open your five fingers and quickly make a fist; Drone low battery warning: Lay your hand flat and quickly press your wrist down.

[0014] A remote control system for the flight attitude of an unmanned aerial vehicle (UAV), which is applied to the remote control method for the flight attitude of an UAV, comprises a signal acquisition module, a signal processing module, a gesture recognition module, a control instruction conversion module and a safety assurance module; The acquisition module is used to wear the myoelectric armband on the operator's forearm and collect the operator's myoelectric signals when performing different preset gestures; The signal processing module is used to process the electromyographic signal to obtain a feature vector, and combine multiple feature vectors representing different gestures to obtain a feature vector template; The gesture recognition module is used to calculate the current feature vector, compare the current feature vector with the feature vector template, and recognize the current gesture; The control instruction conversion module is used to establish a mapping rule table, map the current gesture into a drone control instruction, and determine the drone control signal according to the drone control instruction; The safety assurance module is used to perform double verification on the control command before sending the drone control signal to the drone. When an abnormal situation occurs, different emergency gestures are adopted according to different abnormal situations.

[0015] The beneficial effects of the present invention are as follows: the present invention collects the operator's gesture and electromyographic signals through the myoelectric armband, and directly maps natural gesture movements into drone control instructions, realizing an intuitive and natural control method and lowering the operation threshold. The system adopts multi-layer signal processing technology, which greatly improves the accuracy and adaptability of gesture recognition. The innovative dual verification mechanism and emergency gesture design effectively ensure the safety of flight control and can reliably respond to various emergencies. The modular system architecture design enhances functional scalability. The present invention has excellent anti-interference ability and real-time response characteristics, and can be applied to complex scenarios of military operations and emergency rescue. It breaks through the limitations of traditional remote controls in operation methods and environmental adaptability, and provides a new technical solution for drone control. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic flow chart of the steps of a method for remotely controlling the flight attitude of an unmanned aerial vehicle (UAV) provided by one embodiment of the present invention.

[0017] Figure 2 A schematic diagram of the basic flow of a remote control system for the flight attitude of an unmanned aerial vehicle provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0019] Example 1, with reference to Figure 1 , as one embodiment of the present invention, provides a method for remotely controlling the flight attitude of a UAV, comprising: Step S1: Wear the myoelectric armband on the operator's forearm to collect the operator's electromyographic signals when performing different preset gestures.

[0020] Step S2: Process the electromyographic signal to obtain a feature vector, and combine multiple feature vectors representing different gestures to obtain a feature vector template.

[0021] Step S3: Calculate the current feature vector, compare the current feature vector with the feature vector template, and recognize the current gesture.

[0022] Step S4: Establish a mapping rule table, map the current gesture to a drone control instruction, and determine the drone control signal according to the drone control instruction.

[0023] Step S5: Before sending the drone control signal to the drone, the control command is double-verified. When an abnormal situation occurs, different emergency gestures are used according to different abnormal situations.

[0024] Step S1 specifically includes: The myoelectric armband is worn on the operator's forearm and includes multiple myoelectric sensors.

[0025] The myoelectric signals of the operator when performing different preset gestures on the myoelectric sensor are collected. The different preset gestures include fist clenching, stretching, finger flexion, relaxation, wrist raising, wrist pressing and emergency gestures.

[0026] The collection method and content of electromyographic signals were clarified, laying the foundation for subsequent gesture recognition and drone control.

[0027] Step S2 specifically includes: The electromyographic signal is processed to obtain a feature vector, and multiple feature vectors representing different gestures are combined to obtain a feature vector template. The processing includes signal cleaning and extraction.

[0028] The signal cleaning process includes using a bandpass filter to remove noise and interference from the electromyographic signal to obtain a first electromyographic signal, and rectifying and smoothing the first electromyographic signal to obtain a second electromyographic signal.

[0029] Converting electromyographic signals into stable and recognizable second electromyographic signals lays the foundation for feature extraction.

[0030] The extraction process includes extracting multiple features from the second electromyographic signal that can distinguish different preset gestures, using a filtering method to screen out useful features of the multiple features, and combining the useful features to form a feature vector. The multiple features include time domain features, frequency domain features, and time-frequency features.

[0031] Each preset gesture is repeatedly executed and the electromyographic signal of each repeated preset gesture is collected. The electromyographic signal of each repeated preset gesture is subjected to signal cleaning and extraction processing to obtain multiple feature vectors representing different gestures. The multiple feature vectors representing different gestures constitute a feature vector template.

[0032] Repeating each preset gesture and collecting the electromyographic signals of each repeated preset gesture can obtain richer data, reduce recognition errors caused by individual differences and environmental noise factors, and improve the robustness and generalization ability of the feature vector template. Signal cleaning and extraction processing of the electromyographic signals of each repeated preset gesture can ensure that the feature vectors in the feature vector template can accurately reflect the characteristics of different gestures, thereby improving the accuracy of gesture recognition.

[0033] Step S3 specifically includes: Collect the current electromyographic signal, perform signal cleaning and extraction processing on the current electromyographic signal, determine the current feature vector, compare the current feature vector with the feature vector template, and recognize the current gesture.

[0034] The current feature vector is compared with the feature vector template to find the best matching feature vector, thereby identifying the operator's current gesture and realizing real-time interpretation of the drone control instructions, ensuring that the system can respond to the operator's gesture instructions quickly and accurately, and improving the flexibility and reliability of drone control.

[0035] The comparison specifically includes: A similarity measurement method is used to calculate the similarity between the current feature vector and the feature vector template. If the similarity is greater than or equal to a first threshold, the gesture corresponding to the feature vector template is the current gesture.

[0036] Step S4 specifically includes: A mapping rule table is established based on different preset gestures. The mapping rule table includes fist clenching corresponding to the drone take-off command, stretching corresponding to the drone landing command, bending the fingers corresponding to the drone left flight command, relaxing corresponding to the drone right flight command, raising the wrist corresponding to the drone acceleration command, pressing the wrist corresponding to the drone deceleration command, and emergency gestures corresponding to the drone preset safety command. The current gesture is mapped to the drone control command, and the drone control signal is determined according to the drone control command.

[0037] A mapping rule table is established according to different preset gestures, which establishes a clear connection between gestures and drone control instructions, laying the foundation for subsequent gesture control. The current gesture is mapped to the drone control instruction, realizing the conversion from gesture recognition results to specific drone control instructions. It is a key link in the process of gesture control of drones. The operator can achieve precise control of the drone through simple gestures, which improves the convenience and flexibility of drone operation, and enables the drone to quickly respond to the operator's intentions and perform various complex flight missions.

[0038] Step S5 specifically includes: Before sending the drone control signal to the drone, the control command is double-verified. The double verification includes the initial verification of the control command and the secondary confirmation of the control command. When an abnormal situation occurs, different emergency gestures are used according to different abnormal situations. When the operator performs the emergency gesture, the drone immediately executes the preset safety instructions. Different abnormal situations include the drone needing to make an emergency landing, the drone needing to hover urgently, the drone's GPS signal lost, and the drone's low battery warning.

[0039] Double verification of control commands significantly improves the reliability and safety of drone operations through a multi-level security mechanism. It not only effectively avoids the risks brought by misoperation and abnormal situations, but also enables rapid response in emergency situations, thereby providing drones with more stable and safe flight guarantees.

[0040] The initial verification and secondary confirmation of control instructions specifically include: Initial verification of control commands: Verify whether the control commands correspond to the gestures in the mapping rule table and whether the control commands match the current state of the drone. The state includes flight mode, flight altitude, and drone battery level. If the control commands pass the initial verification, a second confirmation of the control commands will be performed.

[0041] Confirm whether the control command corresponds to the gesture in the preset mapping rule table to prevent the input of invalid or erroneous commands, and verify whether the control command matches the current flight status of the drone, including flight mode, flight altitude and drone power. Only when the control command successfully passes the initial verification will it enter the next step of the control command secondary confirmation link.

[0042] Second confirmation of control instructions: For key control instructions, the operator performs the preset gesture again after performing the preset gesture.

[0043] After the operator issues a preset gesture, he must repeat the same preset gesture again for secondary confirmation, which further improves the safety and reliability of drone control.

[0044] Different emergency gestures are used according to different abnormal situations, including: Drone needs to make an emergency landing: Clench your fist twice in rapid succession.

[0045] Drones need to perform emergency landings when they encounter collision risks, suffer serious system failures, enter no-fly zones, encounter drastic weather changes, or receive emergency landing instructions. This can maximize the safety of the drone and its surroundings and avoid accidents.

[0046] The drone needs to hover urgently: quickly cross your arms over your chest.

[0047] The drone needs to perform emergency hovering in the early stages when it encounters a temporary obstacle, encounters signal interference, the operator needs to make temporary adjustments, and there is a low battery warning. This can help the drone to briefly stop and reassess the flight status and surrounding environment while ensuring safety, and then continue flying when conditions permit.

[0048] Drone GPS signal lost: Open your five fingers and quickly make a fist.

[0049] Trigger the drone to execute pre-set safety procedures to ensure that the drone can respond safely even if it loses its positioning.

[0050] Drone low battery warning: Lay your hand flat and quickly press your wrist down.

[0051] Guide the drone to perform preset safety operations based on the remaining power, avoiding drone crashes due to power exhaustion and ensuring flight safety.

[0052] Through these clear emergency gestures, operators can respond quickly in emergency situations, guide the drone into a safe state, effectively avoid potential dangers, and improve the safety and reliability of drone flight.

[0053] Example 2, reference Figure 2 The present invention provides a remote control system for the flight attitude of an unmanned aerial vehicle, which includes a signal acquisition module, a signal processing module, a gesture recognition module, a control instruction conversion module and a safety assurance module.

[0054] The acquisition module is used to wear the myoelectric armband on the operator's forearm and collect the operator's electromyographic signals when making different preset gestures.

[0055] The signal processing module is used to process the electromyographic signal to obtain a feature vector, and combine multiple feature vectors representing different gestures to obtain a feature vector template.

[0056] The gesture recognition module is used to calculate the current feature vector, compare the current feature vector with the feature vector template, and recognize the current gesture.

[0057] The control instruction conversion module is used to establish a mapping rule table, map the current gesture into a drone control instruction, and determine the drone control signal according to the drone control instruction.

[0058] The safety assurance module is used to double-verify the control instructions before sending the drone control signal to the drone. When an abnormal situation occurs, different emergency gestures are used according to different abnormal situations.

[0059] The present invention collects the operator's gesture and electromyographic signals through a myoelectric armband, and directly maps natural gesture movements into drone control commands, achieving an intuitive and natural control method and lowering the operating threshold. The system adopts multi-layer signal processing technology to greatly improve the accuracy and adaptability of gesture recognition. The innovative dual verification mechanism and emergency gesture design effectively ensure the safety of flight control and can reliably respond to various emergencies. The modular system architecture design enhances functional scalability. The present invention has excellent anti-interference ability and real-time response characteristics, and can be applied to complex scenarios of military operations and emergency rescue. It breaks through the limitations of traditional remote controls in operation methods and environmental adaptability, and provides a new technical solution for drone control.

[0060] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. The storage medium may be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0061] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A remote control method for the flight attitude of an unmanned aerial vehicle, characterized in that: include: Step S1: Wearing the myoelectric armband on the operator's forearm to collect the operator's electromyographic signals when performing different preset gestures; Step S2: Processing the electromyographic signal to obtain a feature vector, and combining multiple feature vectors representing different gestures to obtain a feature vector template; Step S3, calculating the current feature vector, comparing the current feature vector with the feature vector template, and identifying the current gesture; Step S4: establishing a mapping rule table, mapping the current gesture to a drone control instruction, and determining a drone control signal according to the drone control instruction; Step S5: Before sending the drone control signal to the drone, the control command is double-verified. When an abnormal situation occurs, different emergency gestures are used according to different abnormal situations.

2. The method for remotely controlling the flight attitude of an unmanned aerial vehicle according to claim 1, wherein: The step S1 specifically includes: Wearing a myoelectric armband on the operator's forearm, wherein the myoelectric armband includes a plurality of myoelectric sensors; The myoelectric signals of the operator performing different preset gestures on the myoelectric sensor are collected, and the different preset gestures include fist clenching, stretching, flexing fingers, relaxing, raising the wrist, pressing the wrist, and emergency gestures.

3. The method for remotely controlling the flight attitude of an unmanned aerial vehicle according to claim 1, wherein: The step S2 specifically includes: Processing the electromyographic signal to obtain a feature vector, and combining multiple feature vectors representing different gestures to obtain a feature vector template, wherein the processing includes signal cleaning and extraction processing; The signal cleaning process includes using a bandpass filter to remove noise and interference of the electromyographic signal to obtain a first electromyographic signal, and rectifying and smoothing the first electromyographic signal to obtain a second electromyographic signal; The extraction process includes extracting multiple features from the second electromyographic signal that can distinguish the different preset gestures, screening out useful features from the multiple features using a filtering method, and combining the useful features to form a feature vector, wherein the multiple features include time domain features, frequency domain features, and time-frequency features; Each preset gesture is repeatedly executed and the electromyographic signals of each repeated preset gesture are collected. The electromyographic signals of each repeated preset gesture are subjected to signal cleaning and extraction processing to obtain multiple feature vectors representing different gestures. The multiple feature vectors representing different gestures constitute a feature vector template.

4. The method for remotely controlling the flight attitude of an unmanned aerial vehicle according to claim 3, wherein: The step S3 specifically includes: The current electromyographic signal is collected, the signal cleaning process and the extraction process are performed on the current electromyographic signal, a current feature vector is determined, the current feature vector is compared with a feature vector template, and the current gesture is recognized.

5. The method for remotely controlling the flight attitude of an unmanned aerial vehicle according to claim 4, wherein: The comparison specifically includes: A similarity measurement method is used to calculate the similarity between the current feature vector and the feature vector template. If the similarity is greater than or equal to a first threshold, the gesture corresponding to the feature vector template is the current gesture.

6. The method for remotely controlling the flight attitude of an unmanned aerial vehicle according to claim 1, wherein: The step S4 specifically includes: A mapping rule table is established according to different preset gestures, wherein the mapping rule table includes a fist corresponding to a drone take-off command, a stretching corresponding to a drone landing command, a finger bending corresponding to a drone left flight command, a relaxation corresponding to a drone right flight command, a wrist raising corresponding to a drone acceleration command, a wrist pressing corresponding to a drone deceleration command, and an emergency gesture corresponding to a drone preset safety command. The current gesture is mapped to a drone control command, and the drone control signal is determined according to the drone control command.

7. The method for remotely controlling the flight attitude of an unmanned aerial vehicle according to claim 1, wherein: The step S5 specifically includes: Before sending the drone control signal to the drone, the control command is double-verified. The double verification includes the initial verification of the control command and the secondary confirmation of the control command. When an abnormal situation occurs, different emergency gestures are used according to different abnormal situations. When the operator performs the emergency gesture, the drone immediately executes the preset safety instructions. The different abnormal situations include the drone needing to make an emergency landing, the drone needing to hover urgently, the drone's GPS signal being lost, and the drone's low battery warning.

8. The method for remotely controlling the flight attitude of an unmanned aerial vehicle according to claim 6, wherein: The control instruction initial verification and control instruction secondary confirmation specifically include: Control command initial verification: Verify whether the control command corresponds to the gesture in the mapping rule table and whether the control command matches the current state of the drone, including flight mode, flight altitude, and drone battery level. If the control command passes the initial verification, the control command will be confirmed again. Second confirmation of control instructions: For key control instructions, the operator performs the preset gesture again after performing the preset gesture.

9. The method for remotely controlling the flight attitude of an unmanned aerial vehicle according to claim 1, wherein: The use of different emergency gestures according to different abnormal situations specifically includes: Drone needs to make an emergency landing: Clench your fist twice in quick succession; The drone needs to hover urgently: quickly cross your arms over your chest; Drone GPS signal lost: Open your five fingers and quickly make a fist; Drone low battery warning: Lay your hand flat and quickly press your wrist down.

10. A remote control system for the flight attitude of an unmanned aerial vehicle, which is applied to a remote control method for the flight attitude of an unmanned aerial vehicle according to any one of claims 1 to 9, characterized in that: It includes signal acquisition module, signal processing module, gesture recognition module, control instruction conversion module and safety assurance module; The acquisition module is used to wear the myoelectric armband on the operator's forearm and collect the operator's myoelectric signals when performing different preset gestures; The signal processing module is used to process the electromyographic signal to obtain a feature vector, and combine multiple feature vectors representing different gestures to obtain a feature vector template; The gesture recognition module is used to calculate the current feature vector, compare the current feature vector with the feature vector template, and recognize the current gesture; The control instruction conversion module is used to establish a mapping rule table, map the current gesture into a drone control instruction, and determine the drone control signal according to the drone control instruction; The safety assurance module is used to perform double verification on the control command before sending the drone control signal to the drone. When an abnormal situation occurs, different emergency gestures are adopted according to different abnormal situations.

Images