Description:DESCRIPTION:
Field of the invention:
[0001] The present disclosure generally relates to the technical field of unmanned aerial vehicles (UAVs), and in specific, relates to a system and method for real-time operation, navigation, and gyroscope stabilization of unmanned aerial vehicles (UAVs) using hand gesture recognition, thereby leveraging multidisciplinary applications in aerial photography, surveillance, emergency response, and educational platforms.
Background of the invention:
[0002] Unmanned aerial vehicles (UAVs) commonly referred to as drones, have emerged as critical tools across diverse applications, including aerial photography, surveillance, disaster management, and infrastructure inspection. These systems excel in accessing remote or hazardous locations and collecting real-time data, making them invaluable in modern technological ecosystems. However, conventional drone control interfaces, such as joysticks, smartphone applications, or GPS-based waypoint navigation. These methods demand extensive hand-eye coordination and training, which might be prohibitive for novice users or in high-pressure, time-critical scenarios like search-and-rescue missions and live event coverage. The complexity of these interfaces often leads to operational inefficiencies, as users must dedicate substantial cognitive effort to mastering control mechanisms. Furthermore, the reliance on physical controllers and touch-based apps might be impractical in dynamic environments, underscoring the need for more intuitive, user-friendly control solutions to enhance accessibility and operational effectiveness.
[0003] Existing gesture-based control systems adapted to address some of these challenges, have their own limitations that hinder widespread adoption. Camera-based gesture recognition systems, such as those utilizing OpenCV or Media Pipe, are highly sensitive to environmental conditions, including variations in lighting, background motion, and weather phenomena like rain and fog. These systems often fail outdoors and in uncontrolled settings, thereby reducing their reliability for real-world applications. Alternatively, Inertial Measurement Unit (IMU)-based gesture systems, which rely on wearable sensors, are susceptible to magnetic interference and unintended body movements, which leads to inaccurate gesture detection. Both approaches struggle with limited gesture vocabularies, typically recognizing only 5 to 10 commands, which restricts the complexity of user interactions. Additionally, latency in wireless communication, such as Wi-Fi modules like ESP8266 or ESP32, introduces delays in command transmission, compromising drone responsiveness and stability, particularly in mission-critical contexts.
[0004] The prior art includes several patents and research efforts that address aspects of drone stabilization and control but fall short of a comprehensive solution. For instance, patent US20100012790A1 describes gyro-stabilized aerial vehicles that utilize onboard gyroscopic sensors to maintain flight stability by adjusting motor outputs to counter angular deviations. Similarly, EP3619112B1 outlines a networked drone system leveraging IMU data and visual feedback for stabilization and coordination. Research includes gyroscopes and accelerometers, by achieving precise orientation control under environmental disturbances such as wind or motor vibrations. However, these systems focus on flight stability and do not integrate intuitive control interfaces such as gesture recognition. The lack of seamless integration between stabilization and user-friendly control mechanisms limits their ability to address the usability challenges faced by both novice and experienced operators.
[0005] Gesture recognition for drone control has been explored in academic research and patented systems, yet significant gaps remain. The feasibility of real-time hand gesture recognition using wearable IMU-based systems and computer vision techniques, enhanced by deep learning models include convolutional neural networks (CNNs) and long short-term memory (LSTM) networks. A prior art, US20200039646A1 describes a modular flying system with wireless control supporting gesture inputs, highlighting industrial interest in contactless interfaces. However, the system often operates in isolation, focusing on either gesture recognition or stabilization without combining them into a cohesive platform. Environmental sensitivity, limited command sets, and latency issues continue to plague these solutions, reducing their effectiveness in dynamic and outdoor settings. Moreover, the absence of context-aware control modes in existing systems restricts their adaptability to diverse operational scenarios, such as switching between manual and autonomous modes.
[0006] In existing technology, a glove-type unmanned aerial vehicle (UAV) remote control device is adapted to solve the issues of two-handed operation, and difficulty in prolonged use. The device comprises a glove and a control circuit board mounted on a back of the hand, an LCD screen mounted at a top of the control circuit board and connected via a flexible printed circuit (FPC) winding displacement to the LCD screen at the bottom. The glove integrates a gyroscope chip that captures hand gestures, enabling simplified, one-handed UAV control. The glove is in compact design and reduces device size and operational strain, allowing users to control the UAV while freeing the other hand. Additionally, the system might detect the relative position between the UAV and the glove, enabling intuitive control and synchronized movement, thereby enhancing usability, portability, and precision in UAV operations. However, the device might require skilled person to effectively control the UAV. Moreover, the device could be affected by certain environmental conditions.
[0007] Therefore, there is a need for a system and method for real-time operation, navigation, and gyroscope stabilization of unmanned aerial vehicles (UAVs) using hand gesture recognition, thereby leveraging multidisciplinary applications in aerial photography, surveillance, emergency response, and educational platforms. There is also a need for a system that combines multi-domain technologies, including embedded systems, wireless communication, and machine learning, to deliver a seamless user experience. Furthermore, there is also a need for a system that enables hands-free control through hand gesture recognition, eliminating the need for complex joysticks and smartphone applications.
Objectives of the invention:
[0008] The primary objective of the present invention is to provide a system and method for real-time operation, navigation, and gyroscope stabilization of unmanned aerial vehicles (UAVs) using hand gesture recognition, thereby leveraging multidisciplinary applications in aerial photography, surveillance, emergency response, and educational platforms.
[0009] Another objective of the present invention is to provide a system that enables hands-free control through hand gesture recognition, thereby eliminating the need for complex joysticks and smartphone applications and making it accessible to non-expert users, including beginners, solo travelers, vloggers, and content creators.
[0010] Another objective of the present invention is to provide a system that is integrated with inertial measurement unit (IMU)-based and camera-based gesture recognition, thereby ensuring reliable performance across diverse environments.
[0011] Another objective of the present invention is to provide a system that utilizes MPU6050 sensor and PID-tuned controller to maintain UAV balance even under external disturbances like wind and motor vibrations, thereby ensuring smooth and precise flight, outperforming many commercial quadcopters that rely solely on IMUs.
[0012] Another objective of the present invention is to provide a system that offers seamless switching between gesture-based, manual, and semi-autonomous modes via the mobile application, thereby providing flexibility to the UAV to adapt to different scenarios, such as reverting to manual control in high-risk areas or using gesture mode for aerial photography, enhancing operational versatility compared to rigid control systems.
[0013] Another objective of the present invention is to provide a system that monitors real-time data on gesture recognition accuracy, UAV orientation, battery status, and media streaming through the mobile applications.
[0014] Another objective of the present invention is to provide a system that is cost-effective with MPU6050, ESP32 and open-source PX4 firmware, making it ideal for students, researchers, and DIY developers, offering performance comparable to high-end systems at a fraction of the cost.
[0015] Another objective of the present invention is to provide a system that is energy-aware PID tuning and smart power distribution, optimizing flight time (12–30 min with a 3000 mAh LiPo battery) without compromising responsiveness, thereby improving battery life in power-intensive UAV.
[0016] Yet another objective of the present invention is to provide a system that automatically stores photos and videos directly on the mobile app, eliminating the need for external memory cards and reducing the risk of data loss.
[0017] Further objective of the present invention is to provide a system that serves as a teaching tool for embedded systems, control theory, AI/ML (gesture detection), and wireless communication.
Summary of the invention:
[0018] The present disclosure proposes system and method for controlling unmanned aerial vehicle with hand gesture recognition and gyroscope stabilization. The following presents a simplified summary in order to provide a basic understanding of some aspects of the claimed subject matter. This summary is not an extensive overview. It is not intended to identify key/critical elements or to delineate the scope of the claimed subject matter. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is presented later.
[0019] In order to overcome the above deficiencies of the prior art, the present disclosure is to solve the technical problem to provide a system and method for real-time operation, navigation, and stabilization of Unmanned aerial vehicles (UAVs) using hand gesture recognition, thereby leveraging multidisciplinary applications in aerial photography, surveillance, emergency response, and educational platforms.
[0020] According to one aspect, the invention provides a system for real-time operation of unmanned aerial vehicles (UAVs) using hand gesture recognition. In one embodiment herein, the system comprises a computing device and a wearable hand gesture device. Additionally, the computing device having a processor and a memory for storing one or more instructions executed by the processor. The computing device is configured to communicate with a server via a network. The processor is configured to execute plurality of modules for performing multiple operations. The plurality of modules comprises a registration module, a communication module, and a display unit.
[0021] The registration module is configured to allow users to register for accessing the system for controlling operational parameters of the UAVs. The communication module is configured to initiate and manage bidirectional wireless communication between the computing device and the UAV, respectively, via the network, thereby enabling transmission of control signals for controlling the operational parameters.
[0022] In one embodiment herein, the display unit is configured to facilitate the user to control the respective UAV while monitoring real-time telemetry data includes UAV orientation, battery status, and gesture recognition accuracy, thereby facilitating dynamic switching between manual remote control (RC), semi-autonomous, and fully gesture-based operation modes for adaptive UAV operation. Additionally, the display unit is configured to enable the real-time display of telemetry data and customizable gesture-to-command mappings with the UAV, thereby enabling user-defined control over UAV’s operations, includes media initiation and aerial maneuvers.
[0023] In one embodiment herein, the UAV comprises a gyroscopic sensor, plurality of driving units, a controller, at least two capturing units, and a receiver. The gyroscopic sensor includes a 6-axis motion-tracking sensor that detects orientation data and angular velocity during flight of the UAV. The plurality of driving units is configured to provide a precise vector thrust and maneuverability. In one embodiment herein, the plurality of driving units is integrated with electronic speed controllers (ESCs) that are configured to execute control signals from the flight controller within millisecond-scale response times, thereby enabling precise and rapid modulation of thrust for executing complex maneuvers, includes stable hovering, directional transitions, and mid-air flips.
[0024] In one embodiment herein, the controller is configured to process the orientation data received from the gyroscopic sensor in real-time and dynamically adjust the speed of the plurality of driving units for stable flight under external disturbances. Additionally, the controller is configured to execute auto-tuning algorithms that dynamically adjust proportional, integral, and derivative parameters based on the UAV’s dynamics and the performance of the plurality of driving units, thereby ensuring stable flight under various environmental conditions.
[0025] The at least two capturing units are configured to capture high-resolution visual data in multiple directions and transmit it to the computing device for real-time navigation and user feedback. The receiver is configured to receive gesture-based control signals from the wearable hand gesture device and decode the control signals to the controller, which analyzes the gesture commands to facilitate real-time control of the UAV functions include navigation, stability management, activation of the at least two capturing units, and autonomous mode selection.
[0026] In one embodiment herein, the wearable hand gesture device is configured to worm by a user’s hand to generate multiple-gesture movements to control the UAV. The wearable hand gesture device comprises an inertial measurement unit (IMU), a processing unit, and a transmitter. The IMU is configured to detect hand movements and generate gesture data.
[0027] The processing unit is configured to analyze the gesture data received from the IMU and classify gestures using machine learning models, thereby enabling gesture-based control signals for navigation and controlling the UAV. The transmitter is configured to broadcast the classified gesture-based control signals to the computing device, enabling non-contact user interaction and precise control of the UAV under various environmental conditions.
[0028] In one embodiment herein, the wearable hand gesture device is configured to perform feature extraction and gesture classification from the hand movements using the machine learning models include a convolutional neural network (CNN), thereby achieving gesture recognition accurately in indoor environments.
[0029] In one embodiment herein, the computing device is configured to control and manage the at least two capturing units for capturing images and videos, real-time streaming, and gesture detection, thereby facilitating low-latency visual feedback for enhanced user interaction and navigation.
[0030] In another embodiment herein, the computing device is configured to automatically transmit and store captured image and video data to the server in real-time, thereby enabling immediate access for remote viewing and sharing, while eliminating the necessity for external memory storage media. Additionally, the computing device includes at least one of mobile, laptop, tablet, and personal digital assistant (PDA), each having wireless communication capability and user interface support for control and monitoring of the UAV.
[0031] Further, objects and advantages of the present invention will be apparent from a study of the following portion of the specification, the claims, and the attached drawings.
Detailed description of drawings:
[0032] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate an embodiment of the invention, and, together with the description, explain the principles of the invention.
[0033] FIG. 1 illustrates a block diagram of a system for real-time operation of an unmanned aerial vehicle (UAV) using hand gesture recognition, in accordance to an exemplary embodiment of the invention.
[0034] FIG. 2 illustrates a block diagram of a proportional-integral-derivative (PID) tuning plurality of driving units, in accordance to an exemplary embodiment of the invention.
[0035] FIG. 3 illustrates a schematic view of a wearable hand gesture device with multiple-gesture movements, in accordance to an exemplary embodiment of the invention.
[0036] FIG. 4 illustrates a schematic view of the UAV, in accordance to an exemplary embodiment of the invention.
[0037] FIG. 5 illustrate screenshots of a signal transmission to capture pulse waveforms from a transmitter and a receiver, in accordance to an exemplary embodiment of the invention.
[0038] FIG. 6 illustrates a pictorial representation of at least two capturing units that are adapted to provide real-time visual, in accordance to an exemplary embodiment of the invention.
[0039] FIG. 7A illustrates a graphical representation of battery charge, discharge, and flight time variations, in accordance to an exemplary embodiment of the invention.
[0040] FIG. 7B illustrates a graphical representation of the battery capacity and a flight time, in accordance to an exemplary embodiment of the invention.
[0041] FIG. 7C illustrates a graphical representation of battery charging time and current, in accordance to an exemplary embodiment of the invention.
[0042] FIG. 7D illustrates a graphical representation of battery discharge time and current, in accordance to an exemplary embodiment of the invention.
Detailed invention disclosure:
[0043] Various embodiments of the present invention will be described in reference to the accompanying drawings. Wherever possible, same or similar reference numerals are used in the drawings and the description to refer to the same or like parts or steps.
[0044] The present disclosure has been made with a view towards solving the problem with the prior art described above, and it is an object of the present invention to provide a system 100 and method for real-time operation, navigation, and stabilization of Unmanned aerial vehicles (UAVs) 101 using hand gesture recognition, thereby leveraging multidisciplinary applications in aerial photography, surveillance, emergency response, and educational platforms.
[0045] According to one exemplary embodiment of the invention, FIG. 1 refers to a block diagram of the system 100 for real-time operation of the UAV 101 using hand gesture recognition. In one embodiment herein, the system 100 serves as a teaching tool for embedded systems, control theory, AI/ML (gesture detection), and wireless communication. The system 100 enables hands-free control through hand gesture recognition, thereby eliminating the need for complex joysticks and smartphone applications and making it accessible to non-expert users, including beginners, solo travelers, vloggers, and content creators. In another embodiment herein, the system 100 comprises a computing device 102, the UAV 101, and a wearable hand gesture device 118, which are communicates via a network 112 to facilitate gesture-based drone control and media functionality.
[0046] In one embodiment herein, the computing device 102 having a processor 104 and a memory 106 for storing one or more instructions executed by the processor 104. The computing device 102 is configured to communicate with a server 117 via a network 112.The processor 104 is configured to execute plurality of modules 108 for performing multiple operations. The plurality of modules 108 comprises a registration module 110, a communication module 114, and a display unit 116. In one embodiment herein, the registration module 110 is configured to allow users to register for accessing the system 100 for controlling operational parameters of the UAVs 101. The communication module 114 is configured to initiate and mange bidirectional wireless communication between the computing device 102 and the UAV 101, respectively, via the network 112, thereby enabling transmission of control signals for controlling the operational parameters.
[0047] In one embodiment herein, the display unit 116 is configured to facilitate the user to control the respective UAV 110 while monitoring real-time telemetry data includes UAV orientation, battery status, and gesture recognition accuracy, thereby facilitating dynamic switching between manual remote control (RC), semi-autonomous, and fully gesture-based operation modes for adaptive UAV operation. Additionally, the UAV 101 comprises a gyroscopic sensor 120, plurality of driving units 122, a controller 124, at least two capturing units 126, and a receiver 128.
[0048] The gyroscopic sensor 120 including a 6-axis motion-tracking sensor that detects orientation data and angular velocity during flight of the UAV 101. The plurality of driving units 122 is configured to provide accurate vector thrust and manoeuvrability for responsive flight control. The controller 124 incorporating a proportional-integral-derivative (PID) controller, which processes orientation data received from the gyroscopic sensor 120 in real-time and dynamically adjust speed of the plurality of driving units 122 for stable flight under external disturbances. The at least two capturing units 126 are configured to capture high-resolution visual data from multiple directions and transmit it to the computing device 102 for real-time navigation and user feedback.
[0049] Additionally, the receiver 128 is configured to receive gesture-based control signals from the wearable hand gesture device 118 and decode the control signals to the controller 124, which analyze the gesture commands to facilitate real-time control of the UAV 101 functions include navigation, stability management, activation of the at least two capturing units 126, and autonomous mode selection. In one embodiment herein, the wearable hand gesture device 118 is configured to be worn on the user’s hand to generate multiple-gesture movements to control the UAV 101. This device enables hands-free control of the UAV 101 through gesture recognition. The wearable hand gesture device 118 comprises an inertial measurement unit (IMU) 130, a processing unit 132, and a transmitter 134. The IMU 130 is configured to detect hand movements and generate gesture data.
[0050] The processing unit 132 is configured to analyze the gesture data received from the IMU 130 and classify gestures using machine learning models, thereby enabling gesture-based control signals for navigation and controlling of the UAV 101. The transmitter 134 is configured to broadcast the classified gesture-based control signals to the computing device 102, enabling non-contact user interaction and precise control of the UAV 101 under various environmental conditions. In one embodiment, the wearable hand gesture device 118 is configured to perform feature extraction and gesture classification from the hand movements using the machine learning models include a convolutional neural network (CNN), thereby achieving the gesture recognition accurately in indoor environments.
[0051] Additionally, the system 100 enhances the precision and flexibility of gesture recognition through the implementation of advanced machine learning models, such as Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks. These models are configured to process complex spatial and temporal patterns associated with user gestures and are trained on large-scale, heterogeneous datasets to improve recognition accuracy across varied user profiles and environmental conditions.
[0052] The PID controller within the controller 124 is configured to execute auto-tuning algorithms that dynamically adjust the proportional, integral, and derivative parameters in response to the UAV’s dynamics and motor response, thereby ensuring consistent flight stability. The computing device 102 is configured to control and manage the at least two capturing units 126 for capturing images and videos, real-time streaming, and gesture detection, thereby facilitating low-latency visual feedback for enhanced user interaction and navigation. Additionally, the system 100 facilitates gesture detection and user interaction.
[0053] The plurality of driving units 122 are integrated with electronic speed controllers (ESCs) that are configured to execute control signals from the flight controller 124 within millisecond-scale response times, thereby enabling precise and rapid modulation of thrust for executing complex maneuvers, includes stable hovering, directional transitions, and mid-air flips. In one embodiment herein, the display unit 116 is configured to enable the real-time display of telemetry data and customizable gesture-to-command mappings with the UAV 101, thereby enabling user-defined control over UAV’s operations, includes media initiation and aerial maneuvers. The display unit 116 manages automatic storage of captured images and videos directly within the server 117. This feature provides real-time access to media without the need for external memory devices. Additionally, the computing device 102 include, but is not limited to, devices such as mobile phones, laptops, tablets, and personal digital assistants (PDAs), each equipped with wireless communication capabilities and user interface support for controlling and monitoring the UAV 101.
[0054] According to another exemplary embodiment of the invention, FIG. 2 refers to a block diagram 200 of the proportional-integral-derivative (PID) tuning for plurality of driving units 122. In one embodiment herein, the system 100 receives two primary inputs from the UAV’s coordinates, which represent the target or desired position, and the UAV’s speed, which represents its current motion state. These inputs are fed into a summation block that calculates the error between the current and desired states. This error is then processed through three components, which includes proportional block calculates the difference between the target and current coordinates, thereby providing an immediate corrective response based on present error, integral block sums the current and previous proportional values to eliminate accumulated steady-state errors over time, and derivative block evaluates the rate of change of the error, using the speed of the UAV 101 to predict and dampen future error and improve stability.
[0055] According to another exemplary embodiment of the invention, FIG. 3 refers to a schematic view 300 of the wearable hand gesture device 118 with multiple-gesture movements. In one example embodiment herein, the wearable hand gesture recognition device 118 is adapted to interpret various hand configurations based on joint and finger position data. Each hand is overlaid with a skeletal tracking framework composed of black dots at key joint locations and lines representing finger and hand bone segments, allowing the wearable hand gesture device 118 to detect precise finger articulation and palm orientation. The top row of gestures includes an open palm with fingers fully extended and spread apart (representing a "stop" or "high five" gesture), a gesture with the index and little fingers extended while the middle and ring fingers are folded (commonly known as the "rock on" gesture), and a three-finger sign where the index, middle, and little fingers are extended (often used for symbolic or sign language purposes).
[0056] The bottom row shows a fully clenched fist (indicating a "fist" or "punch" gesture), a gesture with three fingers extended and the thumb and little finger touching each other (often used as a counting or signal gesture), and a final gesture forming a circle with the thumb and index finger while the remaining fingers are extended (representing an "OK" sign). These hand gestures are made possible through the wearable hand gesture device 118 equipped with the inertial measurement unit (IMU) and position-sensing components. The skeletal overlay suggests that the device utilizes joint-level tracking, enabling it to translate each specific gesture into control signals. These signals might be used to interact with external systems, such as unmanned aerial vehicles (UAVs) 101, robotics, and virtual interfaces.
[0057] According to another exemplary embodiment of the invention, FIG. 4 refers to a schematic view of the UAV 101. In one example, the UAV 101 features a quadrotor frame, with four arms extending from a central body, each arm hosting the brushless motor 122 and a propeller. The arms are made of lightweight materials for structural rigidity and flight stability. The central fuselage houses key electronic and control components, including the controller 124 (central circuit board) that handles orientation, stabilization, and processing incoming signals, a power distribution board (PDB) that delivers power from the battery to motors and other onboard system 100. The gesture recognition interface is implied to prior oscilloscope pulse data, this UAV 101 is adapted to receive pulse-coded commands wirelessly from the transmitter 134 (e.g., glove or wristband). These signals, differentiated by pulse duration or frequency, could trigger specific actions such as takeoff, hover, rotate, and land.
[0058] According to another exemplary embodiment of the invention, FIG. 5 refer to screenshots 500 of a signal transmission to capture pulse waveforms from the transmitter 134 and the receiver 128. In one embodiment herein, the first screenshot (left), the display shows a series of sharp, periodic digital pulses generated by the transmitter 134. These pulses have consistent timing intervals, indicating a stable pulse train being transmitted. The vertical scale (200 mV/div) and horizontal scale (500 ms/div) suggest a repetitive pulse signal suitable for timing or control communication. A second screenshot (middle) captures a single pulse in greater detail, showing its duration and the time interval between its rising and falling edges. The cursor readings on the screen indicate a time difference (Δt) of 980 microseconds between the start and end of the pulse, corresponding to a frequency of 1.02 kHz. This signal reflects the response received or recognized by the system 100, implying that the signal integrity is maintained over the communication link.
[0059] A third screenshot (right) shows a wider pulse signal at the receiver end, indicating a different gesture or command interpretation. The pulse duration here is measured to be 1.980 milliseconds (Δt), corresponding to a lower frequency of 505.1 Hz. The voltage difference (ΔV) remains consistent, showing reliable amplitude detection at the receiver 128. These oscilloscope traces depict the operation of a gesture-based wireless communication system where specific hand gestures, captured via the transmitter 134. The change in pulse duration between screenshots signifies distinct gesture inputs being communicated and decoded accurately by the system 100.
[0060] According to another exemplary embodiment of the invention, FIG. 6 refers to a pictorial representation 600 of at least two capturing units 126 that are adapted to provide real-time visual. In one example, a graphical user interface (GUI) is commonly used for real-time remote UAV operation, featuring a dual virtual joystick control layout and various gesture-command icons for interactive UAV navigation. At the center of the screen, the background shows a real-time video feed from the UAV, simulating the visual experience of flying over a road in a desert landscape. This implies that the UAV is equipped with at least two capturing units 126, where at least one is faced on a front-facing and another possibly downward or rear-facing, both of which provide real-time visual data to the user interface. The at least two capturing units 126 enable the user to see the UAV’s live viewpoint, improving situational awareness and precision control.
[0061] The virtual joysticks (left and right circles) are used for manual directional and altitude control. The gesture icons across the top (e.g., peace sign, hand raise, walk symbol, waveform) suggest the UAV 101 is responsive to gesture-based commands, with each icon likely representing a specific gesture-triggered action. The auxiliary controls on the left and right sides (e.g., MV, camera icon, stop button). For various camera modes, movement presets, and emergency stop. The GUI interface exemplifies an intelligent UAV control system that merges gesture recognition input with real-time video feedback through dual capturing units, enabling intuitive, immersive, and hands-free control of the drone in dynamic environments.
[0062] According to another exemplary embodiment of the invention, FIG. 7A refers to a graphical representation 700 of battery charge, discharge, and flight time variations. In one embodiment herein, the variations in battery charge time, discharge time, and UAV 101 flight time with respect to different battery capacities, measured in mAh or mA. The x-axis represents battery parameters (200 mAh to 1800 mAh), and the y-axis represents the corresponding time in min. Three curves are depicted charge time (blue line with circles), discharge time (red line with triangles), and flight time (green line with diamonds).
[0063] The charge time curve depicts that as the battery capacity increases from 200 mAh to 1000 mAh, the charge time decreases significantly, from about 11 min varies between 3 min. This indicates more efficient energy intake for higher capacity batteries within that range. Similarity, the discharge time decreases from around 9 min varies between under 3 min as the capacity increases up to 1000 mAh. This implies that higher-capacity batteries discharge more slowly or are better optimized for power delivery. Conversely, the flight time curve displays a consistent upward trend as the battery capacity increases from 900 mAh to 1800 mAh, with flight durations improving from approximately 4 minutes to over 14 minutes. This trend confirms that higher-capacity batteries substantially enhance UAV flight endurance, offering prolonged operational intervals with each incremental increase in energy storage.
[0064] According to another exemplary embodiment of the invention, FIG. 7B refers to a graphical representation 702 of the battery capacity and a flight time. In one embodiment, the graphical representation illustrates a substantially linear correlation between battery capacity (measured in milliampere-hours, mAh) and drone flight time (measured in minutes). The x-axis of the graph spans battery capacities from 1000 mAh to 4000 mAh, while the y-axis reflects corresponding flight durations ranging from approximately 8 to 35 minutes. The data indicates that as battery capacity increases, flight time scales proportionally. Specifically, a 1000 mAh battery yields around 8 minutes of flight time, a 2000 mAh battery provides approximately 15 minutes, a 3000 mAh battery enables about 26 minutes, and the maximum observed capacity of 4000 mAh supports an estimated 35-minute flight. The observed trend suggests a nearly uniform incremental gain of approximately 4 to 5 minutes of flight time for every additional 500 mAh, confirming the efficiency and predictability of capacity-based endurance scaling in UAV systems.
[0065] According to another exemplary embodiment of the invention, FIG. 7C refers to a graphical representation 704 of battery charging time and current. The inverse relationship between the charging current applied to the battery (measured in milliamperes or mA) and the time it takes to fully charge the battery (measured in hr). As the charging current increases along the horizontal axis, the corresponding battery charging time decreases along the vertical axis. Specifically, at a low charging current of 500 mA, the charging time is approximately 4.3 hr. When the charging current is doubled to 1000 mA, the charging time reduces significantly to about 2.2 hr. Further increases in the charging current continue to decrease the charging time, although the rate of decrease appears to lessen at higher currents. For instance, at 2000 mA, the charging time is around 1.2 hr, and at the highest plotted charging current of 3000 mA, the charging time is approximately 0.7 hr. The curve demonstrates that charging a battery faster requires a higher charging current.
[0066] According to another exemplary embodiment of the invention, FIG. 7D refers to a graphical representation 706 of the battery discharge time and the current. In one embodiment herein, the inverse relationship between the discharge current drawn from a battery (measured in milliamperes or mA) and the duration for which the battery can supply power before being fully discharged (measured in hours). As the discharge current increases along the horizontal axis, the corresponding battery discharge time decreases along the vertical axis. Specifically, at a low discharge current of approximately 500 mA, the discharge time is about 3.6 hr. When the discharge current is increased to roughly 1000 mA, the discharge time reduces to approximately 1.8 hr. Further increases in the discharge current lead to a more rapid decrease in the discharge time, with the curve becoming less steep at higher currents. For instance, at a discharge current of 3000 mA, the discharge time is around 0.6 hr, and at the highest plotted discharge current of 10000 mA, the discharge time is approximately 0.2 hr. This graphical representation clearly demonstrates that drawing more current from a battery significantly shortens its operational time.
[0067] Numerous advantages of the present disclosure may be apparent from the discussion above. In accordance with the present disclosure, the system 100 is disclosed. The proposed system 100 enables hands-free control through hand gesture recognition, thereby eliminating the need for complex joysticks and smartphone applications and making it accessible to non-expert users, including beginners, solo travelers, vloggers, and content creators. The system 100 is integrated with inertial measurement unit (IMU)-based and camera-based gesture recognition, thereby ensuring reliable performance across diverse environments. The system 100 utilizes MPU6050 sensor and PID-tuned controller 124 to maintain UAV balance even under external disturbances like wind and motor vibrations, thereby ensuring smooth and precise flight, outperforming many commercial quadcopters that rely solely on IMUs.
[0068] The system 100 offers seamless switching between gesture-based, manual, and semi-autonomous modes via the mobile application, thereby providing flexibility to the UAV 101 to adapt to different scenarios, such as reverting to manual control in high-risk areas or using gesture mode for aerial photography, enhancing operational versatility compared to rigid control systems. The system 100 monitors real-time data on gesture recognition accuracy, UAV orientation, battery status, and media streaming through the mobile applications. The system 100 is cost-effective with MPU6050, ESP32 and open-source PX4 firmware, making it ideal for students, researchers, and DIY developers, offering performance comparable to high-end systems at a fraction of the cost.
[0069] The system 100 is energy-aware PID tuning and smart power distribution, optimizing flight time (12–30 min with a 3000 mAh LiPo battery) without compromising responsiveness, thereby improving battery life in power-intensive UAV. The system 100 automatically stores photos and videos directly on the mobile app, eliminating the need for external memory cards and reducing the risk of data loss. The system 100 serves as a teaching tool for embedded systems, control theory, AI/ML (gesture detection), and wireless communication.
[0070] It will readily be apparent that numerous modifications and alterations can be made to the processes described in the foregoing examples without departing from the principles underlying the invention, and all such modifications and alterations are intended to be embraced by this application.
, Claims:CLAIMS:
I/We Claim:
1. A system (100) for real-time operation of unmanned aerial vehicles (UAVs) (101) using hand gesture recognition, comprising:
a computing device (102) having a processor (104) and a memory (106) for storing one or more instructions executed by the processor (104), wherein the computing device (102) is configured to communicate with a server (117) via a network (112),
wherein the processor (104) is configured to execute plurality of modules (108) for performing multiple operations, wherein the plurality of modules (108) comprises:
a registration module (110) configured to allow users to register for accessing the system (100) for controlling operational parameters of the UAVs (101);
a communication module (114) configured to initiate and mange bidirectional wireless communication between the computing device (102) and the UAV (101), respectively, via the network (112), thereby enabling transmission of control signals for controlling the operational parameters; and
a display unit (116) configured to facilitate the user to control the respective UAV (110) while monitoring real-time telemetry data includes UAV orientation, battery status, and gesture recognition accuracy, thereby facilitating dynamic switching between manual remote control (RC), semi-autonomous, and fully gesture-based operation modes for adaptive UAV operation,
wherein the UAV (101) comprises:
a gyroscopic sensor (120) includes a 6-axis motion-tracking sensor that detects orientation data and angular velocity during flight of the UAV (101);
plurality of driving units (122) configured to provide a precise vector thrust and maneuverability;
a controller (124) configured to process the orientation data received from the gyroscopic sensor (120) in real-time and dynamically adjust speed of the plurality of driving units (122) for stable flight under external disturbances; and
at least two capturing units (126) configured to capture high-resolution visual data in multiple directions and transmit it to the computing device (102) for real-time navigation and user feedback; and
a wearable hand gesture device (118) configured to worm by a user’s hand to generate multiple-gesture movements to control the UAV (101), wherein the wearable hand gesture device (118) comprises:
an inertial measurement unit (IMU) (130) configured to detect hand movements and generate gesture data;
a processing unit (132) configured to analyze the gesture data received from the IMU (130) and classify gestures using machine learning models, thereby enabling gesture-based control signals for navigation and controlling of the UAV (101); and
a transmitter (134) configured to broadcast the classified gesture-based control signals to the computing device (102), enabling non-contact user interaction and precise control of the UAV (101) under various environmental conditions.
2. The system (100) as claimed in claim 1, wherein the UAV (101) comprises a receiver (128) that is configured to receive gesture-based control signals from the wearable hand gesture device (118) and decode the control signals to the controller (124), which analyze the gesture commands to facilitate real-time control of the UAV (101) functions include navigation, stability management, activation of the at least two capturing units (126), and autonomous mode selection.
3. The system (100) as claimed in claim 1, wherein the wearable hand gesture device (118) is configured to perform feature extraction and gesture classification from the hand movements using the machine learning models include a convolutional neural network (CNN), thereby achieving the gesture recognition accurately in indoor environments.
4. The system (100) as claimed in claim 1, wherein the controller (124) is configured to execute auto-tuning algorithms that dynamically adjust proportional, integral, and derivative parameters based on the UAV’s dynamics and the performance of the plurality of driving units (122), thereby ensuring stable flight under various environmental conditions.
5. The system (100) as claimed in claim 1, wherein the computing device (102) is configured to control and manage the at least two capturing units (126) for capturing images and videos, real-time streaming, and gesture detection, thereby facilitating low-latency visual feedback for enhanced user interaction and navigation.
6. The system (100) as claimed in claim 1, wherein the display unit (116) is configured to enable the real-time display of telemetry data and customizable gesture-to-command mappings with the UAV (101), thereby enabling user-defined control over UAV’s operations, includes media initiation and aerial maneuvers.
7. The system (100) as claimed in claim 1, wherein the plurality of driving units (122) is integrated with electronic speed controllers (ESCs) that are configured to execute control signals from the controller (124) within millisecond-scale response times, thereby enabling precise and rapid modulation of thrust for executing complex maneuvers, includes stable hovering, directional transitions, and mid-air flips.
8. The system (100) as claimed in claim 1, wherein the computing device (102) is configured to automatically transmit and store captured image and video data to the server (117) in real-time, thereby enabling immediate access for remote viewing and sharing, while eliminating the necessity for external memory storage media.
9. The system (100) as claimed in claim 1, wherein the computing device (102) includes at least one of mobile, laptop, tablet, and personal digital assistant (PDA), each having wireless communication capability and user interface support for control and monitoring of the UAV (101).