Intelligent robotic system for detecting and rescuing living people in disaster areas

Abstract

An intelligent robotic system for detecting and rescuing living people in disaster areas, consisting of: a mobile chassis configured for crossing debris-strewn and uneven terrain, the chassis comprising several DC geared motors driven by an H-bridge motor driver; a control unit with a microcontroller configured to receive sensor data, perform navigation and detection techniques, and transmit information via wireless communication; a subsystem for person detection comprising at least one passive infrared sensor for detecting heat signatures, at least one microwave Doppler radar module for detecting micro-movements indicative of breathing or heartbeat, and an ultrasonic sensor array for proximity and obstacle detection; an environmental monitoring subsystem comprising at least one gas sensor configured to detect hazardous gases selected from methane, smoke, propane or carbon monoxide; a visual feedback subsystem that includes a camera module configured to capture real-time images and video streams; a wireless communication interface configured for transmitting multi-sensor data and video feeds to a remote mobile application interface; and a power supply comprising at least one rechargeable battery that is operationally connected to the control unit, sensors and the propulsion system, The robot system is configured to detect the presence of living people, monitor environmental hazards, and inform rescue teams in disaster areas about the current situation in real time.

Description

Technical field

[0001] The present invention relates to robotic systems for search and rescue operations and in particular to an intelligent robotic platform with integrated multi-sensor fusion, wireless communication and semi-autonomous navigation for detecting living people and dangerous conditions in disaster areas. Background of the invention

[0002] Natural and man-made disasters such as earthquakes, landslides, industrial accidents, and terrorist attacks often leave victims trapped under rubble or in dangerous, inaccessible environments. Conventional rescue operations are labor-intensive, time-consuming, and expose personnel to hazardous conditions. Existing robotic systems attempt to mitigate these risks. However, they typically rely on limited sensor technology or manual operation, leading to inaccuracies in human detection and inefficiencies in data transmission.

[0003] There is a need for a cost-effective, portable and intelligent robotic system capable of detecting signs of life in disaster areas through the integration of multiple sensors, transmitting real-time situational information, and enabling remote or semi-autonomous navigation in difficult terrain.

[0004] Locating and rescuing people trapped in natural or man-made disasters remains one of the most pressing challenges in emergency response. In earthquakes, industrial explosions, building collapses, floods, landslides, or terrorist attacks, the critical first hours after the event determine the chances of survival for victims who may be trapped under rubble, buried in confined spaces, or stranded in environments filled with smoke, toxic gases, or fire. Traditional search and rescue methods have historically relied on manual rescue teams equipped with basic locating devices such as poles, search dogs, and thermal imaging cameras. While these traditional approaches have saved countless lives, they are limited in terms of accuracy, speed, and safety.Human rescuers are forced to work in structurally unstable zones and risk further collapses, exposure to toxic gases, or direct injury. While dogs are effective in many cases, they suffer from fatigue, environmental pollution from chemical odors, and are limited in their time. Thermal imaging cameras and acoustic devices can be useful but are limited by line-of-sight requirements, signal interference, and susceptibility to false alarms from non-human heat sources or ambient noise.

[0005] As technology advanced, robotic systems were explored for disaster management. Early robotic rescue systems were primarily designed for the visual reconnaissance of dangerous, inaccessible areas. These robots typically used simple platforms on wheels or tracks equipped with cameras that transmitted live video to operators. While they improved situational awareness, they could not reliably detect living people. Their performance was largely limited to capturing visual information, requiring trained operators to manually interpret the video images. Furthermore, video recordings were often unclear in environments filled with dust, smoke, or debris. Navigation was also problematic for such robots; without advanced obstacle avoidance, they would become stuck in difficult terrain or tip over, limiting their usefulness.

[0006] To address these shortcomings, researchers began integrating additional sensor technologies into robotic platforms. One of the most widely used sensors was the passive infrared (PIR) sensor, which detects the infrared radiation emitted by the human body. PIR sensors offered the advantage of being inexpensive and energy-efficient, and of detecting the presence of warm objects relatively accurately within a limited field of view. However, PIR sensors also had significant drawbacks. Their range was limited to a few meters, and their detection was impaired if the object was covered with debris or insulating materials. Furthermore, PIR sensors were prone to false alarms in environments with fluctuating heat sources such as fire, hot machinery, or exposed electrical equipment, making them unreliable as standalone detectors.

[0007] Ultrasonic sensors are also used in robotic rescue systems, primarily for obstacle detection and distance measurement. Their role in detecting living people is secondary, as they are better suited for mapping the environment than for identifying signs of life. Ultrasonic waves cannot penetrate solid debris and therefore cannot directly confirm the presence of survivors behind obstacles. Nevertheless, in combination with other sensor technologies, ultrasonic sensors have contributed to more stable navigation in cluttered environments. Unfortunately, their reliability decreases in noisy or highly reflective environments, and measurement accuracy can be significantly affected by temperature and humidity fluctuations, which are common in disaster areas.

[0008] Microwave Doppler radar technology has attracted attention due to its ability to detect even the smallest human movements, such as breathing or heartbeat, through certain obstacles. This capability positions Doppler radar as a promising tool for confirming the presence of living people at disaster sites, where victims may be unconscious, immobilized, or partially covered. Several prototypes have demonstrated the radar's effectiveness in detecting breathing at distances beyond the range of PIR sensors. However, radar-based systems are susceptible to interference from moving debris, vibrations, or electromagnetic noise in industrial environments. Furthermore, radar modules tend to be more expensive and power-hungry compared to infrared or ultrasonic sensors, limiting their integration into low-cost robotic platforms.Signal interpretation also remains a challenge, as radar outputs must be processed using complex techniques to filter out irrelevant movements and accurately isolate human life signs.

[0009] Gas sensors are used to improve environmental monitoring during rescue operations. Devices like the MQ series gas sensors can detect hazardous substances such as methane, smoke, propane, or carbon monoxide. This is particularly important because many disaster areas involve chemical leaks, fire hazards, or oxygen-depleted zones. By using gas sensors, rescue workers can be warned of unsafe access conditions before human intervention. However, gas sensors themselves do not provide information about the presence of survivors. Their role is complementary and enhances the safety of operations, but they do not directly contribute to locating trapped victims. Furthermore, these sensors often require calibration for specific gases and can trigger false alarms if multiple gases are present simultaneously.

[0010] Another important development is the use of cameras, including optical and thermal imaging systems, mounted on robotic platforms or drones. Thermal imaging cameras can detect the heat signature of people even in darkness or smoke. Integrated into mobile robots, they can visually locate survivors while simultaneously mapping obstacles. Despite this potential, thermal imaging technology reaches its limits when victims are buried under thick layers of debris that block infrared radiation. Cameras also require significant bandwidth for data transmission, especially for video streaming, which can be unreliable in disaster areas with damaged communication infrastructure. Furthermore, human operators must continuously monitor video transmissions, increasing cognitive load and potentially delaying decision-making in time-critical situations.

[0011] While robotic systems with these individual sensor technologies have improved over the years, they still face challenges in disaster situations. A major problem is their reliance on single-sensor solutions or limited sensor combinations. Each sensor modality has its weaknesses, be it range limitations, false alarms, environmental influences, or line-of-sight dependency. Without effective fusion of data from multiple sensors, the probability of misidentification is high. False alarms not only waste valuable time but also direct rescue teams in the wrong direction, while false alarms can lead to survivors being overlooked. Systems that do not integrate multiple complementary sensor approaches therefore fail to achieve the accuracy required for reliable disaster relief.

[0012] Navigation and mobility are another persistent limitation of existing robotic rescue platforms. Many robots are based on simple wheeled or tracked vehicles that often become stuck in rubble, collapsed buildings, or uneven terrain. Some advanced models utilize articulated legs or hybrid mechanisms to improve mobility, but this increases mechanical complexity and power consumption. Inadequate locomotion reduces the range and effectiveness of search operations, as the robot cannot reach deeper or more inaccessible areas where survivors are most likely trapped. Furthermore, many existing robots lack true autonomy; they require continuous remote control by human operators. This dependency increases the cognitive load on rescue teams and reduces efficiency, especially when multiple robots are deployed simultaneously.

[0013] Conventional robotic systems often rely on short-range radio or proprietary connections for communication, which can be unreliable in disaster situations when communication infrastructure is damaged or blocked. Delays or connection losses can disrupt critical real-time data flow, leaving operators unaware of the robot's status or sensor readings. Without robust wireless connectivity, the robot cannot effectively augment the rescue team. Some systems have experimented with mesh networks or wired communication, but these increase logistical complexity and may not guarantee uninterrupted data transmission in heavily congested environments.

[0014] Another drawback of many existing solutions is the lack of integration between recognition and decision-making. Most robots collect data and transmit it to operators, but they don't perform on-board analysis or intelligent signal filtering. This forces human operators to interpret raw sensor data in real time, slowing down decision-making and increasing the risk of human error. Artificial intelligence and sensor fusion have only recently been integrated, and many existing prototypes are still in the experimental stage and lack solid practical applicability.

[0015] From a cost and operational perspective, advanced robotic systems with specialized sensors such as radar, lidar, or high-resolution cameras are often expensive and bulky, making them unsuitable for large-scale deployment in developing regions or for disaster relief organizations with limited resources. Furthermore, excessively heavy or complex systems are difficult to transport quickly to disaster areas, where every minute counts. Even when such systems are available, their operation may require trained personnel, delaying immediate deployment and reducing overall effectiveness.

[0016] Conventional approaches based on manual search, dogs, or single-sensor robots are limited in accuracy, safety, and speed. PIR sensors are inexpensive but unreliable under debris; ultrasonic sensors are effective for navigation but inadequate for detecting lives; Doppler radar provides valuable micro-motion detection but is expensive and prone to interference; gas sensors improve safety but do not confirm survivors; and camera-based systems are highly dependent on line of sight and bandwidth availability. Existing robots also suffer from a lack of mobility, unreliable communication, limited autonomy, and high costs. The result is a fragmented landscape of technologies that, while useful in isolation, do not offer a robust, reliable, and scalable solution to the vital problem of locating and rescuing people in disaster areas. Summary of the invention

[0017] The present invention relates to a robotic system with sensor fusion technology, including passive infrared sensors, ultrasonic sensors, Doppler radar, a gas sensor, and an optical camera, controlled by an ESP32 microcontroller-based unit. The system is designed to detect living people, detect hazardous gases, and transmit live environmental and positional data to emergency services in real time via wireless communication modules.

[0018] The invention also includes a C-shaped chassis with motorized propulsion, enabling movement across uneven, debris-strewn terrain. Real-time data, including images, video streams, and sensor readings, are transmitted to a mobile application, allowing rescue workers to remotely monitor, control, and coordinate rescue strategies. The system increases the speed, safety, and accuracy of locating survivors, thereby optimizing disaster relief efforts.

[0019] The main objective of the present invention is to provide an intelligent robotic system capable of detecting living people in disaster areas more accurately, reliably, and quickly than existing manual or semi-automatic methods. The invention aims to minimize the risks to rescue workers through remote monitoring and autonomous navigation in hazardous or inaccessible areas, thereby significantly reducing the danger to human rescuers from life-threatening conditions such as toxic gases, unstable debris, and fire hazards. A further objective of the invention is to overcome the limitations of single-sensor detection systems through a multi-sensor fusion approach that combines passive infrared sensing, microwave Doppler radar, ultrasonic distance measurement, gas sensing, and real-time visual imaging.This integration ensures that even when sensor function is impaired by environmental factors, the combined analysis of multiple signals enables accurate detection of survivors.

[0020] Another objective of the invention is to provide a cost-effective, lightweight, and portable robotic platform that can be rapidly deployed in disaster areas without requiring specialized infrastructure or highly skilled personnel. The system is designed to adapt to various terrains and environments, including collapsed buildings, industrial accidents, and flood zones. The invention also aims to improve communication between the robot and rescue teams through the use of radio modules integrated into the control unit. This ensures the real-time transmission of sensor data, live video, and alerts to operators via a mobile application interface. Furthermore, the invention is intended to enable semi-autonomous navigation with obstacle avoidance, allowing the robot to navigate through debris fields while human operators can intervene manually when necessary.

[0021] A further objective of the invention is to create a modular system architecture in which components such as sensors, actuators, and communication modules can be independently replaced or upgraded. This modularity supports the future integration of artificial intelligence techniques for victim detection, drone-based aerial reconnaissance, and advanced communication systems for a wider range of applications. Another objective is to improve the safety and effectiveness of disaster relief operations by not only detecting the presence of people but also monitoring hazardous environmental conditions using gas and oxygen sensors. This allows rescue teams to be warned of potential dangers before people enter the area.Furthermore, the invention is intended to optimize energy efficiency and operating time through the use of energy-saving components and efficient locomotion systems, thus ensuring that the robot can perform long operations during extended rescue missions.

[0022] The invention aims to bridge the gap between existing robot prototypes and practical field deployment by providing a robust, scalable, and user-friendly robot platform. By combining accurate survival detection, safety for rescue workers, adaptability to various disaster scenarios, and real-time situational awareness, the invention is intended to become an indispensable tool in modern disaster management and humanitarian aid. BRIEF DESCRIPTION OF THE FIGURE

[0023] These and other features, aspects, and advantages of the present invention will be better understood if the following detailed description is read with reference to the accompanying drawing, in which the same symbols consistently represent the same parts. The following applies: Fig. Figure 1 shows a block diagram of an intelligent robot system for detecting and rescuing living people in disaster areas.

[0024] Experts will also recognize that the elements in the drawing are shown for the sake of simplicity and are not necessarily to scale. For example, the flowcharts illustrate the process by highlighting the main steps to enhance understanding of the aspects of this disclosure. Furthermore, with regard to the design of the device, one or more components of the device may be represented in the drawing by conventional symbols, and the drawing may show only the specific details relevant to understanding the embodiments of this disclosure, so as not to clutter the drawing with details that are readily apparent to those skilled in the art after reading this description. Detailed description of the invention

[0025] For a better understanding of the inventive principles, reference is made below to the embodiment shown in the drawing, which is described in specific terminology. However, this does not limit the scope of the invention. Changes and further modifications of the illustrated system, as well as further applications of the inventive principles, are possible, as would normally occur to a person skilled in the art in the field of invention.

[0026] It is clear to the person skilled in the art that the preceding general description and the following detailed description are exemplary and explanatory of the invention and are not intended as a limitation of it.

[0027] References in this specification to “an aspect”, “another aspect”, or similar expressions mean that a particular feature, structure, or property described in connection with the embodiment is included in at least one embodiment of the present disclosure. Therefore, occurrences of the expressions “in one embodiment”, “in another embodiment”, and similar expressions in this specification may all refer to the same embodiment, but need not.

[0028] The terms "includes," "include," or other variations thereof are intended to cover non-exclusive inclusion, such that a process or method that includes a list of steps may not only contain those steps but may also include other steps not expressly listed or inherent in such process or method. Likewise, the statement "includes..." in the case of one or more devices, subsystems, elements, structures, or components does not, without further limitations, preclude the existence of other devices, subsystems, elements, structures, components, or additional devices, subsystems, elements, structures, or components.

[0029] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as understood by a person skilled in the art in the field of the invention. The systems, methods, and examples provided herein serve only for illustration and are not to be construed as limitations.

[0030] Embodiments of the present disclosure are described in detail below with reference to the attached drawing.

[0031] In Fig.Figure 1 shows a block diagram of an intelligent robotic system for locating and rescuing living people in disaster areas. The system 100 comprises: a mobile chassis (102) for traversing debris-strewn and uneven terrain with multiple DC geared motors driven by an H-bridge motor driver (102a); a control unit (104) with an ESP32 microcontroller (104a) for receiving sensor data, executing navigation and location techniques, and transmitting information wirelessly; a person detection subsystem (106) with at least one passive infrared sensor for detecting heat signatures, at least one microwave Doppler radar module (106a) for detecting micro-movements indicative of breathing or heartbeat, and an ultrasonic sensor array (106b) for proximity and obstacle detection;an environmental monitoring subsystem (108) with at least one gas sensor (108a) for detecting hazardous gases selected from methane, smoke, propane, or carbon monoxide; a visual feedback subsystem (110) comprising a camera module (110a) configured to capture real-time images and video streams; a wireless communication interface (112) configured to transmit multi-sensor data and video feeds to a remote mobile application interface; and a power supply (114) comprising at least one rechargeable battery operationally connected to the control unit, sensors, and locomotion system, the robot system being configured to detect the presence of living people, monitor environmental hazards, and provide real-time situational information to rescue teams in disaster areas.

[0032] In one embodiment, the ESP32 microcontroller (104a) is configured with dual-core processing and integrated Wi-Fi and Bluetooth modules, wherein the microcontroller executes sensor fusion techniques programmed in Embedded C within the Arduino IDE environment, so that data from the passive infrared sensor, Doppler radar and ultrasonic sensors are correlated to produce a composite detection signal that reduces false positive and false negative results.

[0033] In one embodiment, the microwave Doppler radar module (106a) is tuned to detect micro-movements within a frequency band of 10.525 GHz ± 25 MHz, and the radar module is mounted on a vibration-damped mount in the front section of the chassis to minimize false motion detection due to mechanical vibrations during locomotion.

[0034] In one embodiment, the ultrasonic sensor array (106b) comprises at least two ultrasonic transceivers arranged at an angular offset of 30° to 60° relative to the robot's forward axis. The array is configured to perform triangulated obstacle mapping, enabling the robot to autonomously adjust its trajectory in debris-strewn corridors without operator intervention.

[0035] In one embodiment, the gas sensor (108a) is an MQ2 module configured with a sensitivity calibration circuit with a load resistance of 20 kΩ to 30 kΩ, and wherein the gas sensor output is processed by an integrated analog-to-digital converter of the ESP32 to generate calibrated measurements of the methane concentration levels between 200 ppm and 10,000 ppm in real time.

[0036] In one embodiment, the camera module (110a) is a Pi camera configured to capture images with a resolution of at least 640 × 480 pixels at 30 frames per second. The camera is connected to the ESP32 microcontroller via an SPI interface, and the captured video stream is compressed using JPEG encoding before transmission to the mobile application to reduce bandwidth requirements in disaster communication environments.

[0037] In one embodiment, the mobile chassis (102) is a C-shaped frame made of a lightweight aluminum alloy with impact-resistant polymer shielding. The frame includes wheels mounted on a suspension, which are driven by the DC geared motors. The suspension is configured to allow the vehicle to overcome obstacles up to 10 centimeters high without loss of stability.

[0038] In one embodiment, the H-bridge motor driver (102a) is an L298N dual-channel module configured to deliver between 1.5 A and 2.0 A of current per channel. The driver also includes heat sink elements to prevent thermal overload during prolonged operation over rocky terrain.

[0039] In one embodiment, the wireless communication interface (112) is configured to establish both a short-range Bluetooth connection and a long-range Wi-Fi connection. The system is also configured to dynamically switch between Bluetooth and Wi-Fi modes depending on signal strength and network availability to ensure uninterrupted data transmission to the mobile application.

[0040] In one embodiment, the mobile application interface is developed on the Blynk platform, wherein the application is configured to display live sensor data, gas readings, obstacle detection warnings and video feeds on a graphical dashboard, and wherein the application also enables manual override of autonomous navigation by providing directional commands to the ESP32 microcontroller via the wireless communication interface.

[0041] The intelligent robotic system for locating and rescuing living people in disaster areas is designed as an integrated hardware-software platform that performs sensor fusion, autonomous navigation, hazard monitoring, and wireless communication to provide rescue teams with actionable situational awareness. The system's central processing unit is based on an ESP32 microcontroller, chosen for its dual-core architecture, integrated Wi-Fi and Bluetooth connectivity, and built-in analog-to-digital conversion capabilities. The ESP32 executes embedded programs written in C via the Arduino IDE environment, and these programs coordinate sensor data acquisition, the execution of location techniques, locomotion control, and the establishment of wireless data links to remote control devices.The firmware is structured into modular blocks, with each subsystem – human detection, environmental monitoring, locomotion and communication – feeding its processed outputs into a fusion layer that combines the results into coherent operational decisions.

[0042] The person detection technology is based on the combination of signals from three complementary sensor modalities: passive infrared (PIR) sensors, microwave Doppler radar, and ultrasonic distance measurement. The PIR sensor enables first-level heat signature detection and identifies thermal anomalies in the environment corresponding to human body temperature in the range of 30 to 40 degrees Celsius. However, since PIR sensors are susceptible to false triggers from sources of fire or heated debris, the technology does not rely solely on this input. When a PIR event is registered, the firmware triggers the Doppler radar module to scan the same spatial sector. Operating at a frequency of approximately 10.525 GHz, the Doppler radar module detects minute vibrations in reflected microwaves, corresponding to micro-movements such as chest expansion during breathing or slight trembling of the limbs.Signal conditioning circuits filter out high-frequency vibrations caused by the robot's own movement, aided by the vibration-damped mounting bracket. The ESP32 microcontroller then executes a digital signal processing routine that applies a moving average filter to smooth the radar echo, followed by a fast Fourier transform (FFT) to extract periodic frequencies in the 0.1 to 2 Hz range, corresponding to breathing and heartbeat. When such periodic microsignals are detected concurrently with PIR heat signature detection, the technique increases the confidence level of human presence from tentative to confirmed. The ultrasonic array contributes by measuring the precise distance to the detected object and ensuring that the system does not misinterpret background heat sources or static thermal artifacts.The triangulation technique compares the time-of-flight delays of two or more ultrasonic transceivers aligned at an angular offset of 30 to 60 degrees. From this, the microcontroller calculates both the range and the approximate bearing of the detected obstacle, allowing the system to align the PIR and radar scanning more precisely.

[0043] In addition to person detection, the system integrates environmental hazard monitoring via the MQ2 gas sensor. This sensor generates an analog voltage proportional to the concentration of flammable gases such as methane, propane, or smoke particles. The ESP32 digitizes this analog signal and applies a calibration curve based on the sensor's resistance ratio in clean versus contaminated air. To improve accuracy, the microcontroller implements a compensation technique that corrects for ambient temperature fluctuations, which can shift the sensor's base resistance. This technique sets thresholds, such as 200 ppm for methane, above which an immediate hazard warning is generated and sent.This information is not used in isolation, but combined with person detection signals, so that rescue workers receive not only the location of survivors, but also warnings of atmospheric hazards in their vicinity. An optional oxygen concentration sensor can be integrated into the same system. The technology considers an oxygen level below 19.5% as a critical survival threshold.

[0044] The visual subsystem is a Raspberry Pi camera module that provides both still images and streaming video. Since stable, high-bandwidth communication channels are often scarce in disaster areas, the system uses a lightweight JPEG compression technique on the ESP32, encoding images at a reduced resolution of 640 × 480 pixels at 30 frames per second. This trade-off between quality and bandwidth ensures that video feeds can be transmitted over both Wi-Fi and Bluetooth without overloading the available channel. The video data is annotated with metadata from the other sensors, so images captured during active PIR and radar detection are prioritized for transmission. On the operator's mobile application, built on the Blynk platform, the video images are displayed synchronously with the real-time sensor readings, allowing rescue workers to visually confirm detections.

[0045] The propulsion system is designed for stability on uneven terrain and utilizes a closed-loop motor control system driven by the L298N H-bridge module. Each DC geared motor contains an encoder that generates pulse signals corresponding to the wheel rotations. The ESP32 monitors these pulses and adjusts the pulse-width modulation (PWM) outputs to maintain a constant speed across all wheels, thus preventing slippage or rotation errors when the robot travels over rocks. Obstacle avoidance is achieved by processing distance measurements from the 20 Hz ultrasonic array. If the array detects an obstacle within a predefined safety distance, the navigation system stops forward movement and calculates an alternative path using a simple reactive scheme: it compares the distances on both sides and rotates the chassis in the direction with greater ground clearance.If both directions are blocked, the robot begins a retreat maneuver until an alternative path opens up. This basic autonomous navigation allows the robot to penetrate deeper into debris zones without requiring continuous remote control, although manual override via the mobile app is possible at any time.

[0046] The communication technology integrated into the ESP32 dynamically switches between Bluetooth and Wi-Fi transmission modes based on signal quality metrics. The firmware continuously monitors the received signal strength indicators (RSSI) and packet transmission rates. If Wi-Fi becomes unstable due to interference or a lack of infrastructure, the system automatically switches to Bluetooth mode for direct, short-range communication with the operator's device. The multi-sensor data packets are structured with time-stamped fields for PIR detections, radar micro-signals, ultrasonic distance measurements, gas concentrations, and camera images. These packets are transmitted at regular one-second intervals under normal conditions, but are upgraded to a higher frequency during critical events, such as confirming human presence or detecting gas hazards.This event-driven prioritization saves bandwidth while ensuring that vital information reaches the operator without delay.

[0047] The robot also features a local data logging mechanism in the ESP32's non-volatile flash memory. This ensures that sensor readings and video images are archived locally with timestamps for later retrieval, even in the event of a temporary loss of wireless communication. The data logging technique uses ring buffer management to prevent memory overflow during extended missions. Older data is overwritten once the memory limits are reached.

[0048] The power management system optimizes energy consumption by regulating power distribution between the motion and sensor systems. The battery management module monitors voltage and current consumption in real time and transmits this data to the ESP32. During periods of low activity, such as when the robot pauses for radar-based micro-motion scans, the system reduces motor power to idle levels, thus conserving energy for sensor processing and communication. Conversely, during high-torque navigation over scree, non-essential peripherals, such as the camera's frame rate, are temporarily throttled to extend operating time. If the battery level drops below 20%, warning messages are generated, and the operator is notified via the mobile application to consider collection or replacement.

[0049] A unique aspect of the invention is the modular sensor docking interface. Each sensor is connected via standardized power and communication buses, and the firmware uses a plug-and-play detection method that identifies connected modules at startup. The method scans available I 2 It registers C, SPI, and UART addresses, active devices, and updates the Fusion framework accordingly. This enables the quick replacement of damaged sensors in the field or the integration of new modules such as lidar scanners or thermal imaging cameras without complex reprogramming.

[0050] Through this detailed combination of hardware architecture and technology, the robotic system achieves a synergistic balance of detection accuracy, hazard monitoring, autonomous mobility, and communication stability. By correlating PIR detections with Doppler radar micro-movements and ultrasonic distance mapping, the system minimizes false detections and maximizes reliability in complex, hazardous environments. By compressing and prioritizing visual data, it delivers actionable information across limited wireless networks. Energy-efficient design and modular sensor integration ensure sustainable operation and adaptability to future requirements. Overall, the system represents a significant technological and practical advancement in robot-assisted disaster relief technology.

[0051] The intelligent robot system consists of the following main subsystems: 1. Control Unit: The core of the invention is an ESP32 microcontroller, chosen for its integrated Wi-Fi and Bluetooth capabilities, fast data processing, and low power consumption. The controller synchronizes sensor inputs, executes navigation techniques, manages actuator drivers, and establishes wireless communication with the remote operator interface. 2. Person detection subsystem: The system contains multiple sensors for redundancy and accuracy: • A passive infrared (PIR) sensor detects human heat signatures at distances of up to 7 meters. • A microwave Doppler radar module measures micro-movements such as breathing or heartbeat, thus improving detection reliability when heat or motion signals are obscured by debris. • An ultrasonic sensor array measures the proximity to obstacles for navigation and collision avoidance. 3. Environmental monitoring subsystem: An integrated MQ2 gas sensor detects hazardous gases such as methane, smoke, and propane. Oxygen sensors can optionally be integrated to monitor survival conditions. 4. Visual feedback subsystem: A Pi camera module transmits real-time video and still images to the interface of the mobile application, thus providing visual confirmation of human presence and environmental hazards. 5. Locomotion Mechanism: The robot chassis consists of a C-shaped modular frame optimized for movement in rubble. Propulsion is achieved by DC geared motors driven by an L298N H-bridge driver circuit, enabling forward, reverse, and differential rotation. This design ensures stable movement across uneven terrain, collapsed structures, and debris. 6. Communication and User Interface: Wireless communication is achieved via Wi-Fi and Bluetooth modules integrated into the ESP32 platform. Data is transmitted to a mobile application (developed on the Blynk framework) that displays live video, gas readings, motion alerts, and location data. The app enables remote control and, if necessary, allows manual override of the autonomous navigation. 7. Software Integration: The system firmware is developed in Embedded C using the Arduino IDE. Sensor fusion techniques process inputs to detect living people by correlating PIR signals, radar micro-motion data, and visual evidence. Alerts such as "person detected," "gas leak detected," or "obstacle detected" are automatically generated and sent to the operator's mobile device. 8. Device / Structure: The robotic device consists of a compact, portable chassis with modular compartments for sensors, actuators, and control electronics. The front section houses the PIR sensor, radar unit, and camera for optimal field of view. The upper deck integrates the control unit and communication modules, shielded from dust and impacts. The side compartments contain the gas sensor and additional environmental monitors. The C-shaped base frame with suspension wheels driven by DC geared motors ensures high stability when maneuvering through debris. The entire unit is lightweight and quickly deployable. It is powered by rechargeable batteries for extended operation. Advantages of the invention 1. Precise detection of survivors through sensor fusion of PIR, Doppler radar, ultrasonic sensors and camera imaging. 2. Improved rescue safety through minimizing direct human exposure to hazardous disaster environments. 3. Real-time situational awareness with live video, environmental measurements and wireless communication. 4. Portability and adaptability enable rapid deployment and use in multiple disaster scenarios. 5. Autonomous navigation with manual override, ensuring operation even in heavily obstructed environments. 6. Modular and expandable design that supports the integration of AI-based decision-making, drones, or enhanced communication networks in future iterations.

[0052] The present invention relates to robotic systems for disaster relief, and in particular to an intelligent robotic platform with integrated multi-sensor fusion, wireless communication, and semi-autonomous navigation for detecting living people and hazardous environmental conditions in disaster areas. The invention combines passive infrared sensing, microwave Doppler radar, ultrasonic obstacle detection, gas sensing, and real-time visual imaging under a microcontroller-based control system. This enables rapid identification of survivors and real-time situational awareness to support rescue operations in hazardous environments.

[0053] The drawing and the preceding description show examples of embodiments. Those skilled in the art will recognize that one or more of the described elements can be combined to form a single functional element. Alternatively, certain elements can be divided into several functional elements. Elements of one embodiment can be added to another embodiment. For example, the sequence of the processes described here can be changed and is not limited to the manner described here. Furthermore, the actions of a flowchart need not be implemented in the sequence shown; nor does it necessarily have to be performed by all actions. Actions that are not dependent on other actions can also be performed in parallel with the other actions. The scope of the embodiments is in no way limited by these specific examples.Numerous variations are possible, whether explicitly stated in the specification or not, such as differences in structure, dimensions, and material use. The range of embodiments is at least as broad as specified in the following claims.

[0054] Advantages, further benefits, and problem solutions have been described above with reference to specific embodiments. However, the advantages, benefits, problem solutions, and all components that can lead to an advantage, benefit, or solution occurring or becoming more apparent are not to be construed as critical, necessary, or essential features or components of individual or all claims. REFERENCES 100 An intelligent robot system for detecting and rescuing living people in disaster areas. 102 chassis 102a H-bridge motor driver 104 Control unit 104a ESP32 microcontroller 106 Subsystem for Person Recognition 106a microwave Doppler radar module 106b Ultrasonic Sensor Array 108 Environmental Monitoring Subsystem 110 Visual Feedback Subsystem 110a Camera Module 112 Wireless communication interface 114 Power supply

Claims

[1] An intelligent robotic system for detecting and rescuing living people in disaster areas, consisting of: a mobile chassis configured for crossing debris-strewn and uneven terrain, the chassis comprising several DC geared motors driven by an H-bridge motor driver; a control unit with a microcontroller configured to receive sensor data, perform navigation and detection techniques, and transmit information via wireless communication; a subsystem for person detection comprising at least one passive infrared sensor for detecting heat signatures, at least one microwave Doppler radar module for detecting micro-movements indicative of breathing or heartbeat, and an ultrasonic sensor array for proximity and obstacle detection; an environmental monitoring subsystem comprising at least one gas sensor configured to detect hazardous gases selected from methane, smoke, propane or carbon monoxide; a visual feedback subsystem that includes a camera module configured to capture real-time images and video streams; a wireless communication interface configured for transmitting multi-sensor data and video feeds to a remote mobile application interface; and a power supply comprising at least one rechargeable battery that is operationally connected to the control unit, sensors and the propulsion system, The robot system is configured to detect the presence of living people, monitor environmental hazards, and inform rescue teams in disaster areas about the current situation in real time. [2] The intelligent robot system according to claim 1, wherein the microwave Doppler radar module is adjusted to detect micro-movements within a frequency band of 10.525 GHz ± 25 MHz, and wherein the radar module is mounted on a vibration-damped mount in the front section of the chassis to minimize false motion detections due to mechanical vibrations during locomotion. [3] The intelligent robot system according to claim 1, wherein the ultrasonic sensor arrangement comprises at least two ultrasonic transceivers arranged at an angular offset of 30° to 60° relative to the forward axis of the robot, wherein the arrangement is configured to perform triangulated obstacle mapping, enabling the robot to autonomously adjust its flight path in debris-strewn corridors without operator intervention. [4] The intelligent robot system according to claim 1, wherein the gas sensor is an MQ2 module configured with a sensitivity calibration circuit with a load resistance of 20 kΩ to 30 kΩ, and wherein the output of the gas sensor is processed by an integrated analog-to-digital converter of the microcontroller to generate real-time calibrated measurements of the methane concentration levels between 200 ppm and 10,000 ppm. [5] The intelligent robot system according to claim 1, wherein the camera module is a Pi camera configured to capture images with a resolution of at least 640 × 480 pixels at 30 frames per second, wherein the camera is operationally connected to the microcontroller via an SPI interface, and wherein the captured video stream is compressed by JPEG encoding prior to transmission to the mobile application in order to reduce bandwidth requirements in disaster communication environments. [6] The intelligent robot system according to claim 1, wherein the mobile chassis is a C-shaped frame made of a lightweight aluminum alloy with impact-resistant polymer shielding, wherein the frame includes wheels mounted on a suspension driven by the DC geared motors, and wherein the suspension is configured to allow the overcoming of obstacles up to 10 centimeters in height without loss of stability. [7] The intelligent robot system according to claim 1, wherein the H-bridge motor driver is a dual-channel module configured to supply a current between 1.5 A and 2.0 A per channel, the driver also comprising heat sink elements to prevent thermal overload during prolonged operation over rocky terrain. [8] The intelligent robot system according to claim 1, wherein the wireless communication interface is configured to establish both a short-range Bluetooth connection and a long-range Wi-Fi connection, and wherein the system is also configured to dynamically switch between Bluetooth and Wi-Fi modes depending on signal strength and network availability to ensure uninterrupted data transmission to the mobile application.

Images