An unmanned aerial vehicle and a method for extinguishing a fire

Abstract

The unmanned aerial vehicle (1) is configured to carry a fire extinguishing substance as its payload. The fire is extinguished by the unmanned aerial vehicle (1) crashing into the burning object (13). The unmanned aerial vehicle (1) is equipped with multiple sensors enabling it to locate an effective target (14) from the object (13).

Description

BACKGROUND

[0001] This disclosure relates to firefighting devices, wherein the targets may be complex and hard to reach. As one example, high-rise buildings present unique challenges for firefighting operations. The increasing number of high-rise buildings in urban environments, driven by the demand for residential, commercial, and mixed-use spaces, necessitates advanced firefighting strategies. Traditional firefighting methods and equipment often fall short when dealing with the complexities and scale of high-rise fires.

[0002] One of the primary challenges of high-rise firefighting is accessibility. Firefighting vehicles, such as ladders and aerial platforms, have limited reach. For taller buildings, accessing the fire's location from the exterior becomes problematic. Moreover, many high-rise buildings are designed with a sealed façade, which prevents external access and limits the effectiveness of external firefighting measures. This limitation forces firefighters to rely on highly dangerous interior access routes, such as stairwells and elevators, which can be obstructed or compromised during a fire.

[0003] High-rise buildings require a reliable and substantial water supply to combat fires effectively. However, delivering water to great heights presents significant technical challenges. Fires in high-rise buildings can spread rapidly both vertically and horizontally due to the building's design features, such as shafts, stairwells, and open floor plans. The stack effect, where hot air rises and pulls smoke and fire upwards, exacerbates the spread of fire and smoke, making it challenging to contain.

[0004] Firefighting in high-rise buildings poses significant risks to the safety of firefighters. Navigating through smoke-filled and potentially structurally compromised environments can lead to disorientation, making it difficult for firefighters to locate the fire source and evacuate safely if needed. Effective firefighting in high-rise buildings requires seamless coordination and communication among firefighting teams.

[0005] The traditional firefighting equipment and technologies may not be adequately suited for the unique challenges presented by high-rise fires. The deployment of drones, robotics, and advanced fire suppression technologies is often limited by regulatory, logistical, and budgetary constraints.SUMMARY

[0006] This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter. Furthermore, the claimed subject matter is not limited to implementations that solve any or all disadvantages noted in any part of this disclosure.

[0007] The present disclosure relates to unmanned aerial vehicles and, more specifically, to unmanned aerial vehicles configured for firefighting missions. The unmanned aerial vehicle is configured to carry a fire extinguishing substance as its payload. The fire is extinguished by the unmanned aerial vehicle crashing into the burning object. The unmanned aerial vehicle is equipped with multiple sensors enabling it to precisely identify a suitable target within the burning object.

[0008] The unmanned aerial vehicle may autonomously address issues related to deployment speed, distance, or firefighting accuracy. Examples or targets being in fire are high-rise buildings or other hard to reach targets such as fires at sea, on vessels or platforms.

[0009] The unmanned aerial vehicle is equipped with an array of sensors that may include thermal cameras, flame sensors, positioning, heat seeking or speed sensors. The array of sensors is coupled with an onboard computer running an artificial intelligence algorithm. The device may be connected to learning algorithms that enable the unmanned aerial vehicle to pinpoint the critical area of the fire and where its effect can be maximized by selecting its target.

[0010] In one exemplary embodiment, the unmanned aerial vehicle is connected to a remote control center to where it relays the information that is gathering and the decisions its making. These decisions can be overridden by the remote control center. The information gathered from the missions may be utilized by the learning algorithms and used in future mission to complement the decision making by the unmanned aerial vehicle and / or the remote control center.

[0011] The unmanned aerial vehicle may be designed by various and alternative rule sets. One example is launched by an assisted launch, such as launching from another unmanned aerial vehicle, from a sling shot, or from an aircraft. The unmanned aerial vehicle could be designed to use minimal energy during take-off, maximizing the payload capacity to carry as much fire extinguishing substance as possible to the target.

[0012] Often on the high-rise buildings the most effective passage inside is through a window. The structure of the unmanned aerial vehicle is in one example configured to pierce through glass, having materials with high hardness, strength, and density on the nose. Examples of such materials are tungsten carbide, hardened steel, ceramic materials, or boron carbide. The shape of the nose may be designed to provide maximum impact on the glass, ensuring that the unmanned aerial vehicle proceeds through the glass and to the fire.

[0013] Many of the attendant features will be more readily appreciated as they become better understood by reference to the following detailed description considered in connection with the accompanying drawings. The embodiments described below are not limited to implementations which solve any or all the disadvantages of known unmanned aerial vehicles or drones.BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The present description will be better understood from the following detailed description read in light of the accompanying drawings, wherein FIG. 1 illustrates schematically one simplified exemplary embodiment of an unmanned aerial vehicle approaching a fire; FIG. 2 illustrates schematically one simplified exemplary embodiment of another unmanned aerial vehicle; FIG. 3 illustrates schematically one simplified exemplary embodiment of the unmanned aerial vehicle approaching another target; FIG. 4 illustrates schematically a flowchart of a method for extinguishing a fire.

[0015] Like reference numerals are used to designate like parts in the accompanying drawings.DETAILED DESCRIPTION

[0016] The detailed description provided below in connection with the appended drawings is intended as a description of the present examples and is not intended to represent the only forms in which the present example may be constructed or utilized. However, the same or equivalent functions and sequences may be accomplished by different examples.

[0017] Although the present examples are described and illustrated herein as being implemented in an unmanned aerial vehicle or a drone, the apparatus described is provided as an example and not a limitation. As those skilled in the art will appreciate, the present examples are suitable for application in a variety of different types of unmanned aerial vehicles.

[0018] Unmanned aerial vehicles, commonly known as a drones, are aircrafts without a human pilot on board. The unmanned aerial vehicles may be autonomous or be controlled by an external controller such as a wirelessly connected remote controller. During the remote-controlled scenario the unmanned aerial vehicle may comprise a subset of autonomous functions that assist the external controller.

[0019] FIG. 1 illustrates schematically one simplified exemplary embodiment of an unmanned aerial vehicle 1, abbreviated as UAV 1. The exemplary illustration is not limiting the form factor of the UAV 1, as many alternative structural forms are discussed hereinafter. The UAV 1 is intended for a single use as it is designed to be crashed into its target 14 and spread its payload, fire extinguishing substance to its target 14, an object 13 on fire. Suitable objects 13 for the disposable UAV 1 are those that are hard to reach - either because of its height, distance to it, obstacles leading to target 14 or that the object 13 itself causes risk for human firefighters to get close to it. In the example of FIG. 1, the object 13 is a burning building, and the target 14 is a window emitting smoke. The example of FIG. 3 shows the UAV 1 approaching a different kind of object 13, a ship at sea being on fire. The target 14 is the point on the ship where the fire extinguishing substance having been crashed could extinguish the fire.

[0020] Size of the UAV 1 in relation to the object 13 may vary and may be designed by predicting the most successful missions for all scales per object 13. The objects 13 may be tall as the high-rise building, when it may be relevant to emphasize quick climbing properties at the expense of maximum distance. Alternatively, the object 13 may be far, such as the ship at sea. In that case the design emphasis could be on maximum range.

[0021] The UAV 1 comprises a fuselage 10. The fuselage 10 may be a rigid structure covered by a light-weight housing. In one exemplary design, the fuselage 10 comprises external housing portions of the vehicle, i.e. the external shell. In one embodiment the UAV 1 comprises a rigid fuselage 10 and a light-weight external shell. The fuselage 10 may be made of metal, plastic, composite or any other material providing sufficient rigidity for the UAV 1. In one embodiment the UAV 1 comprises a fixed-wing structure, as exemplified in FIG. 1. In one embodiment the UAV 1 comprises a multi-rotor structure, as exemplified in FIG. 2. In one embodiment, the UAV 1 comprises a hybrid structure having fixed wings and rotors.

[0022] In one embodiment, the fuselage 10 comprises a crumble point or crumble area 11 that is configured to break first when the UAV 1 crashes into target 14. In some embodiments, the crumble area 11 is configured to operate together with an impacting edge, or nose 12 of the UAV 1 that is the first contact point of the crashing UAV 1. Depending on the designed usage, the nose 12 may be configured to pierce though glass, element wall, wood panel, fiberglass hull or other common structural materials.

[0023] Examples of nose 12 materials are hard and dense materials, such as tungsten carbide, hardened steel, tungsten-steel alloys, uranium, ceramic-cored projectiles, diamond, boron carbide or tungsten disulfide. The nose 12 may comprise only small amount of this hard material, enough to cause the glass to shatter upon high-speed impact. The crumble area 11 is configured to break after the impact. Once the glass is shattered, the fuselage 10 may release the fire extinguishing substance over the fire. The crumble area 11 is configured to provide improved distribution for the fire extinguishing substance. The crumble area 11 may be designed to release the fire extinguishing substance spreading over predetermined directions.

[0024] In one embodiment, components affecting the material-piercing properties or fire extinguishing substance spread pattern are selectable. For example, the predetermined directions are selected before commencing the flight mission, by selecting the nose 12 material or spread pattern plates, flanges, or any other mechanical structure on the UAV 1. The nose 12 or the crumble area 11 may comprise interchangeable components.

[0025] The UAV 1 comprises at least one processor 15 and a memory 16 storing instructions that, when executed, are configured to control the functions of the UAV 1. In one embodiment the unmanned aerial vehicle comprises a transceiver 17 for communicating wirelessly with a remote unit and for receiving control information. In one embodiment, the remote unit is connected to a control center, or an incident command post. The transceiver 17 may operate over radio interface or over optical or sonic transmission technologies. The incident command post may coordinate and manage emergency response efforts during a fire or other emergencies.

[0026] The processor 15 may execute commands running flying functions or artificial intelligence algorithms. The unmanned aerial vehicle may comprise multiple sensors providing spatial and positioning data. Internal sensors may comprise multiple gyroscopes configured to detect movement from multiple axis; an imaging device may provide data from nearby objects, obstacles, markers or positions. A positioning sensor such as GPS may provide positioning data that the unmanned aerial vehicle may compare to its previously stored map data. Various environmental sensors may provide information about temperature, battery capacity, humidity or wind speed. The data is used within the controlling functions of the processor 15. In one embodiment the remote unit input passes through the controlling application which communicates with the unmanned aerial vehicle. If no remote unit input is available, only the data from the sensors will be used, in order to keep the unmanned aerial vehicle balanced and proceeding towards the target 14.

[0027] A sensor array 18 is configured to detect a thermal target 14, a detail in the burning object 13. The sensor array 18 comprises at least one sensor from a group of a thermal camera, an optical camera, a radar, a Light Detection and Ranging (LIDAR) system, flame sensors, heat sensors or speed sensors. As one example, the speed sensor or an anemometer detects wind speed and / or the relative speed of the UAV 1. The wind speed and direction may also be used to assess the direction where the fire may advance and where could be the most effective target 14 within the burning object 13.

[0028] In one embodiment, the processor 15 and the memory 16 are configured to provide an artificial intelligence system configured to process data from the sensor array 18 for target 14 identification, navigation, or engagement decision-making. In one embodiment the artificial intelligence system is further configured to autonomously adjust the UAV's 1 flight path based on real-time environmental data. For example, wind direction or other information gathered around the UAV 1 may be used by the artificial intelligence to guide the flight path.

[0029] In one embodiment, the sensor array 18 is configured to detect heat signatures for target 14 identification. The heat signature detection may be applied by detecting the hottest area in the object 13 being on fire. One example of the heat signature is defining position below the hottest area, as there may be the actual source of the fire. In one embodiment, the processor 18 models the object 13 such as the high-rise building in a three-dimensional matrix having multiple segments, and the heat signature is based on the relative position between the segments. In one embodiment, the artificial intelligence defines the heat signature. The heat signature may detect weaker structures withing the object 13, such as windows or glass walls, defining those as possible targets 14 where the UAV 1 could crash into. Alternatively, or in addition the artificial intelligence algorithm may be used to detect the weaker structures by using the heat data from the sensor array 18.

[0030] In one embodiment, the artificial intelligence system comprises machine learning algorithms for differentiating between various types of targets 14 and prioritizing them based on the risk of fire spreading. In the three-dimensional matrix space, fire has many directions to spread. The sensor array 18 may be used to detect parts of the object 13 and identify flammable sections, fuel or other high-risk locations within the object 13. In one embodiment, the incident command post may relay to the UAV 1 internal structure of a building, map of corridors inside the building, weak structures such as windows. The UAV 1 may use this information to select the target 14, where the crashing would result the best effect.

[0031] The risk of fire spreading is in one example assessed by machine learning multiple previous fires with similar objects. The machine learning may utilize simulated fires that follow the steps and the outcome of previous registered fires.

[0032] The UAV 1 as disclosed herein may be a single-use device, wherein the vehicle as a whole may be completely destroyed after its mission. As a guiding principle, the unmanned aerial vehicle may be built as economically as possible. Also, many of the materials used may be environmentally friendly or easy to dispose after the crash.

[0033] In one embodiment, the unmanned aerial vehicle is configured to launch by an assisted launch. Assisted launch refers to various methods used to help UAVs 1 take off without requiring a traditional runway or extensive space. The launch systems provide the necessary initial thrust, altitude, or momentum, enabling UAVs 1 to begin their flight efficiently and effectively.

[0034] One benefits of assisted UAV 1 launch is the increased payload capacity, allowing the UAV 1 to carry more fire extinguishing substance and / or simplifying the structure of eh UAV 1. Since the UAV 1 does not need to generate its own take-off thrust, assisted launch systems allow for greater payload capacity. UAVs 1 with assisted launch capabilities can operate from a wider variety of platforms, such as ships, small clearings, or mobile launch vehicles. This flexibility increases their utility across diverse missions and environments. Assisted launch mechanisms provide the initial energy boost needed for take-off, allowing the UAV 1 to conserve onboard power for its primary mission tasks. This energy efficiency can result in longer flight durations and more extensive coverage areas. Assisted launches can be tailored to work in adverse weather or challenging conditions where traditional take-offs would be risky or impossible. This ensures that UAV 1 operations can continue even in less-than-ideal circumstances.

[0035] In one embodiment, the assisted launch is a catapult launch. A catapult system uses mechanical force to accelerate the UAV 1 along a track before release. This acceleration provides the UAV 1 with the initial speed needed to achieve lift-off. Catapults may be powered by elastic bands, compressed air, or hydraulic systems. Alternatively, a sling or a bungee cord may be used to accelerate the UAV 1 into the air. In this embodiment, the UAV 1 is attached to a stretched bungee, and when released, the stored elastic energy propels the UAV 1 forward.

[0036] In one embodiment, the assisted launch is a rail launch. This is similar to the catapult launch, but instead the UAV 1 is placed on a rail system. The rail guides the UAV 1 as it accelerates along it, ensuring stability during the initial phase of flight. The rail launch can use gravity, electromagnets, or a motorized trolley to propel the UAV 1.

[0037] In one embodiment, the assisted launch is an air launch. The UAV 1 may be launched from a larger aircraft in mid-flight. This method provides the UAV 1 with initial altitude and forward speed, effectively reducing the need for extensive onboard propulsion during take-off.

[0038] The fire extinguishing substance may any substance that is known to effectively put out a fire. Water as one example may be used, as it is easily available, but the carrying large amount of water may be difficult for the UAV 1. Water may have better effect if it is deployed as water mist into the target 14. In one embodiment, the fire extinguishing substance comprises at least one of the group of: pressurized carbon dioxide, dry chemical powders composed of monoammonium phosphate or sodium bicarbonate, clean agents, aqueous film-forming foams, wet chemicals, potassium aerosols, and foam aerosols. Carbon dioxide (CO 2 ) is a gas that displaces oxygen and cools the fire, making it effective against Class B (flammable liquids) and Class C (electrical) fires. Dry chemical powder is composed of monoammonium phosphate or sodium bicarbonate. Dry chemical powder is effective against Class A (ordinary combustibles), Class B, and Class C fires. The powder interrupts the chemical reaction of the fire triangle (fuel, heat, and oxygen). Clean agents, halocarbon or halon alternatives like HFC-236fa, HFC-227ea (FM-200), and Novec 1230 are gaseous or vaporizing liquids that extinguish fire without leaving residue. They are effective against Class A, B, and C fires and are commonly used in data centers and places with sensitive electronics. Aqueous film-forming foam (AFFF) is a water-based foam that spreads quickly over flammable liquid surfaces, smothering the fire and preventing re-ignition. It is mainly used for Class B fires and is available in portable canisters. Wet chemicals are specifically designed for Class K (kitchen) fires. Wet chemical extinguishers contain a potassium-based solution that reacts with fats and oils to form a soapy layer, cooling and smothering the fire. Potassium aerosols are compact, lightweight canisters that release fine potassium aerosol to disrupt the chemical reaction of fire. They are effective for enclosed spaces and are used in vehicles, server rooms, and other compact areas. Foam aerosols are lightweight, portable balls filled with a dry powder that releases when exposed to fire. They are tossed into the fire, where they burst and disperse extinguishing powder, suitable for Class A, B, and C fires.

[0039] FIG. 4 is a flowchart showing steps of the method for using the UAV 1. Step 400 comprises providing a communication link between the UAV 1 and the remote unit. The communication link is provided by the transceiver 17. The remote unit may be a remote controller that is in direct contact with the UAV. In one embodiment, the remote controller and the UAV 1 define a system wherein at least part of the processing occurs at the remote controller.

[0040] In step 410 a thermal target 14 is detected by the sensor array 18. The thermal target 14 is a detail within the object 13 that the UAV 1 approaches. The thermal target 14 is in one example a distinct feature within the object that can be separated by the sensor array 18. As one example, the thermal camera indicated the hottest location on a building, where the hottest location is assigned as the UAV's 1 target 14.

[0041] Step 420 comprises carrying a fire extinguishing substance as UAV's payload. The fire extinguishing payload is usually loaded onto the UAV 1 before the launch. In one embodiment, the fire extinguishing substance is integrated into the fuselage 10. In one embodiment, the fire extinguishing substance is loaded onto the UAV before the launch. In some embodiments, the UAV 1 is usable for other purposes - even for single use - and the purpose of the single use mission is defined by the payload.

[0042] In step 430 the fire extinguishing substance is released to the target 14 by crashing into the target 14. The fuselage 10 or the payload container is configured to disintegrate, burst, crack or release the fire extinguishing substance in response to the impact to the target 14.

[0043] In one embodiment, the UAV 1 comprises a backend system learning to pinpoint a critical area of the fire and the UAV 1 choosing the target 14 for crashing into while having a maximum effect, through an artificial intelligence algorithm using multiple previous crashing results. The outcomes of previous UAV 1 impacts are in one embodiment used to develop a neural network that can autonomously determine the optimal flight path for achieving maximum impact on extinguishing a fire, for example from a building. Additionally, the machine learning may be used to mitigate the effects of the impact on the building. The use of machine learning, specifically neural networks, offers the potential to create adaptive systems that can learn from previous experiences. By analysing data from past UAV 1 impacts, a neural network can be trained to optimize flight paths for future missions, improving the likelihood of mission success.

[0044] The first step in training the neural network is to collect data from previous UAV 1 missions. Exemplary embodiments of the data being collected is Flight Path Data, Impact Data and Result Assessment Data. Flight Path Data comprises information on the UAV's 1 flight trajectory, speed, angle of approach, and altitude at various points leading up to the impact. Impact Data comprises details of the impact point on the building, including the location, angle, and force of impact. Result Assessment Data comprises information on the success of fire extinguishing within the building, damage caused to the building including structural integrity, damage spread, and collapse patterns.

[0045] This data is collected using various sensors and recording equipment on the UAV 1 and at the impact site. The data is then aggregated and prepared for analysis. Data preparation may include filtering out noise, normalizing values, and segmenting data into relevant categories, such as successful vs. unsuccessful missions.

[0046] The next step is to extract features from the collected data that are relevant to optimizing UAV 1 flight paths. An exemplar list of features are: Entry Angle, the angle at which the UAV 1 approaches the target 14; Impact Velocity, the speed of the UAV 1 at the moment of impact; Target Location, the specific area of the building that was targeted; Heat Signatures, patterns of detecting the fire in the building, paths of smoke and hot locations; Structural Weakness, identifiable weak points in the building's structure; and Environmental Conditions, external factors such as wind speed, weather conditions, and time of day. Feature extraction ensures that the neural network has meaningful data to learn from. The features are chosen based on their relevance to the outcome of the impact and their potential influence on achieving maximum effect.

[0047] The neural network architecture is designed to process the extracted features and predict the optimal flight path for a given target 14. The architecture includes an input layer, hidden layers and output layer. The input layer consists of nodes corresponding to the extracted features such as entry angle or impact velocity. Hidden layers comprise one or more hidden layers with neurons that process input data, apply weights, and activation functions to model complex relationships. The output layer comprises nodes that provide the predicted optimal flight path parameters, such as trajectory, speed or angle.

[0048] The neural network is designed to be flexible and scalable, allowing for adjustments in the number of layers and neurons as needed to improve training accuracy. Training the neural network involves feeding the neural network with input data, features, from previous missions and comparing its output, predicted flight path, with the actual outcomes - how well the fire has been extinguished and how much damage was caused to the target 14.

[0049] The training process includes the following steps: Forward Propagation: Input data is passed through the network, and predictions are made. Loss Calculation: The difference between the predicted flight path and the actual successful flight path from past missions is calculated using a loss function. The loss function measures how far off the predictions are from the optimal paths. Backpropagation: The neural network adjusts its weights and biases based on the loss calculated. This is done using gradient descent or other optimization algorithms to minimize the loss function. Iteration: The forward propagation, loss calculation, and backpropagation steps are repeated iteratively using a training dataset until the neural network's predictions converge toward the actual successful flight paths.

[0050] Once trained, the neural network is validated using a separate set of data that was not included in the training phase. This ensures that the network can generalize its predictions to new, unseen scenarios. The network's performance is evaluated based on its ability to recommend flight paths that maximize impact on high-rise buildings. Testing in simulated environments can further validate the network's performance, where various scenarios are simulated to test the network's adaptability and accuracy.

[0051] After successful validation, the trained neural network is integrated into the UAV's 1 onboard systems. During real-time operation, the UAV 1 gathers real-time data on environmental conditions and the object 13, the building's characteristics. This data is fed into the neural network, which computes the optimal flight path to achieve maximum impact to target 14, based on its training. The UAV 1 then adjusts its trajectory and speed according to the neural network's output.

[0052] The neural network continues to learn post-deployment by collecting data from each new mission and refining its model. This continuous learning process enables the UAV 1 to adapt to new conditions and improve its targeting effectiveness over time.

[0053] An unmanned aerial vehicle is disclosed herein, comprising a fuselage; a transceiver configured to provide a communication link between the unmanned aerial vehicle and a remote unit; and a sensor array configured to detect a thermal target. The unmanned aerial vehicle is configured to carry a fire extinguishing substance as its payload. The unmanned aerial vehicle is configured to release the fire extinguishing substance to a target by crashing into the target. In one embodiment, the unmanned aerial vehicle comprises at least one processor and a memory storing instructions that, when executed, are configured to provide an artificial intelligence system configured to process data from the sensor array for target identification, navigation, or engagement decision-making; and the artificial intelligence system is further configured to autonomously adjust the unmanned aerial vehicle's flight path based on real-time environmental data. In one embodiment, the sensor array is configured to detect heat signatures for target identification. In one embodiment, the artificial intelligence system comprises machine learning algorithms for differentiating between various types of targets and prioritizing them based on the risk of fire spreading. In one embodiment, the artificial intelligence system comprises machine learning algorithms for differentiating between various types of targets and prioritizing them based on the risk of fire spreading. In one embodiment, the unmanned aerial vehicle is configured to launch by an assisted launch. In one embodiment, the assisted launch is a catapult launch, or a sling launch configured to accelerate the vehicle to flight speed. In one embodiment, the assisted launch is a rail launch configured to accelerate the vehicle to flight speed. In one embodiment, the assisted launch is an air launch from an aircraft. In one embodiment, the unmanned aerial vehicle comprises a nose configured to shatter glass upon impact. In one embodiment, the fire extinguishing substance comprises at least one of the group of: pressurized carbon dioxide, dry chemical powders composed of monoammonium phosphate or sodium bicarbonate, clean agents, aqueous film-forming foams, wet chemicals, potassium aerosols, and foam aerosols. In one embodiment, the unmanned aerial vehicle is configured to learn to pinpoint a critical area of the fire and choosing the target for crashing into while having a maximum effect, through an artificial intelligence algorithm using multiple previous crashing results. In one embodiment, the sensor array comprises at least one sensor from a group of a thermal camera, an optical camera, a radar, and a LIDAR.

[0054] Alternatively, or in addition, a method for extinguishing a fire by an unmanned aerial vehicle is disclosed herein. Said vehicle comprises a fuselage. The method comprises the steps of providing a communication link between the unmanned aerial vehicle and a remote unit by a transceiver; detecting a thermal target by a sensor array; the unmanned aerial vehicle carrying a fire extinguishing substance as its payload; and releasing the fire extinguishing substance to a target by crashing into the target. In one embodiment, the method comprises a step of an artificial intelligence system processing data from the sensor array for target identification, navigation, or engagement decision-making; and the artificial intelligence system is further configured to autonomously adjust the unmanned aerial vehicle's flight path based on real-time environmental data.

[0055] Alternatively, or in addition, the controlling functionality described herein can be performed, at least in part, by one or more hardware components or hardware logic components. An example of the control system described hereinbefore is a computing-based device comprising one or more processors which may be microprocessors, controllers or any other suitable type of processors for processing computer-executable instructions to control the operation of the device in order to control one or more sensors, receive sensor data and use the sensor data. The control system may be positioned on a host system and connected to the apparatus via a signal cable or the messages between the host and the apparatus may be transmitted wirelessly. The computer-executable instructions may be provided using any computer-readable media that is accessible by a computing-based device. Computer-readable media may include, for example, computer storage media, such as memory and communications media. Computer storage media, such as memory, includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information, such as computer-readable instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, RAM, ROM, EPROM, EEPROM, flash memory, or other memory technology, CD-ROM, digital versatile disks (DVD), or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information for access by a computing device. In contrast, communication media may embody computer-readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave, or other transport mechanism. As defined herein, computer storage media does not include communication media. Therefore, a computer storage medium should not be interpreted to be a propagating signal per se. Propagated signals may be present in a computer storage media, but propagated signals per se are not examples of computer storage media. Although the computer storage media is shown within the computing-based device, it will be appreciated that the storage may be distributed or located remotely and accessed via a network or other communication link, for example, by using a communication interface.

[0056] The unmanned aerial vehicle or the external controller may comprise an input / output controller arranged to output display information to a display device which may be separate from or integral to the unmanned aerial vehicle or the external controller. The input / output controller is also arranged to receive and process input from one or more devices, such as a user input device (e.g. a mouse, keyboard, camera, microphone or other sensor). The remote-controlled unmanned aerial vehicle may use various input or output information, or metrics received from sensors, from the host system or as commands from the external controller. In one example, the external controller is a smartphone connected wirelessly to the unmanned aerial vehicle.

[0057] The methods described herein may be performed by software in machine-readable form on a tangible storage medium e.g. in the form of a computer program comprising computer program code means adapted to perform all the steps of any of the methods described herein when the program is run on a computer and where the computer program may be embodied on a computer-readable medium. Examples of tangible storage media include computer storage devices comprising computer-readable media, such as disks, thumb drives, memory etc. and do not only include propagated signals. Propagated signals may be present in a tangible storage media, but propagated signals per se are not examples of tangible storage media. The software can be suitable for execution on a parallel processor or a serial processor such that the method steps may be carried out in any suitable order, or simultaneously.

[0058] Any range or device value given herein may be extended or altered without losing the effect sought.

[0059] Although at least a portion of the subject matter has been described in language specific to structural features and / or acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as examples of implementing the claims and other equivalent features and acts are intended to be within the scope of the claims.

[0060] It will be understood that the benefits and advantages described above may relate to one embodiment or may relate to several embodiments. The embodiments are not limited to those that solve any or all of the stated problems or those that have any or all of the stated benefits and advantages. It will further be understood that reference to 'an' item refers to one or more of those items.

[0061] The steps of the methods described herein may be carried out in any suitable order, or simultaneously where appropriate. Additionally, individual blocks may be deleted from any of the methods without departing from the spirit and scope of the subject matter described herein. Aspects of any of the examples described above may be combined with aspects of any of the other examples described to form further examples without losing the effect sought.

[0062] The term 'comprising' is used herein to mean including the method blocks or elements identified, but that such blocks or elements do not comprise an exclusive list and a method or apparatus may contain additional blocks or elements.

[0063] It will be understood that the above description is given by way of example only and that various modifications may be made by those skilled in the art. The above specification, examples and data provide a complete description of the structure and use of exemplary embodiments. Although various embodiments have been described above with a certain degree of particularity, or with reference to one or more individual embodiments, those skilled in the art could make numerous alterations to the disclosed embodiments without departing from the spirit or scope of this specification.

Examples

Embodiment Construction

[0016]The detailed description provided below in connection with the appended drawings is intended as a description of the present examples and is not intended to represent the only forms in which the present example may be constructed or utilized. However, the same or equivalent functions and sequences may be accomplished by different examples.

[0017]Although the present examples are described and illustrated herein as being implemented in an unmanned aerial vehicle or a drone, the apparatus described is provided as an example and not a limitation. As those skilled in the art will appreciate, the present examples are suitable for application in a variety of different types of unmanned aerial vehicles.

[0018]Unmanned aerial vehicles, commonly known as a drones, are aircrafts without a human pilot on board. The unmanned aerial vehicles may be autonomous or be controlled by an external controller such as a wirelessly connected remote controller. During the remote-controlled scenario the...

BACKGROUND

[0001] This disclosure relates to firefighting devices, wherein the targets may be complex and hard to reach. As one example, high-rise buildings present unique challenges for firefighting operations. The increasing number of high-rise buildings in urban environments, driven by the demand for residential, commercial, and mixed-use spaces, necessitates advanced firefighting strategies. Traditional firefighting methods and equipment often fall short when dealing with the complexities and scale of high-rise fires.

[0002] One of the primary challenges of high-rise firefighting is accessibility. Firefighting vehicles, such as ladders and aerial platforms, have limited reach. For taller buildings, accessing the fire's location from the exterior becomes problematic. Moreover, many high-rise buildings are designed with a sealed façade, which prevents external access and limits the effectiveness of external firefighting measures. This limitation forces firefighters to rely on highly dangerous interior access routes, such as stairwells and elevators, which can be obstructed or compromised during a fire.

[0003] High-rise buildings require a reliable and substantial water supply to combat fires effectively. However, delivering water to great heights presents significant technical challenges. Fires in high-rise buildings can spread rapidly both vertically and horizontally due to the building's design features, such as shafts, stairwells, and open floor plans. The stack effect, where hot air rises and pulls smoke and fire upwards, exacerbates the spread of fire and smoke, making it challenging to contain.

[0004] Firefighting in high-rise buildings poses significant risks to the safety of firefighters. Navigating through smoke-filled and potentially structurally compromised environments can lead to disorientation, making it difficult for firefighters to locate the fire source and evacuate safely if needed. Effective firefighting in high-rise buildings requires seamless coordination and communication among firefighting teams.

[0005] The traditional firefighting equipment and technologies may not be adequately suited for the unique challenges presented by high-rise fires. The deployment of drones, robotics, and advanced fire suppression technologies is often limited by regulatory, logistical, and budgetary constraints.SUMMARY

[0006] This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter. Furthermore, the claimed subject matter is not limited to implementations that solve any or all disadvantages noted in any part of this disclosure.

[0007] The present disclosure relates to unmanned aerial vehicles and, more specifically, to unmanned aerial vehicles configured for firefighting missions. The unmanned aerial vehicle is configured to carry a fire extinguishing substance as its payload. The fire is extinguished by the unmanned aerial vehicle crashing into the burning object. The unmanned aerial vehicle is equipped with multiple sensors enabling it to precisely identify a suitable target within the burning object.

[0008] The unmanned aerial vehicle may autonomously address issues related to deployment speed, distance, or firefighting accuracy. Examples or targets being in fire are high-rise buildings or other hard to reach targets such as fires at sea, on vessels or platforms.

[0009] The unmanned aerial vehicle is equipped with an array of sensors that may include thermal cameras, flame sensors, positioning, heat seeking or speed sensors. The array of sensors is coupled with an onboard computer running an artificial intelligence algorithm. The device may be connected to learning algorithms that enable the unmanned aerial vehicle to pinpoint the critical area of the fire and where its effect can be maximized by selecting its target.

[0010] In one exemplary embodiment, the unmanned aerial vehicle is connected to a remote control center to where it relays the information that is gathering and the decisions its making. These decisions can be overridden by the remote control center. The information gathered from the missions may be utilized by the learning algorithms and used in future mission to complement the decision making by the unmanned aerial vehicle and / or the remote control center.

[0011] The unmanned aerial vehicle may be designed by various and alternative rule sets. One example is launched by an assisted launch, such as launching from another unmanned aerial vehicle, from a sling shot, or from an aircraft. The unmanned aerial vehicle could be designed to use minimal energy during take-off, maximizing the payload capacity to carry as much fire extinguishing substance as possible to the target.

[0012] Often on the high-rise buildings the most effective passage inside is through a window. The structure of the unmanned aerial vehicle is in one example configured to pierce through glass, having materials with high hardness, strength, and density on the nose. Examples of such materials are tungsten carbide, hardened steel, ceramic materials, or boron carbide. The shape of the nose may be designed to provide maximum impact on the glass, ensuring that the unmanned aerial vehicle proceeds through the glass and to the fire.

[0013] Many of the attendant features will be more readily appreciated as they become better understood by reference to the following detailed description considered in connection with the accompanying drawings. The embodiments described below are not limited to implementations which solve any or all the disadvantages of known unmanned aerial vehicles or drones.BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The present description will be better understood from the following detailed description read in light of the accompanying drawings, wherein FIG. 1 illustrates schematically one simplified exemplary embodiment of an unmanned aerial vehicle approaching a fire; FIG. 2 illustrates schematically one simplified exemplary embodiment of another unmanned aerial vehicle; FIG. 3 illustrates schematically one simplified exemplary embodiment of the unmanned aerial vehicle approaching another target; FIG. 4 illustrates schematically a flowchart of a method for extinguishing a fire.

[0015] Like reference numerals are used to designate like parts in the accompanying drawings.DETAILED DESCRIPTION

[0016] The detailed description provided below in connection with the appended drawings is intended as a description of the present examples and is not intended to represent the only forms in which the present example may be constructed or utilized. However, the same or equivalent functions and sequences may be accomplished by different examples.

[0017] Although the present examples are described and illustrated herein as being implemented in an unmanned aerial vehicle or a drone, the apparatus described is provided as an example and not a limitation. As those skilled in the art will appreciate, the present examples are suitable for application in a variety of different types of unmanned aerial vehicles.

[0018] Unmanned aerial vehicles, commonly known as a drones, are aircrafts without a human pilot on board. The unmanned aerial vehicles may be autonomous or be controlled by an external controller such as a wirelessly connected remote controller. During the remote-controlled scenario the unmanned aerial vehicle may comprise a subset of autonomous functions that assist the external controller.

[0019] FIG. 1 illustrates schematically one simplified exemplary embodiment of an unmanned aerial vehicle 1, abbreviated as UAV 1. The exemplary illustration is not limiting the form factor of the UAV 1, as many alternative structural forms are discussed hereinafter. The UAV 1 is intended for a single use as it is designed to be crashed into its target 14 and spread its payload, fire extinguishing substance to its target 14, an object 13 on fire. Suitable objects 13 for the disposable UAV 1 are those that are hard to reach - either because of its height, distance to it, obstacles leading to target 14 or that the object 13 itself causes risk for human firefighters to get close to it. In the example of FIG. 1, the object 13 is a burning building, and the target 14 is a window emitting smoke. The example of FIG. 3 shows the UAV 1 approaching a different kind of object 13, a ship at sea being on fire. The target 14 is the point on the ship where the fire extinguishing substance having been crashed could extinguish the fire.

[0020] Size of the UAV 1 in relation to the object 13 may vary and may be designed by predicting the most successful missions for all scales per object 13. The objects 13 may be tall as the high-rise building, when it may be relevant to emphasize quick climbing properties at the expense of maximum distance. Alternatively, the object 13 may be far, such as the ship at sea. In that case the design emphasis could be on maximum range.

[0021] The UAV 1 comprises a fuselage 10. The fuselage 10 may be a rigid structure covered by a light-weight housing. In one exemplary design, the fuselage 10 comprises external housing portions of the vehicle, i.e. the external shell. In one embodiment the UAV 1 comprises a rigid fuselage 10 and a light-weight external shell. The fuselage 10 may be made of metal, plastic, composite or any other material providing sufficient rigidity for the UAV 1. In one embodiment the UAV 1 comprises a fixed-wing structure, as exemplified in FIG. 1. In one embodiment the UAV 1 comprises a multi-rotor structure, as exemplified in FIG. 2. In one embodiment, the UAV 1 comprises a hybrid structure having fixed wings and rotors.

[0022] In one embodiment, the fuselage 10 comprises a crumble point or crumble area 11 that is configured to break first when the UAV 1 crashes into target 14. In some embodiments, the crumble area 11 is configured to operate together with an impacting edge, or nose 12 of the UAV 1 that is the first contact point of the crashing UAV 1. Depending on the designed usage, the nose 12 may be configured to pierce though glass, element wall, wood panel, fiberglass hull or other common structural materials.

[0023] Examples of nose 12 materials are hard and dense materials, such as tungsten carbide, hardened steel, tungsten-steel alloys, uranium, ceramic-cored projectiles, diamond, boron carbide or tungsten disulfide. The nose 12 may comprise only small amount of this hard material, enough to cause the glass to shatter upon high-speed impact. The crumble area 11 is configured to break after the impact. Once the glass is shattered, the fuselage 10 may release the fire extinguishing substance over the fire. The crumble area 11 is configured to provide improved distribution for the fire extinguishing substance. The crumble area 11 may be designed to release the fire extinguishing substance spreading over predetermined directions.

[0024] In one embodiment, components affecting the material-piercing properties or fire extinguishing substance spread pattern are selectable. For example, the predetermined directions are selected before commencing the flight mission, by selecting the nose 12 material or spread pattern plates, flanges, or any other mechanical structure on the UAV 1. The nose 12 or the crumble area 11 may comprise interchangeable components.

[0025] The UAV 1 comprises at least one processor 15 and a memory 16 storing instructions that, when executed, are configured to control the functions of the UAV 1. In one embodiment the unmanned aerial vehicle comprises a transceiver 17 for communicating wirelessly with a remote unit and for receiving control information. In one embodiment, the remote unit is connected to a control center, or an incident command post. The transceiver 17 may operate over radio interface or over optical or sonic transmission technologies. The incident command post may coordinate and manage emergency response efforts during a fire or other emergencies.

[0026] The processor 15 may execute commands running flying functions or artificial intelligence algorithms. The unmanned aerial vehicle may comprise multiple sensors providing spatial and positioning data. Internal sensors may comprise multiple gyroscopes configured to detect movement from multiple axis; an imaging device may provide data from nearby objects, obstacles, markers or positions. A positioning sensor such as GPS may provide positioning data that the unmanned aerial vehicle may compare to its previously stored map data. Various environmental sensors may provide information about temperature, battery capacity, humidity or wind speed. The data is used within the controlling functions of the processor 15. In one embodiment the remote unit input passes through the controlling application which communicates with the unmanned aerial vehicle. If no remote unit input is available, only the data from the sensors will be used, in order to keep the unmanned aerial vehicle balanced and proceeding towards the target 14.

[0027] A sensor array 18 is configured to detect a thermal target 14, a detail in the burning object 13. The sensor array 18 comprises at least one sensor from a group of a thermal camera, an optical camera, a radar, a Light Detection and Ranging (LIDAR) system, flame sensors, heat sensors or speed sensors. As one example, the speed sensor or an anemometer detects wind speed and / or the relative speed of the UAV 1. The wind speed and direction may also be used to assess the direction where the fire may advance and where could be the most effective target 14 within the burning object 13.

[0028] In one embodiment, the processor 15 and the memory 16 are configured to provide an artificial intelligence system configured to process data from the sensor array 18 for target 14 identification, navigation, or engagement decision-making. In one embodiment the artificial intelligence system is further configured to autonomously adjust the UAV's 1 flight path based on real-time environmental data. For example, wind direction or other information gathered around the UAV 1 may be used by the artificial intelligence to guide the flight path.

[0029] In one embodiment, the sensor array 18 is configured to detect heat signatures for target 14 identification. The heat signature detection may be applied by detecting the hottest area in the object 13 being on fire. One example of the heat signature is defining position below the hottest area, as there may be the actual source of the fire. In one embodiment, the processor 18 models the object 13 such as the high-rise building in a three-dimensional matrix having multiple segments, and the heat signature is based on the relative position between the segments. In one embodiment, the artificial intelligence defines the heat signature. The heat signature may detect weaker structures withing the object 13, such as windows or glass walls, defining those as possible targets 14 where the UAV 1 could crash into. Alternatively, or in addition the artificial intelligence algorithm may be used to detect the weaker structures by using the heat data from the sensor array 18.

[0030] In one embodiment, the artificial intelligence system comprises machine learning algorithms for differentiating between various types of targets 14 and prioritizing them based on the risk of fire spreading. In the three-dimensional matrix space, fire has many directions to spread. The sensor array 18 may be used to detect parts of the object 13 and identify flammable sections, fuel or other high-risk locations within the object 13. In one embodiment, the incident command post may relay to the UAV 1 internal structure of a building, map of corridors inside the building, weak structures such as windows. The UAV 1 may use this information to select the target 14, where the crashing would result the best effect.

[0031] The risk of fire spreading is in one example assessed by machine learning multiple previous fires with similar objects. The machine learning may utilize simulated fires that follow the steps and the outcome of previous registered fires.

[0032] The UAV 1 as disclosed herein may be a single-use device, wherein the vehicle as a whole may be completely destroyed after its mission. As a guiding principle, the unmanned aerial vehicle may be built as economically as possible. Also, many of the materials used may be environmentally friendly or easy to dispose after the crash.

[0033] In one embodiment, the unmanned aerial vehicle is configured to launch by an assisted launch. Assisted launch refers to various methods used to help UAVs 1 take off without requiring a traditional runway or extensive space. The launch systems provide the necessary initial thrust, altitude, or momentum, enabling UAVs 1 to begin their flight efficiently and effectively.

[0034] One benefits of assisted UAV 1 launch is the increased payload capacity, allowing the UAV 1 to carry more fire extinguishing substance and / or simplifying the structure of eh UAV 1. Since the UAV 1 does not need to generate its own take-off thrust, assisted launch systems allow for greater payload capacity. UAVs 1 with assisted launch capabilities can operate from a wider variety of platforms, such as ships, small clearings, or mobile launch vehicles. This flexibility increases their utility across diverse missions and environments. Assisted launch mechanisms provide the initial energy boost needed for take-off, allowing the UAV 1 to conserve onboard power for its primary mission tasks. This energy efficiency can result in longer flight durations and more extensive coverage areas. Assisted launches can be tailored to work in adverse weather or challenging conditions where traditional take-offs would be risky or impossible. This ensures that UAV 1 operations can continue even in less-than-ideal circumstances.

[0035] In one embodiment, the assisted launch is a catapult launch. A catapult system uses mechanical force to accelerate the UAV 1 along a track before release. This acceleration provides the UAV 1 with the initial speed needed to achieve lift-off. Catapults may be powered by elastic bands, compressed air, or hydraulic systems. Alternatively, a sling or a bungee cord may be used to accelerate the UAV 1 into the air. In this embodiment, the UAV 1 is attached to a stretched bungee, and when released, the stored elastic energy propels the UAV 1 forward.

[0036] In one embodiment, the assisted launch is a rail launch. This is similar to the catapult launch, but instead the UAV 1 is placed on a rail system. The rail guides the UAV 1 as it accelerates along it, ensuring stability during the initial phase of flight. The rail launch can use gravity, electromagnets, or a motorized trolley to propel the UAV 1.

[0037] In one embodiment, the assisted launch is an air launch. The UAV 1 may be launched from a larger aircraft in mid-flight. This method provides the UAV 1 with initial altitude and forward speed, effectively reducing the need for extensive onboard propulsion during take-off.

[0038] The fire extinguishing substance may any substance that is known to effectively put out a fire. Water as one example may be used, as it is easily available, but the carrying large amount of water may be difficult for the UAV 1. Water may have better effect if it is deployed as water mist into the target 14. In one embodiment, the fire extinguishing substance comprises at least one of the group of: pressurized carbon dioxide, dry chemical powders composed of monoammonium phosphate or sodium bicarbonate, clean agents, aqueous film-forming foams, wet chemicals, potassium aerosols, and foam aerosols. Carbon dioxide (CO 2 ) is a gas that displaces oxygen and cools the fire, making it effective against Class B (flammable liquids) and Class C (electrical) fires. Dry chemical powder is composed of monoammonium phosphate or sodium bicarbonate. Dry chemical powder is effective against Class A (ordinary combustibles), Class B, and Class C fires. The powder interrupts the chemical reaction of the fire triangle (fuel, heat, and oxygen). Clean agents, halocarbon or halon alternatives like HFC-236fa, HFC-227ea (FM-200), and Novec 1230 are gaseous or vaporizing liquids that extinguish fire without leaving residue. They are effective against Class A, B, and C fires and are commonly used in data centers and places with sensitive electronics. Aqueous film-forming foam (AFFF) is a water-based foam that spreads quickly over flammable liquid surfaces, smothering the fire and preventing re-ignition. It is mainly used for Class B fires and is available in portable canisters. Wet chemicals are specifically designed for Class K (kitchen) fires. Wet chemical extinguishers contain a potassium-based solution that reacts with fats and oils to form a soapy layer, cooling and smothering the fire. Potassium aerosols are compact, lightweight canisters that release fine potassium aerosol to disrupt the chemical reaction of fire. They are effective for enclosed spaces and are used in vehicles, server rooms, and other compact areas. Foam aerosols are lightweight, portable balls filled with a dry powder that releases when exposed to fire. They are tossed into the fire, where they burst and disperse extinguishing powder, suitable for Class A, B, and C fires.

[0039] FIG. 4 is a flowchart showing steps of the method for using the UAV 1. Step 400 comprises providing a communication link between the UAV 1 and the remote unit. The communication link is provided by the transceiver 17. The remote unit may be a remote controller that is in direct contact with the UAV. In one embodiment, the remote controller and the UAV 1 define a system wherein at least part of the processing occurs at the remote controller.

[0040] In step 410 a thermal target 14 is detected by the sensor array 18. The thermal target 14 is a detail within the object 13 that the UAV 1 approaches. The thermal target 14 is in one example a distinct feature within the object that can be separated by the sensor array 18. As one example, the thermal camera indicated the hottest location on a building, where the hottest location is assigned as the UAV's 1 target 14.

[0041] Step 420 comprises carrying a fire extinguishing substance as UAV's payload. The fire extinguishing payload is usually loaded onto the UAV 1 before the launch. In one embodiment, the fire extinguishing substance is integrated into the fuselage 10. In one embodiment, the fire extinguishing substance is loaded onto the UAV before the launch. In some embodiments, the UAV 1 is usable for other purposes - even for single use - and the purpose of the single use mission is defined by the payload.

[0042] In step 430 the fire extinguishing substance is released to the target 14 by crashing into the target 14. The fuselage 10 or the payload container is configured to disintegrate, burst, crack or release the fire extinguishing substance in response to the impact to the target 14.

[0043] In one embodiment, the UAV 1 comprises a backend system learning to pinpoint a critical area of the fire and the UAV 1 choosing the target 14 for crashing into while having a maximum effect, through an artificial intelligence algorithm using multiple previous crashing results. The outcomes of previous UAV 1 impacts are in one embodiment used to develop a neural network that can autonomously determine the optimal flight path for achieving maximum impact on extinguishing a fire, for example from a building. Additionally, the machine learning may be used to mitigate the effects of the impact on the building. The use of machine learning, specifically neural networks, offers the potential to create adaptive systems that can learn from previous experiences. By analysing data from past UAV 1 impacts, a neural network can be trained to optimize flight paths for future missions, improving the likelihood of mission success.

[0044] The first step in training the neural network is to collect data from previous UAV 1 missions. Exemplary embodiments of the data being collected is Flight Path Data, Impact Data and Result Assessment Data. Flight Path Data comprises information on the UAV's 1 flight trajectory, speed, angle of approach, and altitude at various points leading up to the impact. Impact Data comprises details of the impact point on the building, including the location, angle, and force of impact. Result Assessment Data comprises information on the success of fire extinguishing within the building, damage caused to the building including structural integrity, damage spread, and collapse patterns.

[0045] This data is collected using various sensors and recording equipment on the UAV 1 and at the impact site. The data is then aggregated and prepared for analysis. Data preparation may include filtering out noise, normalizing values, and segmenting data into relevant categories, such as successful vs. unsuccessful missions.

[0046] The next step is to extract features from the collected data that are relevant to optimizing UAV 1 flight paths. An exemplar list of features are: Entry Angle, the angle at which the UAV 1 approaches the target 14; Impact Velocity, the speed of the UAV 1 at the moment of impact; Target Location, the specific area of the building that was targeted; Heat Signatures, patterns of detecting the fire in the building, paths of smoke and hot locations; Structural Weakness, identifiable weak points in the building's structure; and Environmental Conditions, external factors such as wind speed, weather conditions, and time of day. Feature extraction ensures that the neural network has meaningful data to learn from. The features are chosen based on their relevance to the outcome of the impact and their potential influence on achieving maximum effect.

[0047] The neural network architecture is designed to process the extracted features and predict the optimal flight path for a given target 14. The architecture includes an input layer, hidden layers and output layer. The input layer consists of nodes corresponding to the extracted features such as entry angle or impact velocity. Hidden layers comprise one or more hidden layers with neurons that process input data, apply weights, and activation functions to model complex relationships. The output layer comprises nodes that provide the predicted optimal flight path parameters, such as trajectory, speed or angle.

[0048] The neural network is designed to be flexible and scalable, allowing for adjustments in the number of layers and neurons as needed to improve training accuracy. Training the neural network involves feeding the neural network with input data, features, from previous missions and comparing its output, predicted flight path, with the actual outcomes - how well the fire has been extinguished and how much damage was caused to the target 14.

[0049] The training process includes the following steps: Forward Propagation: Input data is passed through the network, and predictions are made. Loss Calculation: The difference between the predicted flight path and the actual successful flight path from past missions is calculated using a loss function. The loss function measures how far off the predictions are from the optimal paths. Backpropagation: The neural network adjusts its weights and biases based on the loss calculated. This is done using gradient descent or other optimization algorithms to minimize the loss function. Iteration: The forward propagation, loss calculation, and backpropagation steps are repeated iteratively using a training dataset until the neural network's predictions converge toward the actual successful flight paths.

[0050] Once trained, the neural network is validated using a separate set of data that was not included in the training phase. This ensures that the network can generalize its predictions to new, unseen scenarios. The network's performance is evaluated based on its ability to recommend flight paths that maximize impact on high-rise buildings. Testing in simulated environments can further validate the network's performance, where various scenarios are simulated to test the network's adaptability and accuracy.

[0051] After successful validation, the trained neural network is integrated into the UAV's 1 onboard systems. During real-time operation, the UAV 1 gathers real-time data on environmental conditions and the object 13, the building's characteristics. This data is fed into the neural network, which computes the optimal flight path to achieve maximum impact to target 14, based on its training. The UAV 1 then adjusts its trajectory and speed according to the neural network's output.

[0052] The neural network continues to learn post-deployment by collecting data from each new mission and refining its model. This continuous learning process enables the UAV 1 to adapt to new conditions and improve its targeting effectiveness over time.

[0053] An unmanned aerial vehicle is disclosed herein, comprising a fuselage; a transceiver configured to provide a communication link between the unmanned aerial vehicle and a remote unit; and a sensor array configured to detect a thermal target. The unmanned aerial vehicle is configured to carry a fire extinguishing substance as its payload. The unmanned aerial vehicle is configured to release the fire extinguishing substance to a target by crashing into the target. In one embodiment, the unmanned aerial vehicle comprises at least one processor and a memory storing instructions that, when executed, are configured to provide an artificial intelligence system configured to process data from the sensor array for target identification, navigation, or engagement decision-making; and the artificial intelligence system is further configured to autonomously adjust the unmanned aerial vehicle's flight path based on real-time environmental data. In one embodiment, the sensor array is configured to detect heat signatures for target identification. In one embodiment, the artificial intelligence system comprises machine learning algorithms for differentiating between various types of targets and prioritizing them based on the risk of fire spreading. In one embodiment, the artificial intelligence system comprises machine learning algorithms for differentiating between various types of targets and prioritizing them based on the risk of fire spreading. In one embodiment, the unmanned aerial vehicle is configured to launch by an assisted launch. In one embodiment, the assisted launch is a catapult launch, or a sling launch configured to accelerate the vehicle to flight speed. In one embodiment, the assisted launch is a rail launch configured to accelerate the vehicle to flight speed. In one embodiment, the assisted launch is an air launch from an aircraft. In one embodiment, the unmanned aerial vehicle comprises a nose configured to shatter glass upon impact. In one embodiment, the fire extinguishing substance comprises at least one of the group of: pressurized carbon dioxide, dry chemical powders composed of monoammonium phosphate or sodium bicarbonate, clean agents, aqueous film-forming foams, wet chemicals, potassium aerosols, and foam aerosols. In one embodiment, the unmanned aerial vehicle is configured to learn to pinpoint a critical area of the fire and choosing the target for crashing into while having a maximum effect, through an artificial intelligence algorithm using multiple previous crashing results. In one embodiment, the sensor array comprises at least one sensor from a group of a thermal camera, an optical camera, a radar, and a LIDAR.

[0054] Alternatively, or in addition, a method for extinguishing a fire by an unmanned aerial vehicle is disclosed herein. Said vehicle comprises a fuselage. The method comprises the steps of providing a communication link between the unmanned aerial vehicle and a remote unit by a transceiver; detecting a thermal target by a sensor array; the unmanned aerial vehicle carrying a fire extinguishing substance as its payload; and releasing the fire extinguishing substance to a target by crashing into the target. In one embodiment, the method comprises a step of an artificial intelligence system processing data from the sensor array for target identification, navigation, or engagement decision-making; and the artificial intelligence system is further configured to autonomously adjust the unmanned aerial vehicle's flight path based on real-time environmental data.

[0055] Alternatively, or in addition, the controlling functionality described herein can be performed, at least in part, by one or more hardware components or hardware logic components. An example of the control system described hereinbefore is a computing-based device comprising one or more processors which may be microprocessors, controllers or any other suitable type of processors for processing computer-executable instructions to control the operation of the device in order to control one or more sensors, receive sensor data and use the sensor data. The control system may be positioned on a host system and connected to the apparatus via a signal cable or the messages between the host and the apparatus may be transmitted wirelessly. The computer-executable instructions may be provided using any computer-readable media that is accessible by a computing-based device. Computer-readable media may include, for example, computer storage media, such as memory and communications media. Computer storage media, such as memory, includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information, such as computer-readable instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, RAM, ROM, EPROM, EEPROM, flash memory, or other memory technology, CD-ROM, digital versatile disks (DVD), or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information for access by a computing device. In contrast, communication media may embody computer-readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave, or other transport mechanism. As defined herein, computer storage media does not include communication media. Therefore, a computer storage medium should not be interpreted to be a propagating signal per se. Propagated signals may be present in a computer storage media, but propagated signals per se are not examples of computer storage media. Although the computer storage media is shown within the computing-based device, it will be appreciated that the storage may be distributed or located remotely and accessed via a network or other communication link, for example, by using a communication interface.

[0056] The unmanned aerial vehicle or the external controller may comprise an input / output controller arranged to output display information to a display device which may be separate from or integral to the unmanned aerial vehicle or the external controller. The input / output controller is also arranged to receive and process input from one or more devices, such as a user input device (e.g. a mouse, keyboard, camera, microphone or other sensor). The remote-controlled unmanned aerial vehicle may use various input or output information, or metrics received from sensors, from the host system or as commands from the external controller. In one example, the external controller is a smartphone connected wirelessly to the unmanned aerial vehicle.

[0057] The methods described herein may be performed by software in machine-readable form on a tangible storage medium e.g. in the form of a computer program comprising computer program code means adapted to perform all the steps of any of the methods described herein when the program is run on a computer and where the computer program may be embodied on a computer-readable medium. Examples of tangible storage media include computer storage devices comprising computer-readable media, such as disks, thumb drives, memory etc. and do not only include propagated signals. Propagated signals may be present in a tangible storage media, but propagated signals per se are not examples of tangible storage media. The software can be suitable for execution on a parallel processor or a serial processor such that the method steps may be carried out in any suitable order, or simultaneously.

[0058] Any range or device value given herein may be extended or altered without losing the effect sought.

[0059] Although at least a portion of the subject matter has been described in language specific to structural features and / or acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as examples of implementing the claims and other equivalent features and acts are intended to be within the scope of the claims.

[0060] It will be understood that the benefits and advantages described above may relate to one embodiment or may relate to several embodiments. The embodiments are not limited to those that solve any or all of the stated problems or those that have any or all of the stated benefits and advantages. It will further be understood that reference to 'an' item refers to one or more of those items.

[0061] The steps of the methods described herein may be carried out in any suitable order, or simultaneously where appropriate. Additionally, individual blocks may be deleted from any of the methods without departing from the spirit and scope of the subject matter described herein. Aspects of any of the examples described above may be combined with aspects of any of the other examples described to form further examples without losing the effect sought.

[0062] The term 'comprising' is used herein to mean including the method blocks or elements identified, but that such blocks or elements do not comprise an exclusive list and a method or apparatus may contain additional blocks or elements.

[0063] It will be understood that the above description is given by way of example only and that various modifications may be made by those skilled in the art. The above specification, examples and data provide a complete description of the structure and use of exemplary embodiments. Although various embodiments have been described above with a certain degree of particularity, or with reference to one or more individual embodiments, those skilled in the art could make numerous alterations to the disclosed embodiments without departing from the spirit or scope of this specification.

Examples

Embodiment Construction

[0016]The detailed description provided below in connection with the appended drawings is intended as a description of the present examples and is not intended to represent the only forms in which the present example may be constructed or utilized. However, the same or equivalent functions and sequences may be accomplished by different examples.

[0017]Although the present examples are described and illustrated herein as being implemented in an unmanned aerial vehicle or a drone, the apparatus described is provided as an example and not a limitation. As those skilled in the art will appreciate, the present examples are suitable for application in a variety of different types of unmanned aerial vehicles.

[0018]Unmanned aerial vehicles, commonly known as a drones, are aircrafts without a human pilot on board. The unmanned aerial vehicles may be autonomous or be controlled by an external controller such as a wirelessly connected remote controller. During the remote-controlled scenario the...

Claims

1. An unmanned aerial vehicle, comprising: a fuselage (10); a transceiver (17) configured to provide a communication link between the unmanned aerial vehicle (1) and a remote unit; and a sensor array (18) configured to detect a thermal target (14); characterized in that: the unmanned aerial vehicle (1) is configured to carry a fire extinguishing substance as its payload; and the unmanned aerial vehicle (1) is configured to release the fire extinguishing substance to a target (14) by crashing into the target (14).

2. The unmanned aerial vehicle according to claim 1, characterized by comprising at least one processor (16) and a memory (17) storing instructions that, when executed, are configured to provide an artificial intelligence system configured to process data from the sensor array for target (14) identification, navigation, or engagement decision-making; and the artificial intelligence system is further configured to autonomously adjust the unmanned aerial vehicle's (1) flight path based on real-time environmental data.

3. The unmanned aerial vehicle according to claim 1 or claim 2, characterized in that the sensor array is configured to detect heat signatures for target (14) identification.

4. The unmanned aerial vehicle according to claim 2 or claim 3, characterized in that the artificial intelligence system comprises machine learning algorithms for differentiating between various types of targets (14) and prioritizing them based on the risk of fire spreading.

5. The unmanned aerial vehicle according to any of the claims 2 - 4, characterized in that the vehicle is configured to launch by an assisted launch.

6. The unmanned aerial vehicle according to claim 5, characterized in that the assisted launch is a catapult launch or a sling launch configured to accelerate the vehicle to flight speed.

7. The unmanned aerial vehicle according to claim 5, characterized in that the assisted launch is a rail launch configured to accelerate the vehicle to flight speed.

8. The unmanned aerial vehicle according to claim 5, characterized in that the assisted launch is an air launch from an aircraft.

9. The unmanned aerial vehicle according to any of the claims 1 - 8, characterized by comprising a nose (12) configured to shatter glass upon impact.

10. The unmanned aerial vehicle according to any of the claims 2 - 9 characterized by learning to pinpoint a critical area of the fire and choosing the target (14) for crashing into while having a maximum effect, through an artificial intelligence algorithm using multiple previous crashing results.

11. The unmanned aerial vehicle according to any of the claims 1 - 10 characterized in that the sensor array (18) comprises at least one sensor from a group of a thermal camera, an optical camera, a radar, and a LIDAR.

12. The unmanned aerial vehicle according to any of the claims 1 - 11, characterized the fire extinguishing substance comprises at least one substance from the group of: pressurized carbon dioxide, dry chemical powders composed of monoammonium phosphate or sodium bicarbonate, clean agents, aqueous film-forming foams, wet chemicals, potassium aerosols, and foam aerosols.

13. A method for extinguishing a fire by an unmanned aerial vehicle (1), said vehicle comprising: a fuselage (10); providing a communication link between the unmanned aerial vehicle (1) and a remote unit by a transceiver (18); and detecting a thermal target (14) by a sensor array (18); characterized in that the method comprises the steps of : the unmanned aerial vehicle (1) carrying a fire extinguishing substance as its payload; and releasing the fire extinguishing substance to a target (14) by crashing into the target (14).

14. The method according to claim 13, characterized by an artificial intelligence system processing data from the sensor array for target (14) identification, navigation, or engagement decision-making; and the artificial intelligence system is further configured to autonomously adjust the unmanned aerial vehicle's (1) flight path based on real-time environmental data.

Images