Autonomous robotic system

Abstract

An autonomous robotic system includes at least one sensor, an actuator configured to move in response to input received at the sensor, and a control system operably connected to both the sensor and actuator. The control system includes a processor configured to receive data from the sensor and generate control signals for the actuator. A power supply system provides energy to the components. The system further includes a mechanical structure that is configured to move in response to the actuator's motion. The system is suitable for handling complex, high-risk dynamic environments and is capable of autonomous operation based on sensor input, programmed logic and / or instructions generated by machine learning.

Description

[0001] Attorney Docket No. 35942-100110

[0002] AUTONOMOUS ROBOTIC SYSTEM

[0003] CROSS-REFERENCE TO RELATED APPLICATION

[0004] This patent application is a PCT of pending United States Patent Application Serial No. 63 / 681,445 filed on August 9, 2024, and entitled “AN AUTONOMOUS ROBOTIC SYSTEM” the entirety of which is incorporated by reference in its entirety.

[0005] FIELD OF THE INVENTION

[0006] The present invention generally relates to the field of robotics. In particular, the present invention is directed to an autonomous robotic system.

[0007] BACKGROUND OF THE INVENTION

[0008] Concerns have emerged around safety and operational efficiency in environments involving dense crowds, sensitive border regions, and active military zones. Such environments often require real-time situational awareness, rapid decision making, and flexible and sustained operational presence, which may be difficult and / or dangerous to implement by personnel alone. Traditional methods of surveillance, crowd monitoring, and perimeter security may be limited by human fatigue, communication restrictions, or logistical constraints. Furthermore, in military and boarder environments, there is often a need for scalable, adaptive systems that are able to operate autonomously, coordinate across multiple distributed units, and respond to changing conditions or threats with minimal human supervision and intervention. There is therefore a need for an autonomous robotic system capable of addressing these challenges in complex, high-risk environments by providing persistent and autonomous sensing and response capabilities, as well as enhanced coordination capability, while continuously adapting and optimizing its performance over time according to environmental conditions and mission outcomes.

[0009] SUMMARY OF THE INVENTION

[0010] In an aspect, an autonomous robotic system, the system comprising, at least a sensor; an actuator configured to move in response to input received at the at least a sensor; a control system, connected to the at least a sensor and the actuator, wherein the control system includes at least a processor configured to receive an input from the sensor, and the control system is configured to provide an output to the actuator; a power supply; and a mechanical structure configured to move in response to the motion of the actuator. Attorney Docket No. 35942-100110

[0011] These and other aspects and features of non-limiting embodiments of the present invention will become apparent to those skilled in the art upon review of the following description of specific non-limiting embodiments of the invention in conjunction with the accompanying drawings.

[0012] BRIEF DESCRIPTION OF THE DRAWINGS

[0013] For the purpose of illustrating the invention, the drawings show aspects of one or more embodiments of the invention. However, it should be understood that the present invention is not limited to the precise arrangements and instrumentalities shown in the drawings, wherein:

[0014] FIG. 1 is a block diagram illustrating an exemplary embodiment of autonomous robotic system;

[0015] FIG. 2 is a block diagram illustrating an exemplary embodiment of machine learning module; FIG. 3 is a block diagram of an exemplary embodiment of a computing system that can be used to implement any one or more of the methodologies disclosed herein and any one or more portions thereof;

[0016] FIG. 4 is a block diagram of an exemplary7embodiment of applications of autonomous robotic system;

[0017] FIG. 5 is a block diagram of an exemplary embodiment of distributed network of autonomous robotic systems;

[0018] FIG. 6 is a block diagram of an exemplary embodiment of swarm configuration of distributed network devices;

[0019] FIG. 7 is a block diagram of an exemplary embodiment of machine learning model database; and

[0020] FIG. 8 is a block diagram of an exemplary embodiment of a threat detection.

[0021] The drawings are not necessarily to scale and may be illustrated by phantom lines, diagrammatic representations and fragmentary' views. In certain instances, details that are not necessary for an understanding of the embodiments or that render other details difficult to perceive may have been omitted.

[0022] DETAILED DESCRIPTION OF THE INVENTION

[0023] Referring now to FIG. 1, an exemplary' embodiment of an autonomous robotic system is illustrated. System 100 includes at least a sensor 104. A “sensor’ as used in this disclosure is any device that detects an input from the physical environment. An input may include light, Attorney Docket No. 35942-100110 heat, motion, moisture, pressure, and / or any other environmental condition. A sensor 104 may include but is not limited to a temperature sensor, a pressure sensor, a proximity’ sensor, a light sensor, a motion sensor, a humidity sensor, an accelerometer, a gyroscope, a gas sensor, a touch sensor, a camera, LIDAR, radar, RS SI and the like. An input received by a sensor may be converted to a readable display at the sensor location and / or transmitted electronically over a network for reading and / or further processing as described in more detail below.

[0024] With continued reference to FIG. 1, sensor 104 may include a vision sensor that may capture and process visual information from the environment. Vision sensor may include a camera and / or imaging device that may process captured images and / or video. Vision sensor may include one or more components such as an imaging device, lens, lighting, and / or processor as described in more detail below. Vision sensor may include a 2D vision sensor, a 3D vision sensor, and / or a color vision sensor. Sensor 104 may be configured to output signals to actuator 108, control system 112, and processor 116. Sensor 104 may convert captured information from local environment and convert the information into electrical signals such as analog or digital. Sensor 104 may detect real-time data on troop movements, enemy positions, environmental conditions, soldiers' health, soldiers’ location, soldiers’ stress levels, surveillance information, coordinate supply delivery, execution of tactical missions, and the like. Such captured information may be amplified, filtered, or otherwise processed to make it available for transmission and interpretation. In an embodiment, sensor 104 may be configured to convert into digital form captured information to make it recognizable by processor 116 such as by converting it into binary’ code. In an embodiment, captured information may be converted by processor 116 into for example binary code. Sensor 104 may transmit signals to actuator 108, control system 112, and processor 116 via wired or wireless forms of communication. This may include for example, a PCB trace, cable, Bluetooth, and / or Zigbee as described below in more detail. Receiving device such as actuator 108, control system 112, and / or processor 116 may be configured to interpret the signal received from sensor 104 and take action. This may include for example, triggering an alert, displaying data, adjusting a path traveled, and the like. Sensor 104 and / or any other component of system 100 may create a network of systems and as such devices, which communicate with one another, are remotely monitored and controlled, and make decisions and automate tasks using real time information via the internet of things (IOT). IOT connectivity may aid in collecting real time data relating to surveillance, delivery’ of supplies, and execute tactical missions. Data collected from system 100 and / or a network of system 100s may be transmitted to command centers to enable faster and smarter decisions in tough environmental or physical conditions such as combat zones, oil Attorney Docket No. 35942-100110 fields, coal mines, educational centers such as schools and universities, large plots of land and the like. IOT enabled sensors and camera may aid in monitoring borders and strategic zones and aid in detecting unauthorized activity and alert response teams in real time. Sensor 104 may include a proximity sensor that may detect the presence or absence of an object or its distance from system 100 without physical contact. Proximity7sensor may be configured to sense the approach or presence of an object and trigger action based on that detection. Proximity sensor may include but is not limited to an inductive proximity sensor, a capacitive proximity' sensor, an ultrasonic proximity sensor, a photoelectric proximity sensor, a magnetic proximity' sensor, and / or a radar proximity7sensor. Sensor 104 may include a motion sensor that may detect physical movement in a given area or of an obj ect. Motion sensor may include but is not limited to a passive infrared sensor, an ultrasonic sensor, a microwave sensor, a dual technology sensor, a tomographic motion detector, a vibration sensor and the like. Sensor 104 may include an environmental sensor which measures specific environmental conditions and / or variables in a given area. Environmental sensor may be utilized to monitor and / or assess various aspects of the environment. Environmental sensor may include but is not limited to a temperature sensor, a humidity sensor, an air quality sensor, a pressure sensor, a light sensor, a soil moisture sensor, a sound sensor, a radiation sensor, and / or a gas sensor. Environmental sensor may include LIDAR (Light Detection and Ranging) which uses laser light to measure distances and create detailed 2D or 3D maps of environments. LIDAR may include components including, but not limited to, lasers, scanners, optics, receivers, position and navigation systems, and computing devices as described in more detail below. Data collected from sensor 104 may include movement data from one, multiple, or all vehicles and / or systems in communication. This may allow for generation of a map of the environment that they are operating in, to allow or restrict access to sensitive locations such as indoors, tunnels, and / or signal restricted and / or denied areas. This may be performed using multi-hop or other netw ork architectures that allow7for this. In some instances system 100 may be configured to use one or more communication channels to maintain reliable connectivity7in challenging operating environments. For example, unmanned aerial vehicles (UAVs) flying in a signal jammed zone may employ line-of-sight or optical communication with each other within the jammed zone and upon exiting the jammed zone, transition to radio communication to maintain a link with a base station or continue the line of communication toward a target location. System 100 may be further configured to support distributed computing and recognition of friend or foe identifiers. For example, the system 100 may identify a human member of a swarm via a tracked device such as a smart watch or may Attorney Docket No. 35942-100110 recognize friendly assets by detecting an attached identification tag. System 100 may also include scout units. These scout units may be simpler, lower-capability components optimized for specific tasks. For example, a scout unit may be configured to deploy one or more small stationary devices and / or mobile robots equipped with a visual indicator, such as a light to mark a threat or waypoint, or with a video capture system, for example, a GoPro or similar imaging device.

[0025] With continued reference to FIG. 1, system 100 also includes an actuator 108. An “actuator’ as used in this disclosure is a device that converts energy into motion. Actuator 108 may be used to control the movement and / or activity of system 100. In general, actuator 108 may perform a physical action in response to an input signal. Actuator 108 may be hardware agnostic and depending on the particular use case and application of system 100, actuator 108 may perform functions such as turning the wheels of system 100 and / or using propellers in a quadcopter. Actuator 108 may respond to other commands via the loT, such as the locking of doors, sounding of alarms, and responding to and communicating with law enforcement. Actuator 108 may respond to one or more actuator signals 132. An “actuator signal” as used in this disclosure, is any information being conveyed to or from actuator 108. In certain embodiments, the actuator signal 132 may include any signal received from sensor 104. In certain embodiments, the actuator signal 132 may include any signal received from any other component of system 100. For example, actuator signal 132 may be received as a form of communication from processor 116. Actuator signal 132 may cause actuator 108 to respond to information contained within actuator signal. For example, actuator signal received from sensor 104 that detects potentially hazardous material on the ground such as explosives may cause actuator 108 to change course to get closer to the potentially hazardous material to obtain a sample and uncover if the material truly is hazardous or not. In yet another nonlimiting example, actuator signal that receives information from processor 116 identifying missiles launched overhead may cause actuator 108 to change the direction of travel and stay outside the path of the missiles. In yet another non-limiting example, actuator signal may be used to transmit information from actuator 108 to any other component of system 100. For example, actuator signal may communicate a response back to processor 116 indicating that a course of direction has been changed or that the speed of movement of system 100 has been adjusted. Actuatorl08 may include, but is not limited to, an electrical actuator, a hydraulic actuator, a pneumatic actuator, a mechanical actuator, a thermal actuator, a magnetic actuator, and the like. Actuator 108 may produce linear motion, such as push-pull movement along a straight path, and / or rotational motion, such as turning or spinning movement. In various Attorney Docket No. 35942-100110 embodiments, actuator 108 may include mobile or stationary systems. Mobile systems may include unmanned ground vehicles (UGVs) that may be wheeled, tracked, or legged; UAVs, such as quadcopters, fixed wing aircraft, or hybrid vertical takeoff and landing (VTOL) designs; unmanned surface vessels (USVs); and unmanned underwater vehicles (UVVs). Stationary systems may include, but are not limited to, communication towers, sentry7towers, command and control centers, and / or specialized sensors. The actuator 108 may optionally include an automatic launch and recovery platform (ALRP) operable to host and manage all types of robotic units, with options for automatic recharging, cleaning, maintenance, inspection, part swaps, refueling, payload replenishment, etc. In an embodiment, ALRP may be an independent structure that may be used to store system 100s and perform tasks of charging system 100. cleaning system 100, applying maintenance, inspection of system 100, changing the payload of system 100, changing one or more components of system 100 and the like. In certain embodiments, the ALRP may include robotic arms capable of performing various tasks. The ALRP may operate as part of the swarm and may deploy and recover units as needed. Further, the ALRP may be stationary or mobile, and may be configured as a boat, submarine, truck, car, all-terrain vehicle (ATV). host drone, purpose-built structure (for such applications as building security, venues, borders, or the like), or even as a portable unit carried by personnel for small-scale surgical operations. The ALRP may have a modular or fixed configuration and may support multiple types of robots with various drivetrains, propulsion systems, and payload options. Multiple ALRPs can work together in a swarm to execute coordinated tasks and provide mutual support. Additional ALRPs can be added ad hoc to support changing operational needs and / or to scale the system. Tasks performed by ALRP may include launch tasks that aid in deploying unmanned vehicles, charging system 100, cleaning system 100, applying maintenance to system 100, inspecting system 100, changing the payload of system 100, changing one or more components of system 100, and the like. Launch tasks may include vehicle preparation that automatically configures and arms the ALRP for mission readiness. Launch tasks may include positioning and alignment whereby sensor 104 may be used to control systems in conjunction with processor 116 to align the vehicle for optimal launch trajectory. Launch tasks may include catapult and pneumatic launch that employs mechanisms such as hydraulic, pneumatic, or electromagnetic systems to propel unmanned vehicle into operation. Launch tasks may include autonomous deployment whereby flight and navigation protocols may be implemented with or without manual control. Tasks performed by ALRP may include recovery tasks that aid in retrieving unmanned vehicles. Recovery tasks may include tracking and guidance to monitor a vehicle’s Attorney Docket No. 35942-100110 return path using GPS, radar, or onboard telemetry'. Recovery tasks may include soft capture mechanisms such as using nets, robotic arms, or parachutes to safely retrieve vehicles. Recovery^ tasks may include stabilization such as adjusting platform positioning to ensure safe docking of the vehicle. Recovery tasks make include post-mission handling such as automatically powering down devices, securing them, and storing the vehicle for maintenance or redeployment. Tasks performed by ALRPs may include integrated and real time tasks during a vehicle’s launch. This may include real time monitoring to continuously track vehicle status and environmental conditions. Real time tasks may include autonomous decision making by coordinating with processor 116 to adapt launch and recovery' based on factors such as weather, terrain, mission goals, timing, and the like. Real time tasks may include multi-vehicle coordination such as supporting swarms or fleets of vehicles with synchronized and / or sequential launch and recovery cycles.

[0026] With continued reference to FIG. 1, system 100 includes a control system 112. A “control system” as used in this disclosure is a device that manages, commands, directs, and / or regulates the behavior of system 100. As shown in FIG. 1, the sensor 104 is connected to the control system 112. which is in turn connected to a mechanical structure 120 (described below).

[0027] With continued reference to FIG. 1, system 100 may also include an optional robotic arm configured to perform various maintenance and operational support tasks. These tasks may include, but are not limited to, self-cleaning, maintenance, batery replacement, obstacle removal, and the like. In some embodiments, system 100 may also include compressed air, compressed gas, and / or a water tank for cleaning sensors, points of interest, or other components of system 100, especially in adverse environmental conditions such as in dusty' or muddy conditions.

[0028] With continued reference to FIG. 1, control system 112 includes at least a processor 116. Processor 116 may include any computing device as described in this disclosure, including without limitation a microcontroller, microprocessor, digital signal processor (DSP) and / or system on a chip (SoC) as described in this disclosure. Processor 116 may be hardware agnostic, and as such any processor may be utilized within system 100. A computing device may include, be included in, and / or communicate with a mobile device such as a mobile telephone or smartphone, computer, tablet, smartwatch, mobile hotspot and the like. Processor 116 may include a single computing device operating independently, or may include two or more computing device operating in concert, in parallel, sequentially or the like; two or more computing devices may be included together in a single computing device Attorney Docket No. 35942-100110 or in two or more computing devices. Processor 116 may interface or communicate with one or more additional devices as described below, via a network interface device. The network interface device may be configured to connect to processor 116 to one or more networks, and one or more devices. Examples of a network interface device include, but are not limited to, a network interface card (e.g., a mobile network interface card, a LAN card), a modem, and any combination thereof. Examples of a network include, but are not limited to, a wide area network (e.g., the Internet, an enterprise network), a local area network (e.g.. a network associated with an office, a building, a campus or other relatively small geographic space), a telephone network, a data network associated with a telephone / voice provider (e.g. , a mobile communications provider data and / or voice network), a direct connection between tw o computing devices, and any combinations thereof. The network may employ wired and / or wireless communication, and may be implemented using any suitable topology, including but not limited to multi -hop, mesh, tree, start ring, fully connected, bus, and / or ad hoc configurations. Communication may occur over electromagnetic, sound, radio frequency, and / optical channels. The network may support line-of-sight and / or support long range communications. The network enables information (e.g., data, software, etc.) to be communicated to and / or from a computer and / or a computing device. In certain embodiments, processor 116 may be implemented as a single computing device or as a distributed computing architecture that includes a cluster of computing devices at a first location and a second computing device or cluster of computing devices at a second location. Processor 116 may also include additional computing devices dedicated to data storage, security, traffic distribution for load balancing, and the like. Processor 116 may be configured to distribute one or more computing tasks as described below across a plurality of computing devices, which may operate in parallel, in series, redundantly, or using any suitable scheme for task-sharing or memory-distribution between computing devices. In certain embodiments, processor 116 may be implemented using a “shared nothing” architecture in which data is cached at the worker level. This configuration may facilitate scalability' of system 100 and / or the associated computing device.

[0029] With continued reference to FIG. 1, processor 116 may be designed and / or configured to perform any method, method step, or sequence of method steps in any embodiment described in this disclosure, in any order and with any degree of repetition. For instance, processor 116 may be configured to perform a single step or sequence repeatedly until a desired or commanded outcome is achieved; repetition of a step or a sequence of steps may be performed iteratively and / or recursively using outputs of previous repetitions as inputs to Attorney Docket No. 35942-100110 subsequent repetitions, aggregating inputs and / or outputs of repetitions to produce an aggregate result, reduction or decrement of one or more variables such as global variables, and / or division of a larger processing task into a set of iteratively addressed smaller processing tasks. Processor 116 may perform any step or sequence of steps as described in this disclosure in parallel, such as simultaneously and / or substantially simultaneously performing a step two or more times using two or more parallel threads, processor cores, or the like; division of tasks between parallel threads and / or processes may be performed according to any protocol suitable for division of tasks between iterations. Persons skilled in the art, upon reviewing the entirety7of this disclosure, will be aware of various ways in which steps, sequences of steps, processing tasks, and / or data may be subdivided, shared, or otherwise dealt with using iteration, recursion, and / or parallel processing.

[0030] With continued reference to FIG. 1, control system 112 may work in conjunction with sensor 104 and / or actuator 108. In certain embodiments, control system 112 may be implemented as an open-loop control system, configured to generate outputs based on a set of predefined instructions without being influenced by input or feedback. Alternatively, control system 112 may be implemented as a closed-loop control system configured to monitor outputs and dynamically adjust inputs based on feedback to maintain a desired output. Control system 112 may be configured to regulate and manage the operation of other devices and / or components contained within system 100 to achieve specific performance goals. This may be realized through the use of information from sensor, actuator, and / or any feedback mechanisms. System 100 may autonomously navigate by integrating fused sensor data (including semantic map context) to plan and execute paths without human intervention. Obstacle avoidance may be performed in real time by detecting static and dynamic hazards and adjusting trajectories via local replanning algorithms, thereby preventing collisions while maintaining mission objectives.

[0031] With continued reference to FIG. 1, system 100 also includes a mechanical structure 120. “Mechanical structure” as used in this disclosure is any physical framework providing shape, support, and movement capabilities for system 100. Mechanical structure 120 may include a frame which provides the main supporting structure and foundation for other components. Mechanical structure 120 may include a joint where various components of system 100 are connected, allowing for relative movements. A joint may include a rotational joint and / or a linear joint. Mechanical structure 120 may include a link that may connect one or more joints and form limbs or body parts of system 100. Mechanical structure 120 may include an end effector designed to interact with the environment such as a gripper, tool. Attorney Docket No. 35942-100110 and / or additional sensor. Mechanical structure 120 may include one or more features including, but not limited to. a nozzle, a weapon, a scientific device and the like. Mechanical structure 120 may include a transmission element that transmits motion and force from actuator 108 to other components such as gears, belts, and / or chains. Mechanical structure 120 may aid providing mobility, dexterity, stability, strength, and / or durability. Mechanical structure 120 may enable precise and agile movement by coordinating components and forces of system 100 to manipulate orientation and positioning of system 100. Movement capabilities may include components such as wheels, propellers, legs, and / or any other component that aids system 100 in this task. For example, as actuator 108 adjusts the speed and direction of system 100, then mechanical structure 120 may tilt forward or backward to create pitch in conjunction with movement of actuator 108. In yet another non-limiting example, mechanical structure may tilt left or right to create roll based on movement of actuator 108. Mechanical structure 120 may aid in vertical movement and stability such as during ascension or descension of system 100. Mechanical structure 120 may include gimbals that stabilize sensor 104, cameras, or pay loads by counteracting system 100 motion across pitch, roll, and yaw axes. Mechanical structure 120 may include arms or fins to adjust aerodynamic surfaces such as rudders or elevators. Mechanical structure 120 may include retractable landing gear that may fold during flight to reduce drag but deploy during landing. Mechanical structure 120 may include articulated joints that allow parts of the frame or wings to shift for maneuverability or compact storage.

[0032] With continued reference to FIG. 1, system 100 may also include a user interface 124. A “user interface” as used in this disclosure, is a component by which a user interacts with system 100. User interface 124 may include a graphical user interface containing graphical elements such as windows, icons, buttons and / or menus. Users may interact with system 100 through visual representations and can interact through additional devices such as a mouse or touchscreen. User interface 124 may include a command line interface whereby users may interact with system 100 by typing commands into a console or terminal. User interface 124 may include a touch user interface for touch sensitive devices where a user may interact by touching a screen. User interface 124 may include a voice user interface whereby users interact with system 100 through voice commands. User interface 124 may include a menu-driven interface where users navigate through menus to perform actions. User interface 124 may include form-based interface where users input data into fields within a form. User interface 124 may include natural language interface which allows users to interact using natural language, whether spoken or typed. User interface 124 may include one or more Attorney Docket No. 35942-100110 components including, but not limited to. input controls, navigational components, informational components, and / or containers. User interface 124 may allow for system 100 to interact with one or more users, and / or one or more additional system 100s, and / or one or more additional devices. Such interaction may include a group chat where various system 100s, users, and / or additional devices may communicate with one another.

[0033] With continued reference to FIG. 1, user interface 124 may also include a mixed reality interface. A mixed reality interface may include a user interface 124 that blends real world and virtual elements to allow users to interact with and manipulate physical and digital objects in a combined environment. Mixed reality7may bridge the gap between virtual reality7(VR) and augmented reality (AR) by creating experiences where physical and digital objects coexist and interact in real time. Mixed reality interface may include one or more components including, but not limited to, a head mounted display, a sensor 104, a camera, an input device, a mixed reality7platform, spatial mapping and anchoring, interaction models and the like. Mixed reality interface may include but is not limited to one or more features including for example ai chat, 2D mapping, Dd mapping, augmented reality7, virtual reality, live video feed, a split view and / or multiple user displays displaying relevant information to each user and the like. User interface 124 may be configured to measure emotions of a user to assure aligned thinking during critical decision making periods.

[0034] With continued reference to FIG. 1, system 100 includes a power supply 128. A “power supply’" as used in this disclosure is a device used to provide energy to power system 100. Energy may be generated and provided by one or more sources including, but not limited to, batteries, capacitors, fuel cells, and / or power adapters. Power supply 128 may include a power management system which may include one or more components including a voltage regulator, a battery management system, a power distribution unit, a charging system, and / or backup power. Power supply 128 may be provided by battery power supplies such as lithium- ion batteries, nickel metal hydride batteries, and / or lead acid batteries. Power supply 128 may be provided by tethered power supplies such as AC power adapters and / or DC power adapters. Power supply 128 may be provided by renewable energy sources such as solar panels, and / or wind or hydroelectric generators.

[0035] With continued reference to FIG. 1, system 100 may be utilized for aerial and threat defense. This may include being deployed to neutralize aerial threats such as hostile drones and / or incoming missiles. In an embodiment, system 100 may deploy interceptor drones equipped with countermeasures such as nets or jammers to neutralize a threat. System 100 may be utilized for a public event security system to maintain continuous surveillance of Attorney Docket No. 35942-1001 10 public events, critical infrastructure, and / or high value assets using a swarm of drones. In an embodiment, system 100 may automatically replace drones nearing their power limits with fully charged ones ensuring uninterrupted surveillances. System 100 may aid to augment and / or replace lost, crashed, defected, malfunctioning, and / or overwhelmed systems, drones, robots, or downed equipment. For example, a replacement system 100 may continue the task of injured and / or damaged system 100 so that the injured and / or damaged system 100 can be sent back to ALRP for maintenance and repair. Units nearing failure or depleted energy reserves are autonomously identified and replaced; reserve units are launched via ALRP, degraded units are recovered and serviced without human scheduling, and continuity of coverage is maintained through seamless handoff and deployment logic. System 100 may deploy specialized response drones, UGVs, USVs, etc. to track, engage, neutralize and monitor potential threats, POIs, and / or risks identified by surveillance drones. System 100 may be enabled to provide real-time alerts and information to security personnel, enabling rapid respond and decision making. System 100 may work autonomously as it integrates autonomous responses from other system 100s. This may allow for integration of fields of navigation, computer vision, and / or autonomous activities that allow for a replacement system 100 to be switched out based on conditions and situations. System 100 may work autonomously such as when it is controlled by robotics.

[0036] With continued reference to FIG. 1, system 100 may be utilized for naval security and vessel defense. System 100 may be configured to manage a fleet of surface and underwater drones for comprehensive maritime surveillance and security around naval assets or commercial vessels. System 100 may utilize sonar, radar, and other sensors 104 to detect and identify potential threats such as enemy submarines, torpedoes, mines, or hostile surface vessels. System 100 may be integrated with existing shipboard defense systems to provide an additional layer of protection against both surface and underwater threats. System 100 may be utilized as a border security system to utilize a combination of aerial and ground robots for continuous monitoring of border regions. System 100 may detect and track potential intrusions, such as unauthorized crossings or suspicious activities and provide real-time alerts and intelligence to border security personnel, enabling rapid response and interdiction. System 100 may be configured to detect specific objects such as contraband. System 100 may be utilized for military operations, including front-line support and assistance to military units operating in combat zones. Potential tasks include reconnaissance, surveillance, logistics, medical evacuation, and both offensive and defensive operations, which may involve the use of lethal force. System 100 may enhance situational awareness for military commanders. Attorney Docket No. 35942-100110 enabling more informed decision making and reducing casualties. System 100 may also be employed for disaster relief to assist in response efforts such as search and rescue missions in collapsed buildings or hazardous environments after earthquakes, floods, avalanches, tornadoes, typhoons, and wildfires. System 100 may be utilized to locate survivors, assess structural damage, and deliver essential supplies to affected areas via ground and / or aerial delivery, and provide valuable information, contact, and support to rescue teams to aid in coordination of relief efforts. This may include real-time mapping of affected areas, identifying safe routes for rescuers and UGV s, and / or assessing the structural integrity of buildings. Processor 116 may be trained with one or more images of contraband such as for example, weapons, strategic materials, drugs, counterfeit goods, electronics, and the like. This may be performed utilizing any methodology as described below in more detail in FIG. 2. Any contraband detected by sensor 104, processor 116, and / or any other component of system 100 may be flagged and quarantined for further investigation by personnel. Various components of system 100 may aid in detecting contraband. For example, high resolution cameras may spot suspicious packages or hidden compartments from above. In yet another example, thermal imaging may detect heat signatures from hidden electronics or human activity7. Sensor 104 may be trained to identify' drugs or explosives, based on their fingerprint or detect chemical components such as narcotics or explosives. Radiofrequency scanners may pick up signals from unauthorized cell phones or communication devices. Processor 116 may utilize artificial intelligence to track movement, shapes, and behaviors to flag anomalies.

[0037] Processor 116 may utilize facial recognition to identify known contraband handlers or banned item. System 100 may monitor certain geographical areas where contraband may be more commonly found. Processor 116 may be configured to receive imagery from mobile units. “Imagery” as used in this disclosure, is any data collected by another system 100 deployed under operating conditions. “Mobile units” as used in this disclosure, include any system 100 deployed to collect imagery. Mobile units may include scout units. Processor 116 may then perform domain specific augmentation such as by removing components and / or layers of imagery' such as dust, rain, low-light simulations and the like. Processor 116 may then apply active learning selection to prioritize the threat class. For example, imagery that contains an unknown person may aid in classifying the imagery as containing a possible intruder or person of know n identify’. Processor 116 may then select a machine learning process as a function of the received imagery that has domain specific augmentation performed on it. A machine learning process may be selected as described below in more detail in reference to FIG. 7. Processor 116 may then input the imagery into the selected machine learning process Attorney Docket No. 35942-100110 and output a recommendation as a function of the selected machine learning process. In an embodiment, a YOLO based process may be utilized to train the selected machine learning process. This may be performed as described below in more detail in reference to FIG. 2. A “recommendation” as used in this disclosure, is any next step, suggestion or proposal pertaining to the best course of action in response to a threat, perceived threat, and / or imagery. A recommendation may include deploying additional system 100s to a location to aid in responding to a threat. A recommendation may include deploying a fine tuned network on an edge processor with quantization and pruning for > 30 FPS inference. Upon detection of a threat and / or target by YOLO-based vision module, system 100 may dynamically reallocate UAC-swarm roles via a closed-loop control that fuses LiDAR range data- significantly improving threat-tracking robustness under RF-jam conditions. Machine learning process and / or YOLO based process may be trained on a dataset collected by scout units over deployment areas, comprising greater than 50,000 annotated frames under varied lighting, weather, and occlusion conditions.

[0038] With continued reference to FIG. 1, system 100 may be configured to be part of a companion system. A “companion system” as used in this disclosure, is when system 100 is networked together with one or more other systems to form a network of devices. Companion system may include multiple system 100s that may communicate and share intelligence and information with one another. Companion system may operate using the internet of things (IOT) as described above in more detail. Companion system may allow for deployment of multiple systems 100 to allow for greater density of area coverage and to tackle complex tasks that may require the collaboration of multiple units and / or types of units such as for example a scout unit. Other applications of system 100 include but are not limited to agriculture, lifeguarding, law enforcement, search and rescue, de-mining, counterterrorism, premise security, infrastructure and critical assets security and inspection, disaster response, and parks and rec.

[0039] Referring now to FIG. 2, an exemplary embodiment of a machine-learning module 200 that may perform one or more machine-learning processes as described in this disclosure is illustrated. The machine-learning module may perform determinations, classification, and / or analysis steps, methods, processes, or the like as described in this disclosure using machine learning processes. A “machine learning process,” as used in this disclosure, is a process that automatedly uses training data 204 to generate an algorithm that will be performed by a computing device / module to produce outputs 208 given data provided as inputs 212; this is in contrast to a non-machine learning software program where the Attorney Docket No. 35942-100110 commands to be executed are determined in advance by a user and written in a programming language. Training data may include but is not limited to manual inputs to be used as an example for an algorithm and / or machine learning model, past missions, videos of missions performed by real human operations, or outputs of simulations created internally. To curate the data, we may generate algorithms and / or machine learning models to translate the information given to readable inputs that could be used by any machine learning models described herein. Any device may be able to perform and implement machine-learning module 200. This may allow for local processing such as when system 100 may be operating autonomously.

[0040] Alternatively or additionally, and continuing to refer to FIG. 2, training data 204 may include one or more elements that are not categorized; that is. training data 204 may not be formatted or contain descriptors for some elements of data. Machine-learning algorithms and / or other processes may sort training data 204 according to one or more categorizations using, for instance, natural language processing algorithms, tokenization, detection of correlated values in raw data and the like; categories may be generated using correlation and / or other processing algorithms. As a non-limiting example, in a corpus of text, phrases making up a number “n” of compound words, such as nouns modified by other nouns, may be identified according to a statistically significant prevalence of n-grams containing such words in a particular order; such an n-gram may be categorized as an element of language such as a “word” to be tracked similarly to single words, generating a new category as a result of statistical analysis. Similarly, in a data entry including some textual data, a person’s name may be identified by reference to a list, dictionary', or other compendium of terms, permitting ad-hoc categorization by machine-learning algorithms, and / or automated association of data in the data entry with descriptors or into a given format. The ability to categorize data entnes automatedly may enable the same training data 204 to be made applicable for two or more distinct machine-learning algorithms as described in further detail below. Training data 204 used by machine-learning module 200 may correlate any input data as described in this disclosure to any output data as described in this disclosure. As a non-limiting illustrative example inputs such as geographical areas may be correlated to outputs of number of interceptor drones needed to neutralize aerial threats. In yet another non-limiting example, inputs such as tasks and capabilities may be output to location and mission objectives. In certain embodiments, the system implements a semantic simultaneous localization and mapping (semantic SLAM) pipeline in which geometric maps generated from sensor 104 (e.g., LiDAR, visual SLAM from monocular / stereo / depth cameras, Attorney Docket No. 35942-1001 10 inertial / GNSS data, and mobility telemetry ) are fused with semantic labels produced by the vision-based machine learning module (e.g.. object detections from a YOLO-based network fine-tuned on proprietary', self-gathered datasets). The fused representation — hereafter referred to as the Live Semantic Mapping Engine — produces and maintains a continuously updated, machine-readable digital twin of the operational environment, enabling the system to localize itself while simultaneously enriching the spatial model with meaning (such as threats, assets, personnel, activity zones, and behavioral anomalies) for improved decision making, routing, task allocation, and anomaly detection. In certain embodiments, the onboard vision-processing pipeline employs real-time, single-stage object detection networks from the YOLO family (e.g. YOLOv8 / Y OLOvl 1), with yveights pre-trained or fine-tuned on self-gathered, environment-specific datasets. This may enable rapid, high-accuracy detection of people, vehicles, threats and other mission-relevant objects under the unique lighting, terrain and sensor characteristics of the deployment theater. Semantic SLAM and sensor fusion between sensor 104, lidar capabilities and IMU (inertial measurement units) may allow for all data to be aggregated and build out 2-dimensional (2D) and 3-dimensional (3D) models of the surrounding environment. Applications of YOLO family that provide environment specific datasets may be utilized to recognize objects and label objects contained yvithin a particular area or geolocation. This may allow various layers of 2D and 3D maps to be shown different layers of objects, geography, and topography of a particular area or geolocation. For example, an external map may be input into machine learning module 200 to compare results to maps that may be created using system 100 and / or any autonomous robotic input. Machine learning module 200 and YOLO family may generate digital twins of different locations, geographies, and spaces. A “digital tw in" as used in this disclosure, is a virtual replication of a physical object, location, geography, system, or process designed to mirror its real-world counterpart using real time data, simulation, and analytics. Inputs from other system 100s may be utilized to continuously update and refine maps and digital twins. Semantic SLAM and slam like capabilities may include for example, generation of maps from muti-sensor data (LiDAR, vision, movement data) and restricting / allowing access based on 2D and 3D mapping. Semantic SLAM and slam like capabilities may include vision and machine learning module 200 performing object recognition and classification such as detecting contraband, identifying friends versus foes, and correlating inputs to spatial outputs. Semantic SLAM and slam like capabilities may include fusion of detections with environmental mapping and distributed coordination such as a swarm and distributed netw ork. Attorney Docket No. 35942-100110

[0041] Further referring to FIG. 2, training data may be filtered, sorted, and / or selected using one or more supervised and / or unsupervised machine-learning processes and / or models as described in further detail below; such models may include without limitation a training data classifier 216. Training data classifier 216 may include a “classifier,” which as used in this disclosure is a machine-learning model as defined below, such as a mathematical model, neural net, or program generated by a machine learning algorithm known as a “classification algorithm,” as described in further detail below, that sorts inputs into categories or bins of data, outputting the categories or bins of data and / or labels associated therewith. A classifier may be configured to output at least a datum that labels or otherwise identifies a set of data that are clustered together, found to be close under a distance metric as described below, or the like. A distance metric may include any norm, such as. without limitation, a Pythagorean norm. For example, classification algorithm may receive inputs such as images of potential contraband and output a label indicating if the image contains contraband or not. Machinelearning module 200 may generate a classifier using a classification algorithm, defined as a process whereby a computing device and / or any module and / or component operating thereon derives a classifier from training data 204. Classification may be performed using, without limitation, linear classifiers such as without limitation logistic regression and / or naive Bayes classifiers, nearest neighbor classifiers such as k-nearest neighbors classifiers, support vector machines, least squares support vector machines, fisher's linear discriminant, quadratic classifiers, decision trees, boosted trees, random forest classifiers, learning vector quantization, and / or neural network-based classifiers. As a non-limiting example, training data classifier 216 may classify elements of training data to sub-populations such as path planning, task allocation, formation control, self-healing, object recognition and the like. In an embodiment, detected threats or objects of interest from machine-learning module 200 may be used to seed autonomous pursuit or monitoring tasks, where system 100 may continuously update target state estimates and adjust platform motion to follow or shadow a threat autonomously without human direction or input. In an embodiment, various detected threats and / or inputs may be utilized to select a machine learning model best suited to analyze and output a response to a detected threat. For example, if system 100 detects a threat such as a robot, a machine learning model such as YOLO may be activated whereas if a threat such as person is detected then facial recognition may be activated. Subsequent activities performed by system 100 may be recommended based on a detected threat. For example, if an unknown license plate on a car is detected, then a behavior such as following the car may be recommended. Communication and discussions surrounding future decisions Attorney Docket No. 35942-100110 and outputs from system 100 may be generated using natural language processing. For example, if a threat is detected that is later determined to not be of concern, that can be used to train machine learning module 200 and / or any machine learning process to not be concerned. However, if a threat is detected, then updates about next steps may be recommended. For example, if an unidentified person enters a school zone, then communications may disperse to take the next steps of monitoring building entrances through cameras and patrolling hallways and parking lots.

[0042] Still referring to FIG. 2, machine-learning module 200 may be configured to perform a lazy-leaming process 220 and / or protocol, which may alternatively be referred to as a "lazy loading” or “call-when-needed” process and / or protocol, may be a process whereby machine learning is conducted upon receipt of an input to be converted to an output, by combining the input and training set to derive the algorithm to be used to produce the output on demand. For instance, an initial set of simulations may be performed to cover an initial heuristic and / or “first guess” at an output and / or relationship. As a non-limiting example, an initial heuristic may include a ranking of associations between inputs and elements of training data 204. Heuristic may include selecting some number of highest-ranking associations and / or training data 204 elements. Lazy learning may implement any suitable lazy learning algorithm, including without limitation a K-nearest neighbors algorithm, a lazy naive Bayes algorithm, or the like; persons skilled in the art, upon reviewing the entirety of this disclosure, will be aware of various lazy -learning algorithms that may be applied to generate outputs as described in this disclosure, including without limitation lazy learning applications of machine-learning algorithms as described in further detail below.

[0043] Alternatively or additionally, and with continued reference to FIG. 2, machine-learning processes as described in this disclosure may be used to generate machine-learning models 224. A “machine-learning model,” as used in this disclosure, is a mathematical and / or algorithmic representation of a relationship between inputs and outputs, as generated using any machine-learning process including without limitation any process as described above and stored in memory; an input is submitted to a machine-learning model 224 once created, which generates an output based on the relationship that was derived. For instance, and without limitation, a linear regression model, generated using a linear regression algorithm, may compute a linear combination of input data using coefficients derived during machine-learning processes to calculate an output datum. As a further non-limiting example, a machine-learning model 224 may be generated by creating an artificial neural network, such as a convolutional neural network comprising an input layer of nodes, one or more intermediate layers, and an Attorney Docket No. 35942-100110 output layer of nodes. Connections between nodes may be created via the process of "training" the network, in which elements from a training data 204 set are applied to the input nodes, a suitable training algorithm (such as Levenberg-Marquardt, conjugate gradient, simulated annealing, or other algorithms) is then used to adjust the connections and weights between nodes in adjacent layers of the neural network to produce the desired values at the output nodes. This process is sometimes referred to as deep learning.

[0044] Still referring to FIG. 2, machine-learning algorithms may include at least a supervised machine-learning process 228. At least a supervised machine-learning process 228, as defined herein, include algorithms that receive a training set relating a number of inputs to a number of outputs, and seek to find one or more mathematical relations relating inputs to outputs, where each of the one or more mathematical relations is optimal according to some criterion specified to the algorithm using some scoring function. For instance, a supervised learning algorithm may include inputs such as environmental detections as described above as inputs, correlated to outputs such as recognized landmarks and / or geolocation, and a scoring function representing a desired form of relationship to be detected between inputs and outputs; scoring function may, for instance, seek to maximize the probability that a given input and / or combination of elements inputs is associated with a given output to minimize the probability' that a given input is not associated with a given output. Scoring function may be expressed as a risk function representing an “expected loss’' of an algorithm relating inputs to outputs, where loss is computed as an error function representing a degree to which a prediction generated by the relation is incorrect when compared to a given input-output pair provided in training data 204. Persons skilled in the art, upon reviewing the entirety' of this disclosure, will be aware of various possible variations of at least a supervised machine-learning process 228 that may be used to determine relation between inputs and outputs. Supervised machine-learning processes may include classification algorithms as defined above.

[0045] Further referring to FIG. 2, machine learning processes may include at least an unsupervised machine-learning processes 232. An unsupervised machine-learning process, as used herein, is a process that derives inferences in datasets without regard to labels; as a result, an unsupervised machine-learning process may be free to discover any structure, relationship, and / or correlation provided in the data. Unsupervised processes may not require a response variable; unsupervised processes may be used to find interesting patterns and / or inferences between variables, to determine a degree of correlation between two or more variables, or the like. Attorney Docket No. 35942-100110

[0046] Still referring to FIG. 2, machine-learning module 200 may be designed and configured to create a machine-learning model 224 using techniques for development of linear regression models. Linear regression models may include ordinary least squares regression, which aims to minimize the square of the difference between predicted outcomes and actual outcomes according to an appropriate norm for measuring such a difference (e.g. a vector-space distance norm); coefficients of the resulting linear equation may be modified to improve minimization. Linear regression models may include ridge regression methods, where the function to be minimized includes the least-squares function plus term multiplying the square of each coefficient by a scalar amount to penalize large coefficients. Linear regression models may include least absolute shrinkage and selection operator (LASSO) models, in which ridge regression is combined with multiplying the least-squares term by a factor of 1 divided by double the number of samples. Linear regression models may include a multi-task lasso model wherein the norm applied in the least-squares term of the lasso model is the Frobenius norm amounting to the square root of the sum of squares of all terms. Linear regression models may include the elastic net model, a multi-task elastic net model, a least angle regression model, a LARS lasso model, an orthogonal matching pursuit model, a Bayesian regression model, a logistic regression model, a stochastic gradient descent model, a perceptron model, a passive aggressive algorithm, a robustness regression model, a Huber regression model, or any other suitable model that may occur to persons skilled in the art upon reviewing the entirety of this disclosure. Linear regression models may be generalized in an embodiment to polynomial regression models, whereby a polynomial equation (e.g. a quadratic, cubic or higher-order equation) providing a best predicted output / actual output fit is sought; similar methods to those described above may be applied to minimize error functions, as will be apparent to persons skilled in the art upon reviewing the entirety of this disclosure.

[0047] Continuing to refer to FIG. 2, machine-learning algorithms may include, without limitation, linear discriminant analysis. Machine-learning algorithm may include quadratic discriminant analysis. Machine-learning algorithms may include kernel ridge regression. Machine-learning algorithms may include support vector machines, including without limitation support vector classification-based regression processes. Machine-learning algorithms may include stochastic gradient descent algorithms, including classification and regression algorithms based on stochastic gradient descent. Machine-learning algorithms may include nearest neighbors algorithms. Machine-learning algorithms may include various forms of latent space regularization such as variational regularization. Machine-learning Attorney Docket No. 35942-100110 algorithms may include Gaussian processes such as Gaussian Process Regression. Machinelearning algorithms may include cross-decomposition algorithms, including partial least squares and / or canonical correlation analysis. Machine-learning algorithms may include naive Bayes methods. Machine-learning algorithms may include algorithms based on decision trees, such as decision tree classification or regression algorithms. Machine-learning algorithms may include ensemble methods such as bagging meta-estimator, forest of randomized trees, AdaBoost, gradient tree boosting, and / or voting classifier methods. Machine-learning algorithms may include neural net algorithms, including convolutional neural net processes. Machine learning module 200 may be self-learning and / or customized based on different scenarios and / or environmental tasks. For example, an office that has specific chairs or laptop in an office may cause machine learning module 200 to be trained to specifically detect those specific office furnishings. Machine learning module 200 may be trained on facial recognition of threats that are unique or specific to various applications. For example, the threat to an office building may not be the same as a threat to a maximum security prison. In an embodiment, various machine learning algorithms, models, and / or processes may be organized by risk level and / or threat type within a database. For example, a threat such as cybersecurity may have its own set of algorithms and processes whereas a threat such as environmental conditions may have its own set of algorithms and processes. Different threats and / or detected threats may be weighted depending on factors such as where system 100 may be located, risk level and / or perceived risk level of a threat, time of day when a threat is detected, and the like. In an embodiment, system 100 may obtain additional information based on a perceived threat to better assess a particular threat. For example, if system 100 is analyzing a threat in an unknown environment, it may rely more heavily on information contained within the digital twin and may utilize sensor 104 to obtain additional information and readings. It may communicate such information back to other system 100s as it obtains initial preliminary information to analyze a perceived threat and subsequently request additional support based on progression of a threat or situation.

[0048] It is to be noted that any one or more of the aspects and embodiments described herein may be conveniently implemented using one or more machines (e.g, one or more computing devices that are utilized as a user computing device for an electronic document, one or more server devices, such as a document server, etc.) programmed according to the teachings of the present specification, as will be apparent to those of ordinary skill in the computer art. Appropriate software coding can readily be prepared by skilled programmers based on the teachings of the present disclosure, as will be apparent to those of ordinary Attorney Docket No. 35942-1001 10 skill in the software art. Aspects and implementations discussed above employing software and / or software modules may also include appropriate hardware for assisting in the implementation of the machine executable instructions of the software and / or software module.

[0049] Such software may be a computer program product that employs a machine-readable storage medium. A machine-readable storage medium may be any medium that is capable of storing and / or encoding a sequence of instructions for execution by a machine (e.g.. a computing device) and that causes the machine to perform any one of the methodologies and / or embodiments described herein. Examples of a machine-readable storage medium include, but are not limited to, a magnetic disk, an optical disc (e.g., CD, CD-R, DVD, DVD- R, etc.), a magneto-optical disk, a read-only memory ' ROM ' device, a random access memory ‘’RAM” device, a magnetic card, an optical card, a solid-state memory device, an EPROM, an EEPROM, and any combinations thereof. A machine-readable medium, as used herein, is intended to include a single medium as well as a collection of physically separate media, such as. for example, a collection of compact discs or one or more hard disk drives in combination with a computer memory. As used herein, a machine-readable storage medium does not include transitory forms of signal transmission.

[0050] Such software may also include information (e.g., data) carried as a data signal on a data carrier, such as a carrier wave. For example, machine-executable information may be included as a data-carrying signal embodied in a data carrier in which the signal encodes a sequence of instruction, or portion thereof, for execution by a machine (e.g. , a computing device) and any related information (e.g., data structures and data) that causes the machine to perform any one of the methodologies and / or embodiments described herein.

[0051] Examples of a computing device include, but are not limited to, an electronic book reading device, a computer workstation, a terminal computer, a server computer, a handheld device (e.g., a tablet computer, a smartphone, etc.), a web appliance, a network router, a network switch, a network bridge, any machine capable of executing a sequence of instructions that specify an action to be taken by that machine, and any combinations thereof. In one example, a computing device may include and / or be included in a kiosk.

[0052] FIG. 3 shows a diagrammatic representation of one embodiment of a computing device in the exemplary form of a computer system 300 within which a set of instructions for causing a control system 112 to perform any one or more of the aspects and / or methodologies of the present disclosure may be executed. It is also contemplated that multiple computing devices may be utilized to implement a specially configured set of instructions for causing Attorney Docket No. 35942-100110 one or more of the devices to perform any one or more of the aspects and / or methodologies of the present disclosure. Computer system 300 includes a processor 304 and a memory 308 that communicate with each other, and with other components, via a bus 312. Bus 312 may include any of several types of bus structures including, but not limited to, a memory' bus, a memory controller, a peripheral bus, a local bus, and any combinations thereof, using any of a variety of bus architectures.

[0053] Processor 304 may include any suitable processor, such as without limitation a processor incorporating logical circuitry for performing arithmetic and logical operations, such as an arithmetic and logic unit (ALU), which may be regulated with a state machine and directed by operational inputs from memory and / or sensor 104; processor 304 may be organized according to Von Neumann and / or Harvard architecture as a non-limiting example. Processor 304 may include, incorporate, and / or be incorporated in, without limitation, a microcontroller, microprocessor, digital signal processor (DSP), Field Programmable Gate Array (FPGA), Complex Programmable Logic Device (CPLD), Graphical Processing Unit (GPU), general purpose GPU, Tensor Processing Unit (TPU), analog or mixed signal processor, Trusted Platform Module (TPM), a floating point unit (FPU), and / or system on a chip (SoC).

[0054] Memory 308 may include various components (e.g., machine-readable media) including, but not limited to, a random-access memory' component, a read only component, and any combinations thereof. In one example, a basic input / output system 316 (BIOS), including basic routines that help to transfer information between elements within computer system 300, such as during start-up, may be stored in memory' 308. Memory 308 may also include (e.g., stored on one or more machine-readable media) instructions (e.g. , software) 320 embodying any one or more of the aspects and / or methodologies of the present disclosure. In another example, memory 308 may further include any number of program modules including, but not limited to, an operating system, one or more application programs, other program modules, program data, and any combinations thereof.

[0055] Computer system 300 may also include a storage device 324. Examples of a storage device (e.g. , storage device 324) include, but are not limited to, a hard disk drive, a magnetic disk drive, an optical disc drive in combination with an optical medium, a solid- state memory device, and any combinations thereof. Storage device 324 may be connected to bus 312 by an appropriate interface (not shown). Example interfaces include, but are not limited to, SCSI, advanced technology attachment (ATA), serial ATA, universal serial bus (USB), IEEE 1394 (FIREWIRE), and any combinations thereof. In one example, storage Attorney Docket No. 35942-100110 device 324 (or one or more components thereof) may be removably interfaced with computer system 300 (e.g, via an external port connector (not shown)). Particularly, storage device 324 and an associated machine-readable medium 328 may provide nonvolatile and / or volatile storage of machine-readable instructions, data structures, program modules, and / or other data for computer system 300. In one example, software 320 may reside, completely or partially, within machine-readable medium 328. In another example, software 320 may reside, completely or partially, within processor 304.

[0056] Computer system 300 may also include an input device 332. In one example, a user of computer system 300 may enter commands and / or other information into computer system 300 via input device 332. Examples of an input device 332 include, but are not limited to, an alpha-numeric input device (e.g, a keyboard), a pointing device, a joystick, a gamepad, an audio input device (e.g, a microphone, a voice response system, etc.), a cursor control device (e.g, a mouse), toggle, voice input, text, chat, virtual reality headset, electronic writing instrument such as a pen or pencil, a touchpad, an optical scanner, a video capture device (e.g, a still camera, a video camera), a touchscreen, and any combinations thereof. Input device 332 may be interfaced to bus 312 via any of a variety of interfaces (not shown) including, but not limited to, a serial interface, a parallel interface, a game port, a USB interface, a FIREWIRE interface, a direct interface to bus 312, and any combinations thereof. Input device 332 may include a touch screen interface that may be a part of or separate from display 336, discussed further below. Input device 332 may be utilized as a user selection device for selecting one or more graphical representations in a graphical interface as described above.

[0057] A user may also input commands and / or other information to computer system 300 via storage device 324 (e.g, a removable disk drive, a flash drive, etc.) and / or network interface device 340. A network interface device, such as network interface device 340, may be utilized for connecting computer system 300 to one or more of a variety of networks, such as network 344, and one or more remote devices 348 connected thereto. Examples of a network interface device include, but are not limited to, a network interface card (e g, a mobile network interface card, a LAN card), a modem, and any combination thereof. Examples of a network include, but are not limited to, a wide area network (e.g. , the Internet, an enterprise network), a local area network (e.g, a network associated with an office, a building, a campus or other relatively small geographic space), a telephone network, a data network associated with a telephone / voice provider (e.g., a mobile communications provider data and / or voice network), a direct connection between two computing devices, and any Attorney Docket No. 35942-100110 combinations thereof. A network, such as network 344, may employ a wired and / or a wireless mode of communication. In general, any network topology may be used. Information (e.g, data, software 320, etc.) may be communicated to and / or from computer system 300 via network interface device 340.

[0058] Computer system 300 may further include a video display adapter 352 for communicating a displayable image to a display device, such as display device 336. Examples of a display device include, but are not limited to, a liquid crystal display (LCD), a cathode ray tube (CRT), a plasma display, a light emitting diode (LED) display, and any combinations thereof. Display adapter 352 and display device 336 may be utilized in combination with processor 304 to provide graphical representations of aspects of the present disclosure. In addition to a display device, computer system 300 may include one or more other peripheral output devices including, but not limited to, an audio speaker, a printer, and any combinations thereof. Such peripheral output devices may be connected to bus 312 via a peripheral interface 356. Examples of a peripheral interface include, but are not limited to, a serial port, a USB connection, a FIREWIRE connection, a parallel connection, and any combinations thereof.

[0059] Refernng now to FIG. 4. an exemplary embodiment 400 of applications of autonomous robotic system 100 is illustrated. System 100 may be employed as an aerial and threat system 404. An “aerial and threat system” as used in this disclosure, is any application designed to detect, track and neutralize airborne threats, such as enemy aircraft, drones, missiles, cyber intrusions, unmanned aerial systems (UAS) or other aerial incursions. System 100 may be employed as a public event security system 408. A “public event security system” as used in this disclosure, is any application design to protect attendees, staff, and infrastructure during large gatherings such as concerts, sports games, festivals, political rallies, and the like. System 100 may be employed as a public event security system 408 to access control, monitor crowd behavior and detect threats, generate plans for evacuation, medical aid, and communication during a crisis, protect digital infrastructure such as ticketing and Wi-Fi networks from hacking or data breaches, and coordinate communication amongst security teams and law enforcement. System 100 may be employed as a naval security and vessel defense system 412. A “naval security and vessel defense system” as used in this disclosure, is any application configured to protect naval ships, ports, and maritime assets from threats, whether from the air, sea, or underwater. A naval security and vessel defense system 412 may aid in surveillance to detect incoming threats such as missiles, drones, or hostile vessels. A naval security and vessel defense system 412 may include detection and tracking of weapon systems such as surface to air missiles, electronic Attorney Docket No. 35942-1001 10 warfare such as jamming and spoofing systems, cybersecurity infrastructure such as protecting digital networks and command systems, and surveying physical barriers such as floating fences, nets, and underw ater detection grids around ports or anchored vessels. System 100 may be employed as a border security system 416. A “border security' system” as used in this disclosure, is any framework designed to protect a nation’s borders from various activities. A border security system 416 may include surveillance of physical barriers such as fences, walls, and vehicle checkpoints to deter unauthorized crossings. A border security system 416 may include surveillance tech such as real time monitoring and scanning of cargo to detect contraband in vehicles and containers. A border security system 416 may include biometric systems employed to aid in facial recognition, and digital passports that track movements of persons. A border security system 416 may be employed to aid in identification of illegal immigration, drug and weapon smuggling, human trafficking, terrorist infiltration, and contraband movement. System 100 may be employed as a military front support system 420. A “military front support system” as used in this disclosure, is any infrastructure, personnel, and technologies that provide logistical, operational, and tactical support to military personnel. A military front support system 420 may be employed near or around active conflict and military zones. A military front support system 420 may be utilized for logistical support to track military supplies such as food, ammunition, fuel, medical aid, and equipment. A military front support system 420 may be utilized for maintenance and repair to ensure vehicles, weapons, and gear are operational through mobile workshops and field technicians. A military front support system 420 may be utilized to facilitate secure and reliable communication and coordination between units and command centers. A military front support system 420 may be utilized for intelligence gathering to provide real time combat data. A military’ front support system 420 may be utilized for force protection such as penmeter security, counter terrorism systems and surveillance to defend and support units from attack. System 100 may be employed as a disaster relief system 424. A “disaster relief system” as used in this disclosure, is a coordinated network of resources, technologies, personnel and protocols designed to respond and recover from natural or manmade disasters. A disaster relief system 424 may be employed to aid in saving lives, reducing suffering, and restoring communities as quickly and efficiently as possible. A disaster relief system 424 may include emergency aiding with mobilizing and tracking emergency response teams, coordinating shelter and housing for displaced individuals, coordinating food and water distribution, aiding in logistics for moving supplies, evacuating individuals and surveying infrastructure. System 100 may include an oil field system 428. Attorney Docket No. 35942-100110

[0060] An “oil field system” as used in this disclosure, is a system that monitors oil fields or rigs that contain significant underground deposits of petroleum. An oil field system 428 may include monitoring and surveillance of reservoirs that trap crude oil and natural gas, extraction infrastructure such as drilling rigs, pump jacks, pipelines, and support facilities.

[0061] Referring now to FIG. 5, an exemplary' embodiment 500 of distributed network of autonomous robotic systems is illustrated. A “distributed network” as used in this disclosure, is one or more interconnected autonomous robotic systems that share resources, data, and maintain operations together without relying on a single central point. A distributed network includes companion system as described above in more detail in reference to FIG. 1. The distributed network may be made up of multiple autonomous robotic systems that may communicate and share information with one another via the internet of things 504 (IOT). This may allow' for the distributed network to coordinate deployment of multiple system 100s to increase area coverage density and facilitate execution of complex tasks. Additional system 100s can be added to the distributed network to expand capacity and allow' a function or mission to continue even if a system 100 fails.

[0062] Referring now to FIG. 6. an exemplary embodiment 600 of swarm configuration of distributed network devices is illustrated. Distributed netw ork consisting of one or more systems 100s may confirm into a swarm configuration 604. A “swarm configuration” as used in this disclosure, is any set and coordination of the distributed network to w ork together as a collective system. The swarm configuration 604 may include various formation patterns based on mission needs. The swarm configuration 604 may include various communication protocols that allow for the distributed network to communicate with one another. The swarm configuration may include task allocation where each system 100 may have a defined role such as surveillance, attack, relay, etc. The swarm configuration may include collision avoidance whereby algorithms are employed to prevent interference or crashes. The swarm configuration may include an autonomy level where some system 100s may be fully autonomous whereby others may have some human oversight. The swarm configuration includes any configuration described above as the companion system.

[0063] Referring now to FIG. 7, an exemplary embodiment of a machine learning model database 700 is illustrated. Machine learning model database may be implemented as any database structure. Database 700 may include for example, a hierarchical database, a network database, a relational database, an object-oriented database, an NoSQL database, a time-series database, an in-memory database, and the like. Database 700 may include one or more data entries containing machine learning models organized by threat type to contain Attorney Docket No. 35942-100110 outputs and recommendations specifically created and tailored to different categories of perceived threats. For example, an entry may include an environmental threat 704 which may contain various machine learning models utilized to assess inputs and perceived threats relating to environmental conditions such as natural disasters, hurricanes, earthquakes, volcanoes, floods, droughts, wildfires, epidemics, pandemics, tsunamis, tornadoes, heatwaves, blizzards, landslides, avalanches and the like. An entry may include autonomous threat 708 which may contain various machine learning models utilized to assess inputs and perceived threats relating to autonomous threats such as autonomous weapon systems (AWS), unmanned aerial vehicles (UAVs), autonomous ground vehicles, unmanned maritime systems, Al-driven command and control systems, and the like. An entry' may include cybersecurity threat 712 which may contain various machine learning models utilized to assess inputs and perceived threats relating to cybersecurity7treats such as malware, phishing, social engineering, man in the middle attacks, denial of service and distributed DOS, injection attacks, zero day exploits, insider threats, supply chain attacks, DNS tunneling, IOT based attacks and the like. An entry may include an unidentified person threat 716 which may contain vanous machine learning models utilized to assess inputs and perceived threats relating to unknown persons detected at various locations and / or at specific locations.

[0064] Referring now to FIG. 8, an exemplary embodiment of a threat detection 800 is illustrated. System 100 may identify a threat 804. A “threat” as used in this disclosure, is any situation and / or person that may cause harm, danger, damage, and / or impact. A threat may include an intruder who may enter an area or zone without permission. A threat may include a threat of warfare and / or conventional military' threats such as direct combat, strategic bombing, and / or missile strikes. A threat may include unconventional and asymmetric threats such as guerrilla warfare, sabotage, assassinations, proxy wars, and the like. A threat may include cyber attacks and information threats such as hacktivism, disinformation campaigns, and / or cyber attacks. A threat may include economic and political threats such as sanctions and blockades, economic coercion, and / or lawfare. A threat may include hybrid warfare such as use of proxy forces, cyber and information warfare legal manipulation, and the like. A threat may include a natural disaster, such as a meteorological disaster including hurricanes, ty phoons, cyclones, tornadoes, blizzards, heatwaves, and thunderstorms; geological disasters such as earthquakes, volcanic eruptions, landslides, and sinkholes; hydrological disasters such as floods, tsunamis, and avalanches; climatological disasters such as droughts, wildfires, pes infestations and disease outbreak. A threat may include hazardous Attorney Docket No. 35942-100110 and / or dangerous work conditions such as physical hazards including poorly maintained equipment, slippery floors, exposed wiring, broken stairs, and the like. A threat may include chemical hazards such as improper storage of chemicals, lack of ventilation, lack of access to safety data sheets, and the like. A threat may include biological hazards such as mold or pest infestations. A threat may include ergonomic hazards such as poor workstation design, excessive manual labor, working in small or cramped spaces and the like. A threat may include psychosocial hazards such as workplace bullying or harassment, excessive workload or long hours, lack of support and the like. Threat may then be matched to YOLO family datasets 808. For example, a threat identified as a potential tornado may be matched to YOLO family dataset 808 which may have weights pre-trained or fine tuned on self-gathered datasets based on data captured during an actual tornado. A selected YOLO family dataset may then be utilized to train a machine learning process 808. A machine learning process 808 includes any machine learning process as described above in more detail in reference to FIGS. 1-7. A machine learning process 808 may output a response which may activate one or more system 100s to respond to a threat 804. In some instances, a response to a threat may include for example, SWARM configuration 604. This may be performed utilizing any methodology as described above in more detail in reference to FIGS. 1-7.

[0065] The foregoing has been a detailed description of illustrative embodiments of the invention. Various modifications and additions can be made without departing from the spirit and scope of this invention. Features of each of the various embodiments described above may be combined with features of other described embodiments as appropriate in order to provide a multiplicity of feature combinations in associated new embodiments. Furthermore, while the foregoing describes a number of separate embodiments, what has been described herein is merely illustrative of the application of the principles of the present invention. Additionally, although particular methods herein may be illustrated and / or described as being performed in a specific order, the ordering is highly variable within ordinary skill to achieve methods, systems, and software according to the present disclosure. Accordingly, this description is meant to be taken only by way of example, and not to otherwise limit the scope of this invention.

[0066] Exemplary embodiments have been disclosed above and illustrated in the accompanying drawings. It will be understood by those skilled in the art that various changes, omissions and additions may be made to that which is specifically disclosed herein without departing from the spirit and scope of the present invention.

Claims

Attorney Docket No. 35942-100110CLAIMSWhat is claimed is:

1. An autonomous robotic system, the system comprising: at least a sensor; an actuator configured to move in response to input received at the at least a sensor; a control system, connected to the at least the sensor and the actuator, wherein the control system includes at least a processor configured to receive an input from the sensor, and the control system is configured to provide an output to the actuator; a power supply; and a mechanical structure configured to move in response to the motion of the actuator.

2. The autonomous robotic system of claim 1, wherein the at least a sensor further comprises at least one of a vision sensor, a proximity sensor, a motion sensor, and an environmental sensor.

3. The autonomous robotic system of claim 1, wherein the actuator further comprises at least one of an unmanned ground vehicle, an unmanned aerial vehicle, and an unmanned underwater vehicle.

4. The autonomous robotic system of claim 1, wherein the control system further comprises a user interface.

5. The autonomous robotic system of claim 4, wherein the user interface further comprises a mixed reality interface.

6. The autonomous robotic system of claim 1, wherein the power supply further comprises a battery.

7. The autonomous robotic system of claim 1, wherein the power supply further comprises a power management system.

8. The autonomous robotic system of claim 1, wherein the mechanical structure comprises at least one of a frame configured to provide a supporting structure and foundation for other components, a joint configured to connect various components, a link configured to connect one or more joints, an end effector configured to interact with the environment, a nozzle, a weapon, a scientific device, and a transmission element configured to transmit motion and force from the actuator.

9. The autonomous robotic system of claim 1 further comprising an aerial and threat defense system.Attorney Docket No. 35942-10011010. The autonomous robotic system of claim 1 further comprising a public event security system.

11. The autonomous robotic system of claim 1 further comprising a naval security and vessel defense system.

12. The autonomous robotic system of claim 1 further comprising a border security' system.

13. The autonomous robotic system of claim 1 further comprising a military front support and assistance system.

14. The autonomous robotic system of claim 1 further comprising a disaster relief system.

15. The autonomous robotic system of claim 1 further comprising a companion system.

16. The autonomous robotic system of claim 1 further comprising an oil field system.

17. The autonomous robotic system of claim 15, wherein the companion system further comprises a swarm configuration.

18. The autonomous robotic system of claim 15, wherein the autonomous robotic system is configured to be networked with at least one companion system to form a distributed network of devices, enabling the coordinated deployment of multiple systems to increase area coverage density and facilitate execution of complex tasks.

19. The autonomous robotic system of claim 1, wherein the processor is further configured to: receive imagery from mobile units; perform domain specific augmentation on the received imagery; select a machine learning process as a function of the received imagery; input the received imagery' into the selected machine learning process; output a recommendation as a function of the selected machine learning process.

20. The autonomous robotic system of claim 19 further comprising applying a YOLO-based process to train the selected machine learning process.

Images