El Departamento de Defensa de EE.UU. busca sistemas de reconocimiento de objetivos mejorados con inteligencia artificial para ayudar a las tropas, veh\u00edculos y barcos a destruir drones El proyecto C-UAS Close-In Kinetic Defeat Enhancement se centra en el reconocimiento asistido de objetivos (AiTR). Este sistema utiliza conceptos como la IA, el aprendizaje autom\u00e1tico y la visi\u00f3n artificial para crear un sistema capaz de detectar amenazas \u2014y distinguirlas de elementos que no representan una amenaza, como las aves\u2014 con mayor rapidez que un operador humano.<\/p>\n
The Department of Defense is looking for\u00a0AI-enhanced<\/a>\u00a0target recognition to help troops, vehicles and ships destroy\u00a0drones<\/a>.<\/p>\n The C-UAS Close-In Kinetic Defeat Enhancement project focuses on aided\u00a0target recognition<\/a>, or AiTR. This uses concepts such as AI, machine learning and computer vision to create a system that can\u00a0detect threats<\/a>\u00a0\u2014 and distinguish them from non-threats such as birds \u2014 faster than a human operator can.<\/p>\n The first phase of the project is aimed at remote weapons stations, and specifically the ubiquitous Common Remotely Operated Weapon Station, or CROWS, turrets fitted to a variety of military vehicles.<\/p>\n \u201cThe primary objective is to accelerate the engagement timeline, initially focusing on Unmanned Aircraft Systems (UAS), with a secondary focus on other threats like vehicular and man-sized targets,\u201d explained the Defense Innovation Unit\u00a0solicitation<\/a>. The deadline is May 15.<\/p>\n Prototypes must \u201cdemonstrably improve\u201d the ability of current remote weapons stations to detect, track and engage Groups 1 and 2 \u2014 targets with a weight of 55 pounds and under.<\/p>\n Detection should be at ranges greater than 600 meters, and engagement at a minimum of 100 meters. The system should be effective against drones moving at speeds of at least 30 meters per second, or 67 miles per hour, per the solicitation.<\/p>\n The second phase of the project seeks to boost C-UAS capabilities on \u201cboth moving and stationary platforms, including ground and maritime environments,\u201d the solicitation said.<\/p>\n Specifications include the ability to hit a Group 1 drone \u2014 under 20 pounds \u2014 moving at 7 meters per second, or 16 miles per hour, at a range of 50 to 200 meters. Weapons should be able to engage targets while depressed to minus 10 degrees or elevated directly overhead to 90 degrees, the document stated.<\/p>\n This requires contractors to provide a prototype that can \u201cbe fired in land and maritime environments,\u201d the solicitation says, \u201crather than just a laboratory setting at time of pitch.\u201d<\/p>\n Most noteworthy, meanwhile, is the third phase of the project: adding aided target recognition to small arms carried by dismounted troops.<\/p>\n \u201cDesired solutions include systems capable of deflecting or self-aiming standard-issue rounds to increase hit probability against manually selected, transient targets, while integrating networked sensor and small arms fire control systems,\u201d DIU said.<\/p>\n The system must be capable of engaging drones moving at least 7 meters per second, and \u201cmust be adaptable to dismounted legacy small arms, scalable across calibers and configurations, and maintain baseline weapon performance in the event of system degradation or failure,\u201d the document states. \u201cA semi-automatic, live-fire capable prototype is required.\u201d<\/p>\n The final phase of the project seeks to improve integration between sensors and weapons.<\/p>\n \u201cA commercial wireless edge network architecture that bridges to military systems and the reverse is essential across all stages of this effort to manage data transfer from sensors and weapon\/fire control systems,\u201d the DIU wrote.<\/p>\n The U.S. military is beginning to embrace aided target recognition. The Army is already\u00a0testing<\/a>\u00a0small UAVs equipped with AiTR to help infantry squads control drones.<\/p>\n But the Pentagon is also aware that AI and targeting is\u00a0controversial<\/a>.<\/p>\n The DIU project specifies that there must be a human in the loop. Solutions must strictly adhere to\u00a0DOD\u2019s AI Ethical Principles<\/a>. Non-compliance \u201cwill result in immediate disqualification,\u201d DIU warned.<\/p>\n