{"id":2736,"date":"2018-03-07T09:09:43","date_gmt":"2018-03-07T12:09:43","guid":{"rendered":"https:\/\/www.nachodelatorre.com.ar\/mosconi\/?p=2736"},"modified":"2018-03-07T09:09:43","modified_gmt":"2018-03-07T12:09:43","slug":"nueva-tecnologia-para-volar-drones-en-ambientes-densos","status":"publish","type":"post","link":"https:\/\/www.fie.undef.edu.ar\/ceptm\/?p=2736","title":{"rendered":"Nueva Tecnolog\u00eda para volar drones en ambientes densos"},"content":{"rendered":"

Un grupo de investigadores del Laboratorio de Ciencias de la Computaci\u00f3n e Inteligencia Artificial del MIT ha desarrollado un sistema llamado “NanoMap”. Esta tecnolog\u00eda utiliza la incertidumbre de un dron en su beneficio permitiendo que los veh\u00edculos a\u00e9reos no tripulados naveguen en entornos complejos a un ritmo constante de 20 mph. El equipo de investigaci\u00f3n est\u00e1 estudiando casos de uso espec\u00edficos que incluyen escenarios de b\u00fasqueda y rescate, defensa y entretenimiento. Las empresas de entrega que utilizan veh\u00edculos a\u00e9reos no tripulados pueden incorporar esta tecnolog\u00eda en \u00e1reas densamente pobladas.\u00a0<\/p>\n

\n
\n

A group of researchers at MIT\u2019s Computer Science and Artificial Intelligence Laboratory has developed a system called \u201cNanoMap.\u201d This technology uses a drone\u2019s uncertainty to its benefit allowing for unmanned aerial vehicles to navigate through complex environments at a consistent 20 mph pace. The research team is looking at specific use-cases including search-and-rescue scenarios, defense, and entertainment. Delivery companies using UAVs can incorporate this technology in densely populated areas.<\/p>\n

The\u00a0key ingredient<\/a>\u00a0of using a drone\u2019s uncertain position to the system\u2019s benefit was vital in achieving the speed in environments such as warehouses of forests. By forcing the UAV to constantly reconsider its position, obstacle avoidance was continuous.<\/p>\n

Graduate student Pete Florence, the lead author of a recent research paper based on similar ideas, stated that the approach employed here is far more reliable than traditional map-based navigation when it comes to thick, concentrated environments.\u00a0He said<\/a>, \u201cOverly confident maps won\u2019t help you if you want drones that can operate at higher speeds in human environments. An approach that is better aware of uncertainty gets us a much higher level of reliability in terms of being able to fly in close quarters and avoid obstacles.\u201d<\/p>\n

How exactly does NanoMap work?\u00a0According to MIT<\/a>, the system uses depth-sensing to measure the vehicle\u2019s surroundings, continuously, thereby allowing it to not only plan for its next moves but for movements a few steps ahead. Added to that, Florence alludes to a kind of artificial intelligence here, in regards to learning from the past and planning for the future. \u201cIt\u2019s kind of like saving all of the images you\u2019ve seen of the world as a big tape in your head,\u201d Florence explained. \u201cFor the drone to plan motions, it essentially goes back in time to think individually of all the different places that it was in.\u201d The implementation of NanoMap apparently reduced the drone\u2019s crash rate from 25 percent to 2 percent, which is an extraordinary decrease and one that drone delivery companies eager to operate in narrow,\u00a0inner-city environments<\/a>\u00a0are likely eager to employ.<\/p>\n

Let’s take a look at NanoMap in action, shall we?<\/p>\n<\/div>\n<\/div>\n