AI-driven combat drone can search buildings and perform suicide attacks

Israeli defense technology company Elbit Systems has launched a deadly, autonomous suicide drone. The Lanius is an agile racing quad with a range of AI-powered target recognition, mapping and classification capabilities, and the ability to explode if necessary.

Quadcopter drones are becoming a staple of modern warfare, as evidenced by the current conflict in Ukraine. It’s easy to see why; they’re cheap, easy to use, and getting smarter. They allow you to see and map a dangerous area without risk to the pilot, they can often move completely undetected by adversaries, and it is remarkably simple to attach and/or release a lethal payload.

The Lanius is designed to travel in groups of three, sitting above a larger mothership-style drone until deployed. Its maximum takeoff weight is 1.25 kg (2.76 lb), including a lethal or non-lethal payload of up to 150 g (5.3 oz). A small, hobby-style lithium battery gives it a maximum flight time of about seven minutes.

Up to three Lanius drones can ride on the back of a mothership drone, or they can be physically transported by operators in the field

Elbit systems

In addition to a simple, square carbon fiber racing drone chassis, the Lanius is equipped with numerous sensors and cameras, as well as an Nvidia Jetson AI system-on-module designed specifically for rapid interpretation of data streams. fast with low power consumption. It connects to Elbit’s Legion-X combat swarm management software for multi-drone autonomous missions.

Alone or in a swarm, the Lanius is designed to enter an area and begin mapping it autonomously using its AI capabilities and collision avoidance systems. It will detect and tag points of interest, as well as things like doors and windows whether they are closed or open, and it will enter buildings and search for them with or without direction or direct control from a human pilot. .

It is designed to detect humans and attempt to classify them as friendly or hostile, combatant or non-combatant, armed or unarmed. When an armed threat is detected, it offers its human operator the ability to “engage” the target using the weaponry on board. There is always a human in the loop; this thing won’t try to kill anyone on its own.

Nvidia Jetson systems aboard the Lanius attempt to detect, classify and tag humans in real time
Nvidia Jetson systems aboard the Lanius attempt to detect, classify and tag humans in real time

Elbit systems

It provides another tactical advantage in the ability to sit in ambush mode watching a particular area – for example, a locked door that might have hostile threats on the other side. In this case, the Lanius can land quietly and watch the door. If the door opens and she sees something she considers an armed threat, she alerts the operator remotely and offers the option to engage again. This could definitely be an effective way to watch a team’s back or flanks as they move through a dangerous area.

It’s probably relatively slow and clunky at this point, but given how quickly quadcopter drones and deep learning technologies have developed over the past decade, you can bet these machines will advance rapidly over the of the next few years. Check out a very dramatic video below.

Elbit/LANIUS systems

Source: Elbit systems Going through DroneDJ

window.fbAsyncInit = function() {

appId : ‘38456013908’,

xfbml : true,
version : ‘v3.3’

(function(d, s, id){
var js, fjs = d.getElementsByTagName(s)[0];
if (d.getElementById(id)) {return;}
js = d.createElement(s); = id;
js.src = “”;
fjs.parentNode.insertBefore(js, fjs);
}(document, ‘script’, ‘facebook-jssdk’));

Leave a Reply

%d bloggers like this: