Share this on WhatsApp Google’s Project Tango smartphone is loaded with advanced sensors, vision processors and motion tracking camera that let it track millimeter precise positioning in space by creating 3D maps in real time. On the other end Parrot AR Drone 2.0 powered by a 1GHz 32 bit ARM Cortex A8 processor has its own set of sensors for advanced navigation. So the researchers at the University of Pennsylvania led by Professor Vijay Kumar have combined both these gadgets to demonstrate how the capabilities of each can be used to provide highly advanced navigation capabilities for the drone. The drone can be stabilized in the air without the use of any external GPS device or sensors using Tango phone which can open immense possibilities for flying UAVs. The advanced 3D maps that the Tango phone can create will help immensely in navigating drones in tight spaces or pre-planned paths. This surely is going to lower the barrier to entry for autonomous robots. In the video given below you can see how this drone retreats back to its set coordinates if even altered physically by hand.

And the next step in development is to make the system navigate indoor spaces with precision for various kinds of operations. Share this on WhatsAppOn March 5, the pilot of an Alitalia flight on its final approach to Runway 31 R at New York's JFK International Airport spotted something odd in the air—a small, black flying machine with four propellers flying too close for comfort. parrot ar drone bladesThe aircraft, likely a "quadrocopter" style drone, passed within 200 feet of the Alitalia airliner at an altitude of about 1,750 feet.ar drone for sale cape town Yesterday, the FBI issued a call for help from the public, requesting anyone with information about the drone or its operators to contact the FBI's New York field office. buy parrot ar drone online

An FBI spokesperson told Ars that there had been no new developments in the case. While investigators believed the drone was a quadrocopter, they had not officially confirmed this detail. But given the size of the drone—less than three feet across—and the pilot's report that it had four propellers, the vertical-takeoff quadrocopter design is the most likely suspect.parrot ar drone gamestop Commercial drones in the "microdrone" class, such as the Microdrones quadrocopter recently snatched up by an Italian university student, are expensive and not widely available to individuals. parrot ar drone raceThey are, however, available used on the aftermarket for about $20,000. parrot ar drone how highMore traditional radio-controlled commercial drones used in film and video production, such as those made by Quadrocopter, sell for slightly less.ar drone parrot buy online

But kit quad-rotor drones, like the ArduPirates drones built using Arduino programmable microcontrollers and ArduCopter code, can be built for around $300 and use GPS to navigate on a programmed course. The Parrot AR Drone, controllable by mobile devices based on Apple's iOS and Google's Android, is also in that price range. Though while that drone could operate at 1,750 feet, it would need modification to be controlled from the ground at that altitude. There's been some speculation that the drone may have been flown out of Brooklyn's Floyd Bennett Field, a popular spot for model aircraft hobbyists. But given the size of the drone (under three feet across, according to the pilot who spotted it) and its type, it's more likely the device was launched somewhere east of the airport in the Five Towns area in Nassau County, a collection of affluent suburbs on Long Island's South Shore. This drone could simply have been flying into commercial airspace by accident or malfunction.

But small drones could just as easily be launched with malicious intent. While a quadrocopter drone of the size described in the March 5 incident would weigh no more than about 12 pounds (and much less if it was a hobbyist's kit drone), it could still do serious damage to an airliner during takeoff or landing. A collision with a small drone could have an effect on a jetliner similar to a birdstrike. Birds colliding with aircraft have broken windscreens of jets and have even, in the case of US Airways Flight 1549, taken out engines. In January of 2009, just a few days before the geese took down Flight 1549, a helicopter carrying oil platform workers in Louisiana hit a red-tailed hawk and crashed, killing eight of its nine passengers. A drone intentionally GPS-guided into an airport's approach or takeoff airspace could do more than just crash into aircraft. If a drone was built with the intent of causing damage to a plane or distracting its crew at a crucial moment, it might carry a small explosive or a camera-aimed laser pointer, for example.

Given how easily small drones can be built or obtained and how difficult it is to track them, it will require a lucky break for authorities to track down the drone and its operator. And this isn't a problem that regulation will solve—drones of this size can be assembled by someone with fairly basic technical skills. You can already download and 3D-print most of the parts for a quadrocopter drone, much like you can with firearms.They might not be delivering our mail (or our burritos) yet, but drones are now simple, small, and affordable enough that they can be considered a toy. even customize and program some of them via handy dandy Application Programming Interfaces (APIs)! The Parrot AR Drone has an API that lets you control not only the drone's movement but also stream video and images from its camera. In this post, I'll show you how you can use Python and node.js to build a drone that moves all by itself. So given that I'm not a drone, or a machine vision professional, I'm going to have

to keep things simple. For this project, I'm going to teach my drone how to follow I know, I know, it's a far cry from a T-800 Model 101 (or even something like this), but given my time and budget constraints it's a good place to start! In the meantime, feel free to send your best autonomous terminators or drone swarms my way. When I opened my drone on Christmas morning I wasn't entirely sure what I was going to do with it, but one thing was for certain: This thing was cool. The AR Drone 2.0 (I know super lame name) is a quadcopter. If you're imagining those fit in the palm of your hand, single-rotor, RC gizmos, you're in the wrong ballpark. The first thing I noticed (and was most surprised by) was how big the AR Drone is. With its "indoor shell" on, it's about 2 feet wide, 2 feet long, and 6 inches high. It's also kind of loud--in a good way (like a terrify your dog kind of way, unlike this down to drone pup). Combine that with 2 cameras--one front and one bottom, and you've got yourself the ultimate grown up geek toy.

What sets the AR Drone apart is that it's old (in drone years)--it was first released in 2012. might seem like a bad thing BUT since we're trying to program this gizmo, it's actually Given that it's had 4 years to "mature", there are some really great APIs, helper libraries, and project/code samples for controlling/programming the drone (see list of resources below). So in essence, someone else has already done the hard part of figuring out how to communicate with the drone in bytecode, so all I have to do is import the node_module and I'm off to the figurative drone races. Programming the drone is actually quite easy. I'm using the ar-drone node.js module. found that it works really well despite not being under super active development. To start, let me show you how to do a pre-programmed flightplan. The following program is going to: Pretty simple little program. Now even though it's pretty straightforward, I will still highly recommend having an emergency landing script readily available.

you never know you need one till you really need one ;) You can also pull off some fancier moves--you know, to impress your friends. favorite is a backflip. Ok now for the second piece of the puzzle: teaching our drone how to see. To do this, we're going to be using OpenCV and the Python module cv2. be a little prickly to work with, but it can do some really impressive stuff and even has some machine learning libraries baked right into it. We're going to be using OpenCV to do some basic object tracking. We're going to have the in its field of vision. Sort of like a bull at a bullfight. Good news for us is that cv2 makes this really easy to do. As you can see above, I'm using a color mask to filter the pixels in an image. a simple but intuitive approach. And more importantly it works. Processed with red filterOk well maybe not quite like a T-800 Model 101, but it's at least a start. Ok here comes the tricky part. We've got our little node.js script that can control

the drone's navigation, and we've got the python bit that can detect where red things are in an image, but the question looms: How do we glue them together? Well my friends, to do this I'm going to use Yhat's own model deployment software, ScienceOps. I'm going to deploy my Python code onto ScienceOps, where it'll be accessible via an API, and then from node.js I can call my model on ScienceOps. What this means is that I've boiled my OpenCV red-filtering model into a really simple HTTP endpoint. I'm using ScienceOps to make my childhood drone bull fighting dreams come true, but you could use it to embed any R or Python model into any application capable of making API requests, be it drone or otherwise. I don't need to mess around with any cross-platform baloney, and if I need to up the horsepower of my model (say for instance if I'm controlling more than one drone), I can let ScienceOps scale out my model automatically. If you want more info about

deploying models (or drones) into production using ScienceOps, head over to our site or schedule a demo to see it live. What does all this mean? Well for one, it means my node.js code just got a lot simpler. use the Yhat node.js library to execute my model:Now I can pretty much just drop this into my navigation script. All I need to do is tell my script how I want to react to the response. In this case it's going to be a couple steps:What could possibly go wrong? As the adage goes, If at first you don't succeed try, try again. It took me a few iterations to get the autonomous piece to actually work. Turns out, combining individual components has the propensity to compound your error! But not to worry! My drone took its fair share of bumps and bruises but it's a tough little guy--Pro Tip: You can patch up your drone with duct tape. Just be sure to apply equal amounts to each side of the drone so it's balanced! A couple of things I learned the hard way: