Tag Archives: autopilot

Tesla Autopilot engaged in Model X. Credit: Wikimedia Commons.

Tesla’s Autopilot reaches one billion miles driven: that’s 10 times the distance from Earth to the Sun

Tesla Autopilot engaged in Model X. Credit: Wikimedia Commons.

Tesla Autopilot engaged in Model X. Credit: Wikimedia Commons.

Tesla electric vehicles have collectively driven more than one billion miles on Autopilot. That’s 10% of the total mileage driven by all Tesla vehicles across the globe to date, including vehicles sold before Autopilot was even introduced.

Autopilot was first rolled out in 2015, and ever since Tesla has introduced both hardware and software updates that improve autonomous driving. Last month, Tesla introduced new features in Software Version 9, including Navigate on Autopilot, which brings the company’s cars a step closer to becoming fully autonomous on the road.

“[Navigate on Autopilot] is one of the first major steps toward full self-driving. You can enter in an address, and from highway on-ramp to highway off-ramp, the car will change lanes. It will go from one highway to the next automatically and take off-ramp automatically. It’s pretty wild. It’ll overtake a slow car. It’s basically integrating navigation with the Autopilot capability,” Musk recently said during his recent appearance at the Recode Decode podcast. “I think we’ll get to full self-driving next year. As a generalized solution, I think. Like we’re on track to do that next year. So I don’t know. I don’t think anyone else is on track to do it next year.”

As it stands today, Autopilot is not fully ready for all types of roads. However, Tesla seems compelled to make all its cars fully autonomous. According to Andrej Karpathy, Tesla’s AI Director, the company already has large neural networks that are capable of safely navigating Teslas through different types of roads and traffic. However, these updates can’t be rolled out momentarily due to hardware constraints. For Autopilot to evolve into a truly autonomous feature, Tesla cars will have to be fitted with more computing power in the future. Upgrade to Hardware 3, which involves swapping the Autopilot computer, is free for all customers who purchased the Full Self-Driving suite.

“This upgrade allows us to not just run the current neural networks faster. But more importantly, it will allow us to deploy much larger, computationally more expensive networks to the fleet. As you make networks bigger by adding more neurons, the accuracy of all their predictions increases with the added capacity. So in other words, we are currently at a place where we’ve trained large neural networks that work very well, but we are not able to deploy them to the fleet due to computational constraints,” Karpathy said during the third quarter earnings call.

The Silicon Valley auto-maker is also rolling updates to its valet parking feature dubbed “Summon”. The feature works on all cars manufactured in the past two years and, in the future, it will drive the electric vehicle to your phone location — even across the continent. The advanced Summon also allows users to “follow you like a pet” as long as you hold down the Summon button on the Tesla app. The update should be ready in a couple of weeks as an over-the-air software upgrade.

“Also, you’ll be able to drive it from your phone remotely like a big RC [remote control] car if in line of sight,” added Musk.

The surprising reason why birds never crash mid-air: they always veer right

bird mid-air collision

Credit: QBI YouTube

Despite thousands of birds might fly together in a flock, you’ll never seem them crashing into each other — not even when two flocks fly into each other from opposite direction.  Professor Mandyam Srinivasan and colleagues from the University of Queensland, Australia, think they’ve finally found out how birds manage to pull this off: a combination of varying altitude and, most importantly, veering right — always!

“Birds must have been under strong evolutionary pressure to establish basic rules and strategies to minimise the risk of collision in advance,” Professor Srinivasan said.

“But no previous studies have ever examined what happens when two birds fly towards each other.”

To study how birds respond to a possible mid-flight collision, the researchers recorded ten budgerigars who were released from the opposite ends of a tunnel. In total, 102 flights were filmed with high-speed cameras and not one single collision was observed, despite some close calls.

After painstakingly studying frame by frame the strategies employed by the birds, the researchers found the birds rarely flew at the same altitude. It may be that each individual has its preferences for flying at a certain height. It might also be that the position within a group hierarchy determines the flight altitude — this is the subject of an upcoming research.

What the models undeniably suggest, however, is that the birds always veer right when faced with the prospect of hitting a neighbor. The findings published in PLOS One might be helpful to improve aircraft autopilot features by making them safer.

“As air traffic becomes increasing busy, there is a pressing need for robust automatic systems for manned and unmanned aircraft, so there are real lessons to be learned from nature,” said Srinivasan.

“As air traffic becomes increasing busy, there is a pressing need for robust automatic systems for manned and unmanned aircraft, so there are real lessons to be learned from nature.”



Tesla Model X with beautifully extended Falcon Wings. Credit: Tesla Motors

Tesla Autopilot might have saved this guy’s life

Tesla Model X with beautifully extended Falcon Wings. Credit: Tesla Motors

Tesla Model X with beautifully extended Falcon Wings. Credit: Tesla Motors

Joshua Neally, a 37-year-old attorney in Springfield, Missouri claims his recently purchased Tesla Model X saved his life. After suddenly becoming engulfed in pain, not being able to see or drive properly, Mr. Neally quickly activated the Autopilot feature and basically left his car drive itself all the way to the nearest hospital, more than 20 miles away.

“Car, to the hospital quickly!”

In May, Tesla came under serious fire after a Tesla Model S driver was killed in an accident while Autopilot was on. It’s not clear yet if Tesla is responsible in any way for the unfortunate fatality, but a government investigation is underway.

It’s worth noting that Tesla’s Autopilot is an experimental feature, cut with a lot of legal fine tape. Even so, the company claims there have been fewer accidents involving Tesla’s cars on Autopilot than there ought to be otherwise, statistically speaking mile per mile. Later, Electrek reported a pedestrian’s life was saved by Autopilot’s Automatic Emergency Braking (AEB), and most recently news outlets reported the story of Neally.

Joshua Neally and his Tesla Model X. Credit: Facebook

Joshua Neally and his Tesla Model X. Credit: Facebook

It was July 26 when Neally was commuting home for his daughter’s birthday when a sudden spasm of intense pain struck his chest and abdomen. The Tesla owner reported the pain was so severe he had bouts of blindness. Clearly, he was in no condition to drive, but he did manage to muster enough strength to order his Model X to drive him to the nearest hospital. He reasoned this would be faster than calling for an ambulance. The car obliged and took him to the off-ramp near a hospital in Branson. At this point, Neally took control of the vehicle and steered it for the final stretch and quickly found himself in ER.

Neally later found out from a doctor that he suffered a pulmonary embolism, a medical condition that blocks the artery and kills around 50,000 each year. The doctor told him he was fortunate to be alive.

This episode is quite inspiring and will likely bring Tesla some much needed positive PR following the unfortunate fatal Tesla accident which involved Autopilot. Yet again, Tesla Motors stresses that Autopilot is an experimental feature designed to work solely on highways where traffic is predictable and the car can easily coordinate itself. In this particular incident, Neally was lucky enough to find himself on a motorway when his pulmonary embolism struck, but had he been in the middle of a busy town the Autopilot couldn’t have helped him. All the more reason, maybe, for Tesla to roll out Autopilot 2.0 — but very, very carefully. Right now, thousands of Tesla drivers are willing participating in a huge experiment, recording millions of miles and terabytes of data for Tesla. How the company will intend to use this data will remain to be seen.


Tesla autopilot goes live – it’s creepy and beautiful

A couple of days back we wrote that Tesla‘s new model S will be featuring an autopilot mode that will go live on October 15 – today. Well, now we have the first reactions, and they’re amazing.

First of all, it has to be said that this is not a driverless car – the driver has to be inside and from time to time, he still have to make a decision. For example, when the ‘Autopilot’ software doesn’t have enough data to properly steer the car, it will alert you to either “hold the steering-wheel” or “take control immediately”. But you get to see the cars ahead and behind you in real time, and the best thing is that the car does the most boring part of driving for you – it slows down when there’s a red light or someone in front of you, it can read road signs and traffic lights… it’s basically what the name says: it’s an autopilot.

Elon Musk, Tesla’s CEO explained the difference between autopilot and driverless:

The interviewer here clearly doesn’t understand what mister Musk is saying – a driver still needs to be there at all time and take responsibility for the driving, but (and this is a big but) this will reduce accidents, because the software is excellent at keeping a constant distance from other cars and is much more efficient at staying safe than the average driver.

A quadrirotor, where EPFL scientists test their new technology.

Moving closer to 100% autopilot airplanes. A reality?

In Philip K. Dick’s novels, a common denominator is the complete autonomy of the surrounding technology. The human characters often interact with their toaster which knows what kind of grill cheese they prefer and even makes small talk, to the extent of exasperation from the human counterpart. A more palpable side to reality is the transportation – most of the time in Dick’s novels, the characters prance from one corner of the globe to another by an aerial vehicle, which simply gets you to your destination fast and easy without any kind of human intervention – you just need to sit tight, and maybe put up with your aerovehicle’s chattering.

A quadrirotor, where EPFL scientists test their new technology.

A quadrirotor, where EPFL scientists test their new technology.

Now, three EPFL laboratories are working closely together as part of a joint effort to design a completely autonomous flight system for airplanes that is safe and reliable, and happy to put pilots out of work. Now, you might say that this has already been implemented for UAVs; hold your horses though. When carrying people, you’re in a whole different ball game.

For one, this is an immense technological challenge which requires interdisciplinary expertise, which is why three extremely well staffed laboratories from one of the best tech schools in the world have been enlisted for the project. These are the Real-Time Coordination and Distributed Interaction Systems Group (REACT), which is working on predicting trajectories and in-flight collision avoidance; the Computer Vision Laboratory (CVLab), which has the job of outfitting the aircraft with a veritable visual intelligence system; the Distributed Intelligent Systems and Algorithms Laboratory (DISAL), which will test algorithms on small, lightweight flying robots.

Yes, all available resources will be called out for this one, and, again, this is a lot harder than it may seem. The REACT team, for instance, which has a long history with unmanned vehicles will try to develop a system which makes use of any positioning and sensing device inside an airplane, whether it’s GPS, ground-based radar, cameras, infrared cameras etc, and develop a position and trajectory algorithm based on the data fed by these devices.

This will came in handy for DISAL which in charge of developing an algorithm that will help communicate between airplanes. “We will work on integrating trajectory prediction, avoidance, stability, vision, and data-exchange algorithms developed by various laboratories, and see how to get them working together in real time,” explains laboratory director Alcherio Martinoli.

CVLab will work with high definition cameras, designed to recognize objects. “What seems to be a simple task for the human eye is incredibly complex to reproduce technically,” explains CVLab scientist Vincent Lepetit . “The main difficulty lies in the enormous amount of information that has to be processed; each image is made up of several hundred thousand pixels.”

Apparently, all the three labs have been called upon for the project by Honeywell, a huge industry player in the oil and mechanical engineering scene, but also in the aerospace sector.

“These new technologies will not only help us improve general flight safety, for example by providing better autopilot systems, but they will certainly also have other uses in automating everyday life,” says George Papageorgiou, director of the Aerospace Advanced Technology Europe System Engineering & Applications Department at Honeywell.

In the first instance, according to Honeywell officials, such a system will be first used for small airplanes or drones in non-military applications, such as forest fire surveillance or monitoring access to industrial sites and borders.

Would you fly on complete autopilot? Discuss below in the comment section.