Gadgetory

I don't think anything says we're living in the future quite like the proliferation of self-driving cars now granted they're not exactly all over the roads yet but given the huge investments that automakers and tech companies are making in them it seems like it's a matter of when rather than if but how exactly do they work I mean most of our trains aren't even self-driving and those things aren't quite literally on Rails well as you'd expect self-driving cars are jam-packed with tons of equipment to help them both see and understand their environment some of it is rather familiar such as a data connection for traffic info and a GPS transponder to allow the car to know where it is but while GPS is fine for providing driving directions in a human controlled car it has a margin of error of up to several meters and besides to control a car with such a slow and error-prone system would result in more than a few fender-benders so to start with self-driving cars also use freaking laser beams to build a map of what's around them lidar which you can learn more about up here can be built into units that can spin 360 degrees shooting invisible lasers in all directions then measuring how long it takes for each beam to hit an object and bounce back this allows the car to judge not only the distances but even the shapes of the objects immediately around it giving the car even more information is traditional radar to help it gauge speed gyroscopes and accelerometers to provide more movement data than would be possible with a traditional speedometer and high resolution cameras now you might think well we've already got frickin laser beams what are the cameras for well although the cars other systems give it a pretty good idea of what's in the general vicinity the cameras really help provide a complete picture as they can see in color this helps your car distinguish let's say a caution sign from a Construction sign so you put all of this together and the car has a coherent 3d map that provides the data that it needs to make this visions for example lidar and video can determine whether that thing up ahead is telling the car to stop or yield whether the vehicle in front is a small sports car or a large truck so that it can decide whether to pass or whether that two wheeled contraption is a motorcycle or a bicycle so the car can get around the cyclist and give her a bit more space also many self-driving cars have ultrasonic sensors in the wheels so the car will know how close it is to the curb and other vehicles while parking and even microphones so that they can hear a police or EMS siren to get out of the way in a timely manner I mean that's gonna be one improvement on the roads around here once self-driving cars are ubiquitous people can be so rude going to an emergency anyway that's how all the data gets collected but what about the processing an experienced driver can take in information from the environment filter out everything that's not important and make all the kinds of decisions we talked about before in a fraction of a second so of course then you need a lot of computing power for a self-driving car to pull off the same thing this is made possible by running many processors in parallel to crunch these numbers it's actually quite similar to how desktop GPUs work these types of processors also happen to be more trainable with machine learning so for example you can teach a car what a pedestrian looks like by showing it a large data set with lots of photos of people crossing the road but what if a self-driving car didn't only have to rely on its own sensors and processors well another goal is to have these cars communicate with each other while they're on the road so they can actually tell other cars what they're doing and why enhancing safety and taking some of the guesswork away from the individual vehicles and if you think about it having many cars working together like this in unison could help with lots of other issues - like easing congestion by coordinating movement so that traffic can keep flowing smoothly also in the future especially wants faster 5g connections become more common we could even see smart infrastructure that communicates with the I mean think about a parking garage that could tell a car that it's too full to accommodate it or transponders in construction zones that could tell them to slow down and prepare for narrower lanes of course we do still have a long way to go before this kind of tech is commonplace but given how many semi autonomous cars are available for purchase today and how much money is being poured into this whole endeavor along with the ever-rising processing and data speeds we continue to enjoy the hope is that in the near future our car trips will be much easier and safer since well over 90 percent of car accidents are attributable to human error and speaking of self-driving cars today's episode was brought to you by IBM spectrum storage did you know that a self-driving car can generate up to 15 terabytes of data every hour and lots of this is actually not even used while they're driving so it's really common in the AI industry to have to ingest just tons of this raw data and transform it after the fact while the car's not even driving into intelligence and IBM is using spectrum storage to help automakers manage all this data so it's optimized for AI and machine learning with industry-leading GPU accelerated servers and IBM spectrum scales software-defined storage combined with groundbreaking performance and simplified deployment so get the fast lane to insights into whatever field you're in by learning more about data storage for AI and IBM storage solutions for autonomous driving at the link below so thanks for watching guys like just like check out our other videos and leave a comment with video suggestions and don't forget to subscribe and follow too not this one I mean this one - but but but also tech wiki that the button below