Kevin Lepton

I am the writer, editor and publisher behind this future technology blog and I predict you will keep reading to see what is coming right around that metaphorical corner.

Dec 112017
 

 

Vestri Robot with imagination

Vestri Robot with imagination

 

Wouldn’t it be nice if a robot could learn how to use an object without any help from humans? Apparently, that’s what a robot called Vestri can do.

Developed by a team from the University of California in Berkeley, Vestri can “see” into the future – but just for a few seconds – with that foresight allowing them to maneuver objects they have never been in contact with. The technology making it possible is called “visual foresight”, which may one day be used on self-driving cars or used to create home assistants that are more intelligent.

The researchers from UC Berkeley took inspiration from how children play. Kids play around with toys to figure out how it works. That very concept was programmed into the robot. So once the robot is done playing with an object, it then creates a predictive model which it taps into to perform a task.

The robot is helped by cameras, which help it see the next sequence of events. It uses the cameras to create different scenarios that haven’t happened yet. It “imagines” the possible events then picks the most effective method to achieve something. For example, moving an object from one place to the next.

Sergey Levine, an assistant professor at Berkeley, said in a university press release that the method allows the robot to visualize how different behaviors will affect the surrounding environment. This ability allows for “intelligent planning of highly flexible skills in complex real-world situations.”

The methods used are different from conventional computer-vision models, where lots images numbering in the thousands or millions are labeled and programmed into the machine. Instead, the method used for Vestri involves information that is autonomously collected.

The technology developed by researchers at UC Berkeley can be used on self-driving cars in the future. A car with such a technology can anticipate events that may happen on the road. But that is a plan for the future. For now, researchers are focusing on how Vestri can learn simple manual skills from autonomous play.

What Vestri can do right now is still very simple, but it’s sufficient enough to allow them to move objects around without any obstacles.

A deep learning technology lies at the heart of Vestri’s system, and it is based on convolutional recurrent video prediction, or dynamic neural advection (DNA). DNA-based models are able to predict how image pixels will move from frame to frame based on the actions of the robot. Improvements to DNA-based models have allowed robotic control that is based on video prediction to perform complex tasks such as sliding toys around obstacles.

Before this, robots learned skills with the help of humans who provided feedback. This is why the work done with Vestri is so exciting as it has shown that robots can learn without needing human assistance.

UC Berkeley researchers will continue to study control via video prediction, but further research will involve on improving prediction and prediction-based control, as well as coming up better methods that allow the robot to collect more focused video data so they can perform even more complex tasks like picking and placing objects, soft object manipulation, and assembly.

 

The Case for Self-Driving Cars of the Future

 Future Cars  Comments Off on The Case for Self-Driving Cars of the Future
Nov 242017
 

Over the past few years, there have been many news stories about self-driving vehicles becoming a practical part of people’s daily lives. What was once a part of science-fiction is quickly becoming reality as the technology progresses. The question becomes whether self-driving vehicles will go into widespread use sooner or later. The latest annual report from the National Highway Traffic Safety Commission (NHTSA) reports that 37,461 people died on American highways in 2016.

A recent report has related that even if self-driving or “highly automated vehicles” (HAVs) are only slightly safer than standard cars and trucks driven by humans, they should be put on the road as soon as possible. The reasoning is obvious as the number one reason for vehicular accidents is human error. By taking the human element out of the equation, the number of deaths on the roads will be reduced. So, saving lives becomes the paramount reason why self-driving vehicles should be on the road.

Self-Driving Car

Self-Driving Car

 

The report itself is based on roughly 500 situations that involve vehicular safety on the road and comparing self-driven to human-driven cars and trucks. While the safety of self-driving vehicles is certainly provable using computer simulations, collecting the real-world data necessary to make all the proper changes and advancement to the technology needed in making it a reality will take years.

This is because computer simulations only work with the information that is programmed into them. It is estimated that hundreds of millions, if not billions of miles will be needed before enough information is collected to create safe self-driving vehicles. And that might take hundreds of years given the current pace of testing.

Another aspect of the report that is being called into question is the actual number of lives that might be saved. It is not known if the number estimated is closer to the truth or not, even if it is generally agreed that self-driving vehicles should, under normal conditions, be safer that those driven by humans.

Getting the number of traffic fatalities down is the prime goal of self-driving vehicles, but the question is whether pushing more of these vehicles on the road now makes sense before the technology is fully ready. There is also the natural fear and apprehension that many people have about trusting their driving to a computer instead of themselves. It will likely take a new generation growing up with self-driving vehicles on the road that have proven to be safe before most people are comfortable with having them around. As for now, far more drivers are interested in having computer support systems that help them drive safer and more efficiently.

With so much that is still not known about the interaction between computer and human-driven vehicles and the myriad of situations that occur on the roadways, it will take years before all the kinks can be worked out. This means that you will likely see automated large trucks, taxis, and other transportation vehicles on the road first because their routes are more predictable.

References:

https://www.nbcnews.com/mach/science/there-may-be-one-million-reasons-self-driving-cars-make-ncna819111

https://www.technologyreview.com/s/609450/autonomous-vehicles-are-you-ready-for-the-new-ride/

 

 

Robot DNA for Future Medicine

 Future Medical Technology  Comments Off on Robot DNA for Future Medicine
Oct 172017
 

A lot of science fiction novels and movies have featured the use of Nano technology to shrink down people and machines. They are also sent inside human bodies to actively interfere with a threat to the health of the person they are inside of. Today, that idea is a little bit closer to reality. There has been a recent advancement with nanotechnology. Scientists at Caltech were able to programmed robots that are made of DNA.

It’s not a nano vessel where shrunken people can board yet, but this significant advancement has a lot of positive implications on the future of biotechnology.

In an article by the online publication of Science magazine, scientists at the California Institute of Technology has designed a nano robot made from DNA that has a functional body composed of hands, arms, and feet.

In their experiments, the researchers were able to create these DNA robots that can perform a preprogramed set of tasks.  The robots ‘walked’ and ‘carried’ around molecules to a defined location. Although this might not seem to be a lot at first glance, this is definitely a step into the right direction.

The California-based research team of scientists headed by Anupama Thubagere and Lulu Qian both leading bioengineers at Caltech were the ones who spearheaded this advancement. The potential application for this new capability to control DNA Robots is endless and they have yet to tap its full power.

What are the potential applications?

This development could be applied on how medicine is administered. Nano robots could directly neutralize a disease at the molecular level. In theory this will skyrocket the effectiveness of drugs being able to directly treat a sickness at it roots. A concrete example would be Nano robots being able to search and reach cancer cells accurately, which is still not entirely possible by the current medical technology available. With this new development they can program the robot to be able to set up molecular factories that manufacture medicine as needed.

What are the robots made of?

If you view the body at the Nano-level, you will see a whole new alien world that is teaming with life. A living body is composed of a system of interconnected living cells. There are thousands of naturally occurring nanomachines that are responsible for moving cargo in and out these cells, such as the Kinesin and Dynein.

The robots that were recently made are composed of nucleotides and the whole machines are only 20 nanometers in length each. A single robot has simple but functional parts, which includes an arm, a hand, foots, and a leg. Its walk is more like a crawl due to the natural structure of DNA – which is essentially what the robot is made of.

How does it move?

The secret of the movement of this particular nanobot lies within the nature of the behavior of the four bases of DNA, which are adenine, guanine, thymine, and cytosine. The adenine on a particular DNA can attach to the thymine of another DNA strand, while the cytosine of one DNA strand can connect to the guanine of another.