New research in Machine Learning has taught machines how to identify a door, a door handle, how to open that door, and how to confirm that the task was done properly. All by watching humans doing the same task!
As discussed in previous posts, the machine can already recognize the objects it finds in photos and videos. So researchers are expanding on that technology to create robots that learn by watching humans in an unsupervised fashion.
The Building Blocks in Google Research Labs
Below is an example of a human physically instructing a machine to open a door. This technique appeared to work pretty well, especially when supplemented with machine learning.
Interestingly enough, researchers found that they could allow multiple robots to learn at the same time, this way they can all benefit from the experience and learning from one another. The more machines participating, the faster they all learned.
The Problem
Notice the wire connected to the back of the door in the video above. This line runs to a sensor that tells the robot if the door was actually opened or not. The problems presented here show that machines need a way to learn to do these things in an unsupervised fashion. No physical training by humans should be needed other than visual cues and of course, in real life there are no sensors on the backs of doors.
Machine Learning By Watching
In the demonstration below, we can see how the robot is learning to imitate human motions even though the machine does not have identical body parts. For example, the human has two legs that must bend in order to squat, while the robot has a different setup. Regardless of the physical differences in their bodies, the machine has learned how to best mimic the human with the hardware it has, by watching the human move.
Next, researchers applied the same technology to doors. This allows the machines to learn the actions needed to open a door by watching humans rather than being manually instructed.
Rewards
This technology also allows the machine to determine for itself, if it has completed the task appropriately. If the machine determines that the door was opened (without the use of a sensor), then it uses this experience to create a reward or a goal to help re-enforce more complicated but similar tasks.
The researchers started slow, and then gradually increased the complexity of the scenarios noticing that machines were able to learn better when they learned in small chunks and were allowed to use experience from the past to build on.
In the video below, we can see a researcher changing the orientation of a door and the machine is able to conduct the task every time without any sensors.
Modern science is very close to creating machines that can self-teach and self-reward entirely autonomously.
The future for robots looks bright!
References:
https://research.googleblog.com/2016/10/how-robots-can-acquire-new-skills-from.html
https://research.googleblog.com/2017/07/teaching-robots-to-understand-semantic.html
Long time no see... Think I found this after I saw your name pop up on one of Peter's posts.
The way technology has advanced is really amazing, although things like self improving mechanisms always scare me a little. I wonder if the robots, provided their "brains" get complex and powerful enough will also develop a consciousness and if they will be able to understand ethics...
Hi @reinhard-schmid,
Great to hear from you, thanks for stopping by!
I think this is where @builderofcastles was going. Humans still spend a lot of time training machines, and while they learn on their own to an extent, working with the unknown is not feasible at this time. Unless there are humans there to guide things, the machine does not really learn much. In those terms, I suppose even ethics could be "taught". So perhaps the scariest question of all is...
Who is training the machines, what are their values, and what do they think like?
Right now, the answer seems to be, "Capitalist Corporations".
You know, companies like Google! Self driving cars and such!
amazing post, i agree with your thoughts "the future of robots is so bright", i like your thoughts it would be much better if the robot learn from human activity instead of sensors, even now in many countries we can see robots are working in hotels and shops and doing good work, so all is all induction of robots in life is great development and i hope we see more improvement ahead in this technology, Stay blessed and have a fantastic weekend ahead.
The news coming out of the AI world never ceases to delight & terrify me at the same time!
You double posted this.
Today, instead of steemit not getting the post, the reverse is happening.
Steemit is getting the post and the browser is not getting the update.
I use steemd.com to check.
You just wrote an article that said the machines were taught to recognize a door. They are no where near self-teaching. In fact, no one has even broached the subject of working with an unfamiliar entity.
I more than double posted, I did not realize this was even getting posted because it kept telling me there was an error. Sorry about this folks.
My intention was to describe this as the early building blocks of autonomous robotic learning through simply watching humans, as the reference articles indicate. At the very end they wrap it up nicely saying...
"Our experiments show how limited semantically labeled data can be combined with data that is collected and labeled automatically by the robots, in order to enable robots to understand events, object categories, and user demonstrations. In the future, we might imagine that robotic systems could be trained with a combination of user-annotated data and ever-increasing autonomously collected datasets, improving robotic capability and easing the engineering burden of designing autonomous robots. Furthermore, as robotic systems collect more and more automatically annotated data in the real world, this data can be used to improve not just robotic systems, but also systems for computer vision, speech recognition, and natural language processing that can all benefit from such large auxiliary data sources."
Thanks for sharing. A much more practical way of teaching than writing complex code