Track Our Progress



This is where we post about our recent efforts within the community and abroad to spread awareness of science and technology through presentations, robot demonstrations, and other events! Check back regularly for updates, recaps, and progress of our Because Robots… project.

Meet Darwin, a robot that learns from its mistakes

2

Different capabilities of the Darwin robot.
Today’s robots are usually programmed by someone clacking away at the keyboard in order to make them perform a task, as mundane as they may seem to us humans; 20 lines of code could constitute as little as less than a second of activity in the real world. The obvious problem with this, then, is that coding often takes up a large portion of time (and sometimes money) when it comes to making a robot work the way it’s supposed to, time that could be spent on design and strategizing. While traditional coding isn’t going anywhere, a subfield in computer science is quickly attracting roboticists everywhere: Machine learning.

“Right now if, for example, you have a company that builds robots, for every piece of hardware that you build, you also have to figure out how you are going to manually control it.”


— Sergey Levine, a member of the team developing Darwin

The idea that a robot can learn just as, and possibly better than, an average human can is not new, with interest for it extending all the way back to the 1940s. After all, without machine learning, we wouldn’t be hearing all the hype for self-driving cars, facial recognition software wouldn’t exist, and our email inboxes would still be filled with messages asking us to act on savings for some shoddy store across the street you’re pretty sure went out of business a decade ago. In many ways, machine learning is one of the unsung heroes of modern society.

Unnecessarily long exposition aside, one of the frontrunners of the machine learning effort includes a group spearheaded by Pieter Abbeel from UC Berkeley’s Robot Learning Lab, in which the team built a robot no taller than your shin that learns from its past mistakes as it ambles around and ultimately falls over. Again and again and again.

A deactivated Darwin robot.While it’s not an extraordinary sight to behold at first, what separates it from other robots is that it has the capacity to adapt from its mistakes and devise new techniques in order to suit its environment, all without any human assistance. Aptly named Darwin, after the scientist Charles Darwin who was responsible for his groundbreaking work on evolution, and sporting a neural network that imitates the human brain, it learns how to walk very much like a toddler would go about it, tentatively taking a few steps forward, sometimes falling backwards, but ultimately becoming incredibly proficient at it.

“Imagine learning a new skill, like how to ride a bike. … After some practice, you figure it out.”


— John Schulman, a PhD candidate from UC Berkeley’s Robot Learning Lab

In the demonstration, the team showcases Darwin with other motions besides walking, including leaning and arm movements. While it’s tethered to a leash to prevent it from falling over as much, it’s still cool to watch.

Abbeel’s team hopes to one day see their efforts come into fruition in the commercial and government market, including potential robots for rescue operations and delivering mail. A global robot takeover akin to that of the Terminator films is still a ways away, however, which might come as a relief (or disappointment) for some of you. But it can no longer be denied that in our quest for efficiency, accuracy, and convenience, instead of thinking robot, we’ve had to think human. Turns out they’re not so different from us after all.

“More work is necessary to move these results from simulation to the real world, but I think eventually this research will have a very big impact on robotics. It might be the path to actual humanoid robots, like Star Wars’ C-3PO.”


— John Schulman

Not so mundane, now, is it?

0
0
  
Also posted in Images | Tagged , , , , | 2 Comments

Ebola Killing Bot

With the deadly virus Ebola ravaging through Africa, and even prompting a scare in Dallas, a company in Texas has developed new type of disinfection bot.

Named “Little Moe”, this machine uses bright bursts of UV-C light to quickly disinfect a room. According to the company, the robot’s light bulb, which contains Xenon, can kill up to 99.9% of dangerous viruses and bacteria; in less than 5 minutes. It achieves this by splitting open bacterial cell walls to kill dangerous pathogens commonly found in hospitals.

The robot can completely disinfect a room in 5 minutes, and destroy Ebola on any surface in 2 minutes. This robot is advantageous because the UV light eliminates the need for dangerous chemicals.

+2
0
  
Also posted in Images | Tagged | Leave a comment

Google Smart Contact Lenses

Wearable devices have quickly changed the way we interact with each other, making  technology much more intimate than once seemed possible.

Google, again, as always, is taking this intimacy to a whole new level. The tech giant has recently unveiled a new plan to make a smart contact lens. However, this gadget isn’t going to be used to deliver your e-mail straight into your skull — at least not yet, it’s currently planned to be used to detect diabetes. The lens houses a sensor that measures the glucose levels in tears. A tiny pinhole in the lens lets tear fluid seep over the glucose monitor to get regular readings. Right now, the company said, it can get a level reading once every second.

Of course, with anything that records any data, people are scared of where the data will be stored. Google has assured people that the data will never reach Google’s servers. But really, who cares? I bet no one will have any problems when the lens can surf the web.

0
0
  
Also posted in Images | Tagged , , | Leave a comment

Battlecry 13

This last weekend, I attended Battlecry 13 at  Worcester Polytechnic Institute (WPI). With 48 teams in attendance, Battlecry is one of the larger and more competitive off season events here on the east coast. I took a whiteboard and a dry erase marker, and set off on a mission to talk to as many teams as I could about our website and to get some pictures of students and volunteers.

By the end of the day, I was able to talk to about 30 teams and took pictures of most of them. They’ll be added to the site soon as soon as they are processed. Many of the teams liked the site and passed it on to their student members. I was especially proud of one teachers comment, “This site inspires me! I can’t wait to see what my kids will think of this…”

+4
0
  
Also posted in Images | Tagged , | Leave a comment

Spreading The Word Abroad in Hsinchu, Taiwan

2

Two members of FIRST Team 846, Michael Lin and Akshat Agrawal, traveled to Hsinchu, Taiwan this spring break and spread the word of FIRST and our project throughout various schools and even got to talk to the mayor of the city! The mayor’s way of finishing the phrase? “Because Robots make life easier and more efficient” (written in his native Chinese).

Mayor of Hsinchu with FIRST Team 846 member Michael Lin

Some more efforts of Michael and Akshat include:

  1. Spoke with a junior highschool principal and director of their program (an English teacher) about Because Robots and FIRST.
  2. Michael Lin spoke to a class of 43 in the high school he visited about FIRST and received good feedback.
  3. Spoke with the entire high school (~700 students) about FIRST, which includes speaking with multiple directors and the principal of the school.

Both Michael and Akshat are still in Taiwan, so check back soon for more updates of their trip!

 

+11
0
  
Posted in News | 2 Comments