For a while, it looked like Rethink Robotics would shake up the world with its collaborative robots: rather than having to write code, workers could teach bots to perform tasks by guiding them through the process. However, the market doesn't appear t...
It can be frustrating when telling robots what to do, especially if you aren't a programmer. Robots don't really understand context -- when you ask them to "pick it up," they don't usually know what "it" is. MIT's CSAIL team is fixing that. They'v...
A team from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) wanted robots to be a more natural extension of our bodies. See, you'd usually have to issue vocal or very specific mental commands to control machines. But the method...
Between the HTC Vive and the Oculus Rift, we've come a long way towards being able to step in to virtual worlds -- but touching those false realities is a different matter. Solving this means finding a haptic technology that can adapt to needs of a c...
Even for robots, practice makes perfect. At least that's how it works for the technique developed by Brown University assistant professor Stefanie Tellex, which teaches robots how to pick up objects so they can relay the info to other robots. Telle...
The robotic revolution is not about replacing humans entirely, but about taking human-machine cooperation to a new level. The Robot Positioning System developed by Rethink Robotics equips machines with the adaptability they need to work alongside humans.
Since they lack a mind of their own, most robots can only handle pre-programmed events. Industrial robots are hence mostly seen working on their own, as human coworkers may turn out to be very unpredictable. Rethink’s Robot Positioning System (RPS) brings in the required flexibility so that industrial robots and human workers can team up safely.
Part of the Intera 3.1 Rethink softwre, the RPS makes complicated programming unnecessary. Basically, the Baxter general purpose robot that has been equipped with this software can learn from his human coworkers. At first, his actions need to be guided manually, but after that, it takes control and performs them automatically, at a pace that humans are comfortable with.
“Manufacturing robots have always been caged, not only to protect the workers around them from harm, but also to protect their precisely configured environments from being disrupted by those same workers,” explains Scott Eckert, CEO at Rethink Robotics. “With Baxter, we brought the manufacturing robot out of its cage by making it safe enough to work next to people; and now, we’ve made it safe for the robot to work effectively in real-world conditions as well, by allowing it to adapt to everyday variations that people naturally produce.”
How safe is it to work around Baxter? This inexpensive industrial robot has plenty of sensors and safety systems to make sure that no one gets hurt while working with it. Besides that, the Landmarks code-marked cards give Baxter an idea about where his location should be in reference to his workstation. Considering that the robot can work with up to 20 Landmarks and can be appointed to multiple workstations, the entire concept is very impressive.
Check out the following video to get an idea about how the Baxter industrial robot looks and works in real-life:
Baxter was exhibited at the Pack Expo 2014 trade show in Chicago between November 2-5, and hopefully it will find its way to factories in the not-so-distant future. Its flexibility and capability to adjust to various conditions make it a valuable co-worker, no doubt.
Would you believe that friendly-looking robot giving that guy a hug is an industrial robot? You probably thought they were all just arms that weld and move heavy objects. Well, most are. Baxter obviously is different.
Baxter is the work of roboticist Rodney A. Brooks of Rethink Robotics, and he was obviously designed to be human-friendly. The robot is made to be easily trainable by an assembly line worker, and if you grab Baxter’s hand, it will turn its head and its cartoon eyes on it’s tablet-sized face will look at you as if to say “Hey there, human.” And that’s the point.
The company is betting that in the future robots will work side-by-side with humans. Naturally, they want to be at the forefront here and are working hard to make normally dangerous bots more friendly. It sounds good, until a hug from this guy tears someones head off.
No one would characterize existing factory robots as especially warm and fuzzy: they're usually disembodied limbs that are more likely to cut you than hug you. Rethink Robotics wants to put a friendly face on those machines, both figuratively and literally. Its about-to-ship Baxter worker robot carries a touchscreen face that's as much about communicating its intent as giving humans something more relatable. Likewise, it's designed to be easily programmed by its organic coworkers and react appropriately -- you guide Baxter by one of its two arms to tell it what to do, and its combination of cameras and a quad-core processor let it adapt to real-world imperfections. Even the series elastic actuators in its arms give it a softer, subtler movement that's less likely to damage products or people. While Baxter isn't as ruthlessly quick as most of its peers, the relatively low $22,000 price and promise of an SDK for its Linux brain in 2013 should make it easier to accept than the six-digit costs and closed platforms of alternatives. We just hope we're not being lulled into a false sense of security as lovable robots invade our manufacturing base ahead of the inevitable Robopocalypse.
For a while, it looked like Rethink Robotics would shake up the world with its collaborative robots: rather than having to write code, workers could teach bots to perform tasks by guiding them through the process. However, the market doesn't appear t...
It can be frustrating when telling robots what to do, especially if you aren't a programmer. Robots don't really understand context -- when you ask them to "pick it up," they don't usually know what "it" is. MIT's CSAIL team is fixing that. They'v...
A team from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) wanted robots to be a more natural extension of our bodies. See, you'd usually have to issue vocal or very specific mental commands to control machines. But the method...
Between the HTC Vive and the Oculus Rift, we've come a long way towards being able to step in to virtual worlds -- but touching those false realities is a different matter. Solving this means finding a haptic technology that can adapt to needs of a c...
Even for robots, practice makes perfect. At least that's how it works for the technique developed by Brown University assistant professor Stefanie Tellex, which teaches robots how to pick up objects so they can relay the info to other robots. Telle...
