Researchers from the Columbia Engineering team have developed a self-aware robot that is capable of learning how to use its body without any human assistance. That’s right, this robot arm managed to create a kinematic model of itself and then used it to plan motion, reach goals and avoid obstacles in all kinds of situations.
The robot arm was even able to automatically recognize and then compensate for damage to its body. To observe this, the researchers placed it inside a circle of five streaming video cameras where the robot watched itself freely. It moved around to learn exactly how its body moved in response to multiple motor commands, and after about 3-hours, its internal deep neural network had finished the process. This robot arm would work well with IBM’s autonomous AI-powered Mayflower ship.
Segway Ninebot E22 Electric Kick Scooter, Lightweight and Foldable, Upgraded Motor Power, Dark Grey
- More Powerful Upgraded Motor: With a new Version of 300w brushless direct current motor, E22 can reach to 12.4 mph, travel up to 13.7 miles and a max load of 220 lbs. The upgrade brings greater riding dynamic plus stronger 15% hill grade capability.
- Safe & Comfortable Riding: Supreme Shock Absorption, no tire Punctures, the upgraded 9-inch Dual Density tires deliver more stability and comfort than the 8-inch solid tires; Dual Braking System and Bell enhanced safety when riding
- Lightweight & Foldable: E22 folds in just one step, and can easily fit in the back of your car. This device is also easy to carry, with a net weight of only 28 lbs (13.5kg), allowing you to single-handedly carry it into subways or elevators
- Innovative & Superior Technology: Smart Battery Management System (Smart-BMS) has undergone 7 years of continuous technological development and produced 300 million batteries. ensuring user safety, and accurate power display.
- Quality Assurance: With the enhanced performance and design, the new E22 is perfect for your last mile journey; One-year or 180-day warranty for different parts, please refer to warranty information in product details below.
We were really curious to see how the robot imagined itself. But you can’t just peek into a neural network, it’s a black box. It was a sort of gently flickering cloud that appeared to engulf the robot’s three-dimensional body. As the robot moved, the flickering cloud gently followed it,” said Hod Lipson, professor of mechanical engineering and director of Columbia’s Creative Machines Lab.
