AI News, Video Friday: Deep-Learning Robots, DRC Practice, and Drone Pilot Competition
- On Tuesday, February 13, 2018
- By Read More
Video Friday: Deep-Learning Robots, DRC Practice, and Drone Pilot Competition
Apologies for the light posting this week: the entire IEEE Spectrum team (both digital and print)was closeted away in meetings working onways to better serve you, dear reader.
Leading the video news for today is research from UC Berkeley focused on teaching robots to learn tasks in ways that can be adapted to new situations, using a deep learning approach based on neural nets.
The upshot is that it enables robots (like Berkeley’s PR2, named BRETT) to learn new tasks in a matter of hours andperform those tasks generally independently of their environment, all with a minimal amount of sensors.
“We still have a long way to go before our robots can learn to clean a house or sort laundry, but our initial results indicate that these kinds of deep learning techniques can have a transformative effect in terms of enabling robots to learn complex tasks entirely from scratch.
From unmanned aerial systems to undersea communications, practical applications flow from the team headed by Mueller, an associate professor of mechanical engineering.
Learning how bats navigate through dense thickets without crashing into each other could also help unmanned aircraft designers create better delivery vehicles, Mueller says.
This eager device could be quickly released in large numbers over a disaster zone in order to bring back photos and establish contact with people in need.
What sets this device apart is the ability of the arms to unfold by themselves: the force generated by the rotors causes the arms to move into place.
NYT ] And while we’re on the subject, from Caltech: Neural prosthetic devices implanted in the brain's movement center, the motor cortex, can allow patients with amputations or paralysis to control the movement of a robotic limb—one that can be either connected to or separate from the patient's own limb.
However, current neuroprosthetics produce motion that is delayed and jerky—not the smooth and seemingly automatic gestures associated with natural movement.
Now, by implanting neuroprosthetics in a part of the brain that controls not the movement directly but rather our intent to move, Caltech researchers have developed a way to produce more natural and fluid motions.
Our future studies will investigate ways to combine the detailed motor cortex signals with more cognitive PPC signals to take advantage of each area's specializations.'
In the clinical trial, designed to test the safety and effectiveness of this new approach, the Caltech team collaborated with surgeons at Keck Medicine of USC and the rehabilitation team at Rancho Los Amigos National Rehabilitation Center.
The arrays were connected by a cable to a system of computers that processed the signals, decoded the intent of the subject, and controlled output devices that included a computer cursor and a robotic arm developed by collaborators at Johns Hopkins University.
During the Robotics Mining Competition, participating teams' custom-built, remote-controlled mining robots will traverse simulated Martian terrain features and excavate simulated regolith.
And anyway, I don’t think this is the sort of flight that anyone was dreaming of since the dawn of time, since no people are actuallyflying in this competition: it’s just the robots.
UMD Robotics ] “The founder of Sirius XM satellite radio, Martine Rothblatt now heads up a drug company that makes life-saving medicines for rare diseases (including one drug that saved her own daughter's life).
Brothers In Arms: These Robots Put A New Twist On 3D Printing
In October, engineers at Avio Aero, a GE Aviation company, used a futuristic process called cold spray to repair a gearbox on the GE90, the largest and most powerful jet in the world.
The bits land with such force that the solid-state particles start behaving like liquid, form a new layer and restore worn-out sections without changing the mechanical properties of the original.
GE recently introduced a beta version of the world’s largest 3D printer for metals, which can build parts as large as 1 meter along each of three axes.
That’s why the team reached out across the hall to Joe Vinciquerra, a GE scientist exploring ways to include artificial intelligence and machine learning into 3D printing and other manufacturing technologies.
By applying those changes in real time, the quality of every new painting increases.” Vinciquerra says that the robots should be able to improve as time goes on and limit mistakes by analyzing the set of instructions the robots followed each time they made a part.
One way in which we are building our additive toolbox is by looking at how each additive technique balances the others — an artist wouldn’t limit themselves to one color of paint and one size brush.”
Introducing Robotics: Build a Robot Arm
In this course, we demonstrate the build principles using the LEGO MINDSTORMS NXT kit.
While this kit is no longer produced, you can complete the project using a variety of technologies.
You might choose to purchase a robotics development kit or borrow hobby robot components.
With support from MathWorks, free access to MATLAB will be provided for the duration of the course plus 30 days.
How to Control a Robotic Arm with Your Mind, by Using Machine Learning
If you’ve lost the use of your arms, the idea of being able to control a robotic replacement arm with your mind might seem like an awesome idea at first.
Though previous experiments showed that brain-computer interfaces could allow people to control virtual objects like moving a cursor on a screen or a helicopter in a flight simulator, and even real objects like small quadcopters, this study takes it to the next level with real-world implications.
“This is the first time in the world that people can operate a robotic arm to reach and grasp objects in a complex 3D environment using only their thoughts without a brain implant,” said Bin He, a biomedical engineering professor at the University of Minnesota and lead author on the study, which was published earlier this month in Scientific Reports.
These overlapping layers of brain activity are mapped using functional magnetic resonance imaging (fMRI) and sorted and analyzed using advanced signal processing techniques, something He and his team explored in previous experiments which laid the foundation for this study.
Without the need for surgery, the risk of infection and complications, such non-invasive brain-computer interfaces may the future path toward easily manipulating not only prosthetic limbs but also assistive exoskeletons that would give more mobility to a rapidly aging population.
- On Wednesday, January 16, 2019
Google Develops Robot Arms that Learn to Pick Up Objects
Google recently created robots that use deep neural networks to learn how to pick up objects and move them.
How to Make a Robotic Arm at Home out of Cardboard
incredible idea Learn: How to Make Robotic Arm with 5 fingers.
How to Make Hydraulic Powered Robotic Arm from Cardboard
How to Make Hydraulic Powered Robotic Arm from Cardboard In this video I show you how to make robotic arm from cardboard, it's quite fun to plaw with. Especially by moving coca cola cans....
Google's DeepMind AI Just Taught Itself To Walk
Google's artificial intelligence company, DeepMind, has developed an AI that has managed to learn how to walk, run, jump, and climb without any prior guidance. The result is as impressive as...
A Robot Teaches Itself How to Walk
Cornell University professor Hod Lipson demonstrates how a robot can teach itself to walk without any knowledge of its form and function. "Within a relatively small number of these babbling...
Niryo One - Learning Mode : Teach the robot what to do with your hands !
Pre-order Niryo One now : Learning mode demonstration with Niryo One. You can easily program a sequence of positions just by moving the robot with your hand. You..
How to control someone else's arm with your brain | Greg Gage
Greg Gage is on a mission to make brain science accessible to all. In this fun, kind of creepy demo, the neuroscientist and TED Senior Fellow uses a simple, inexpensive DIY kit to take away...
Fast Robotic Assembly of CPU and Memory Modules on a Circuit Board
The KR 3 AGILUS is one of KUKA's newest robots. Fast, agile and flexible it can be used for a wide variety of tasks, including sensitive assembly in the electronics industry. In this example...
How to Make a Gesture Control Robot at Home
Learn- How to make an Arduino Based Gesture control robot. the accelerometer detects movement and wirelessly operate robot using the RF433 module. Required Material- You can buy components...
Trainable Robotic Arm 1
Inspired by the Baxter robot, this arm can be trained to move with your own hands. Once the train button is pressed, you move the arm and gripper as needed while the Arduino stores the positions...