Speedy collision detector could make robots better human assistantsNovember 14, 2017
Electrical engineers at the University of California San Diego have developed a faster collision detection algorithm that uses machine learning to help robots avoid moving objects and weave through complex, rapidly changing environments in real time. The algorithm, dubbed "Fastron," runs up to 8 times faster than existing collision detection algorithms.
A team of engineers, led by Michael Yip, a professor of electrical and computer engineering and member of the Contextual Robotics Institute at UC San Diego, will present the new algorithm at the first annual Conference on Robot Learning Nov. 13 to 15 at Google headquarters in Mountain View, Calif. The conference brings the top machine learning scientists to an invitation-only event. Yip's team will deliver one of the long talks during the 3-day conference.
The team envisions that Fastron will be broadly useful for robots that operate in human environments where they must be able to work with moving objects and people fluidly. One application they are exploring in particular is robot-assisted surgeries using the da Vinci Surgical System, in which a robotic arm would autonomously perform assistive tasks (suction, irrigation or pulling tissue back) without getting in the way of the surgeon-controlled arms or the patient's organs.
"This algorithm could help a robot assistant cooperate in surgery in a safe way," Yip said.
The team also envisions that Fastron can be used for robots that work at home for assisted living applications, as well as for computer graphics for the gaming and movie industry, where collision checking is often a bottleneck for most algorithms.
A problem with existing collision detection algorithms is that they are very computation-heavy. They spend a lot of time specifying all the points in a given space--the specific 3D geometries of the robot and obstacles--and performing collision checks on every single point to determine whether two bodies are intersecting at any given time. The computation gets even more demanding when obstacles are moving.
To lighten the computational load, Yip and his team in the Advanced Robotics and Controls Lab (ARClab) at UC San Diego developed a minimalistic approach to collision detection. The result was Fastron, an algorithm that uses machine learning strategies--which are traditionally used to classify objects--to classify collisions versus non-collisions in dynamic environments. "We actually don't need to know all the specific geometries and points. All we need to know is whether the robot's current position is in collision or not," said Nikhil Das, an electrical engineering Ph.D. student in Yip's group and the study's first author.
The name Fastron comes from combining Fast and Perceptron, which is a machine learning technique for performing classification. An important feature of Fastron is that it updates its classification boundaries very quickly to accommodate for moving scenes, something that has been challenging for the machine learning community in general to do.
Fastron's active learning strategy works using a feedback loop. It starts out by creating a model of the robot's configuration space, or C-space, which is the space showing all possible positions the robot can attain. Fastron models the C-space using just a sparse set of points, consisting of a small number of so-called collision points and collision-free points. The algorithm then defines a classification boundary between the collision and collision-free points--this boundary is essentially a rough outline of where the abstract obstacles are in the C-space. As obstacles move, the classification boundary changes. Rather than performing collision checks on each point in the C-space, as is done with other algorithms, Fastron intelligently selects checks near the boundaries. Once it classifies the collisions and non-collisions, the algorithm updates its classifier and then continues the cycle.
Because Fastron's models are more simplistic, the researchers set its collision checks to be more conservative. Since just a few points represent the entire space, Das explained, it's not always certain what's happening in the space between two points, so the team developed the algorithm to predict a collision in that space. "We leaned toward making a risk-averse model and essentially padded the workspace obstacles," Das said. This ensures that the robot can be tuned to be more conservative in sensitive environments like surgery, or for robots that work at home for assisted living.
The team has so far demonstrated the algorithm in computer simulations on robots and obstacles in simulation. Moving forward, the team is working to further improve the speed and accuracy of Fastron. Their goal is to implement Fastron in a robotic surgery and a homecare robot setting.
University of California - San Diego
Related Robots Articles:
Eight years ago, Ted Adelson's research group at MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) unveiled a new sensor technology, called GelSight, that uses physical contact with an object to provide a remarkably detailed 3-D map of its surface.
A University at Buffalo research team has published a paper that implies that the rush to ban and demonize autonomous weapons or 'killer robots' may be a temporary solution, but the actual problem is that society is entering into a situation where systems like these have and will become possible.
An EPFL team is developing soft, flexible and reconfigurable robots.
When you have too many robots together, they get so focused on not colliding with each other that they eventually just stop moving.
The startup LuxAI was created following a research project at the Interdisciplinary Centre for Security, Reliability and Trust (SnT) of the University of Luxembourg.
Scientists at Hokkaido University have developed light-powered molecular motors that repetitively bend and unbend, bringing us closer to molecular robots.
A soft actuator using electrically controllable membranes could pave the way for machines that are no danger to humans.
Clutter is a special challenge for robots, but new Carnegie Mellon University software is helping robots cope, whether they're beating a path across the moon or grabbing a milk jug from the back of the refrigerator.
Toyohashi Tech researchers in cooperation with researchers at Kyoto University have presented the first neurophysiological evidence of humans' ability to empathize with a robot in perceived pain.
Engineers at MIT have now hit upon a way to impart more dexterity to simple robotic grippers: using the environment as a helping hand.
Related Robots Reading:
The Wild Robot Escapes
by Peter Brown (Author)
An instant New York Times bestseller!
The sequel to the bestselling The Wild Robot, by award-winning author Peter Brown
Shipwrecked on a remote, wild island, Robot Roz learned from the unwelcoming animal inhabitants and adapted to her surroundings--but can she survive the challenges of the civilized world and find her way home to Brightbill and the island?
From bestselling and award-winning author and illustrator Peter Brown comes a heartwarming and action-packed sequel to his New York Times bestselling The Wild Robot,... View Details
National Geographic Readers: Robots
by Melissa Stewart (Author)
Discover the coolest robots of today and tomorrow in this colorful, photo-packed book. In this inviting and entertaining format, kids will learn about the science behind these amazing machines. This Level 3 reader is written in an easy-to-grasp style to encourage the scientists of tomorrow! National Geographic supports K-12 educators with ELA Common Core Resources.
Visit www.natgeoed.org/commoncore for more information. View Details
The Wild Robot
by Peter Brown (Author)
Wall-E meets Hatchet in this New York Times bestselling illustrated middle grade novel from Caldecott Honor winner Peter Brown
Can a robot survive in the wilderness?
When robot Roz opens her eyes for the first time, she discovers that she is alone on a remote, wild island. She has no idea how she got there or what her purpose is--but she knows she needs to survive. After battling a fierce storm and escaping a vicious bear attack, she realizes that her only hope for survival is to adapt to her surroundings and learn from the island's... View Details
Robots, Robots Everywhere! (Little Golden Book)
by Sue Fliess (Author), Bob Staake (Illustrator)
The bestselling Little Golden Book all about robots!
Robots are everywhere in this bright and funny board book – and preschoolers are going to love it! Whether up in space, beneath the seas, or even under couches, award-winning illustrator Bob Staake’s bold and colorful bots make this book a must have.
For more Bob Staake books, be sure to read:
I’m a Bulldozer
I’m a Truck
I’m a Monster Truck
Beachy and Me
My Pet Book View Details
Rise of the Robots: Technology and the Threat of a Jobless Future
by Martin Ford (Author)
The New York Times-bestselling guide to how automation is changing the economy, undermining work, and reshaping our lives
"Lucid, comprehensive, and unafraid...;an indispensable contribution to a long-running argument."--Los Angeles Times
Winner of the 2015 FT & McKinsey Business Book of the Year Award
Top Business Book of 2015 at Forbes
One of NBCNews.com 12 Notable Science and Technology Books of 2015
What are the jobs of the future? How many will there be? And who will have them? As technology continues to accelerate and machines begin taking care... View Details
Your Robot Dog Will Die
by Arin Greenwood (Author)
Fusing the heart of Julie of the Wolves with the imagination of Little Brother and Ship Breaker, this speculative YA is a must-read for any dog lover.
Seventeen-year-old Nano Miller was born and raised on Dog Island: home to Mechanical Tail, the company behind lifelike replacements for “man’s best friend.” The island is also home to the last living dogs, all but extinct. When a global genetic experiment went awry and canines stopped wagging their tails, mass hysteria ensued and the species was systematically euthanized. Here, they are studied in a... View Details
Robots (Scholastic Reader, Level 2)
by Gail Tuchman (Author)
The world is being taken over by robots! There are robots that build towers, make cars, flip pancakes and play football. There are robots that travel deep under water, far into space, and into the most extreme danger zones. Some walk like a human, others fly like a bee, or swim like a turtle, or run like a dog. In this Level 2 reader, young readers will discover different kinds of robots: how they work, the jobs they do, and what exciting things they might do in the future. The book uses simple text and full-color photographs throughout.
With compelling themes, supporting facts,... View Details
Robots (The MIT Press Essential Knowledge series)
by John M. Jordan (Author)
An accessible and engaging account of robots, covering the current state of the field, the fantasies of popular culture, and implications for life and work.
Robots are entering the mainstream. Technologies have advanced to the point of mass commercialization―Roomba, for example―and adoption by governments―most notably, their use of drones. Meanwhile, these devices are being received by a public whose main sources of information about robots are the fantasies of popular culture. We know a lot about C-3PO and Robocop but not much about Atlas, Motoman, Kiva, or... View Details
Carson Dellosa Robots Prize Pack Stickers (168063)
by Carson-Dellosa Publishing (Compiler)
Perfect for reward or recognition, each prize pack of these acid-free and lignin-free stickers includes 24 sheets of 9 stickers each for a total of 216 stickers! Each sticker measures approx. View Details