Nav: Home

Speedy collision detector could make robots better human assistants

November 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.
-end-
Paper title: "Fastron: An Online Learning-Based Model and Active Learning Strategy for Proxy Collision Detection." Authors of the study are Nikhil Das, Naman Gupta and Michael Yip in the Advanced Robotics and Controls Lab (ARClab) at UC San Diego.

University of California - San Diego

Related Robots Articles:

Tactile sensor gives robots new capabilities
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.
Researchers question if banning of 'killer robots' actually will stop robots from killing
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.
Soft robots that mimic human muscles
An EPFL team is developing soft, flexible and reconfigurable robots.
Team of robots learns to work together, without colliding
When you have too many robots together, they get so focused on not colliding with each other that they eventually just stop moving.
Social robots -- programmable by everyone
The startup LuxAI was created following a research project at the Interdisciplinary Centre for Security, Reliability and Trust (SnT) of the University of Luxembourg.
On the path toward molecular robots
Scientists at Hokkaido University have developed light-powered molecular motors that repetitively bend and unbend, bringing us closer to molecular robots.
Gentle strength for robots
A soft actuator using electrically controllable membranes could pave the way for machines that are no danger to humans.
Robots get creative to cut through clutter
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.
Humans can empathize with robots
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.
Giving robots a more nimble grasp
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:

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


House of Robots
by James Patterson (Author), Chris Grabenstein (Author), Juliana Neufeld (Illustrator)

The story of an extraordinary robot that signs up for an ordinary fifth grade class and changes elementary school forever is now in paperback!
It's never easy for Sammy Hayes-Rodriguez to fit in, so he's dreading the day when his genius mom insists he bring her newest invention to school: a robot he calls E--for "Error". E not only thinks he's Sammy's brother... he's actually even nerdier than Sammy. Will E be Sammy's one-way ticket to Loserville? Or will he prove to the world that it's cool to be square? 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


The Wild Robot
by Peter Brown (Author)

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 unwelcoming animal inhabitants.
As Roz slowly befriends the animals, the island starts to feel like home--until, one day, the robot's mysterious past comes back to... View Details


Robot-Proof: Higher Education in the Age of Artificial Intelligence (MIT Press)
by Joseph E. Aoun (Author)

How to educate the next generation of college students to invent, to create, and to discover -- filling needs that even the most sophisticated robot cannot.

Driverless cars are hitting the road, powered by artificial intelligence. Robots can climb stairs, open doors, win Jeopardy, analyze stocks, work in factories, find parking spaces, advise oncologists. In the past, automation was considered a threat to low-skilled labor. Now, many high-skilled functions, including interpreting medical images, doing legal research, and analyzing data, are within the skill sets of... View Details


Rise of the Robots: Technology and the Threat of a Jobless Future
by Martin Ford (Author)

Winner of the 2015 FT & McKinsey Business Book of the Year Award
A New York Times Bestseller

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 of themselves, fewer people will be necessary. Artificial intelligence is already well on its way to making "good jobs" obsolete: many paralegals, journalists, office workers, and even computer... 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


DK Eyewitness Books: Robot
by Roger Bridgman (Author)

Take a detailed look at the fascinating world of robots - from the earliest single-task machines to the advanced intelligence of robots with feelings. Young readers will be amazed to learn all that robots can do: perform delicate surgical operations, clean city sewers, work as museum tour guides, or even battle each other in combat. Find out how humans have created these mechanical minds and bodies. View Details


I, Robot
by Isaac Asimov (Author)

The three laws of Robotics:
1) A robot may not injure a human being or, through inaction, allow a human being to come to harm
2) A robot must obey orders givein to it by human beings except where such orders would conflict with the First Law.
3) A robot must protect its own existence as long as such protection does not conflict with the First or Second Law.

With these three, simple directives, Isaac Asimov changed our perception of robots forever when he formulated the laws governing their behavior. In I, Robot, Asimov chronicles the development of the robot through a... View Details


The Robots of Dawn (The Robot Series)
by Isaac Asimov (Author)

A millennium into the future two advances have altered the course of human history: the colonization of the Galaxy and the creation of the positronic brain. Isaac Asimov's Robot novels chronicle the unlikely partnership between a New York City detective and a humanoid robot who must learn to work together.

Detective Elijah Baiey is called to the Spacer world Aurora to solve a bizarre case of roboticide. The prime suspect is a gifted roboticist who had the means, the motive, and the opportunity to commit the crime. There's only one catch: Baley and his positronic partner, R. Daneel... View Details

Best Science Podcasts 2017

We have hand picked the best science podcasts for 2017. Sit back and enjoy new science podcasts updated daily from your favorite science news services and scientists.
Now Playing: TED Radio Hour

Simple Solutions
Sometimes, the best solutions to complex problems are simple. But simple doesn't always mean easy. This hour, TED speakers describe the innovation and hard work that goes into achieving simplicity. Guests include designer Mileha Soneji, chef Sam Kass, sleep researcher Wendy Troxel, public health advocate Myriam Sidibe, and engineer Amos Winter.
Now Playing: Science for the People

#448 Pavlov (Rebroadcast)
This week, we're learning about the life and work of a groundbreaking physiologist whose work on learning and instinct is familiar worldwide, and almost universally misunderstood. We'll spend the hour with Daniel Todes, Ph.D, Professor of History of Medicine at The Johns Hopkins University, discussing his book "Ivan Pavlov: A Russian Life in Science."