Robotic Grip Improved

Grip is a big thing in robotics.  This will be a big deal for classic smart home applications for eldercare.  And in factory manufacturing applications.

Giving robots a faster grasp
An algorithm speeds up the planning process robots use to adjust their grip on objects, for picking and sorting, or tool use.

Jennifer Chu | MIT News Office

If you’re at a desk with a pen or pencil handy, try this move: Grab the pen by one end with your thumb and index finger, and push the other end against the desk. Slide your fingers down the pen, then flip it upside down, without letting it drop. Not too hard, right?

But for a robot — say, one that’s sorting through a bin of objects and attempting to get a good grasp on one of them — this is a computationally taxing maneuver. Before even attempting the move it must calculate a litany of properties and probabilities, such as the friction and geometry of the table, the pen, and its two fingers, and how various combinations of these properties interact mechanically, based on fundamental laws of physics.

Now MIT engineers have found a way to significantly speed up the planning process required for a robot to adjust its grasp on an object by pushing that object against a stationary surface. Whereas traditional algorithms would require tens of minutes for planning out a sequence of motions, the new team’s approach shaves this preplanning process down to less than a second.

Alberto Rodriguez, associate professor of mechanical engineering at MIT, says the speedier planning process will enable robots, particularly in industrial settings, to quickly figure out how to push against, slide along, or otherwise use features in their environments to reposition objects in their grasp. Such nimble manipulation is useful for any tasks that involve picking and sorting, and even intricate tool use.

“This is a way to extend the dexterity of even simple robotic grippers, because at the end of the day, the environment is something every robot has around it,” Rodriguez says.

The team’s results are published today in The International Journal of Robotics Research. Rodriguez’ co-authors are lead author Nikhil Chavan-Dafle, a graduate student in mechanical engineering, and Rachel Holladay, a graduate student in electrical engineering and computer science.

Modular Re-Forming Robotics

Interesting because this allows autonomous interaction with its environment by re-forming to meet physical requirements.  Instructive video.

Modular Robot Builds Structures to Complete Tasks  via IdeaConnection

An autonomous robotic system from Cornell and the University of Pennsylvania can reform itself and build structures to allow it to complete tasks.
Penn GRASP Lab, Cornell and Harvard  ... 

Saving Lives with Swarms of Drones

Self assembling and autonomous drones for safety and rescue platforms.

Saving Lives with Aerial Drones in CACM

Researchers at the University of Pennsylvania General Robotics, Automation, Sensing & Perception Laboratory have created a system of aerial drones that can connect to form rigid structures for emergency rescues. .... " 

Drone Swarms Flying without GPS

Brought up in a recent challenge for Drone Swarms and Drones indoors.

This Autonomous Quadrotor Swarm Doesn't Need GPS    By Evan Ackerman in IEEE Spectrum

UPenn's autonomous quadrotor swarm doesn't need GPS or external localization to fly indoors or outdoors. .... "

Deep Learning Solving the Complex Subtasks

Good example of how, by breaking up complex sub tasks, you can perform difficult goals.  We, as humans, don't have to 'solve' the problem of sight every time we want to see, and thus can get to more difficult goals.  Also naturally linking to the swarm solution idea.

2016: The Year that Deep Learning Took over the Internet     by Cade Metz, In Wired: 

" .... On the West coast of Australia, Amanda Hodgson is launching drones out towards the Indian Ocean so that they can photograph the water from above. The photos are a way of locating dugongs, or sea cows, in the bay near Perth—part of an effort to prevent the extinction of these endangered marine mammals. The trouble is that Hodgson and her team don’t have the time needed to examine all those aerial photos. There are too many of them—about 45,000—and spotting the dugongs is far too difficult for the untrained eye. So she’s giving the job to a deep neural network.

On the West coast of Australia, Amanda Hodgson is launching drones out towards the Indian Ocean so that they can photograph the water from above. The photos are a way of locating dugongs, or sea cows, in the bay near Perth—part of an effort to prevent the extinction of these endangered marine mammals. The trouble is that Hodgson and her team don’t have the time needed to examine all those aerial photos. There are too many of them—about 45,000—and spotting the dugongs is far too difficult for the untrained eye. So she’s giving the job to a deep neural network.  ....  " 

UPenn's Lab Flies Drones Through Windows

In IEEE Spectrum,  some remarkable things that drones can now be programmed to do, like fly through half open windows.   Out of UPenn's labs.   Demonstrated in video at the link.  Gives me considerable pause about what our drone and robotic enabled future will look like.  For now,  keep your windows completely closed.

See also Vijay Kumar Lab, Penn Engineering

Cognitive Operational Systems, LLC

Brought to my attention for retail inventory applications. 

" ... Cognitive Operational Systems, LLC (COSY) is a spinout of UPenn's GRASP Laboratory. The company focuses on leveraging University research for enabling industry solutions in computer vision, perception, and artificial intelligence. COSY became one of the early occupants of Pennovation Works in the summer of 2015.

COSY technology enables robots to navigate retail store floors, managing inventory, ensuring planogram and promotional compliance.  COSY will also map stores including layout and architecture. And that's only the beginning...

COSY’s “beacon-free” technology provides indoor localization and turn-by-turn navigation in environments with no GPS — like indoors. This back-end technology can be used to enable augmented reality interfaces, audio-based navigation aids for the blind, and even mobile drones. ... " 

Also, their blog.

Multimodal Robotic Drones

From the University of PA Grasp lab, in IEEE Spectrum.    Bimodal, here meaning it can walk or fly.   Applications that make sense?     Bi specialization for specific environments or needs.

" ... Some of the most versatile and adaptable robots also exhibit multimodal characteristics: they can fly and climb, or jump and glide, or even fly and swim. But flying and walking seems to be by far the most useful combination, as evidenced by the variety of animals that can do it, and researchers at the University of Pennsylvania’s GRASP Laboratory have designed a new robot called Picobug that can fly, walk, and even (soon) grab on to stuff. ... " 

Haptography: Digitizing Touch

Haptography: Digitizing our sense of touch - by Katherine Kuchenbecker of UPenn GRASP:

Overview of research topic.
Is it possible to incorporate the sense of touch into the digital world? Katherine Kuchenbecker thinks so. At TEDYouth 2012, Katherine shares her work in the field of haptics, while discussing its potential to change fields such as gaming, museums, dentistry and stroke rehabilitation. ...  "

Robots, Sensors and Math at Penn

Good, thoughtful but non technical article,
 I have posted about the GRASP Laboratory here before.  In the Alumni magazine.

" ... Last March seven researchers from the University of Pennsylvania landed in Dayton, Ohio for two days of meetings at the Air Force Research Laboratory. The lab, housed on Wright-Patterson Air Force Base, has been home over the years to breakthroughs in everything from lasers to propulsion technology, and the agenda for these meetings was no less forward-looking: to consider ways of engineering fully autonomous flying robots able to work together to search buildings, track targets, and gather information about areas that are too dangerous for US soldiers to enter.

Among the representatives from Penn was Andrea Mitchell University Professor Robert Ghrist, a Penn Integrates Knowledge (PIK) professor with appointments in the departments of mathematics and electrical/systems engineering. Not long ago, the presence of an applied mathematician like Ghrist at this kind of meeting would have been surprising. His specialty is algebraic topology, an abstract branch of mathematics that studies the properties of different kinds of spaces and has existed as a purely academic pursuit for most of its history.

Yet over the last decade, Ghrist has found a number of innovative ways to use algebraic topology to solve real-world problems in robotics and sensor networks. These discoveries have helped make him one of the best-funded mathematicians in the world. Over the last decade he’s been a principal investigator on more than $20 million in grants from military organizations including the Defense Advanced Research Projects Agency, the Department of Defense, and the Office of Naval Research. 
 ... " 
" ... Since coming to Penn, Ghrist has spent a lot of time collaborating with engineers in the General Robotics, Automation, Sensing & Perception, or GRASP, Laboratory. Much of his work there has focused on technology for autonomous vehicles, which, rather than taking commands from a remote human operator, as many drones do, are able navigate an environment completely on their own. This ability is especially useful in places where good maps are lacking and GPS signals are unreliable, like the interior of a building or beneath the ocean.  .... " 

Grasp Robotics Laboratory at Penn

Brought to my attention, new things ongoing at the GRASP Lab at the University of Pennsylvania. Robot swarms that fly and cooperate.  See an exciting video on their quadrotor swarms.   I had previously mentioned here our own look at swarming robotics, but we did not foresee the flying angle. Also follow on Twitter.

" ... The General Robotics, Automation, Sensing and Perception (GRASP) Laboratory integrates computer science, electrical engineering and mechanical engineering in a vibrant, collaborative environment that fosters interactions between students, research staff and faculty. GRASP has grown into a $10 million research center with impressive technological innovations. Pioneering GRASP researchers are building autonomous vehicles and robots, developing self-configuring humanoids, and making robot swarms a reality. Our doctoral students are trained in theory and practice and mentored to become leaders in research and education. The graduates of the interdisciplinary Master's in Robotics program are uniquely equipped to face research and development challenges of the fast-growing robotics industry.We invite you to visit the GRASP lab to experience  the future of robotics research and education. ... " 

Grasp Lab at Penn

I don't remember Penn being particularly well known for robotics work. Yet their Grasp lab (general robotics, automation, sensing and perception) around since 1979, has been in the news lately for putting flying drones through hoops. Cool video. Now I know and will follow.