Video Friday is your weekly selection of awesome robotics videos, collected by your edgy Automaton bloggers. We’ll also be posting a weekly calendar of upcoming robotics events for the next two months; here’s what we have so far (send us your events!):
RoboBusiness Europe – June 1-3, 2016 – Odense, Denmark
Dynamic Walking 2016 – June 4-7, 2016 – Holland, Mich., USA
IEEE RAS MRSSS 2016 – June 6-10, 2016 – Singapore
CR-HRI – June 6-10, 2016 – Orlando, Fla., USA
NASA SRRC Level 1 – June 6-11, 2016 – Worcester, Mass., USA
Field Robot Event – June 14-18, 2016 – Haßfurt, Germany
EuroEAP 2016 – June 14-15, 2016 – Copenhagen, Denmark
RSS 2016 – June 18-22, 2016 – Ann Arbor, Mich., USA
European Land Robot Trial – June 20-24, 2016 – Eggendorf, Austria
Automatica 2016 – June 21-25, 2016 – Munich, Germany
ISR 2016 – June 21-22, 2016 – Munich, Germany
ICROM 2016 – June 23-25, 2016 – Singapore
The Rise of Machine Learning – June 24, 2016 – San Francisco, Calif., USA
UK Robotics Week – June 25-1, 2016 – United Kingdom
Hamlyn Symposium on Medical Robotics – June 25-28, 2016 – London, England
TAROS 2016 – June 28-30, 2016 – Sheffield, United Kingdom
RoboCup 2016 – June 30-4, 2016 – Leipzig, Germany
Amazon Picking Challenge – June 30-4, 2016 – Leipzig, Germany
IEEE AIM 2016 – July 12-15, 2016 – Banff, Canada
DLMC 2016 – July 13-15, 2016 – Zurich, Switzerland
ROS Industrial Workshop – July 14-15, 2016 – Singapore
MARSS 2016 – July 18-22, 2016 – Paris, France
Let us know if you have suggestions for next week, and enjoy today’s videos.
IHMC has managed to get their ATLAS balancing on the edge of cinder blocks, balancing itself with outstretched arms as it does so. Very humanlike:
The robot is able to detect and explore partial footholds (in this case line contacts). The walking algorithm autonomously adjusts to the foothold. To balance on the line contacts the robot uses its upper body momentum and will lunge to prevent falling. Footstep locations are specified by the operator. Swing time is approximately 0.8 seconds.
From the guys high-fiving behind those computers in the background there, I’m guessing that this was not the first attempt.
[ IHMC ]
Harnessing the collective intelligence of plant behaviour, the reEarth project explores new forms of bio-cooperative interaction between people and nature, within the built environment. While plants lack a nervous system, they can, much like animals, become electro-chemically stimulated by their surrounding environment. Through the study of plant electro-physiology, we have wired their primitive ‘intelligence’ into the control-loop of an autonomous robotic ecosystem. Half garden, half machine – a new cybernetic lifeform we’ve named Hortum machina, B.
Echoing the architecture of Buckminster Fuller, the geodesic sphere, is both exoskeleton and ecological iconography. Its core of twelve garden modules, each carrying native British species on outwardly-extending linear actuators allow the structure to become mobile by shifting its centre-of-gravity. Electro-physiological sensing of the state of individual plants collectively and democratically controls decision-making of the orientation of the structure and its mobility. In the near future context of driverless cars, autonomous flying vehicles, and seemingly endless other forms of intelligent robotics co-habiting our built environment. Hortum machina, B is a speculative urban cyber-gardener.
Plants aren’t well known for obeying traffic laws, unfortunately.
Thanks William Victor!
A few years ago, the FoldiMate laundry-folding robot ran a Kickstarter campaign where they ended up with $12k out of a $250k goal, with the robots selling for somewhere around $5k each. Now, FoldiMate is back with a new design and a promise to deliver by 2018 for under $850:
Note that (as PR2 discovered) the tricky part of laundry is really the sorting and unfolding, which FoldiMate doesn’t do. So the question is, by the time you’ve done all that and clipped each item individually into FoldiMate so that it can fold them for you, are you really saving that much time or effort?
Let’s use a big industrial robot arm to smash a bunch of TVs because why not! You won’t learn anything watching this video, but the noises are very satisfying:
[ The Geek Group ]
Before robots can move freely on sidewalks or other crowded spaces, they’ll need to understand the unwritten rules of pedestrian behavior. Jackrabbot is the prototype for a new generation of "social robot" designed to learn how to move among humans.
Presumably, Jackrabbot is allowed to run into people who are too busy looking at their phones to pay attention to where they’re going, because that’s what I do.
Android meets humanoid. At Google I/O last month, SoftBank engineers presented the new Android SDK that developers can use to create apps for Pepper, the Euro-trance dancing humanoid:
Android applications have been built that entertain us, connect us with one another, organize our lives, and much more. Pepper is a humanoid robot from SoftBank Robotics, and in this session, engineers from SoftBank Robotics will explore the capabilities, practicalities and opportunities of this exciting development landscape. Developers will gain insights into writing interactive applications for Pepper, from creating custom animations to specialized dialogue sequences. Attendees will even get to see Pepper in action.
[ Google I/O ]
XDog is a small and (relatively) low-cost quadruped robot that was developed by Wang Xingxing at Shanghai University:
[ YouTube ]
Thanks Wang Xingxing!
Why use your hands when you can use your mind? Arizona State University researchers recently demonstrated how to control a swarm of quadrotors using brain signals.
The quadrotors are controlled to pass through a narrow passage by adjusting their formation. The formation control, in this case swarm cohesion, is controlled in real-time using brain signals. Extracted control variable and brain activations are shown in the second part of the video on the left and right top corners respectively.
[ HORC ASU ]
This video is great because of everything that it teaches you about insect collision dynamics, but also because of all the slow-motion footage of bees running into stuff, which is unintentionally hilarious:
When your robot can handle rough terrain better than your students pushing its safety gantry:
[ MARLO ]
Quick! Hit it with a crowbar before it sees you!
[ YouTube ]
Erin Kennedy (of RoboBrrd fame) is Kickstarting a project to use DIY robots to assist in remote shoreline cleanup:
They’re not asking for much, and it’s a good cause.
[ Kickstarter ]
Watch this video and imagine the level of sophistication that it would require to do all of this stuff in real life with real robots:
The only thing that’s missing here is the clever dog, the evil penguin, and the cheese fixation.
The second annual Flying Robot International Film Festival is now accepting submissions!
[ FRIFF ]
Huh, I would not have thought that a ball-balancing robot would be any good outside at all, even a tripedal (trispheral?) one:
Our omni-directional robot Rocky driving over various outdoor terrains. Currently, Rocky is operating using completely open-loop control. Due to significant internal slip within the drive train, motor encoder readings are not an accurate indication of wheel position or ground position. Future research plans to use LIDAR to produce ground-truth position feedback.
[ UT Austin ]
Robots making Mardi Gras floats, and also cows.
[ Kern Studios ]
Less than 100 years from now, robots will be friendly, useful participants in our homes and workplaces, predicts UBC mechanical engineering professor and robotics expert Elizabeth Croft. We will be living in a world of Wall-Es and Rosies, walking-and-talking avatars, smart driverless cars and automated medical assistants.
[ UBC ]
This is basically just a well-produced advertisement for DJI, but since it’s got whales in it, we’ll let it slide.
Seriously, though, this is one of those niche applications that drones are uniquely very good at.
[ Snotbot ]
Sikorsky, a Lockheed Martin Company, has successfully demonstrated a 30-mile autonomous flight using a Sikorsky S-76® commercial helicopter to complete Phase 1 of an $8 million award from the Defense Advanced Research Projects Agency (DARPA)’s Aircrew Labor In-Cockpit Automation System (ALIAS) program.
I especially like how the interface looks almost exactly like a video game, complete with a ridiculous font.
[ Lockheed Martin ]
Why? I don’t know why. But here you go.
[ Ollie ]
Blake Kelly, VP of design at Jibo, attempts to convince you that social robots are an incredibly important thing:
Lots of promises, and we’re still hoping that they’ll be able to deliver.
[ Jibo Blog ]
And finally, a talk by Matt Travers from CMU on “Shape-Based Compliance in Locomotion”:
Natural systems move through unstructured, complex environments with an adaptability and robustness that motion-control scientists have yet to deeply understand, let alone reliably emulate. My work thus looks to biology, not to mimic or replay motions back on robotic devices, but to better understand the composition of successful motion-control strategies as they exist in the natural world. To this end, I will present recent work that uses modal decomposition techniques as well as tools from the field of geometric mechanics to better represent and ultimately interpret the motion of biological systems. I will discuss how traditionally kinematic techniques can be used to help define dynamic motion primitives that dramatically extend the capabilities of articulated robots operating in complex terrains. Specifically, I will present an approach for defining impedance-based primitives that enable different robotic platforms to blindly feel their way through unstructured two- and three-dimensional environments. Lastly, I will discuss future applications of my work in the areas of highly-adaptive soft and semi-soft robot locomotion and manipulation control.
Evan Ackerman is a senior editor at IEEE Spectrum. Since 2007, he has written over 6,000 articles on robotics and technology. He has a degree in Martian geology and is excellent at playing bagpipes.
Erico Guizzo is the digital product manager at IEEE Spectrum. An IEEE Member, he is an electrical engineer by training and has a master’s degree in science writing from MIT.