Video Friday is your weekly selection of awesome robotics videos, collected by your Automaton bloggers. We’ll also be posting a weekly calendar of upcoming robotics events for the next few months; here's what we have so far (send us your events!):
IEEE IRC 2018 – January 31-2, 2018 – Laguna Hills, Calif.
HRI 2018 – March 5-8, 2018 – Chicago, Ill.
Let us know if you have suggestions for next week, and enjoy today's videos.
Since Christmas hasn't gotten its act together and has poor coordination with Video Friday, there are some last-minute robot Chrismas videos that didn't make it in last week. The first comes from EPFL's Reconfigurable Robotics Lab:
[ RRL ]
Two 6-DOF spacecraft simulators dance to holiday music at Caltech's Aerospace Robotics and Control Lab.
[ CAST ]
Sawyer is putting a gift into a bag into a box, just for you:
I'm not sure Sawyer is allowed that stocking if it doesn't have any legs.
[ Rethink Robotics ]
Velodyne and their VLP-32C wish you a Happy Holidays that's a solid two minutes longer than it needs to be:
[ Velodyne ]
Crescent Industries, in New Freedom, PA, decked out its Baxters (and a musically inclined Sawyer) to wish a merry Christmas to anyone who happened to drive past:
If you have a lot of presents and the corporate support of Anki, you too can make a ludicrous toy car track:
[ Anki ]
Team BlackSheep brings you along on a snowy winter drone sleigh ride.
[ Team BlackSheep ]
I did not know this, but apparently ANYmals are fiercely territorial:
[ IRIS ]
Robot successfully not running into things:
For robotic vehicles to navigate safely and efficiently in pedestrian-rich environments, it is important to model subtle human behaviors and navigation rules. However, while instinctive to humans, socially compliant navigation is still difficult to quantify due to the stochasticity in people's behaviors. Existing works are mostly focused on using feature-matching techniques to describe and imitate human paths, but often do not generalize well since the feature values can vary from person to person, and even run to run. This work notes that while it is challenging to directly specify the details of what to do (precise mechanisms of human navigation), it is straightforward to specify what not to do (violations of social norms). Specifically, using deep reinforcement learning, this work develops a time-efficient navigation policy that respects common social norms. The proposed method is shown to enable fully autonomous navigation of a robotic vehicle moving at human walking speed in an environment with many pedestrians.
[ MIT ACL ]
I appreciate how polite this PR2 is as it learns new generalized tasks through natural language instruction:
[ HRI Laboratory ]
The Robotics And Rehabilitation (RoAR) Lab develops innovative robots and methods to help humans relearn, restore, or improve functional movements. The lab is housed both in Engineering and Medical campuses of Columbia University. Led by Dr. Sunil Agrawal, the lab works actively with clinical faculty from Columbia University Medical Center and hospitals around New York City.
[ Roar Lab ]
Donny the Drone (voiced by Guy Pearce) has just been named the “Person of the Year” by World Times magazine. Donny takes the stage to dramatically tell his story of how he came to have real human emotions. His anecdotes are portrayed with highlights from his world-spanning adventures that have shaped who he has become. As the ceremony goes on, Donny’s vision becomes grander, more ambitious and potentially concerning. Will Donny be able to freely pursue his dream of helping all over the world—or will mankind’s darker, paranoid instincts intervene before Donny achieves ultimate, worldwide control.
Ken Goldberg speaks at TEDxOakland. I can't really tell you what the talk is about, specifically, but it's a good one, and well worth 10 minutes of your time.
[ TEDxOakland ]
In this week's episode of Robots in Depth, Per speaks with Daniel Lofaro from George Mason University.
Daniel Lofaro talks about how he works very hard to make things easier and how co-robotics, where humans and robots collaborate is the way forward. Bringing cost down cost and better AI is critical for this. He talks about how robotics needs a “killer app”, something that makes it compelling enough for the customer to take the step of welcoming a robot into the business or home. Daniel also discusses creating an ecosystem of robots and apps, and how competitions can help do this.
[ Robots in Depth ]
In October, IEEE hosted a TechEthics conference in Washington DC. Here are videos of two of the speakers: Rodney Brooks, and Heather Knight.
[ IEEE TechEthics ]
Heather Knight also organizes the annual Robot Film Festival, and at the IEEE TechEthics Conference, she brought along a selection of films to share. Here are three of our favorites.
[ Robot Film Fest ]
A lecture from the ITEC Summer School 2017 on Cognitive Architectures by Tamim Asfour: Engineering Humanoid Robots that Learn from Humans and Sensorimotor Experience.
Humanoid robotics has made significant progress and will continue to play central role in robotics research and many applications of the 21st century. Engineering complete humanoid robots, which are able to learn from human observation and sensorimotor experience, to predict the consequences of actions and exploit the interaction with the world to extend their cognitive horizon remains a research grand challenge. In this talk, I will present recent results and discuss future directions of research, which combine robotics, machine learning and computer vision to speed-up learning and facilitate intuitive programming of complex robotics tasks.