Close

Video Friday: IROS 2013 Special Edition

Today we bring you videos directly from one of the world's largest robot conferences

4 min read
Video Friday: IROS 2013 Special Edition

Over the past two weeks, we brought you several stories from the IEEE International Conference on Intelligent Robots and Systems (IROS). And next week we should still have some more IROS posts. But today is Friday, and we know what you want: you want robot videos. So sit back and enjoy this IROS 2013 special edition of Video Friday.

Some people fear robots are going to take all our jobs. Add one more profession to the list: massage therapist. A team of Chinese researchers programmed a compliant robotic arm to give people back rubs. The 4-DOF manipulator uses series elastic actuators to operate safely, and according to the researchers, "experimental results show that the developed robotic arm can effectively imitate the TCM [Traditional Chinese Medicine] remedial massage techniques."

"Design and Control of Anthropomorphic BIT Soft Arms for TCM Remedial Massage," by Yuancan Huang, Jian Li, Qiang Huang, and Changxin Liu, from CNRS/LAAS, Beijing Institute of Technology, and Beijing University of Chinese Medicine. Presented at 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Tokyo, Japan.

 

 

Many intriguing places we want to explore on the surface of Mars won't be accessible using rovers. One possible solution, as described by researchers from JPL, is a rover tethered to a bigger rover (or stationary spacecraft), in what is known as a mother/daughter configuration. The mother provides mechanical support, power, and communication to the daughter via a umbilical cord. One challenge is retrieving the tethered daughter rover after its mission is over, but the JPL researchers came up with a method for autonomous re-docking even after an "an extreme terrain excursion."

"Autonomous Vision-based Tethered-Assisted Rover Docking," by Dorian Tsai, Issa A.D. Nesnas, and Dimitri Zarzhitsky, from Aalto University, Helsinki, Finland, and Jet Propulsion Laboratory, California Institute of Technology. Presented at 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Tokyo, Japan.

 

 

Steerable needles could be a big advance for drug delivery, biopsy procedures, and other medical applications. But even with these smart, robotic needles, multiple punctures might still be necessary when a surgeon needs to reach different targets inside a patient's body. If you don't like needles (who does?), here's some good news: researchers from the University of Texas at Dallas presented a method of minimizing the number of entry points by retracting the needle a bit, rotating it, and reinserting it to reach a different point. 

"Insertion planning for steerable flexible needles reaching multiple planar targets," by Jaeyeon Lee and Wooram Park, from the University of Texas at Dallas. Presented at 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Tokyo, Japan.

 

 

Robots that can learn, from very few demonstrations, how to perform complex tasks that we humans can easily execute remain one of the holy grails in robotics. Now Italian researchers working on this problem have found the perfect challenge to test their methods: rolling out pizza dough.

"On Improving the Extrapolation Capability of Task-Parameterized Movement Models," by Sylvain Calinon, Tohid Alizadeh, and Darwin G. Caldwell, from the Department of Advanced Robotics, Istituto Italiano di Tecnologia (IIT). Presented at 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Tokyo, Japan.

 

 

Most robots, when dropped to the floor, break. Not AirBurr. This flying robot was designed to crash on things and survive, and these slow motion videos show exactly how it does that trick.

"Euler Spring Collision Protection for Flying Robots," by Adam Klaptocz, Adrien Briod, Ludovic Daler, Jean-Christophe Zufferey and Dario Floreano, from senseFly and Swiss Federal Institute of Technology in Lausanne. Presented at 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Tokyo, Japan.

 

 

We've seen a proliferation of prosthetic hands in the past few years. But while most attempt to replicate the appearance of a human hand, this Japanese three-finger prosthesis goes in the opposite direction and looks like a futuristic robot hand straight out of a manga novel.

"Trans-Radial Prosthesis with Three Opposed Fingers," by Masahiro Yoshikawa, Yuya Taguchi, Shin Sakamoto, Shunji Yamanaka, Yoshio Matsumoto, Tsukasa Ogasawara, and Noritaka Kawashima, from Nara Institute of Science and Technology (NAIST), National Institute of Advanced Industrial Science and Technology (AIST), Keio University, University of Tokyo, and National Rehabilitation Center for the Persons with Disabilities (NRCD). Presented at 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Tokyo, Japan.

 

 

Remember the superfast book scanner created at the University of Tokyo? One limitation of that device was that the user had to manually flip through the pages. Looks like the Ishikawa Lab researchers are still working on that project, and now they came up with an automatic page turner machine that is perfect for their scanner.

"Automatic Page Turner Machine for High-speed Book Digitization," by Yoshihiro Watanabe, Miho Tamei, Masahiro Yamada and Masatoshi Ishikawa, from the Graduate School of Information Science and Technology, Univ. of Tokyo. Presented at 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Tokyo, Japan.

 

 

Boston Dynamics' LS3 quadruped is an incredibly agile robot in rough terrain. Its mechanical design plays a big role, but knowing where to put (or not to put) its feet is equally important. This video shows what LS3's stereo vision system sees and how its near-field terrain mapping works to detect different kinds of obstacles—and keep the robot on its feet.

"High Fidelity Day/Night Stereo Mapping with Vegetation and Negative Obstacle Detection for Vision-in-the-Loop Walking," by Max Bajracharya, Jeremy Ma, Matt Malchano, Alex Perkins, Alfred A. Rizzi, Larry Matthies, from Jet Propulsion Laboratory, California Institute of Technology and Boston Dynamics. Presented at 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Tokyo, Japan.

 

 

Kojiro, a musculoskeletal humanoid robot developed at University of Tokyo's JSK Lab, was succeeded by Kenshiro, and in the past few years its creators have taught the robot to perform a variety of moves, from playing drums to hula hooping. This time we see Kenshiro doing a "twist squat" using its human-inspired knee muscles and tendons. 

"Achievement of Twist Squat by Musculoskeletal Humanoid with Screw-Home Mechanism," by Yuki Asano, Hironori Mizoguchi, Toyotaka Kozuki, Yotaro Motegi, Junichi Urata, Yuto Nakanishi, Kei Okada and Masayuki Inaba, from the University of Tokyo. Presented at 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Tokyo, Japan.

 

 

Robots building robots are always a scary sight. But at least it looks like they're going to include e-stop buttons on themselves. Phew! Now we know how to stop the robopocalypse.

"Robotic Assembly of Emergency Stop Buttons," by Andreas Stolt, Magnus Linderoth, Anders Robertsson, Rolf Johansson, from Lund University, Sweden. Presented at 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Tokyo, Japan.

The Conversation (0)

How the U.S. Army Is Turning Robots Into Team Players

Engineers battle the limits of deep learning for battlefield bots

11 min read
Robot with threads near a fallen branch

RoMan, the Army Research Laboratory's robotic manipulator, considers the best way to grasp and move a tree branch at the Adelphi Laboratory Center, in Maryland.

Evan Ackerman
LightGreen

This article is part of our special report on AI, “The Great AI Reckoning.

"I should probably not be standing this close," I think to myself, as the robot slowly approaches a large tree branch on the floor in front of me. It's not the size of the branch that makes me nervous—it's that the robot is operating autonomously, and that while I know what it's supposed to do, I'm not entirely sure what it will do. If everything works the way the roboticists at the U.S. Army Research Laboratory (ARL) in Adelphi, Md., expect, the robot will identify the branch, grasp it, and drag it out of the way. These folks know what they're doing, but I've spent enough time around robots that I take a small step backwards anyway.

The robot, named RoMan, for Robotic Manipulator, is about the size of a large lawn mower, with a tracked base that helps it handle most kinds of terrain. At the front, it has a squat torso equipped with cameras and depth sensors, as well as a pair of arms that were harvested from a prototype disaster-response robot originally developed at NASA's Jet Propulsion Laboratory for a DARPA robotics competition. RoMan's job today is roadway clearing, a multistep task that ARL wants the robot to complete as autonomously as possible. Instead of instructing the robot to grasp specific objects in specific ways and move them to specific places, the operators tell RoMan to "go clear a path." It's then up to the robot to make all the decisions necessary to achieve that objective.

Keep Reading ↓ Show less