Video Friday: More Boston Dynamics, Giant Fighting Robots, and ANYmal Quadruped

Your weekly selection of awesome robot videos

5 min read

Evan Ackerman is IEEE Spectrum’s robotics editor.

Erico Guizzo is IEEE Spectrum's Digital Innovation Director.

ANYmal quadruped robot from ANYbotics
ANYmal quadruped robot from ANYbotics.
Photo: ANYbotics

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 two months; here’s what we have so far (send us your events!):

IEEE CASE 2017 – August 20-23, 2017 – Xi’an, China
IEEE ICARM 2017 – August 27-31, 2017 – Hefei, China
IEEE RO-MAN – August 28-31, 2017 – Lisbon, Portugal
CLAWAR 2017 – September 11-13, 2017 – Porto, Portugal
FSR 2017 – September 12-15, 2017 – Zurich, Switzerland
Singularities of Mechanisms and Robotic Manipulators – September 18-22, 2017 – Johannes Kepler University, Linz, Austria
ROSCon – September 21-22, 2017 – Vancouver, B.C., Canada
IEEE IROS – September 24-28, 2017 – Vancouver, B.C., Canada
RoboBusiness – September 27-28, 2017 – Santa Clara, Calif., USA
Drone World Expo – October 2-4, 2017 – San Jose, Calif., USA

Let us know if you have suggestions for next week, and enjoy today’s videos.

It’s not always clear whether Boston Dynamics’ robots are operating autonomously or being controlled by a human, but it’s definitely clear in this video of a presentation and demo by Marc Raibert: At the end, the human driving Atlas accidentally walks the robot off the stage. Like, literally off the stage. Oops.

Props to Marc for making it funny at the end there, heh.

[ Boston Dynamics ]

From Yoichi Masuda at Osaka University:

We developed a mobile robot that rolls by active deformation of the soft outer shell. The robot have a wire drive module and soft outer shell that are joined only by pre-stressed wires. The soft shell and wire drive help realize a tough, low-cost, and lightweight design.

AIM 2017 ]

This is Eagle Prime, America's entrant into the Giant Robot Duel, in its first-ever live-fire combat trial. Eagle Prime is the first MK3-class MegaBot from MegaBots, Inc. It weighs in at 12 tons, stands 16 feet tall, seats two, is powered by a 430 horsepower V8 LS3 engine, and costs a cool $2.5M. Cupholders come standard. Eagle Prime will be representing Team USA in the upcoming Giant Robot Duel against Suidobashi Heavy Industries. Subscribe to this channel to watch the Duel!

[ MegaBots ]

We’re starting to see videos trickle out from RoboCup 2017; here’s the teen/adult size final featuring Nimbro:

In the final game of the AdultSize soccer tournament our NimbRo-OP2 robot met Sweaty (Hochschule Offenburg, Germany). Both players were capable. They walked quickly, saw the ball reliably and kicked strongly. NimbRo had advantages in fights for the ball and maintained a very stable balance. It scored one goal after the other. After 7:0 at half time, the game ended early with a score of 11:1 for NimbRo.

[ Nimbro ]

Péter Fankhauser and his colleagues from ANYbotics recently took their quadruped robot ANYmal for a series of live demos at the World Petroleum Congress in Turkey. “ANYmal climbed over and underneath obstacles and over stairs, and performed automated visual inspection of industrial equipment,” Fankhauser tells us. “The entire demonstration ran fully autonomously about 10 times a day for a full week.”

[ ANYbotics ]

Thanks Péter!

We present a computational tool for designing compliant mechanisms. Our method takes as input a conventional, rigidly-articulated mechanism defining the topology of the compliant design. This input can be both planar or spatial, and we support a number of common joint types which, whenever possible, are automatically replaced with parameterized flexures. As the technical core of our approach, we describe a number of objectives that shape the design space in a meaningful way, including trajectory matching, collision avoidance, lateral stability, resilience to failure, and minimizing motor torque. Optimal designs in this space are obtained as solutions to an equilibrium-constrained minimization problem that we solve using a variant of sensitivity analysis. We demonstrate our method on a set of examples that range from simple four-bar linkages to full-fledged animatronics, and verify the feasibility of our designs by manufacturing physical prototypes.

[ Disney Research ]

Go on, guess what happens when a terrifying battlebot goes up against a Neato XV-11 robot vacuum:

Of course, if you’ve ever watched RoboGames, you’ll immediately recognize the XV-11’s nearly unbeatable strategy of not doing anything while simultaneously not exploding for no reason. Also, the battlebot is mostly plastic, although that doesn’t make it any less terrifying:

[ Fetch Robotics Weaponized Plastic Fighting League ] via [ Griswald Brooks ]

Relay is best known for its charming hotel deliveries, but it can work in factories, too.

Savioke ]

Rethink has as much experience as anyone trying to deal with the robots stealing jobs hype. Rethink’s CPMO Jim Lawton explains why you probably don’t have to worry.

[ Rethink ]

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.

[ arXiv ]

Social robotics researchers at Halmstad University in Sweden are using a Baxter on Ridgeback robot to explore how robots can help people in everyday life.

[ Clearpath ]

Sarah Petkus is a roboticist and artist who is currently in the middle of a three week residency at the European Space Agency. Her robot, NoodleFeet (which has noodle feet) got to play with a little mini ExoMars rover in the ESA’s Mars sandbox.

[ NoodlFeet ] via [ ESA ]

The Duke University Marine Lab is the first to win Federal Aviation Administration certification to operate scientific drones and provide training. Their biggest drone is an amphibious plane with a 9-foot wingspan that can fly for 90 minutes at a time. Like several of their other drones, this one can fly itself back and forth within a predefined area, like “mowing the lawn” for data. David Johnston, assistant professor of the practice of marine conservation ecology at Duke University, has found that drone technology allows his research team to collect huge volumes of data from remote or extreme locations. He believes this is transforming how people study and learn about marine ecosystems.

[ NSF ]

The only thing I get from auto translated captions on this video is “why regret and gas,” which pretty much sums it up:

[ Vstone ]

Kate Darling gives a brief talk on why public perception of AI is so important, and why you should really stop comparing AI to, uh, babies:

[ AI Now ]

At a time when collaborative robot applications are being introduced at a rapid pace, we need efficient ways to develop their interfaces with people. Used strategically, expressive motion has the power to increase robot acceptance, improve human-robot coordination, and perhaps even make robotic systems more enjoyable. By adapting strategies from theatre, Heather Knight’s research improves the ability of non-anthropomorphic robots to effectively layer nonverbal behaviours on their task actions, and interact with us successfully & charismatically.

[ Thinking Digital ]

Curiosity has been exploring Mars for five years, and here’s what it’s seen:

Wow, I remember seeing that very first hazcam image from the media center at JPL, when the protective dust cover was still covering the camera and nobody had any idea what we were looking at (and then posting about it like 30 seconds later). For lots more, here’s a long lecture from JPL about Curiosity’s first five years on Mars.

[ MSL ]

The Conversation (0)