Video Friday: Giant Robot Bug, SpaceX Rocket Landing, and Flamethrower Drone

Your weekly selection of awesome robot videos

Image: Suzumori Endo Lab/Tokyo Tech via YouTube

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!):

Robotics Alley – February 28- March 1, 2017 – Minneapolis, Minn., USA
HRI 2017 – March 6-9, 2017 – Vienna, Austria
IEEE ARSO – March 8-10, 2017 – Austin, Texas, USA
IEEE SSRR – March 10-13, 2017 – Shanghai, China
NYC Drone Film Festival – March 17-19, 2017 – New York, N.Y., USA
European Robotics Forum – March 22-24, 2017 – Edinburgh, Scotland
NDIA Ground Robotics Conference – March 22-23, 2017 – Springfield, Va., USA
Automate – April 3-3, 2017 – Chicago, Ill., USA
ITU Robot Olympics – April 7-9, 2017 – Istanbul, Turkey
ROS Industrial Consortium – April 07, 2017 – Chicago, Ill., USA
U.S. National Robotics Week – April 8-16, 2017 – USA
NASA Swarmathon – April 18-20, 2017 – NASA KSC, Florida, USA
RoboBusiness Europe – April 20-21, 2017 – Delft, Netherlands
RoboGames 2017 – April 21-23, 2017 – Pleasanton, Calif., USA

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

The Suzumori Endo Lab at Tokyo Tech has developed this tendon-driven quadruped robot, which can walk in any direction thanks to a symmetrical design:

It moves just a little too quickly for my general level of comfort around robots that look like giant bugs.

[ Suzumori Endo Lab ]

I don’t think it’s recognized widely enough that SpaceX is building giant rockety robots with a whole bunch of very sophisticated autonomy going on:

[ SpaceX ]

At some point, someone in a meeting said, “The best way to solve this problem is by putting a flamethrower on a drone.”

I need to have more meetings like that.

[ RT ]

Looks like those Fetch research robots have started helping their humans make progress on useful problems, like how to clean items up off of a table so that I don’t have to, because I am a very busy and important human:

[ Columbia ]

Nom nom.

What happens when you combine ferocious Siberian tigers with modern technology? Bouncing, pouncing, and even a bit of trouncing. Video footage of a habitat for these rare felines in northeast China’s Heilongjiang Province shows them meandering about until they catch sight of a drone with a camera buzzing around. The rather chubby tigers played cat and mouse with the drone until a 2 or 3-year-old tiger swiped at the camera, a large paw filling its screen before losing signal. The group proceeded to tear the drone apart, with one literally chewing on the gadget as if it was a bird of prey. Unlike a bird, the drone started to give off smoke, which scared off the surrounding tigers. Staff members of the park in a well-protected vehicle then went to pick up the remains of the drone. This drone chasing is becoming more popular among these well-nourished tigers in the habitat. Don’t worry. With the exercise they’re getting from these chases, and more importantly, the approach of spring so the tigers don’t need to hoard as many calories, experts predict that they will once again be lean and mean in about two months.

[ CCTV ] via [ Gizmodo ]

I am still very much not at all convinced that drones are likely to be a useful or efficient way to deliver packages in most situations, but that’s not stopping UPS, which recently demonstrated a drone mounted on the roof of a delivery truck.

Kudos to UPS (and its partner Workhorse, which seems to have developed most of the drone delivery system) for at least explaining some of the technical details behind their demo. Now, as far as I can tell the drone has no sense and avoid, so it’s unclear how this approach could scale to work in different locations.  

[ TechCrunch ]

Is a robot tax a good idea? Bill Gates seems to think so:

[ Quartz ]

New from ST Robotics:

The ST R17HS is one of the industry’s fastest robots: standard tool speed is over four times as fast as the nearest competitor, yet it’s less than half the price. The ST R17HS uses state-of-the-art brushless servomotors and boasts an effective reach of 750mm, a repeatability of 0.2 mm and a maximum speed after acceleration of 480 deg/sec in the robot’s waist, elbow, hand and wrist, with a shoulder speed of 300 deg/sec.

For just under $19k, you get the R17HS robot arm, controller, software, teach pendant, and unlimited free technical support.

[ ST Robotics ]

Oh no, TurtleBot 3 is thirsty!

Warning: Do not attempt to quench the thirst of your robot unless it is water cooled.

[ Robotis ]

SuperDroid Robots created this robotic ATV and passenger to “promote ATV safety”:

Because the safest way to ride an ATV is to just have a robot ride it for you.

Also, Uncanny Valley anyone?

[ SuperDroid Robots ]

Eelume is a disruptive technology for subsea inspection, maintenance and repair (IMR). Eelume vehicles are basically self-propelled robotic arms whose slender and flexible body can transit over long distances and carry out IMR in confined spaces not accessible by conventional underwater vehicles.

[ Eelume ] via [ PopSci ]

Unstructured bin picking of sensitive objects has been particularly challenging for robotics in e-commerce logistics and food handling applications. Not only do such products need to be accurately located and picked from a bin, the robot needs to delicately handle the product to avoid damage or bruising. The apple picking system seen here from FANUC America Authorized System Integrator Soft Robotics, Inc. resolves these issues, effectively using a FANUC LR Mate industrial robot to safely and accurately pick and pack apples.

[ Soft Robotics ] via [ Fanuc ]

MRK-Systeme GmbH has developed an automation solution with human-robot collaboration (HRC) capability for the BMW Group using KUKA robots for high payloads. It enables the factory in Landshut, Bavaria to carry out quality assurance for crankshaft housing in an ergonomically friendly manner in safe coordination with human workers.

Robots that don’t squish people into goo, hooray!

[ Kuka ]

From Lockheed Martin:

The Exechon XMini is the next-generation intelligent portable machine system, combining the flexibility and high dynamics of the articulated arm robot with the stiffness and accuracy of the rigid machine tool.

[ Exechon ]

This has to be one of the coolest Husky mods I’ve ever seen:

Yeah, double UR5 arms and Robotiq grippers.

[ Clearpath ]

This has to be one of the coolest Husky mods I’ve ever seen:

We present the deployment of a 16-DoF dual-arm mobile manipulator as an on-stage actor in the MIT2016 Pageant, a 60 minute live play performed for the centennial celebration of the Massachusetts Institute of Technology campus move from Boston to Cambridge. The robot performed using expressive motions, navigated a 250ft-long thrust stage through a wireless connection, and was directed remotely by a human operator using a shared autonomy system. We report on the technical framework and human-robot interaction that enabled the performance, including motion planning, coordination of action with human actors, and the challenges in navigation, manipulation, perception and system reliability.

[ MIT ]

We wrote about this “pollution-eating” robot that runs on the energy produced by microbial fuel cells a while back, but that doesn’t make this TEDx talk from roboticist Jonathan Rossiter any less interesting:

[ TEDxWarwick ]

UW’s Ben Taskar Memorial Lecture features Pieter Abbeel on Deep Reinforcement Learning for Robotics:

Deep learning has enabled significant advances in supervised learning problems such as speech recognition and visual recognition. Reinforcement learning provides only a weaker supervisory signal, posing additional challenges in the form of temporal credit assignment and exploration. Nevertheless, deep reinforcement learning has already enabled learning to play Atari games from raw pixels (without access to the underlying game state) and learning certain types of visuomotor manipulation primitives. I will discuss major challenges for, as well as some preliminary promising results towards, making deep reinforcement learning applicable to real robotic problems.

[ UW ]

Want to learn ROS but have no idea where to start? ETH Zurich has an online lecture that starts at the very beginning:

[ Programming for Robotics Course ]

This week’s CMU RI Seminar comes from Davide Scaramuzza, Professor and Director of the Robotics and Perception Group, University of Zurich:

Autonomous quadrotors will soon play a major role in search-and-rescue and remote-inspection missions, where a fast response is crucial. Quadrotors have the potential to navigate quickly through unstructured environments, enter and exit buildings through narrow gaps, and fly through collapsed buildings. However, their speed and maneuverability are still far from those of birds. Indeed, agile navigation through unknown, indoor environments poses a number of challenges for robotics research in terms of perception, state estimation, planning, and control. In this talk, I will give an overview of my research activities on visual navigation of quadrotors, from slow navigation (using standard frame-based cameras) to agile flight (using active vision and event-based cameras). Topics covered will be: visual inertial state estimation, monocular dense reconstruction, active vision and control, event-based vision.

[ CMU RI ]

Video Friday: Giant Robot Bug, SpaceX Rocket Landing, and Flamethrower Drone