Video Friday: Autonomous Pizza Delivery, Handwriting Robot, and ROS Master

Video Friday is your weekly selection of awesome robotics videos, collected by your starving 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!):

European Robotics Forum – March 21-23, 2016 – Ljubljana, Slovenia

RoboCup European Open – March 30-4, 2016 – Eindhoven, Netherlands

WeRobot 2016 – April 1-2, 2016 – Miami, Fla., USA

National Robotics Week – April 2-10, 2016 – United States

AISB HRI Symposium – April 5-6, 2016 – Sheffield, United Kingdom

ROS-Industrial Training Class – April 6-8, 2016 – San Antonio, Texas, USA

Robotics in Education 2016 – April 14-15, 2016 – Vienna, Austria

NASA Swarmathon – April 18-22, 2016 – NASA KSC, Fla., USA

LEO Robotics Congress – April 21, 2016 – Eindhoven, Netherlands

International Collaborative Robots Workshop – May 3-4, 2016 – Boston, Mass., USA

ICARSC 2016 – May 4-6, 2016 – Bragança, Portugal

Robotica 2016 – May 4-8, 2016 – Bragança, Portugal

ARMS 2016 – May 9-13, 2016 – Singapore

ICRA 2016 – May 16-21, 2016 – Stockholm, Sweden

NASA Robotic Mining Competition – May 18-20, 2016 – NASA KSC, Fla., USA

Skolkovo Robotics Conference – May 20, 2016 – Skolkovo, Russia

Innorobo 2016 – May 24-26, 2016 – Paris, France

RoboCity16 – May 26-27, 2016 – Madrid, Spain

RoboBusiness Europe – June 1-3, 2016 – Odense, Denmark

IEEE RAS MRSSS 2016 – June 6-10, 2016 – Singapore

CR-HRI – June 6-10, 2016 – Orlando, Florida

NASA SRRC Level 1 – June 6-11, 2016 – Worcester, Mass., USA

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

Domino’s in New Zealand (or Australia, we’re not sure) has developed this pizza-delivery robot and I can’t tell if they’re serious or not:

The New Zealand government at least, is taking them seriously, according to Stuff.co.nz:

Transport Minister Simon Bridges said Domino’s had made contact "a few weeks ago" to inform the Government about DRU and see if New Zealand was interested in hosting trials. Bridges said there were "no particular legal blockages" to trialling driverless technology on the country’s roads, but the authorities needed to ensure any trials met safety requirements and other regulations. Backing projects like Domino’s were about "cementing our country’s place as an early adopter and tech-savvy place", he said. "If we were to see more of this, i think it would really enhance New Zealanders’ lifestyles: we’d be ahead of the curve, we’d be getting hold of advanced technologies earlier." Officials from the Ministry of Transport and the NZ Transport Agency would work with Domino’s about the possibility of trialling the system in New Zealand and safety management planning, Bridges said. 

And before it was delivering pizza, this mobile base had a slightly more dangerous job:

[ Domino’s ] via [ Stuff.co.nz ]

The Johns Hopkins University Applied Physics Laboratory has developed this drone called CRACUNS (don’t even ask) that can hang out underwater (even in corrosive salt water) and then launch itself into the air:

[ JHU APL ]

One of two things suggested by this video is probably true. Thing one is that Pepper can measure your size. Thing two is that Pepper will still be functional (and relevant) 27 years from now.

My question (well, one of my questions) is how on earth did Pepper get through the door?

[ Aldebaran ]

DJI’s new Phantom 4 has some impressive vision-based obstacle-avoidance skills, and some serious hardware makes that possible. Inside the Phantom 4 is a high-performance, low-power vision processing unit (VPU) from Movidius:

[ Movidius ]

ParaZero’s pyrotechnic safety parachute needs just 2.5 meters to fully deploy and cushion your drone to a safe (if uncontrolled) landing.

I mean, that’s cool, but when it’s calling itself “pyrotechnic” I’m expecting at least a little bit of fiery explosion, you know?

[ ParaZero ] via [ DIY Drones ]

Skip ahead to about 1:30 in this video to see the dramatic effect that rigid fingernails have on grasping with soft pneumatic fingers:

“Improving Soft Pneumatic Actuator Fingers Through Integration of Soft Sensors, Position and Force Control, and Rigid Fingernails,” by John Morrow, Hee-Sup Shin, Calder Phillips-Grafflin, Sung-Hwan Jang, Jacob Torrey, Riley Larkins, Steven Dang, Yong-Lae Park, and Dmitry Berenson will be presented at ICRA 2016.

[ ARC Lab ]

Simone Giertz (her last name is somehow pronounced “yeach”) has made a robot to help her argue on the Internet:

Personally, I prefer to pick the keyboard up and beat my face with it, which would require a different kind of robot to duplicate. I find that you get higher quality comments that way.

[ Simone Giertz ]

MARLO is one of three ATRIAS 2.1 robots designed and built by Prof. Jonathan Hurst and the Dynamic Robotics Laboratory at Oregon State University. Unlike most other 3D walking robots, MARLO does not have large feet with powered ankles. This forces the robot to balance dynamically, but may lead to more natural and efficient walking. The walking controller is designed using nonholonomic virtual constraints.

You’d think they might be able to find a way of gently stopping MARLO instead of killing it over and over again. Looks kinda painful.

[ Paper ]

FFRobotics (Formerly FFMH-Tech) delivers the first Fresh Fruit Robotic Harvester while offering a unique opportunity for farmers/growers to reduce costs significantly by supplementing or replacing human pickers from the dwindling pool of harvesting labor. The Harvester minimizes fruit damage and increases efficiency and productivity of picking fresh fruit. Our Fresh Fruit Robotic Harvester can precisely and gently pick 10 times more usable fruit compared with an average worker.

Clearpath Robotics has more (including some more up to date pics) at the link below.

[ FFRobotics ] via [ Clearpath Robotics ]

“Fast Nonlinear Model Predictive Control for Unified Trajectory Optimization and Tracking,” from Michael Neunert at ETH Zurich:

This video presents a framework for real-time, full-state feedback, unconstrained, nonlinear model predictive control that combines trajectory optimization and tracking control in a single, unified approach. The proposed method uses an iterative optimal control algorithm, namely Sequential Linear Quadratic (SLQ), in a Model Predictive Control (MPC) setting to solve the underlying nonlinear control problem and simultaneously derive the optimal feedforward and feedback terms. Our customized solver can generate trajectories of multiple seconds within only a few milliseconds. The performance of the approach is validated on two different hardware platforms, an AscTec Firefly hexacopter and the ball balancing robot Rezero. In contrast to similar approaches, we perform experiments that require leveraging the full system dynamics.

[ ETH Zurich ]

Thanks Jonas!

This handwriting robot from Evil Mad Scientist Labs is mesmerizingly satisfying to watch:

[ AxiDraw ] via [ Make ]

TIAGo is a robotic platform for research with navigation, perception, manipulation and HRI abilities. It is ROS compatible and has applications in Ambient Assisted Living, light industry, or anything else that combines its abilities. TIAGo shown in this video is an improved version of its proof-of-concept.

[ PAL Robotics ]

“Proprioceptive Control of an Over-Actuated Hexapod Robot in Unstructured Terrain,” from Navinda Kottege at CSIRO, just submitted to IROS:

Legged robots such as hexapods have the potential to traverse unstructured terrain. This paper introduces a novel hexapod robot (Weaver) using a hierarchical controller, with the ability to efficiently traverse uneven and inclined terrain. The robot has five joints per leg and 30 degrees of freedom overall. The two redundant joints improve the locomotion of the robot by controlling the body pose and the leg orientation with respect to the ground. The indirect force controller reacts to unstructured terrain and thus achieves self-stabilizing behavior without prior profiling of the terrain through exterioceptive sensing. Instead of adding force sensors, the force is calculated by processing the torque output of the actuators. We experimentally evaluate Weaver with the proposed controller and demonstrate that it can effectively traverse challenging terrains and high gradient slopes, reduce angular movements of the body by more than 55% and reduce the cost of transport (up to 50% on uneven terrain and by 85% on a slope with 20 degrees). The controller also enables Weaver to walk up inclines of up to 30 degrees, and remain statically stable on inclines up to 50 degrees. Furthermore, we present a new metric for legged robot stability performance along with a method for proprioceptive terrain characterization.

[ CSIRO ]

Thanks Navinda!

Are you a ROS Master? No? Would you like to be?

It’s even got a turtle on the cover! $55 on Amazon.

[ Master ROS for Robotics ]

Here’s the first episode of a web series from UW Madison, showcasing some of the robotics research being done there:

You can watch the second episode here.

[ UW Science Narratives ]

Episode 1 of “Moon Shot,” a documentary on the Google Lunar XPRIZE:

Legendary roboticist Red Whittaker is a professor who splits his time between teaching future engineers at Carnegie Mellon and owning/operating a working cattle farm in rural Pennsylvania. With a crack team of former students, he co-founded Astrobotic because he believes robots are the best solution for exploring remote, harsh environments—from nuclear disaster zones to the moon.

[ Google Lunar XPRIZE ]