Agility Robotics Digit humanoid robot learning about personal space
Programmed with a personal space mode, the humanoid robot Digit, from Agility Robotics, tries to keep its distance from an annoying engineer.
Image: Agility Robotics 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 few months; here’s what we have so far (send us your events!):

Robotic Arena – January 25, 2020 – Wrocław, Poland
DARPA SubT Urban Circuit – February 18-27, 2020 – Olympia, Wash., USA
ICARSC 2020 – April 15-17, 2020 – Ponta Delgada, Azores

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

One of Digit’s autonomy layers ensures a minimum distance from obstacles, even mobile ones like pesky engineers. In this video, the vision system is active and Digit is operating under full autonomy.

I would pay money to watch a second video that’s just like this one except Agility has given Digit a voice and it’s saying this stuff dynamically.

[ Agility Robotics ]

The Intel RealSense lidar camera L515 is the world’s smallest and most power efficient hi-resolution lidar, featuring unparalleled depth and accuracy that makes it perfect for indoor uses cases. The L515 is designed with proprietary technology that creates entirely new ways to incorporate lidar into smart devices to perceive the world in 3D.

[ Intel ]

This project investigates a design space, a fabrication system and applications of creating fluidic chambers and channels at millimeter scale for tangible actuated interfaces. The ability to design and fabricate millifluidic chambers allows one to create high frequency actuation, sequential control of flows and high resolution design on thin film materials. We propose a four dimensional design space of creating these fluidic chambers, a novel heat sealing system that enables easy and precise millifluidics fabrication, and application demonstrations of the fabricated materials for haptics, ambient devices and robotics.

[ MIT ]

This looks like it could be relaxing.

[ Eura Shin ]

This is only sort of robotics related, but it’s cool: changing the direction of a ping pong ball by nudging it with controllable ultrasound.

[ University of Tokyo ]

Check out the natural gait on this little running robot from Nagoya Institute of Technology:

[ Nagoya ]

UAV Turbines announced that it successfully demonstrated its Monarch Hybrid Range Extender (HREX), a microturbine powered generator technology that extends the range of electrically powered medium-sized unmanned aircraft.

In UAV Turbines’ HREX system, the engine extracts energy from the fuel and uses it to power the propulsion motor directly, with any excess electric power used to top off the battery charge. This greatly increases range before the weight of the added fuel becomes uneconomical. There are many tradeoffs in optimizing power for any specific system; for example, some energy is lost in the extraction process, but as the fuel is consumed, the net weight of the aircraft drops. It is this flexibility that enables engine optimizations not otherwise possible with a single power source.

[ UAV Turbines ]

Happy Holidays from Sphero!

[ Sphero ]

Happy Holidays from Yaskawa, which, despite having access to lots of real robots, stubbornly refuses to use them in their holiday videos.

[ Yaskawa ]

Join us in celebrating the life of Woodie Flowers, professor emeritus of mechanical engineering at MIT and co-founder of the FIRST Robotics Competition. A beloved teacher and pioneer in hands-on engineering education, Flowers developed design and robotics competitions at MIT, FIRST, and beyond, while promoting his concept of “gracious professionalism.”

[ MIT ]

I still really like the design of EMYS, although I admit that it looks a little strange when viewed from the side.

[ EMYS ]

Japanese college students compete to make the best laundry hanging robot, where speed and efficiency are a hilarious priority.


The U in U-Drone stands for: Underground, Unlimited, Unjammable, User-Friendly and Unearthing. A prototype of a compact cable drone (U-Drone) has been developed in the one year project. It has been tested and demonstrated in underground tunnels (without GPS reception), whereby the drone can be operated at distances of up to 100 meters.

The commands to the U-Drone, and the images and data from the drone to the operator, run through an (unjammable) lightweight cable. The replaceable spool with the 100 meter cable is connected to the U-Drone and therefore unwinds from the drone during the flight in such a way that the drone is not stopped when the cable gets stuck.

[ Delft Dynamics ]

Interesting tiltrotor design for a drone that can apply a probe to a structure at any angle you want.

[ Skygauge ]

NASA has developed a flexible way to test new designs for aircraft that use multiple rotors to fly. The Multirotor Test Bed, or MTB, will let researchers study a wide variety of rotor configurations for different vehicles, including tiltrotor aircraft, mid-sized drones and even air taxis planned for the coming era of air travel called Urban Air Mobility.

[ NASA ]

Here’s a robot not to get on the wrong side of.

The Javelin Joint Venture team, a partnership of Lockheed Martin and Raytheon Company, successfully fired Javelin missiles from a Kongsberg remote weapon station integrated onto an unmanned vehicle platform. The demonstrations, conducted at the Redstone Test Center, Ala., validated the integration of the weapon station, missile and vehicle.

Raytheon ]

From Paul Scharre, who knows what he’s talking about more than most, a nuanced look at the lethal autonomous robots question.

[ Freethink ]

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

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