Close

Video Friday: Afghan Girls Robotics Team Reaches Safety

Your weekly selection of awesome robot videos

3 min read
Members of the Afghan Girls Robotics Team leaving aircraft in Mexico
Photo: Mexico Foreign Ministry

Video Friday is your weekly selection of awesome robotics videos, collected by your friends at IEEE Spectrum robotics. 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!):

DARPA SubT Finals – September 21-23, 2021 – Louisville, KY, USA
WeRobot 2021 – September 23-25, 2021 – [Online Event]
IROS 2021 – September 27-1, 2021 – [Online Event]
ROSCon 2021 – October 20-21, 2021 – [Online Event]

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


Five members of an all-girl Afghan robotics team have arrived in Mexico, fleeing an uncertain future at home after the recent collapse of the U.S.-backed government and takeover by the Taliban.

[ Reuters ] via [ FIRST Mexico ]

Thanks, Fan!

As far as autonomous cars are concerned, there's suburban Arizona difficulty, San Francisco difficulty, and then Asia rush hour difficulty. This is a 9:38 long video that is actually worth watching in its entirety because it's a fully autonomous car from AutoX driving through a Shenzhen urban village. Don't miss the astonished pedestrians, the near-miss with a wandering dog, and the comically one-sided human-vehicle interaction on a single lane road.

The AutoX Gen5 system has 50 sensors in total, as well as a vehicle control unit of 2200 TOPS computing power. There are 28 cameras capturing a total of 220 million pixels per second, six high-resolution LiDAR offering 15 million points per second, and 4D RADAR with 0.9-degree resolution encompassing a 360-degree view around the vehicle. Using cameras and LiDAR fusion perception blind spot modules, the Gen5 system covers the entire RoboTaxi body with zero blind spots.

[ AutoX ]

Sometimes, robots do nice things for humans.

[ US Soccer ]

Body babbling? Body babbling.

[ CVUT ]

Thanks, Fan!

Matias from the Oxford Robotics Institute writes, "This is a demonstration of our safe visual teach and repeat navigation system running on the ANYmal robot in the Corsham mines/former Cold War bunker in the UK. This is part of some testing we've been doing for the DARPA SubT challenge as part of the Cerberus team."

[ Oxford Robotics ]

Thanks, Matias!

We built a robotic chess player with a universal robot UR5e, a 2D camera, and a deep-learning neural network to illustrate what we do at the Mechatronics, Automation, and Control System Lab at the University of Washington.

[ MACS Lab ] via [ UW Engineering ]

Thanks, Sarah!

Autonomous inspection of powerlines with quadrotors is challenging. Flights require persistent perception to keep a close look at the lines. We propose a method that uses event cameras to robustly track powerlines. The performance is evaluated in real-world flights along a powerline. The tracker is able to persistently track the powerlines, with a mean lifetime of the line 10x longer than existing approaches.

[ ETHZ ]

I could totally do this, I just choose not to.

[ Flexiv ]

Thanks, Yunfan!

Drone Badminton enables people with low vision to play badminton again using a drone as a ball. This has the potential to diversify the physical activity for people with low vision.

[ Digital Nature Group ]

Even with the batteries installed, the Open Dynamic Robot Initiative's quadruped is still super skinny looking.

[ ODRI ]

At USC's Center for Advanced Manufacturing, we have developed a space for multidisciplinary human-robot interaction. The Baxter robot collaborates with the user to execute their own customizable tie-dye design.

[ USC Viterbi ]

I will never understand the impulse that marketing folks have to add bizarre motor noises to robot videos.

[ DeepRobotics ]

FedEx and Berkshire Grey have teamed up to streamline small package processing.

[ FedEx ]

ABB robot amalyzing COVID tests in a fully automated, unmanned state, back and forth between the stations Assist in the delivery of specimens between points, 24 hours a day, 24 hours a day, test results of 96 specimens can be completed every 60 minutes, processing more than 1,800 specimens per day.

[ ABB ]

Thanks, Fan!

This is, and I quote, "the best and greatest robot death scene of all time."

[ The Black Hole ]

Thanks, Mark!

Audrow Nash interviews Melonee Wise for the Sense Think Act podcast.

[ Sense Think Act ]

Tom Galluzzo interviews Andrew Thomaz for the Crazy Hard Robots podcast.

[ Crazy Hard Robots ]

The Conversation (0)

Letting Robocars See Around Corners

Using several bands of radar at once can give cars a kind of second sight

10 min read
Horizontal
Illustration of the modeling of a autonomous vehicle within a urban city intersection.

Seeing around the corner is simulated by modeling an autonomous vehicle approaching an urban intersection with four high-rise concrete buildings at the corners. A second vehicle is approaching the center via a crossing road, out of the AV’s line of sight, but it can be detected nonetheless through the processing of signals that return either by reflecting along multiple paths or by passing directly through the buildings.

Chris Philpot

An autonomous car needs to do many things to make the grade, but without a doubt, sensing and understanding its environment are the most critical. A self-driving vehicle must track and identify many objects and targets, whether they’re in clear view or hidden, whether the weather is fair or foul.

Today’s radar alone is nowhere near good enough to handle the entire job—cameras and lidars are also needed. But if we could make the most of radar’s particular strengths, we might dispense with at least some of those supplementary sensors.

Keep Reading ↓ Show less