Home » Video Friday: Robotic Canine Can’t Fall

Video Friday: Robotic Canine Can’t Fall

by Oliver
0 comment

Video Friday is your weekly choice of superior robotics movies, collected by your folks at IEEE Spectrum robotics. We additionally publish a weekly calendar of upcoming robotics occasions for the subsequent few months. Please ship us your occasions for inclusion.

RoboCup German Open: 17–21 April 2024, KASSEL, GERMANY
AUVSI XPONENTIAL 2024: 22–25 April 2024, SAN DIEGO
Eurobot Open 2024: 8–11 May 2024, LA ROCHE-SUR-YON, FRANCE
ICRA 2024: 13–17 May 2024, YOKOHAMA, JAPAN
RoboCup 2024: 17–22 July 2024, EINDHOVEN, NETHERLANDS
Cybathlon 2024: 25–27 October 2024, ZURICH

Enjoy in the present day’s movies!

I feel suggesting that robots can’t fall is far much less helpful than as an alternative suggesting that robots can fall and get shortly and simply get again up once more.

[ Deep Robotics ]

Sanctuary AI says that this video exhibits Phoenix working at “human-equivalent pace,” however they don’t specify which human or beneath which circumstances. Though it’s sooner than I might be, that’s for positive.

[ Sanctuary AI ]

“Suzume” is an animated movie by Makoto Shinkai, during which one of many characters will get was a three-legged chair:

Shintaro Inoue from JSK Lab on the University of Tokyo has managed to construct a robotic model of that very same chair, which is fairly spectacular:

[ Github ]

Thanks, Shintaro!

Humanoid robotic EVE coaching for house help like placing groceries into the kitchen cupboards.

[ 1X ]

This is the RAM—robotic autonomous mower. It might be dropped anyplace on the planet and can get up with a mission to make tall grass round it shorter. Here is a fast clip of it engaged on the Presidio in SF.

[ Electric Sheep ]

This 12 months, our robots braved a Finnish winter for the primary time. As the snow clears and the times get longer, we’re trying again on how our robots made 1000’s of deliveries to S Group clients in the course of the colder months.

[ Starship ]

Agility Robotics is doing its greatest to reply the (quite common) query of “Okay, however what can humanoid robots truly do?”

[ Agility Robotics ]

Digit is nice and every part, however Cassie will all the time be considered one of my favourite robots.

[ CoRIS ]

Adopting omnidirectional Field of View (FoV) cameras in aerial robots vastly improves notion skill, considerably advancing aerial robotics’s capabilities in inspection, reconstruction, and rescue duties. We suggest OmniNxt, a completely open-source aerial robotics platform with omnidirectional notion.

[ OmniNxt ]

The MAkEable framework enhances cellular manipulation in settings designed round people by streamlining the method of sharing realized expertise and experiences amongst completely different robots and contexts. Practical assessments verify its effectivity in a variety of situations, involving completely different robots, in duties comparable to object greedy, coordinated use of each arms in duties, and the trade of expertise amongst humanoid robots.

[ Paper ]

We performed trials of Ringbot outside on a 400 meter observe. With an influence supply of 2300 milliamp-hours and 11.1 Volts, Ringbot managed to cowl roughly 3 kilometers in 37 minutes. We commanded its goal pace and path utilizing a distant joystick controller (Steam Deck), and Ringbot skilled 5 falls throughout this trial.

[ Paper ]

There is a notable lack of consistency about the place precisely Boston Dynamics desires you to assume Spot’s eyes are.

[ Boston Dynamics ]

As with each single cooking video, there’s plenty of background prep that’s required for this robotic to cook dinner a whole meal, however I might totally demolish these fries.

[ Dino Robotics ]

Here’s every part you must find out about Wing supply drones, besides for a way a lot human time they really require and the true value of constructing deliveries by drone, as a result of these issues aren’t enjoyable to speak about.

[ Wing ]

This CMU Teruko Yata Memorial Lecture is by Agility Robotics’ Jonathan Hurst, on “Human-Centric Robots and How Learning Enables Generality.”

Humans have dreamt of robotic helpers endlessly. What’s new is that this dream is turning into actual. New developments in AI, constructing on foundations of {hardware} and passive dynamics, allow vastly improved generality. Robots can step out of extremely structured environments and change into extra human-centric: working in human areas, interacting with individuals, and doing a little primary human workflows. By connecting a Large Language Model, Digit can convert pure language high-level requests into advanced robotic directions, composing the library of expertise collectively, utilizing human context to realize actual work within the human world. All of that is new—and it’s by no means going again: AI will drive a fast-following robotic revolution that’s going to alter the way in which we dwell.

[ CMU ]

You may also like

Leave a Comment