Video Friday is your weekly selection of amazing robotics videos collected by your friends ieee spectrum Robotics. We also post a weekly calendar of upcoming robotics events for the next few months. Please send us your programs for inclusion.
ROSCON 2025: 27-29 October 2025, Singapore
Enjoy today’s video!
Welcome to this world—height 180 cm and weight 70 kg. H2 Bionic Humanoid- Born to serve everyone safely and friendly.
Starting at US$29,900 plus taxes and shipping.
, unitary ,
Its title, “The Eagle Stole Our FPV Drone,” pretty much sums it up.
, team blacksheep ,
Thank you, Kyu-jin!
Just FYI, any robot that looks like it tastes delicious baked goods is guaranteed favorable coverage on Video Friday.
, Cleo Robotics ,
Ollie now follows a smooth, coordinated whole-body sequence from lying down to getting back up. Standing 165 cm tall and operating with 31 degrees of freedom, Ollie continues to demonstrate natural and fluid movements.
, Limx Dynamics ,
Thanks, Jinyan!
Friend of the blog Bram Vanderborgh visits the exhibition site at IROS 2025 in Hangzhou, China.
, IROS 2025 ,
In a candid conversation with Professor Sam Madden, Ty Brady, Chief Technologist at Amazon Robotics, will discuss the trajectory of robotics and how generic AI plays a role in robotics innovation.
, MIT Generative AI Impact Consortium ,
Professor Dimitrios Kanoulas delivered an invited lecture at the workshop at IROS 2025 on The Art of Robustness: Surviving Failures in Robotics.
, IROS 2025 ,
This GRASP talk from the University of Pennsylvania is by Suraj Nair of Physical Intelligence on the topic “Scaling Robot Learning with Vision-Language-Action Models.”
The past several years have seen tremendous advances in the capabilities of AI systems, largely driven by foundation models that scale expressive architectures with diverse data sources. Although the impact of this technology on vision and language understanding is quite clear, its use in robotics is still in its infancy. Scaling robot learning still presents many open challenges – from selecting the right data for scale, to developing algorithms that can effectively fit this data to closed-loop operation in the physical world. In Physical Intelligence, our goal is to tackle these questions. This talk will present our recent work on building the Vision-Language-Action model, covering topics such as architecture design, data scaling, and open research directions.
, University of Pennsylvania GRASP Laboratory ,
From articles on your site
Related articles on the web
