Video Friday this is your weekly selection of amazing robotics videos collected by your friends on IEEE spectrum robotics. We're also posting a weekly calendar of upcoming robotics events for the next few months. Please send us your events to turn on.
KLAVAR 2025: September 5–7, 2025, SHENZHEN, CHINA
ACTION 2025: September 23-24, 2025, SAN FRANCISCO.
CORL 2025: September 27–30, 2025, SEOUL
IEEE Humanoids: September 30 – October 2, 2025, SEOUL.
World Robot Summit: October 10–12, 2025, OSAKA, JAPAN
IN 2025: October 19-25, 2025, HANGZHOU, CHINA.
Enjoy today's videos!
Boston Dynamics came back and they danced robot dogs bigger, better and bolder than ever! Watch as they bring a “dead” robot to life and perform a never-before-seen synchronized dance to “Good Vibrations.”
And what's more interesting, here's a discussion of how they made it work:
[ Boston Dynamics ]
I don't really care whether there will be robot falls. I wonder if he'll get up again.
[ LimX Dynamics ]
The robot autonomously connects several wires to the environment using small flying anchors – drones equipped with attachment mechanisms at the ends of the wires. Driven by a built-in RGB-D camera to monitor and sense the environment, the system enables wiring in unprepared environments and supports simultaneous multi-wire connections, expanding the operating range of wire-guided robots.
[ JSK Robotics Laboratory ] V [ University of Tokyo ]
Thank you, Shintaro!
For a robot that has almost no face, these are pretty good emotions.
[ Pollen ]
Skill learning from human motion offers a promising path toward generalizing humanoid whole-body control policies, but two key cornerstones are missing: (1) a scalable, high-quality motion tracking system that accurately translates kinematic references into robust, highly dynamic motions on real-world hardware, and (2) a distillation approach that can efficiently learn these motion primitives and arrange them to solve subsequent problems. We address these gaps with BeyondMimic, a real-world system that enables learning from human motion for universal and naturalistic control of humanoids through controlled diffusion.
[ Hybrid Robotics ]
Introducing our open source metal bipedal robot MEVITA. All components can be purchased through e-commerceand the robot consists of a minimum number of parts. All hardware, software and learning environments are released as open source.
[ MEVITA ]
Thank you, Kento!
I always thought that being able to rent robots (or exoskeletons) to help you move furniture or otherwise move things would be very helpful.
[ DEEP Robotics ]
A new study explains how tiny water bugs use fan-shaped propellers to propel themselves through streams at speeds of up to 120 body lengths per second. The researchers then created a similar fan-shaped design and used it to propel and maneuver an insect-sized robot. This discovery opens up new possibilities for developing small machines that can operate during floods or other difficult situations.
[ Georgia Tech ]
Dynamic movement from leg robots is an important but complex topic in expanding operational range mobile robots. To achieve generalized walking on your feet across different landscapes while maintaining the robustness of learning-based controllers, this paper proposes robot-driven attention-based map encoding. proprioceptionwhich is trained as part of an end-to-end controller using reinforcement learning. We show that the network learns to focus on areas that can be navigated for future reference points as the robot dynamically navigates diverse and complex landscapes.
[ Paper ] from [ ETH Zurich ]
In the fifth issue of our Moonshot Podcast Deep Dive Video Interview Series, X's Captain of Moonshots Astro Teller sits down with Google DeepMind Chief Scientist Jeff Dean for a conversation about the origins of Jeff's groundbreaking scaling work neural networks. They discuss the first time artificial intelligence captured Jeff's imagination, Google Brain's earliest platform, the team's stratospheric achievements in image recognition and speech-to-text, how AI is evolving, and more.
[ Moonshot Podcast ]
Articles from your site
Related articles on the Internet
