Videos: Humanoid Robot Martial Arts, Perseverance, More

Video Friday is your weekly selection of awesome robotics videos, collected by your friends on IEEE Spectrum robotics. We are also publishing a weekly calendar of upcoming robotics events for the next few months. Please send us your events for inclusion.

ICRA 2026: June 1-5, 2026, VIENNA

Enjoy today’s videos!

Thus, humanoid robots are close to maximum human performance. I would like to point out, however, that this is probably very far from the maximum performance of robots, which has not yet been effectively exploited, because it requires more than just copying humans.

[ Unitree ]

“The Street Dance of China” Transforming lightness into seriousness and rhythm into impact. It’s a head-on collision between metal and rhythms. This Chinese New Year, watch PNDbotics Adam bring the heat with a difference.

[ PNDbotics ]

You had me at Robot Pandas.

[ MagicLab ]

NASA’s Perseverance rover can now accurately determine its own position on Mars without waiting for human help from Earth. This is possible thanks to a new technology called Mars Global Localization. This technology quickly compares panoramic images from the rover’s navigation cameras with onboard orbital terrain maps. This is done with an algorithm that runs on the rover’s helicopter base station processor, which was originally used to communicate with the Ingenuity Mars helicopter. In just a few minutes, the algorithm can pinpoint Perseverance’s position to within about 10 inches (25 centimeters). The technology will help the rover drive further autonomously and continue exploring.

[ NASA Jet Propulsion Laboratory ]

Legs? Where we’re going, we don’t need legs!

[ Paper ]

It’s a bit of a robotics tangent, but it succeeds because of the cute images of jumping spiders.

[ Berkeley Lab ]

Corvus One for Cold Chain is designed to live and operate continuously in freezing environments, down to -20°F, while maintaining full flight and barcode scanning performance.

I’m sure there’s a great reason to put a cold storage facility in the Mojave Desert.

[ Corvus Robotics ]

The video documents current progress in the Shiva robot’s picking cadence when picking strawberries. It first shows the previous state, then the further development and finally the field test.

[ DFKI ]

Data powers an organization’s digital transformation, and ST Engineering MRAS leverages Spot to gain a comprehensive view of critical equipment and facilities. Working autonomously, Spot collects information on the status of machines – and now, thanks to the integration of the Leica BLK ARC for reality capture, detailed and accurate point cloud data for their digital twin.

[ Boston Dynamics ]

The title of this video is “Go Out and Have Fun!” » Is this mainly what humanoid robots are used for at the moment, roughly…?

[ Engine AI ]

ASTORINO is a modern 6-axis robot based on 3D printing technology. Programmable in AS language, it facilitates lesson preparation with ready-to-use teaching materials, is easy to use and repair, and gives the opportunity to learn and make mistakes without fear of breaking it.

[ Kawasaki ]

Can I have this in my living room?

[ Yaskawa ]

What does it mean to build one humanoid robot in seven months and the next one in just five months? This documentary takes you behind the scenes of Humanoid, a British AI and robotics company that builds reliable, safe and useful humanoid robots. You’ll hear directly from our engineering, hardware, product, and other teams as they share their perspectives on the journey to turn physical AI into reality.

[ Humanoid ]

This IROS 2025 keynote is from Tim Chung, now at Microsoft, on “Catalyzing the future of teams of humans, robots and AI agents in the physical world.”

The convergence of technologies – from basic AI models to diverse sensors and actuators to ubiquitous connectivity – is transforming the nature of interactions in the physical and digital world. People have accelerated their collaborative connections and productivity through digital and immersive technologies, no longer limited by geography, language or access. Humans have also harnessed and interacted with AI in many different forms, with the advent of large-scale AI models (i.e. large language models) forever changing (and at an ever more astonishing rate) the nature of human-AI teams, realized in the AI ​​“co-pilot” era. Likewise, robotics and automation technologies now offer greater opportunities to work with and/or near humans, enabling increasingly collaborative physical robots to have a significant impact on real-world activities. It is the combined effect of implementing these three capabilities, each complementary in valuable ways, and we envision the triad formed by human-robot-AI teams as revolutionizing the future of society, economics and technology.

[ IROS 2025 ]

This GRASP SFI talk is given by Chris Paxton of Agility Robotics, on “How close are we to general purpose humanoid robots?” »

With billions of dollars in funding pouring into robotics, general-purpose humanoid robots seem closer than ever. And it certainly feels like the pace of robotics is faster than ever, with several companies beginning large-scale deployments of humanoid robots. In this presentation, I will examine the challenges that remain in scaling robot learning, examining lessons from a year of discussions with researchers around the world.

[ University of Pennsylvania GRASP Laboratory ]

This week’s CMU RI seminar is led by Jitendra Malik of UC Berkeley, on “Robot Learning, Inspired by Child Development.”

For intelligent robots to become ubiquitous, we must “solve” locomotion, navigation, and manipulation with sufficient reliability in widely varying environments. In locomotion, we are now seeing demonstrations of humanoid walking in various difficult environments. In navigation, we continued the “Go to Any Thing” task: a robot, upon entering a newly rented Airbnb, should be able to find objects such as televisions or potted plants. RL in simulation and sim-to-real have been cutting-edge technologies for us, assisted by some technical innovations. I will outline promising directions for future work.

[ Carnegie Mellon University Robotics Institute ]