Friday video is your weekly selection of impressive robotics videos, collected by your friends in Spectrum ieee robotics. We also publish a weekly calendar for the next robotics events for the coming months. Please Send us your events for inclusion.
Corl 2025: September 27-30 2025, Seoul
IEEE HUMANOIDIDS: September 30 to October 2, 2025, Seoul
World Robots Summit: October 10-12, 2025, Osaka, Japan
IROS 2025: 19-25 October 2025, Hangzhou, China
Take advantage of today’s videos!
Gemini Robotics 1.5 is our most competent vision-action vision-action model that transforms visual information and motor control instructions for a robot to perform a task. This model thinks before acting and shows its process, helping robots to assess and perform complex tasks more transparent. He also learns through achievements, accelerating skills learning.
https://www.youtube.com/watch?v=uobzwjpb6xm
[ Google DeepMind ]
A simple gesture of “traction of strength” brings in housing directly into his hand. This is a fantastic example of how an intuitive interaction can transform complex technology into an extension of our intention.
https://www.youtube.com/watch?v=Vb73rl3HDK
[ Robust.ai ]
I can’t help it, I feel bad for this poor little robot.
https://www.youtube.com/watch?v=owbnt87cmki
[ Urban Robotics Laboratory, KAIST ]
Hey look, no legs!
https://www.youtube.com/watch?v=5ydlz54unyy
[ Kinisi Robotics ]
Researchers from the University of Michigan and the University of Shanghai Jiao Tong have developed a soft robot that can crawl along a flat path and climb on vertical surfaces using its unique origami structure. The robot can move with precision generally observed only in rigid robots.
https://www.youtube.com/watch?v=P4WSZMJ6KNW
[ University of Michigan Robotics ]
UniLee G1 learned of “anti-gravity” mode: stability is considerably improved under any action sequence, and even if it falls, it can quickly get up.
https://www.youtube.com/watch?v=bpslmx_v38e
[ Unitree ]
Kepler Robotics began the mass production of K2 Bumblebee, the first humanoid robot in the world available in the world powered by Tesla’s hybrid architecture.
https://www.youtube.com/watch?v=iadq_1ulirq
[ Kepler Robotics ]
Locomotion controllers based on reinforcement learning (RL) often require a meticulous reward adjustment to follow the speeds or positions of objectives while preserving a smooth movement on various fields. The methods of imitation of movement via RL using demonstration data reduce the engineering of rewards but fail to generalize to new environments. We approach this by proposing a hierarchical RL framework in which a low -level policy is first formed to imitate animal movements on flat terrain, thus establishing priority. Real world experiences with a quadruped robot Anymal-D confirm the ability of our policy to generalize animal locomotion skills on complex terrains, demonstrating a soft and efficient locomotion and local navigation performance in the middle of difficult land with obstacles.
https://www.youtube.com/watch?v=g20Geadn6gm
[ ETHZ RSL ]
I think we entered the “differentiation-Through-Novelty” phase of robot vacuum cleaners.
https://www.youtube.com/watch?v=zmuw_mn2odg
[ Roborock ]
In this work, we present Kinethreads: a new haptic exosuit design of the whole body built around string -based engine mechanisms, which maintains our light (<5kg), soft and flexible, quick to wear (<30 seconds) costume, relatively low effects (~ $ 400), and yet capable of rendering expressive effects, distributors and force (up to 120).
https://www.youtube.com/watch?v=4EV0W_TBUW8
[ ACM Symposium on User Interface and Software Technology ]
In this episode of the Podcast IBM AI In Action, Aaron Saunders, CTO of Boston Dynamics, plunges into the potential transformer of robotics fueled by AI, emphasizing how robots become safer, more profitable and widely accessible through robotics as a service (RAAS).
https://www.youtube.com/watch?v=djtfw4v9a_c
[ IBM ]
This CMU Ri seminar is of Michael T. Tolley of the UCSD, on “soft robotics of biological inspiration”.
https://www.youtube.com/watch?v=rounxcn3irc
Robotics have the potential to solve many current urgent problems in areas ranging from health care to manufacturing through help in the event of a disaster. However, the traditional approaches used on the factory floor do not work well in unstructured environments. The key to solving many of these challenges is to explore new non -traditional conceptions. Fortunately, nature surrounds us with examples of new ways of navigating and interacting with the real world. The Dr. Tolley robotics and design laboratory seeks to borrow the main principles of operation of biological systems and apply them to robotic design.
[ Carnegie Mellon University Robotics Institute ]
From your site items
Related items on the web
