<img src="https://spectrum.ieee.org/media-library/nine-glossy-humanoid-robots-walking-in-sync-inside-a-spacious-industrial-room.png?id=61621100&width=1200&height=800&coordinates=150%2C0%2C150%2C0"/><br/><br/><p><span>Video Friday is your weekly selection of awesome robotics videos, collected by your friends at </span><em>IEEE Spectrum</em><span> robotics. We also post a weekly calendar of upcoming robotics events for the next few months. Please </span><a href="mailto:automaton@ieee.org?subject=Robotics%20event%20suggestion%20for%20Video%20Friday">send us your events</a><span> for inclusion.</span></p><h5><a href="https://actuate.foxglove.dev/">ACTUATE 2025</a>: 23–24 September 2025, SAN FRANCISCO</h5><h5><a href="https://www.corl.org/">CoRL 2025</a>: 27–30 September 2025, SEOUL</h5><h5><a href="https://2025humanoids.org/">IEEE Humanoids</a>: 30 September–2 October 2025, SEOUL</h5><h5><a href="https://worldrobotsummit.org/en/">World Robot Summit</a>: 10–12 October 2025, OSAKA, JAPAN</h5><h5><a href="http://www.iros25.org/">IROS 2025</a>: 19–25 October 2025, HANGZHOU, CHINA</h5><p>Enjoy today’s videos!</p><div class="horizontal-rule"></div><div style="page-break-after: always"><span style="display:none"> </span></div><p class="rm-anchors" id="c-nmhem7iya">A billion dollars is a lot of money. And this is actual money, not just a valuation. but <a data-linked-post="2668901591" href="https://spectrum.ieee.org/figure-new-humanoid-robot" target="_blank">Figure</a> already had a lot of money. So what are they going to be able to do now that they weren’t already doing, I wonder?</p><p class="shortcode-media shortcode-media-youtube"><span class="rm-shortcode" data-rm-shortcode-id="4d8502ce5186d2705a7882d43fe3ab46" style="display:block;position:relative;padding-top:56.25%;"><iframe frameborder="0" height="auto" lazy-loadable="true" scrolling="no" src="https://www.youtube.com/embed/c-NmheM7iyA?rel=0" style="position:absolute;top:0;left:0;width:100%;height:100%;" width="100%"></iframe></span></p><p>[ <a href="https://www.figure.ai/news/series-c">Figure</a> ]</p><div class="horizontal-rule"></div><blockquote class="rm-anchors" id="knf-uqb9k50"><em>Robots often succeed in simulation but fail in reality. With PACE, we introduce a systematic approach to sim-to-real transfer.</em></blockquote><p class="shortcode-media shortcode-media-youtube"><span class="rm-shortcode" data-rm-shortcode-id="be798615031e1066a524c5f505e37ee6" style="display:block;position:relative;padding-top:56.25%;"><iframe frameborder="0" height="auto" lazy-loadable="true" scrolling="no" src="https://www.youtube.com/embed/kNf-uQb9k50?rel=0" style="position:absolute;top:0;left:0;width:100%;height:100%;" width="100%"></iframe></span></p><p>[ <a href="https://arxiv.org/pdf/2509.06342">Paper</a> ]</p><div class="horizontal-rule"></div><blockquote class="rm-anchors" id="gvnkmsfaq3q"><em>Anthropomorphic robotic hands are essential for robots to learn from humans and operate in human environments. While most designs loosely mimic human hand kinematics and structure, achieving the dexterity and emergent behaviors present in human hands, anthropomorphic design must extend to also match passive compliant properties while simultaneously strictly having kinematic matching. We present ADAPT-Teleop, a system combining a robotic hand with human-matched kinematics, skin, and passive dynamics, along with a robotic arm for intuitive teleoperation.</em></blockquote><p class="shortcode-media shortcode-media-youtube"><span class="rm-shortcode" data-rm-shortcode-id="3606bbb871767f6712a61d613be8d14f" style="display:block;position:relative;padding-top:56.25%;"><iframe frameborder="0" height="auto" lazy-loadable="true" scrolling="no" src="https://www.youtube.com/embed/gVNkmsFAQ3Q?rel=0" style="position:absolute;top:0;left:0;width:100%;height:100%;" width="100%"></iframe></span></p><p>[ <a href="https://www.nature.com/articles/s44182-025-00034-3">Paper</a> ]</p><div class="horizontal-rule"></div><blockquote class="rm-anchors" id="7yynevey4w8"><em>This robot can walk without any electronic components in its body, because the power is transmitted through wires from motors concentrated outside of its body. Also, this robot’s front and rear legs are optimally coupled and can walk with just four wires.</em></blockquote><p class="shortcode-media shortcode-media-youtube"><span class="rm-shortcode" data-rm-shortcode-id="e29524fe1ff4790d1acff1d5ed9f53f4" style="display:block;position:relative;padding-top:56.25%;"><iframe frameborder="0" height="auto" lazy-loadable="true" scrolling="no" src="https://www.youtube.com/embed/7yyNevEY4W8?rel=0" style="position:absolute;top:0;left:0;width:100%;height:100%;" width="100%"></iframe></span></p><p>[ <a href="http://www.jsk.t.u-tokyo.ac.jp/">JSK Lab</a> ]</p><p>Thanks, Takahiro!</p><div class="horizontal-rule"></div><blockquote class="rm-anchors" id="akdagvctgck"><em>Five teams of Los Alamos engineers competed to build the ultimate hole-digging robot dog in a recent engineering sprint. In just days, teams programmed their robot dogs to dig, designing custom “paws” from materials like sheet metal, foam, and 3D-printed polymers. The paws mimicked animal digging behaviors—from paddles and snowshoes to dew claws—and helped the robots avoid sinking into a 30-gallon soil bucket. Teams raced to see whose dog could dig the biggest hole and dig under a fence the fastest.</em></blockquote><p class="shortcode-media shortcode-media-youtube"><span class="rm-shortcode" data-rm-shortcode-id="2029c0d4609508135ca20dee5abd01c7" style="display:block;position:relative;padding-top:56.25%;"><iframe frameborder="0" height="auto" lazy-loadable="true" scrolling="no" src="https://www.youtube.com/embed/AkDaGvctGCk?rel=0" style="position:absolute;top:0;left:0;width:100%;height:100%;" width="100%"></iframe></span></p><p>[ <a href="https://www.lanl.gov/media/publications/national-security-science/peanut-butter-potting-soil-and-prototype-engineering">Los Alamos</a> ]</p><div class="horizontal-rule"></div><blockquote class="rm-anchors" id="6pwi4-ycv8m"><em>This work presents UniPilot, a compact hardware-software autonomy payload that can be integrated across diverse robot embodiments to enable resilient autonomous operation in GPS-denied environments. The system integrates a multimodal sensing suite including lidar, radar, vision, and inertial sensing for robust operation in conditions where unimodal approaches may fail. A large number of experiments are conducted across diverse environments and on a variety of robot platforms to validate the mapping, planning, and safe navigation capabilities enabled by the payload.</em></blockquote><p class="shortcode-media shortcode-media-youtube"><span class="rm-shortcode" data-rm-shortcode-id="3c13955bf3f3f0379f8648dbc2af7b0c" style="display:block;position:relative;padding-top:56.25%;"><iframe frameborder="0" height="auto" lazy-loadable="true" scrolling="no" src="https://www.youtube.com/embed/6pwI4-YCV8M?rel=0" style="position:absolute;top:0;left:0;width:100%;height:100%;" width="100%"></iframe></span></p><p>[ <a href="https://www.autonomousrobotslab.com/">NTNU</a> ]</p><p>Thanks, Kostas!</p><div class="horizontal-rule"></div><blockquote class="rm-anchors" id="ytwo7lldn4c"><em>KAIST Humanoid v0.5. Developed at the DRCD Lab, KAIST, with a control policy trained via reinforcement learning.</em></blockquote><p class="shortcode-media shortcode-media-youtube"><span class="rm-shortcode" data-rm-shortcode-id="ae6a815f2600aad733f4334e7bf427b9" style="display:block;position:relative;padding-top:56.25%;"><iframe frameborder="0" height="auto" lazy-loadable="true" scrolling="no" src="https://www.youtube.com/embed/ytWO7lldN4c?rel=0" style="position:absolute;top:0;left:0;width:100%;height:100%;" width="100%"></iframe></span></p><p>[ <a href="https://dynamicrobot.kaist.ac.kr/">KAIST</a> ]</p><div class="horizontal-rule"></div><p class="rm-anchors" id="f1aaxaskcso">I just like the determined little hops.</p><p class="shortcode-media shortcode-media-youtube"><span class="rm-shortcode" data-rm-shortcode-id="5dea6c650decc4cb4722fcb16487c566" style="display:block;position:relative;padding-top:56.25%;"><iframe frameborder="0" height="auto" lazy-loadable="true" scrolling="no" src="https://www.youtube.com/embed/F1AaxaSkCSo?rel=0" style="position:absolute;top:0;left:0;width:100%;height:100%;" width="100%"></iframe></span></p><p>[ <a href="https://global.agilex.ai/">AgileX</a> ]</p><div class="horizontal-rule"></div><p class="rm-anchors" id="ovigdxft4le">I’m always a little bit suspicious of robotics labs that are exceptionally clean and organized.</p><p class="shortcode-media shortcode-media-youtube"><span class="rm-shortcode" data-rm-shortcode-id="807ab0f11e3ee3bb6eb4ea1f1c3dbbc0" style="display:block;position:relative;padding-top:56.25%;"><iframe frameborder="0" height="auto" lazy-loadable="true" scrolling="no" src="https://www.youtube.com/embed/OvIGDxft4lE?rel=0" style="position:absolute;top:0;left:0;width:100%;height:100%;" width="100%"></iframe></span></p><p>[ <a href="http://www.pndbotics.com/">PNDbotics</a> ]</p><div class="horizontal-rule"></div><p class="rm-anchors" id="g7rid4yb1tg">Er, has PAL Robotics ever actually seen a kangaroo...?</p><p class="shortcode-media shortcode-media-youtube"><span class="rm-shortcode" data-rm-shortcode-id="40bb97eb68951ab2cf32595229209047" style="display:block;position:relative;padding-top:56.25%;"><iframe frameborder="0" height="auto" lazy-loadable="true" scrolling="no" src="https://www.youtube.com/embed/G7riD4yb1tg?rel=0" style="position:absolute;top:0;left:0;width:100%;height:100%;" width="100%"></iframe></span></p><p>[ <a href="https://pal-robotics.com/robot/kangaroo/">PAL</a> ]</p><div class="horizontal-rule"></div><p class="rm-anchors" id="ug-5bn-5nja">See <a data-linked-post="2662502813" href="https://spectrum.ieee.org/video-friday-spot-tripping" target="_blank">Spots</a> push. Push, Spots, push.</p><p class="shortcode-media shortcode-media-youtube"><span class="rm-shortcode" data-rm-shortcode-id="b981f42cf3e82ff65d0ae891016201d2" style="display:block;position:relative;padding-top:56.25%;"><iframe frameborder="0" height="auto" lazy-loadable="true" scrolling="no" src="https://www.youtube.com/embed/UG-5BN-5NjA?rel=0" style="position:absolute;top:0;left:0;width:100%;height:100%;" width="100%"></iframe></span></p><p>[ <a href="https://hrilab.tufts.edu/">Tufts</a> ]</p><div class="horizontal-rule"></div><blockquote class="rm-anchors" id="-kusnexvj2g"><em>Training humanoid robots to hike could accelerate development of embodied AI for tasks like autonomous search and rescue, ecological monitoring in unexplored places, and more, say University of Michigan researchers who developed an AI model that equips humanoids to hit the trails.</em></blockquote><p class="shortcode-media shortcode-media-youtube"><span class="rm-shortcode" data-rm-shortcode-id="63568b335acd55f879c838722a171bc1" style="display:block;position:relative;padding-top:56.25%;"><iframe frameborder="0" height="auto" lazy-loadable="true" scrolling="no" src="https://www.youtube.com/embed/-KUSNeXvj2g?rel=0" style="position:absolute;top:0;left:0;width:100%;height:100%;" width="100%"></iframe></span></p><p>[ <a href="https://ai.engin.umich.edu/stories/simulated-humanoid-robots-learn-to-hike-rugged-terrain-autonomously">Michigan</a> ]</p><div class="horizontal-rule"></div><p class="rm-anchors" id="b94_w7jir-8">I am dangerously close to no longer being impressed by breakdancing humanoid robots.</p><p class="shortcode-media shortcode-media-youtube"><span class="rm-shortcode" data-rm-shortcode-id="d9e4bd320ddfbec127374717853b7082" style="display:block;position:relative;padding-top:56.25%;"><iframe frameborder="0" height="auto" lazy-loadable="true" scrolling="no" src="https://www.youtube.com/embed/b94_W7JiR-8?rel=0" style="position:absolute;top:0;left:0;width:100%;height:100%;" width="100%"></iframe></span></p><p>[ <a href="https://www.fftai.com/">Fourier</a> ]</p><div class="horizontal-rule"></div><p class="rm-anchors" id="7htev2udsae">This, though, would impress me.</p><p class="shortcode-media shortcode-media-youtube"><span class="rm-shortcode" data-rm-shortcode-id="2f06b441b4657ae0dac3b58eef872ba9" style="display:block;position:relative;padding-top:56.25%;"><iframe frameborder="0" height="auto" lazy-loadable="true" scrolling="no" src="https://www.youtube.com/embed/7htEV2UDsAE?rel=0" style="position:absolute;top:0;left:0;width:100%;height:100%;" width="100%"></iframe></span></p><p>[ <a href="https://team.inria.fr/hucebot/">Inria</a> ]</p><div class="horizontal-rule"></div><p class="rm-anchors" id="2sya8elzmes">In this interview, Clone’s co-founder and CEO Dhanush Radhakrishnan discusses the company’s path to creating the synthetic humans straight out of science fiction.</p><p>(If YouTube brilliantly attempts to auto-dub this for you, switch the audio track to original [which YouTube thinks is Polish] and the video will still be in English.)</p><p class="shortcode-media shortcode-media-youtube"><span class="rm-shortcode" data-rm-shortcode-id="2af28ac84dc5e5924f314e5ecd1f1940" style="display:block;position:relative;padding-top:56.25%;"><iframe frameborder="0" height="auto" lazy-loadable="true" scrolling="no" src="https://www.youtube.com/embed/2SYA8ELZmEs?rel=0" style="position:absolute;top:0;left:0;width:100%;height:100%;" width="100%"></iframe></span></p><p>[ <a href="https://clonerobotics.com/">Clone</a> ]</p><div class="horizontal-rule"></div><blockquote class="rm-anchors" id="jyflldzulu4"><em>This documentary takes you behind the scenes of the HMND 01 Alpha release: the breakthroughs, the failures, and the late nights of building the U.K.’s first industrial humanoid robot. </em></blockquote><p class="shortcode-media shortcode-media-youtube"><span class="rm-shortcode" data-rm-shortcode-id="2c43cb390cb755d0e0f2f6621d47010e" style="display:block;position:relative;padding-top:56.25%;"><iframe frameborder="0" height="auto" lazy-loadable="true" scrolling="no" src="https://www.youtube.com/embed/jyflLDzUlu4?rel=0" style="position:absolute;top:0;left:0;width:100%;height:100%;" width="100%"></iframe></span></p><p>[ <a href="https://thehumanoid.ai/">Humanoid</a> ]</p><div class="horizontal-rule"></div><blockquote class="rm-anchors" id="pgbzetzx424"><em>What is the role of ethical considerations in the development and deployment of robotic and automation technologies, and what are the responsibilities of researchers to ensure that these technologies advance in ways that are transparent, fair, and aligned with the broader well-being of society?</em></blockquote><p class="shortcode-media shortcode-media-youtube"><span class="rm-shortcode" data-rm-shortcode-id="ea6a9e5cce37d63d68dc35f58029fe20" style="display:block;position:relative;padding-top:56.25%;"><iframe frameborder="0" height="auto" lazy-loadable="true" scrolling="no" src="https://www.youtube.com/embed/pgBzETzX424?rel=0" style="position:absolute;top:0;left:0;width:100%;height:100%;" width="100%"></iframe></span></p><p>[ <a href="https://icra40.ieee.org/icra-2024/program/debates-and-panels/">ICRA@40</a> ]</p><div class="horizontal-rule"></div><p class="rm-anchors" id="srpx2hkap98">This UPenn GRASP SFI lecture is from Tairan He at Nvidia on “Scalable Sim-to-Real Learning for General-Purpose Humanoid Skills.”</p><p class="shortcode-media shortcode-media-youtube"><span class="rm-shortcode" data-rm-shortcode-id="0d8abdfe6c31b1afb6e3368449dd09b0" style="display:block;position:relative;padding-top:56.25%;"><iframe frameborder="0" height="auto" lazy-loadable="true" scrolling="no" src="https://www.youtube.com/embed/sRpx2hkap98?rel=0" style="position:absolute;top:0;left:0;width:100%;height:100%;" width="100%"></iframe></span></p><blockquote><em>Humanoids represent the most versatile robotic platform, capable of walking, manipulating, and collaborating with people in human-centered environments. Yet despite recent advances, building humanoids that can operate reliably in the real world remains a fundamental challenge. Progress has been hindered by difficulties in whole-body control, robust perceptive reasoning, and bridging the sim-to-real gap. In this talk, I will discuss how scalable simulation and learning can systematically overcome these barriers.</em></blockquote><p>[ <a href="https://www.grasp.upenn.edu/events/fall-2025-grasp-sfi-tairan-he/">UPenn</a> ]</p><div class="horizontal-rule"></div>

تسلط حلقة فيديو الجمعة لهذا الأسبوع الضوء على استثمار كبير بقيمة مليار دولار في الروبوتات البشرية، مما يبرز الاهتمام المتزايد والتقدم في تكنولوجيا الروبوتات. لا يسلط هذا التمويل الضوء فقط على إمكانيات الروبوتات البشرية في مختلف الصناعات، بل يعكس أيضًا التكامل المتزايد للروبوتات في الحياة اليومية. مع مشاهدة هذه التطورات، من المثير التفكير في التطبيقات المستقبلية وكيف يمكن أن تحول عالمنا.

Este Video Friday destaca una inversión significativa de mil millones de dólares en robots humanoides, lo que subraya el creciente interés y los avances en la tecnología robótica. Esta financiación no solo enfatiza el potencial de los robots humanoides en diversas industrias, sino que también refleja la creciente integración de la robótica en la vida cotidiana. Al presenciar estos desarrollos, es emocionante pensar en las futuras aplicaciones y cómo podrían transformar nuestro mundo.

Cette semaine, Video Friday met en avant un investissement significatif d'un milliard de dollars dans les robots humanoïdes, soulignant l'intérêt croissant et les avancées dans la technologie robotique. Ce financement souligne non seulement le potentiel des robots humanoïdes dans diverses industries, mais reflète également l'intégration croissante de la robotique dans la vie quotidienne. En assistant à ces développements, il est passionnant de penser aux futures applications et à la manière dont elles pourraient transformer notre monde.

This week's Video Friday highlights a significant investment of a billion dollars in humanoid robots, showcasing the growing interest and advancements in robotics technology. This funding not only emphasizes the potential of humanoid robots in various industries but also reflects the increasing integration of robotics into everyday life. As we witness these developments, it's exciting to think about the future applications and how they could transform our world.

Video Friday: A Billion Dollars for Humanoid Robots

Right now, humanoid robots are where smartphones were in 2007. The question is how fast they will transform our lives.

الروبوتات البشرية على وشك أن تصبح جزءًا أساسيًا من حياتنا اليومية مثل الهواتف الذكية في عام 2007، مع تقدم التكنولوجيا الذي يشير إلى تحول سريع في قدراتها وتطبيقاتها. تشير المشهد الحالي إلى اهتمام متزايد بالروبوتات البشرية، مما يعكس تغييرًا كبيرًا في كيفية تفاعل التكنولوجيا مع البيئات البشرية.

Los robots humanoides están a punto de convertirse en algo tan integral para la vida diaria como lo fueron los teléfonos inteligentes en 2007, con avances tecnológicos que sugieren una rápida transformación en sus capacidades y aplicaciones. El panorama actual indica un creciente interés en los robots humanoides, reflejando un cambio significativo en cómo la tecnología podría interactuar con los entornos humanos.

Les robots humanoïdes sont sur le point de devenir aussi essentiels à la vie quotidienne que les smartphones en 2007, avec des avancées technologiques suggérant une transformation rapide de leurs capacités et applications. Le paysage actuel indique un intérêt croissant pour les robots humanoïdes, reflétant un changement significatif dans la manière dont la technologie pourrait interagir avec les environnements humains.

Humanoid robots are poised to become as integral to daily life as smartphones were in 2007, with advancements in technology suggesting a rapid transformation in their capabilities and applications. The current landscape indicates a burgeoning interest in humanoid robots, reflecting a significant shift in how technology could interact with human environments.

Video Friday: A Billion Dollars for Humanoid Robots

Was this article worth reading? Share it

Fluidwave

Ai doll

sync. labs