A thread of robot friends that I have met in person, because I meet lots of robots.

F.03 just crossed 9 straight days walking on this treadmill: 348 miles and 1.2 million steps Started as a side project to stress the robot for any failures. Let's see how long it can go

thanks for having me on the show to talk about @mundanebot

planning is overrated just take the shortest term action that is in the general direction of your goal reality is a super high dimensional space, so this basically always works

The back of the Navier-Stokes milestone shirt is the last line of the chain-of-thought from the solution:

hot take: despite the absolutely bonkers engineering to build this and the confidence to do it live, this is a fundamentally easier control problem than humanoids / dexterous manipulation, and can be solved with model based methods like iLQR / MPC

Just verified it's deployable.

Our design language has evolved since the last reveal: from S3XY to Cybertruck, Cybercab & Optimus Roadster is inspired by the SR-71 & F-35

それもこれもAIがネットに上がっている数々のZMPに関する研究成果をアセットとして利用出来るからだしZMP歩行はユーゴスラビア発祥だけれども日本が国費も投じて育てて来た分野なので世界は梶田修司先生に向かって敬礼すべき🫡

🎉 Our TwinX paper is out in Advanced Intelligent Systems! Building on WiXus, TwinX connects two robots with a single wire, enabling docking, separation, reconfiguration, and distributed cooperation—from quadrupedal locomotion to dual-arm manipulation! shin0805.github.io/twinx-bri…

Teleoperating two Ability Hands with @ManusMeta gloves on @AgilexRobotics Nero arms 🦾🦾 Hand and arm data streams into a full 3D sim synced to a depth camera, all built with @claudeai. Real to sim data that can train models to run these tasks autonomously. Boom 💥

🚀48V駆動が一般的な高出力Flat BLDCモータを, さらに高速に駆動するにはどうしたらよいでしょうか？ 我々は, 96 V GaNモータドライバ LunaDrive を開発しました！ 高電圧・大電流駆動と遅延補償FOCにより, 高速回転領域でも安定した制御を実現します！ #IROS2026 woodrobo.github.io/lunadrive…

🎉 Our paper, “LunaDrive: A Delay-Compensated High-Voltage GaN FET-Based Motor Driver for Dynamic Robots with Flat BLDC Motors,” has been accepted to #IROS2026! LunaDrive enables 96 V operation of high-power flat BLDC motors, paving the way for faster and more dynamic robots.

I just tried out that Reverse Engineer Anything trending git repo. It decompiled a steam game I had previously purchased and launched it in Unity in less than 30 minutes using OPUS 5.5 on medium reasoning. Absolutely cracked tbh…. Fully decompiled to C#

I can openly state things because no one will believe me. For example, Joseph Suarez is right about everything

Excited to share that our paper has been accepted to #Humanoids2026 (38% acceptance rate)! 🎉 Looking forward to presenting our work and seeing you all in San Jose! 🤖

gta v running natively on ios (a recent fun project of mine)

Our blind humanoid is going to Silicon Valley! 🤖⚽️🧳🛹 Blind Dexterity: Whole-Body Humanoid Manipulation via Pure Proprioception 🎉 just got accepted to IEEE Humanoids 2026! 🎉 📍Santa Clara, CA 🗓️ Dec 6-9, 2026 Many thanks to my coauthors and reviewers for their useful feedback! w/ @OKaidanov @liu_puze @Jan_R_Peters at @ias_tudarmstadt @DFKI Project: aditya.bhatts.org/BlindDexte… arXiv: arxiv.org/abs/2608.29487

🚨🚨 ROBOT REVEAL 🚨🚨 At @mundanebot , we're building a second body for the skilled trades. A tradesperson puts on our exoskeleton and controls a robot that works where people shouldn’t have to. We’re starting with energized electrical gear, confined spaces, and high-pressure testing, and expanding from there into the dangerous, dirty, and physically demanding work that keeps our infrastructure running. Today the person is fully in control. Every job they run also teaches the system, so over time AI takes on more of the repetitive work, and skilled tradespeople handle the hard calls and edge cases. This is about productivity, not replacement. There aren’t enough skilled tradespeople for the infrastructure we need to build. The ones we have deserve tools that keep them out of harm’s way and multiply what each of them can get done. This week we brought Mundane to National Electrical and Communications Association (NECA) in Las Vegas. More than 100 tradespeople suited up and tried the robot for themselves, and we were awarded Best Booth. We were lucky to be joined by Jake Holthaus from Written in Red, an IBEW lineworker with 15 years of experience. We’re working with Jake alongside Brady Hansen to build this technology with the trades, not just for them. This is the future of the trades. And this is only the start. More soon.

Takes on end effectors are too binary. People love to claim: "grippers are better than hands!" "tendons are superior!" or "direct drive wins." But its much more nuanced than that...

Meet Workhorse 🐴: we study how to learn whole-body loco-manipulation skills from human demos without teleop. Here is my favourite video: we tried everything to make it fail🏒. One take, real-time, fully autonomous.