Michael Cho - Rbt/Acc

Super psyched for this competition! While folding origami is not "economically valuable task" which many commercial labs care about outright, I love this challenge b/c: 1. Origami, at the highest level, is IMO one of the most complicated dexterous task human hands are capable of. 2. I reckon even for fairly simple origami designs, you'd need more than 2 fingers. So this is a task that really showcase the use of 5-fingered hands. 3. Folding origami involves lots of occlusion. In fact, I've seen an origami master fold a crane more or less completely based on touch. This means tactile and even force sensing would be required for complicated origami designs. 4. Origami is an art form with long cultural history in Japan. It's not just the physical manipulation techniques involved, there's also a creative aspect that I think will be a frontier goal for Embodied AI to shoot for. 5. We're co-organizing this challenge with the Nippon Origami Association, who are basically the human experts. This means we'll have human expert benchmark against what embodied AI can do. I reckon this is such a difficult task that this competition will last for years before embodied AI (both model and hardware improvements) can catch up to human performance. I'm also very confident that on the path of solving robotic origami we'd have also unlocked some fundamental manipulation capabilities that'd be useful in lots of other real-world dexterous tasks. Grateful to be able to do this with my buddies @DJiafei @chris_j_paxton as well as strong partners from @SharpaRobotics @LightwheelAI @BitRobotNetwork as well as friends from academia.

@francislee2020 Congrats on the talk; u deserve it Hongyang!

Go for #whole_body_intelligence :)

So much gem in this talk from @pulkitology #RSS2026

Some very cool humanoid works from Lizhi!

Full episode dropping soon! Geeking out with Lizhi Yang on HANDOFF: Humanoid Agentic Task-Space Whole-Body Control via Distilled Complementary Teachers lzyang2000.github.io/HANDOFF/ Co-hosted by @micoolcho @chris_j_paxton

Out of 13 papers at the Humanoid session at #RSS2026 , 12 of them use @UnitreeRobotics G1 for real-world eval. Basically G1 has become the default embodiment for humanoid research, at least for this current generation/cohort. There's some FUD abt their IPO but if u look at their penetrarion rate in the research community, they have completly won.

Great #RSS2026 (Sydney) opening talk from Matei Ciocarlie; just one complaint: where's Messi photo in this slide?? 😅

@shahdhruv_ @alexzhang_robo Will definitely check these out at the poster session!

While I am very sad to miss RSS this year, my brilliant students and collaborators will be presenting five exciting papers 🧵: 1. Visual Verification Enables Inference-time Steering and Autonomous Policy Improvement by @alexzhang_robo veritas-improvement.github.io We show a simple recipe for self-improving generalist policies using a VLM verifier and an off-the-shelf generator (policy).

@oyhsu "Minimum deployable robot" probably gonna be some specific embodiment-task-environment combo that get success rate close to 99% so customers will start paying for and get data flywheel going to hill climb towards 6sigma; clothes folding robot is a prime candidate.

A review of patterns we've observed in physical AI over the last 2-3 years, as the field has continued to make technical progress and aggregate talent and capital across new and existing companies: In 2023-2024, we started noticing more teams building for a given layer of the robotics stack. Whereas historically teams built all their own infrastructure, the promise of scaling laws for robotics meant generality was on the table, and what generality enables is for teams to build on top of a common platform — a huge advantage given the long tail nature of the physical world. We also posited that given the variance of the physical world, the proliferation of such a platform might resemble more of an open ecosystem in the vein of Android. This dynamic could kick off an apps>infrastructure cycle that robotics has historically lacked, but every other major technology cycle has seen (web, mobile, crypto, etc.). This is partially because there has been no breakout robotics app, but maybe, like with language models, this would be a case where infrastructure (and generality) kicks off the cycle. I wrote about that idea here 2 years ago: a16z.com/toward-a-gener… Much of 2024-2025 was focused on the infrastructure side of this ecosystem, particularly around different methods of scaling robot data. Concurrently, there was also more activity in building the hardware platform and components of robot infrastructure, as well as the emergence of tools built for a 'robotics developer' persona. 2025-2026 saw more entrepreneurs and engineers shift their focus towards the application layer. Specifically, the idea of a 'neo-systems integrator', or a company focused on deploying the new generation of learning-based robots, started coming into focus as more early stage teams began to pursue this. Concurrently, large robotics labs began pursuing both first and third party deployments, and the app<>infrastructure relationship started taking shape. I wrote about the deployment layer and some of the problems to be solved in deploying learning-based systems here: a16z.news/p/the-physical… In parallel, throughout 2024-2026 we saw the proliferation of research around different elements of solving generalist robotics. Beyond overarching methods built around VLAs, world state prediction, and sim, there were key building blocks in areas like human motion transfer, online RL, domain randomization, and bridging the high and low levels. Moreover, we continue to see more evidence for scaling laws for robot actions. This research progress across the field forms the building blocks for the pursuit of generalist robotics and a robust robotics developer ecosystem. I've also started focusing more on the frontiers of physical AI beyond robotics, specifically on incorporating physical reasoning and physical modalities into AI in general. Much of this work is still somewhat nascent, and I wrote about some of these areas here: a16z.com/frontier-syste… Some of the things I think are interesting to observe now: - Where we are in the Perezian financial/technological cycle with robotics. - Without knowing the thresholds we have to scale to see inflections in robot capabilities, robustness, and generalization, what is a minimum deployable robot? - Signals around adoption of common hardware platforms for robotics developers. - The combination of scaling less-than-reliable deployments + continual learning for robots. In general, I continue to believe that many of the most interesting things in robotics in the coming years will be emergent behaviors and properties. This is exciting and also involves working with a lot of unknown unknowns.

@lacey_wisdom @plcapital Energy begets AI. Meanwhile, AI will also push for new advancements in Energy (be it new generation sources or just less wastage thro transmission).

AI's hidden cost isn't the models. It's the electricity. ChatGPT hit 1B monthly users in May 2026 and every single query burns energy. At @plcapital, we don't see a compute crisis coming. We see an energy one 🧵 (1/9)

Full episode dropping soon! Geeking out with @XuZhengton @YepingWang on Contact-Grounded Policy: Dexterous Visuotactile Policy with Generative Contact Grounding contact-grounded-policy.github.io Co-hosted by @chris_j_paxton @DJiafei

Still baby steps...we need to accelerate!

Loving the actuated neck here; also how it looks down to check out its own dexterous hands! Congrats to @RemiCadene & the @UMA_Robots team!

Full episode dropping soon! Geeking out with @XuZhengton @YepingWang on Contact-Grounded Policy: Dexterous Visuotactile Policy with Generative Contact Grounding contact-grounded-policy.github.io Co-hosted by @chris_j_paxton @DJiafei

@s_wistreich @RoboPapers @chris_j_paxton @DJiafei Tks for ur sharing Suzannah! Very very cool project; thanks for open sourcing too!

So much fun chatting on @RoboPapers about Dexskin and tactile sensing! Thank you @chris_j_paxton and @DJiafei for having us, episode below👇

Very cool work from the DexSkin team! I saw the live demo myself at Stanford; really neat, affordable and open source!!

Full episode dropping soon! Geeking out with @s_wistreich @BaiyuShi147 on DexSkin: High-Coverage Conformable Robotic Skin for Learning Contact-Rich Manipulation dex-skin.github.io Co-hosted by @chris_j_paxton @DJiafei

We added new skills to the Rerun repo to make it easier to investigate existing robotics data with Rerun. Very excited to see the new Human in the Wild dataset by @bitrobotnetwork, @huggingface, and @unitreerobotics this week as a great opportunity to try them out, We'll be playing more with this dataset in the coming weeks, but check out the repo below if you want to start looking at and querying this new dataset in the interim.

@liu730chaoqi Congrats! Looks really cool!

Really excited to finally share IMPACT! One thing I really like about this project is that it tackles a practical challenge in robot learning: adapting to changing environmental dynamics online, while still running at 1000 Hz on real robot hardware. That’s a much harder systems and control problem than it might sound. Huge credit to @WinstonGu_ for leading this work. As a co-author, I got to see firsthand how much engineering and systems work went into making this happen. He’s an exceptionally strong and independent researcher. Check out the thread below 👇

@juanbenet has a new podcast! Early episodes (mostly on neurotech) all look bangers! There goes my entire weekend 😅

@fancy_yzc Would love to have u guys come on RoboPapers, when u'r ready :) Super cool work; congrats again Zhecheng!

@micoolcho Thx, Michael! We may release a relevant technical report in the future.

🌶️🤖𝐖𝐞 𝐜𝐨𝐨𝐤𝐞𝐝 𝐭𝐡𝐞 𝐫𝐨𝐛𝐨𝐭𝐢𝐜𝐬 𝐰𝐨𝐫𝐥𝐝’𝐬 𝐟𝐢𝐫𝐬𝐭 𝐩𝐥𝐚𝐭𝐞 𝐨𝐟 𝐌𝐚𝐩𝐨 𝐓𝐨𝐟𝐮.🤖🌶️ This was not just a cooking demo. It was a 30-minute, long-horizon robotics challenge packed with delicate, continuous, high-dexterity actions. With only a small number of demonstrations, our model learned to perform complex manipulation over an extended sequence. At the same time, we pushed hard on motion control and system-level optimization, making the robot move smoothly while keeping the high success rate. For us, this plate of Mapo Tofu is more than a dish. It is a small but meaningful step toward home robots that can handle real everyday tasks with the dexterity, consistency, and reliability people expect.