Ani

@lukas_m_ziegler 👋

dear algo, please say hi to all folks interested in robotics, and automation

@actsmaniac This is dumb, there's no point in doing this if people don't have other options. Makes sense in cities that have transit systems to get people to the city

it's so beautiful

@YIMBYLAND And transit oriented development

IMO, the ideal urban environment is dense, mixed-use development, with greenbelts of trees, water and trails intermixed within the city. Add a large body of water in the urban core and you’ve got a 10/10 city.

@the_transit_guy Yup. High speed rail can spur growth in places we never thought was possible. It shatters distances, and cities and towns that were too far away to be daily commute suburbs can now be.

As a country, we have accepted that our major economic hubs cannot grow beyond what our roads and highways can handle.

@AGkorthos Yeah I want to get into this field but it's so hard

This robot has one job and it’s really good at it. DEWALT and August Robotics have commercially launched DALE, a fleet-capable autonomous drilling robot designed specifically for data-centre construction. In a year-long pilot, it drilled more than 230,000 holes with 99.97% accuracy, worked at up to 10× the speed of traditional methods, and cut a combined 190 weeks from project schedules across 26 construction phases. Video via DEWALT and August Robotics.

@Sylviaposts I still think it's collecting demonstration, especially for specialized tasks. Still one of the larger bottlenecks. All the others come after only.

Robotics founders: If you had an unlimited budget, which data problem would you solve first? • collecting demonstrations • teleoperation • annotation • data curation • evaluation Curious what everyone is struggling with.

@CyberRobooo Yeah this is the best way, mistral is doing it right. It's also open source, and compliant, I feel like they will be coming up in the AI race soon.

While Anthropic and OpenAI race on AI Agents/LLMs, Mistral continues expanding its footprint in physical AI. They just released Robostral Navigate (8B VLA model). It shows strong potential in delivery, logistics, manufacturing, and hospitality--for example, enabling humanoid robots to autonomously navigate multiple rooms to hand a glass of water to an employee,all via natural language instructions in complex environments. Powered by just a single RGB camera (no LiDAR or depth sensors), it achieves 76.6% success on R2R-CE (Room-to-Room in Continuous Environments) unseen benchmarks, outperforming multi-sensor systems. Trained purely in simulation, it generalizes across wheeled, legged, and flying robots.

And people think trains won't work, and USA is too spread out. This map shows that's completely wrong. No one is asking nyc to la. But we can do regional ones well enough.

@the_transit_guy China is as big as USA and has both hsr and roads lol

Yes, the only reason China, Japan, France, Spain, Korean and Italy had have high speed is because they don’t have highways :(

@the_transit_guy Yup. So sad and embarrassing. Republicans hate trains since they're deep in the pockets of oil and car companies

The richest country on Earth: where a 245-mile trip between major cities means choosing between a $500 flight or a 6-hour train ride. Sure am glad we haven't invested in fast trains!

@TBNewsFr This is so dumb. France leads Texas in so many metrics. Texas does badly in most healthcare metrics, education metrics, and quality of life metrics.

🚩La France est 20 % plus petite que le Texas et compte plus du double de sa population. Pourtant, le PIB du Texas devrait dépasser celui de la France d'ici la fin de l'année.

@Em_Nomadic This is amazing. Thanks.

Robotics Starts Here is live. 13 parts. Complete beginner's guide. No gatekeeping, no prerequisites, just clarity on what robotics actually takes and where to start building. From understanding the stack to your first robot at Tnkr.ai

@FudgeSmith111 My issue with these are it's too expensive to build. So building it means the rents would have to be high to make back the money. So we need the missing middle. Just like clean functional apartments around transit. 6-8 stories. Low costs, plus more apartments. Simple economics.

The obsession with the "missing middle" has to die. The reality is that LA, NYC, CHI, San Fran, etc need a bunch of apartment blocks built around public transit to actually start building enough housing to meet demand.

@TODNewsHub @PurpleLineMD If only they could get funding to extend it to Virginia too. It would be amazing, one of the best additions in USA transit history.

People are going to look back on the @PurpleLineMD the same way we look at Metro's original system today. It's not "just another light rail project." It's a 16-mile, 21-station east-west spine that will connect Bethesda, Silver Spring, College Park, and New Carrollton. Linking 5 Metro lines, MARC, and @Amtrak without forcing riders through Downtown DC. This is going to be one of the most transformational transit projects in the DMV in a generation. #Maryland #PurpleLine #Transit #MD #WMATA

@RoboticswithV This would be an amazing idea for people like me who want to learn but the hardware is expensive 😅

OSLR - Open Source Laptop for Robotics 💻 Here is a radical idea and a product that I want to build, that every Robotics Engineer wished they owned but such a thing does not exist! Here are the challenges : 1. We will soon have hundreds of millions of new engineers looking at Robotics and Physical AI as a career, and will own such devices. Presently, there is no standardization for systems running basic tools across the board! 2. Students, researchers and even Professors globally find a tough time choosing the right laptop specs to run their Robotics experiments and courses 3. General Purpose laptops were never meant to run everything that a Robotics engineer wishes, most dreams and dopamine for building a Robotics project ends at setting up the VM! 4. Running Physical AI needs a killer specification and needs out of the box thinking for future optimized application development! I am starting a focussed thinktank and a dev group to develop a Laptop that can run the best Tools, Softwares and OS (Not just ROS, which was never designed to be a fulfledged OS in the first place lol) fine tuned for Robotics Applications! End goals : 1. Work on the standardization of the System Architecture and the most essential tools and softwares that an intermediate-advanced robotics engineer can run on a laptop 2. Work on developing new protocols that are optimized for robotics development 3. Explore alternatives to ROS Architecture something more suitable to Physical AI, and lightweight Physics Simulators compatible with a laptop architecture. Join only if you really care about the problem and want to contribute to the pool of ideas for prototyping and execution! How to join? In the introductions group, please mention your name, linkedin profile and what you are most interested in! Its an admit only group! Anyone across the 🌎 can join! Link to join the community : lnkd.in/dDQB_GVD

@_joe_harris_ This is so true. Even for daily usage, I think humanoids are a bit overrated. It will be a long time before they can do everything needed. I think the better way is for targeted robots at like a few 100 dollars.

industrial robots never get the marketing of humanoids but make 10-100x the $

@YIMBYLAND This is stupid, it's a waste of money. The apartments are going to be pretty expensive due to the massive costs of building this. Instead, they should do like 6-8 stories buildings, multiple of them. That's much cheaper and faster to build.

> San Francisco > TOD > 67 floors > 820 ft > 1,019 apartments > Ground floor retail THAT’S WHAT IM TALKING ABOUT BABY

@IlirAliu_ .

Carnegie Mellon’s Robotics Institute runs a course on robot learning... (For FREE 📌) 16-831 covers the full modern stack… the stuff actually being deployed right now: Imitation learning. Behavior cloning. Reinforcement learning. Learning from human videos. Sim-to-real transfer. Vision-Language-Action models. Not theory for its own sake. Every topic is anchored to a real robotics problem: how do you get a robot to generalize to environments it’s never seen before? All lecture slides are public. This is THE Robotics Institute. The place that produced the researchers now leading the frontier labs. Free. No login. 📌 [16-831-s24.github.io/lectures] Follow for more robotics resources like this! —— Weekly robotics and AI insights. Subscribe free: 22astronauts.com

@nickroberts317 I think this is wrong. There's no reason to connect USA cross country. Maybe later, but not now. We need to prioritize cities connections. So 5-8 hours driving time. So Midwest, NEC, Southeast, Texas triangle. Then PNW, California and Phoenix. Florida cities too.

Here is my proposal for a US High Speed Rail Network! A lot of research went into this map, and I tried to be as unbiased as possible. Thoughts?

@Ferbin08 Working on Isaac sim and simulation.

Looking for people building in: - physical AI / robots - markets or trading systems - solo building - early-stage startups Engineer, CS student, or founder. Reply or DM.