飞舟Afei Wan

HVAC→AD→VLA→Robotics. Prev:DNTC→Xpeng,Now FutureXplore, Seeking like‑minded co‑founder for our embodied‑AI startup based in Guangzhou,Open my follow list for🤖

[yishan @tspy]

https://t.co/7RRfhyg36u

[yishan @tspy]

https://t.co/yfgIybxuCM

[yishan @tspy]

太疯狂，万物皆可逆向的REA

在GitHub的Star已经超过100K

闭源软件被迫开源

代码再次贬值😂

[Ilir Aliu @IlirAliu_]

'Robotics Fundamentals' - Viam just put part 2 online. No hardware required.
Free. 📌

101 showed you how to build a palletizing robot in simulation.
102 takes you a step further: making sure your robot can run on its own.

120 minutes. 12 lessons. No hardware required.

This time, you'll learn how to:

→ Turn your control code into a production-grade robot module
→ Automatically start, supervise, and restart your code
→ Configure dependencies and robot behavior
→ Build a DoCommand API
→ Deploy updates to entire robot fleets over the cloud
→ Schedule tasks so your robot runs unattended

The interesting part is what happens after you've written the code.

Your robot keeps running even when your laptop is turned off. And you can deploy updates remotely without having to touch the machine.

Everything runs in simulation, so you can learn the same workflows used to deploy and maintain robots in the field.

Free. Self-paced. No physical robot needed.

📌 https://t.co/HyyubdvpQg

Follow for more robotics resources!

———
Weekly robotics and AI insights.
Subscribe free: https://t.co/KzvUrLseUp

[yishan @tspy]

https://t.co/iC9zrLcWRa

[Alloy Robotics @AlloyRobotics]

This paper visualised: "Multiple contact planning for minimizing damage of humanoid falls" (Ha & Liu, IROS 2015) turns falling into a planning problem.

- Model fall as a chain of inverted pendulums
- Solve for contact order with dynamic programming
- Minimise largest single impact, not the total
- Fall like a judoka!

[飞舟Afei Wan @AfeiWan]

@TeckZhee @qqqq_996 @DevinOlsenn @XPENG_Global Pre-map and pre-routine are different

[Lukas Ziegler @lukas_m_ziegler]

This is the capital of robotics! 🌁

Silicon Valley is home to so many physical AI companies that you could spend a month visiting them and still not see even 10% of them (trust me, I tried).

So, the Bay Area is the world's leading ecosystem for robotics startups, bringing together top AI talent, top universities, experienced founders, and unmatched access to capital.

The region is anchored by Stanford University and University of California, Berkeley, two of the world's top universities for AI and robotics. They produce a constant stream of researchers, founders, and breakthrough technologies.

The Bay Area is also home to many of the companies shaping the future of robotics and AI, including @Figure_robot, @physical_int, @GeneralistAI, and major AI labs such as @OpenAI, or @GoogleDeepMind.

This concentration of talent makes it easy for startups to recruit experienced engineers and collaborate with leaders in embodied AI.

Not mentioning that it  is also home to leaders such as @NVIDIARobotics, whose headquarters and leadership in AI chips power much of today's robotics revolution, and Tesla, whose work on autonomous driving and humanoid robots has created a deep pool of robotics, AI, and manufacturing talent.

Perhaps its biggest advantage is access to capital, talent and ambition.

The Bay Area has the world's deepest network of venture capital firms, serial entrepreneurs, and technical leaders who are willing to fund bold, long-term robotics companies.

In the comments I'll post the companies from the ecosystem.

‼️ Note that Bay Area has >300 robotics companies, research labs, and innovation hubs, so this is a curated selection of the notable product companies, not an exhaustive census!

P.S. I'm constantly working on improving these maps, so if your company is missing, please DM me with basic info about the co, and I will include it in the next release.

P.S.2 I have last open slots for my December RoboTour in the Bay Area, if you want to create content together and show the world what are you cooking, dm! :)

~~ 

♻️ Join the weekly robotics newsletter, and never miss any news → https://t.co/GoA3ZuwoPB

[Praveen Kumar Verma @Alacritic_Super]

Honestly, the ESP32 is a total cheat code for building cheap tech.

For the price of a coffee, you get a tiny board that has built-in Wi-Fi, Bluetooth, and plenty of power to run awesome projects. It is making it so easy to build smart home gadgets and IoT devices from scratch.

What's your favorite ESP32 project so far?

Video Source: @QingQ77

[Zhuokai Zhao @zhuokaiz]

🌐 Project: https://t.co/R5IVQlyI8x
📄 Paper: https://t.co/zBZU150cCU
💻 Code and Lean 4 proofs: https://t.co/5ldLdcEjfw

[飞舟Afei Wan @AfeiWan]

@moo_jin_kim @StanfordAILab @OpenAI @chelseabfinn @percyliang Open to Open for a big Open.Congrats Moo!

[yishan @tspy]

学会机械臂后，就可以让它替你完成繁重的工作

当今世上，所有超过 500 人的制造工厂，都是远古的工厂，是落后的，是不思进取的

同时也是不适合继续生存的制造工厂

现在不变革，就是等着被超级智能时代所抛弃，不会等很久……

[飞舟Afei Wan @AfeiWan]

@qqqq_996 @DevinOlsenn @XPENG_Global patches applied to certain road segments are still visible in the new version.

[Md Ismail Šojal 🕷️ @0x0SojalSec]

a tiny AI 0.5B just turned a normal phone video into a fully labeled 3D room run phone.

SpatialLM that understands walls, doors, furniture, and everything layout.

it trained as a standard multimodal LLM.
Most vision models see pixels, SpatialLM sees space.

Open models : https://t.co/kGXjHkIdiE

[飞舟Afei Wan @AfeiWan]

@DevinOlsenn @XPENG_Global Better to take an entirely new route mid-journey.Everything will be in sight.😊

[Lukas Ziegler @lukas_m_ziegler]

Turning video into humanoid robot motion! 🤳🏼

Training humanoid robots needs huge amounts of motion data, but real-world capture doesn’t scale.

Mocap is expensive, dangerous edge cases are rare, and you can’t ask humans to repeatedly fall or crash.

Video2Robot tackles this by converting videos into physics-grounded humanoid simulations.

Motion is generated to respect balance, inertia, ground contact, and joint limits, then directly retargeted to robot simulators.

One prompt can generate a full humanoid motion sequence, including multi-agent interactions and failure cases like falls or collisions, scenarios that are hard or impossible to capture safely in the real world.

The pipeline is model-agnostic and works with existing video generators, making it a practical way to scale data for robots.

If robots are going to operate in the real world, they need to be trained on the failures too, not just the perfect demos.

Here's the GitHub: https://t.co/kAOxN1r7VF

~~

♻️ Join the weekly robotics newsletter, and never miss any news → https://t.co/GoA3ZuwWF9

[Jacob H. Rothschild @ja_rothschild]

For those who missed it yesterday, I wrote the explainer on robot control I wish I'd had when I got into robot learning. For ML people, no robotics background assumed, with animations.

What's in it:
- what a policy's output actually does to a servo
- PID, and why a cheap arm overshoots (clip below)
- how teleop data gets recorded
- joint space vs. task space, FK and IK
- why an SO-100 can reach exactly 0% of the gripper poses within arm's length
- why ACT outputs joint angles, while OpenVLA doesn't

Everything is shown on the SO-100 arm that @LeRobotHF uses. Next one will be on ACT. Follow me to catch it.

[Ronin @DeRonin_]

which board should you actually start with?

Arduino vs ESP32 vs Raspberry Pi

4 months into robotics as a hobby, here's what i'd tell myself on day one:

1. start with arduino

use it when you're learning:

- motors
- servos
- sensors
- basic circuits

atmega328p, 16 mhz, 2 kb of ram, and 5v logic so most hobby parts plug straight in

when your code runs, nothing interrupts it, and that makes timing easy to reason about

best place to learn the fundamentals without debugging an operating system at the same time

you outgrow it the day you add wifi or a camera

2. move to esp32

use it when you want:

- wifi
- bluetooth
- wireless control
- anything that reports back to your phone

dual core at 240 mhz, 520 kb ram, radios on the chip, around $5 a board

more connectivity and still hands on, so you keep writing the same kind of code

two things that cost me a weekend each:

3.3v logic, so your 5v sensors need a level shifter or they read garbage

and on the original esp32 the adc2 pins stop reading the moment wifi turns on

3. go for raspberry pi

use it when your robot needs:

- computer vision
- ai and ml
- ros 2
- heavy processing

now you're running a computer inside your robot, with all of the upside and all of the cost

linux decides when your code runs, so pwm timing jitters and servos twitch

and pulling the power without a shutdown corrupts the sd card, which i learned twice

also worth knowing, raspberry makes a real microcontroller too, the pico, about $4

so the quick version:

never wired anything before -> arduino

want wifi and the best price -> esp32

need vision or a camera -> raspberry pi

and yes, you can use more than one

arduino -> control
esp32 -> connect
raspberry pi -> compute

that combination is what took me 4 months to understand

the pi is the brain and the microcontroller is the spine, and a real robot wants both

also, if you want to learn robotics engineering for 6 months, read the article below:

[飞舟Afei Wan @AfeiWan]

@DevinOlsenn @XPENG_Global Most likely you’re driving on a pre-mapped route.