30+ teams locked in for 36 hours at the Physical AI hackathon we hosted last weekend in SF 🌉🤖
We equipped them with lerobot arms to solve three tasks: shape insertion, charger plugging, and liquid pouring.
Here are the 7 winners and what they built (with github and video): 🧵👇
It takes a village. Huge shoutout to all sponsors, judges, mentors, and everyone who helped bring this to life. 🫶
@DhruvDiddi, @GZinMetaverse, @astridwilde, @DevSodhi, @ruslanjabari, @dantelentini, @hthieblot, @FurqanR and the entire @fdotinc team, @virtuals_io,@Kevinfromkz, @DBuniatyan, @activeloop team, @rerundotio, @DecartAI @OroLabs, @dgmonsoon, @staxelai, @dolylupec, @protocollabs, @henry_yu_01, @alpercanbe, @clayhaight, @ashwinl, @TKesdogan, @_ddbrx, @celesteanglm, @makeitmatto, @manu_fe23, @ruiyang_w
🥇1st place: ETA0.1
They built an Autonomous Robot Barista using an ACT policy. ☕️
95% accuracy and zero spills after ~100k steps. They introduced real-time perturbations (moving the cup mid-pour), and with just 10k fine-tuning steps, the robot learned to adapt on the fly.
Code: github.com/anjalidhabaria/ph…
Team: @sangam_chapagai, @MahimanaB, @DhabariaAnjali, Gary Lim, Benedict Chan
🥈2nd place: Pivot
To address the combinatorial challenges of long-horizon robotic manipulation, Team PIVot implements a hierarchical architecture that pairs a low-frequency VLM "thinker" for high-level planning with a high-frequency, language-conditioned policy for skill execution.
Code: github.com/praveenVnktsh/PIV…
Team: @praveenvnktsh, @vib2810_, @shriishwaryaasv
🥉3rd place: Automate
Trained an ACT policy from scratch on a real robot and reached ~90% success on a multi-puzzle insertion task with minimal data, showing emergent recovery and alignment behaviors. A great reminder that high-quality demos beat pretraining when working with real-world robotics.
Github: github.com/poorvirhebbar/ins…
Team @Poorvi_rh, @anishmadan23, @SamuelPfrommer
🎖️SoloTech Award: RoboSquad
A 5th grader. Yes, really.
The next generation of roboticists is already here. 🚀
🎖️World Intelligence Award: ServingU
A classic "divide and conquer" engineering approach. 🥤
They split pouring into 3 subtasks, training and benchmarking ACT vs. Diffusion for each (ACT won). Finally, they built a custom script to orchestrate the models sequentially, achieving pixel-perfect coffee pouring.
Code: github.com/Neil7281/Physical…
Team: @neel7281 @JesusBetan86866, @mark_mau_, Liu Cathy, Garima Bhandari
🎖️Protocol Labs Award: Ladybug
An autonomous physical audiobook reader. 🐞📖
The arm turns the page, scans it (OCR), streams text-to-speech, and waits for the audio to finish before turning the page again. The loop: Manipulate → Read → Speak → Repeat.
Github: github.com/alisoncossette/la…
Team: Alison Cossette, Andreea Turcu, Sudhir Dadi
🎖️Activeloop Award: Robocafe
A voice-controlled butler. 🗣️🦾
This team trained a robot to respond to voice prompts to serve croissants, pour water (half or full glass!), and even clean up the table afterwards. Complex task chaining handled by different ACT models.
Github: github.com/dragonkhoi/roboca…
Team: Nestor Tkachenko, Khoi Le
SF is officially the capital of Physical AI. 🌉
Thrilled to announce @cline and @virtuals_io are joining us as a sponsors for the Physical AI Hackathon in SF on Jan 31 – Feb 1!
400+ builders have already applied to get their hands on real hardware and multimodal data.
If you’re building in Physical AI, this is the room you need to be in.
RSVP: luma.com/8ca2z1rr
More details: physicalaihack.com
We’re hosting the largest Physical AI hackathon at Founders Inc 🤖
Jan 31 – Feb 1
• I’m bringing hours of imitation learning data for VLA/VLM (video, tactile, depth, audio)
• Our partners are bringing egocentric models, fine-tuning pipelines, and real robots you can deploy on
No sims. No slides.
You’ll watch robots actually get better.
More info 👉 physicalaihack.com
RSVP 👉 luma.com/8ca2z1rr
We’re hosting the largest Physical AI hackathon at Founders Inc 🤖
Jan 31 – Feb 1
• I’m bringing hours of imitation learning data for VLA/VLM (video, tactile, depth, audio)
• Our partners are bringing egocentric models, fine-tuning pipelines, and real robots you can deploy on
No sims. No slides.
You’ll watch robots actually get better.
More info 👉 physicalaihack.com
RSVP 👉 luma.com/8ca2z1rr
