Lucy Shi
@lucy_x_shi
CS PhD student @Stanford. Robotics research @physical_int. Interested in robots, rockets, and humans.
Introducing Hi Robot – Hierarchical Interactive Robot Our first step at @physical_int towards teaching robots to listen and think harder. A 🧵 on how we make robots more steerable 👇
Sadly I won’t be at ICML in person, but @chelseabfinn will be presenting Hi Robot tomorrow at 4:30pm in West Exhibition Hall B2-B3 (#W-403). Don’t miss it!
Introducing Hi Robot – Hierarchical Interactive Robot Our first step at @physical_int towards teaching robots to listen and think harder. A 🧵 on how we make robots more steerable 👇
If you are interested in solving complex long-horizon tasks, please join us at the 3rd workshop on Learning Effective Abstractions for Planning (LEAP) at @corl_conf! 📅 Submission deadline: Sep 5 🐣 Early bird deadline: Aug 12
We're excited to announce the third workshop on LEAP: Learning Effective Abstractions for Planning, to be held at #CoRL2025 @corl_conf! Early submission deadline: Aug 12 Late submission deadline: Sep 5 Website link below 👇
SRT-H has been published in Science Robotics (and featured on the cover). :) Turns out, when we apply YAY Robot to surgical settings, the robot can perform real surgical procedures like gallbladder removal autonomously.
Introducing Hierarchical Surgical Robot Transformer (SRT-H), a language-guided policy for autonomous surgery🤖🏥 On the da Vinci robot, we perform a real surgical procedure on animal tissue. Collaboration b/w @JohnsHopkins & @Stanford
Your bimanual manipulators might need a Robot Neck 🤖🦒 Introducing Vision in Action: Learning Active Perception from Human Demonstrations ViA learns task-specific, active perceptual strategies—such as searching, tracking, and focusing—directly from human demos, enabling robust…
Q-learning is not yet scalable seohong.me/blog/q-learnin… I wrote a blog post about my thoughts on scalable RL algorithms. To be clear, I'm still highly optimistic about off-policy RL and Q-learning! I just think we haven't found the right solution yet (the post discusses why).
In LLM land, a slow model is annoying. In robotics, a slow model can be disastrous! Visible pauses at best, dangerously jerky motions at worst. But large VLAs are slow by nature. What can we do about this? An in-depth 🧵:
How to build vision-language-action models that train fast, run fast & generalize? In our new paper, we formalize & analyze the approach of our π-0.5 model & further improve it with a single stage recipe. Blog: pi.website/research/knowl… Paper: pi.website/download/pi05_…
Giving history to our robot policies is crucial to solve a variety of daily tasks. However, diffusion policies get worse when adding history. 🤖 In our recent work we learn how adding an auxiliary loss that we name Past-Token Prediction (PTP) together with cached embeddings…
Humanoid robots should not be black boxes 🔒 or budget-busters 💸! Meet Berkeley Humanoid Lite! ▹ 100% open source & under $5k ▹ Prints on entry-level 3D printers—break it? fix it! ▹ Modular cycloidal-gear actuators—hack & customize towards your own need ▹ Off-the-shelf…
We made π0 “think harder”: our new Hierarchical Interactive Robot (Hi Robot) method “thinks” through complex tasks and prompts, directing π0 to break up complex tasks into basic steps, handling human feedback, and modifying tasks on the fly.
Can we prompt robots, just like we prompt language models? With hierarchy of VLA models + LLM-generated data, robots can: - reason through long-horizon tasks - respond to variety of prompts - handle situated corrections Blog post & paper: pi.website/research/hirob…