Peiqi Liu

We just released RUKA, a $1300 humanoid hand that is 3D-printable, strong, precise, and fully open sourced!

The key technical breakthrough here is that we can control joints and fingertips of the robot **without joint encoders**. All we need here is self-supervised data collection and learning.

When life gives you lemons, you pick them up.

(trained with robotutilitymodels.com)

The robot behaviors shown below are trained without any teleop, sim2real, genai, or motion planning. Simply show the robot a few examples of doing the task yourself, and our new method, called Point Policy, spits out a robot-compatible policy!

We just released AnySense, an iPhone app for effortless data acquisition and streaming for robotics. We leverage Apple’s development frameworks to record and stream:

1. RGBD + Pose data
2. Audio from the mic or custom contact microphones
3. Seamless Bluetooth integration for external sensors

Stretch Community News - February 2025 — Hello Robot Gazebo Harmonic, Stretch AI, Dynamic memory, and more!

What's new in the Stretch community this month?

❄️ Gazebo Harmonic
❄️ Dynamic semantic maps for open-vocabulary tasks
❄️ Natural-language narration of robot experiences
❄️ Implicit human-robot communication

And more! Follow the link below for more details:

hello-robot.com/community-up...

DynaMem: Online Dynamic Spatio-Semantic Memory for Open World Mobile Manipulation DynaMem is an OVMM system adapting a spatio semantic memory to dynamically changing environments.

DynaMem is now fully refactored & integrated into Stretch AI repo!
Try it out: github.com/hello-robot/...
Project page: dynamem.github.io

We all want a home robot that can actually help us out. Why can't I ask my robot "where did I leave my water bottle" and get a good answer?

In Graph-EQA, we build a 3d memory as the robot explores, using that memory to make decisions.

saumyasaxena.github.io/grapheqa/

A look at the future: chatting with my robot via Discord to ask it to find something in my house.

This uses an LLM to understand what the human wants and generate a task plan, then builds an open-vocab 3d scene representation to find and pick up objects

I'd like to introduce what I've been working at @hellorobot.bsky.social: Stretch AI, a set of open-source tools for language-guided autonomy, exploration, navigation, and learning from demonstration.

Check it out: github.com/hello-robot/...

Thread ->

New paper! We show that by using keypoint-based image representation, robot policies become robust to different object types and background changes.

We call this method Prescriptive Point Priors for robot Policies or P3-PO in short. Full project is here: point-priors.github.io

Modern policy architectures are unnecessarily complex. In our #NeurIPS2024 project called BAKU, we focus on what really matters for good policy learning.

BAKU is modular, language-conditioned, compatible with multiple sensor streams & action multi-modality, and importantly fully open-source!

Since we are nearing the end of the year, I'll revisit some of our work I'm most excited about from the last year and maybe a sneak peek of what we are up to next.

To start of, Robot Utility Models, which enables zero-shot deployment. In the video below, the robot hasnt seen these doors before.