NeRFs and Gaussian Splats excel at static 3D modeling but robots work in dynamic, unpredictable environments. POGS (Persistent Object Gaussian Splats) combines semantic, visual, and grouping features that can be queried with language and spatially updated as environments change

Checkout this cool #ICRA25 paper led by Justin Yu and Kush Hari showing distilling foundational features into a 3D Gaussian Splat is useful for pose tracking and manipulation in dynamic environments! Code available: berkeleyautomation.github.io/POGS/ Toyota Research Institute (TRI) AUTOLab

our new system trains humanoid robots using data from cell phone videos, enabling skills such as climbing stairs and sitting on chairs in a single policy (w/ Hongsuk Benjamin Choi Junyi Zhang David McAllister)

Excited to introduce PyRoki ("Python Robot Kinematics"): easier IK, trajectory optimization, motion retargeting... with an open-source toolkit on both CPU and GPU

Tired of teleoperating your robots? We built a way to scale robot datasets without teleop, dynamic simulation, or even robot hardware. Just one smartphone scan + one human hand demo video → thousands of diverse robot trajectories. Trainable by diffusion policy and VLA models

Next challenge: scalable learning of robot manipulation skills from truly in-the-wild videos, such as YouTube!

Interested in collecting robot training data without robots in the loop? 🦾 Check out this cool new approach that uses a single mobile device scan and a human demo video to generate diverse data for training diffusion and VLA manipulation policies. 🚀 Great work by Max Fu

Robots that navigate grocery stores with semantic 3D maps created by language-augmented gaussian splats

People who are really serious about robot learning should make their own robot hardware.

It's been over 2 years since we first released GELLO. We’ve updated the project with 3 new GELLOs to control the YAM, ARX and similar arms! Enables easy data collection for policy training (ie finetuned Pi0!). All open source contributions from 劉添慶 and hmahesh007!

Great talk by Justin Yu presenting the Real2Render2Real paper at CoRL in Seoul! A great collaboration between UC Berkeley and Toyota Research Institute (TRI). The code for this paper is now available, check it out here: github.com/uynitsuj/real2… Toyota Research Institute (TRI) AUTOLab Ken Goldberg

Phew! Humans slightly ahead (but not for long!)

🚀 Introducing SARM: Stage-Aware Reward Modeling for Long-Horizon Robot Manipulation Robots struggle with tasks like folding a crumpled T-shirt—long, contact-rich, and hard to label. We propose a scalable reward modeling framework to fix that. 1/n

Happy to announce that we have open sourced the code for Real2Render2Real! Let's see how far we can scale synthetic datagen fidelity for robot manipulation! github.com/uynitsuj/real2…

Marques Brownlee 1X NEO review when? 👀

Some of my favorites on reward modeling, RL, and robust VLA from the community: arxiv.org/abs/2505.10911 from Jesse Zhang arxiv.org/abs/2510.14830 from Kun Lei arxiv.org/abs/2509.25358 from Qianzhong Chen and pi0.6 from Physical Intelligence today: physicalintelligence.company/blog/pistar06