@srigopal Yep! You can fit the graph on your training demos (and optimize hyperparams for matching subtask annotations). Then, as long as the representations/policy doesn’t change, you should be able to check rollouts against the demos you fit the graph on!
🤖 Understanding what exactly happens during your robot policy deployments is key to improving it. But interpreting raw rollouts is hard because they lack structure.
Introducing Behavior Graphs: turn many rollouts into an interpretable graph of what the policy is doing.
🧵👇
Furthermore, Behavior Graphs are strong progress estimators without any network training: across 43 datasets, they improve rank correlation with true progress by 22.9% and reduce mean absolute error by 53.5% over the strongest baseline, VLM-based and learned estimators included.
Humanoid retargeting and IK in microseconds [no GPU required]
Orders of magnitude speedups, with perfect contact handling: accelerate your robots today at https://t.co/58MzJm0h9U
w/ @drmapavone
Can an agent learn a pool table’s physics by playing on it? 🎱
While agents can close the visual gap, the difference between real world and sim dynamics remains significant. For CoRL late breaking🤠, we let an agent take real shots to try and close this real2sim dynamics gap: https://t.co/g12jkuuB4n
Very fun short project with @XilunZhangXZ@MatthewFoutter@Luis_A_Pabon@drmapavone
Having trouble keeping your humanoid robots under control? Luckily, our latest #CoRL2026 paper (w/ @drmapavone) keeps them in check: enforcing constraints never seen during training, while minimally interfering with the underlying RL policy
https://t.co/KSCVAwjkcF
This is a fantastic set of resources if you’re looking to learn about autonomous robots! It’s been great to TA this course at Stanford this quarter and see the students develop and deploy some of the methods covered. Now, the course materials are open to everyone!
Ever wondered what it’s like to learn robot autonomy @Stanford? Now you can.
Today, we’re opening up the robot autonomy teaching materials that my collaborators and I have been developing over the past several years—for anyone, anywhere, completely free.
At the heart of this effort is Principles of Robot Autonomy (PoRA), a textbook inspired by the Stanford robot autonomy course series I’ve been teaching since 2017.
Robot autonomy has evolved from a research discipline into a technology deployed in the real world. Building capable autonomous systems requires more than understanding individual algorithms: it requires understanding how perception, state estimation, planning, control, and learning work together in a complete autonomy stack.
That’s what we set out to teach with PoRA: bringing classical robotics and modern AI together in one coherent framework, grounded in both theory and practice.
Coming soon in print from Cambridge University Press, Principles of Robot Autonomy is also freely available online and comes with a comprehensive collection of open educational resources:
📖 Textbook, https://t.co/wRvXr4VCIP — Foundations of robot autonomy, from classical methods to modern AI-based approaches.
🎥 Video lectures, https://t.co/Yw3P1aGzBG Lectures from my Stanford courses on robot autonomy and on optimal and learning-based control.
💻 Interactive exercises, https://t.co/kyPV8AnyB3 — Hands-on Python implementations and Jupyter notebooks.
📝 Teaching materials, https://t.co/a6MqqYAcEN — Lecture slides and resources for instructors.
🌐 Explore all PoRA resources, https://t.co/oAsjrMJxZT — Including Ask the Book, an AI study assistant integrated throughout the textbook to answer questions, explain derivations, and connect ideas across chapters.
📣 Read the Stanford announcement: https://t.co/f6BBBZZQmg
Our goal is simple: to make high-quality education in robot autonomy accessible to students, researchers, engineers, educators, and anyone curious about how autonomous robotic systems work.
I believe that sharing knowledge is fundamental to the mission of a university. Autonomous robotics—and Physical AI more broadly—are among the defining technological frontiers of our time. We want to help more people understand these technologies, build with them, and advance the field.
A huge thank you to my co-authors, @DanieleGammelli, Joseph Lorenzetti, @katielulula, and @GioeleZardini, and to everyone who helped bring this project to life.
Explore the resources, use them in your own learning or teaching, and please share them with anyone who might find them useful!
#Robotics #PhysicalAI #ArtificialIntelligence #AutonomousSystems #Education
@Stanford@StanfordEng@StanfordAILab@StanfordHAI
Robots need memory 🧠: remembering where your favorite cup is or which drawer is locked.
How can a robot remember across large spaces, interactions, & fine-grained detail?
Introducing MessyMem (accepted to #CoRL2026 🚀): Learning-from-Doing Memory for Mobile Manipulation. 🧵
🤔 Can VLA models teach themselves the best way to reason?
We introduce R&B-EnCoRe which is a self-improving pretraining cycle for reasoning VLAs to propose and self-discover what embodiment-specific reasoning looks like.
🔗 https://t.co/kamclCDAbU
📃 https://t.co/4Q9jlxj3e5
How can robots with different end-effectors efficiently learn from each other?
In our latest work, we propose a new approach for learning imitation learning policies across end-effectors that enables efficient cross-embodiment skill transfer through two steps:
🧵
TLDR: we found a scalable way to align the action spaces of different end-effectors. Cross-embodied diffusion policies trained with our method using latent actions enable skill-transfer and multi-robot control 🦾