CS PhD @Stanford🌲 | @UCBerkeley alum. Robot learning & embodied AI
Joined November 2018
- Tweets85
- Following313
- Followers1K
- Likes1.4K
Ria Doshi retweeted
In language models, turning a generative model into a critic is simple: pass in the output and prompt for a score. Robot policies can't do this - they output physical actions & there's no built-in vocabulary to predict scores.
So when it comes to RL on robot policies, we typically train a separate critic from sparse rewards - blind to everything the policy learned from the actions in the pretraining data.
We think this has it backwards - can a critic learn from those actions the way the policy does? (1/n)
Ria Doshi retweeted
Precise assembly is an important benchmark for robotics. Standard industrial automation fails to generalize, but robot learning struggles with contacts.
In this work, we extract force signals from proprioception and generalize well beyond the training distribution. Check it out!
Every robot already carries contact sensors: its own joints. When a robot touches something, its joints drift slightly off their commands, and the encoders pick it up. Legged robots and humanoids already leverage this signal to walk blind - but is it enough for blind precise assembly?
We find that it is! Our policies can insert pegs, mesh gears, and thread nuts using only the robot's joint positions - no camera, no tactile, and no object poses. And the peg policy works zero-shot in the real world! 🧵
w/ my amazing co-first author @younghyo_park, and advised by @kushalk_ and @pulkitology.
Ria Doshi retweeted
Want to know how well agents can really control robots directly?
In RoboARCade, we systematically evaluate and diagnose frontier agents controlling robots directly using tens of thousands of dollars’ worth of agent trajectories. RoboARCade contains diverse, precise, and long-horizon tasks. Paper, code, assets and every trace are out today. roboarcade.org
Ria Doshi retweeted
Mobile manipulation policies can break from base pose errors of just a few cm, which are common after navigation. Can we get pose generalization without additional demos? Introducing MobileVISTA: collect demos at one base pose, get a policy that works from many 🧵👇
Website: sdwistreich.github.io/mobile…
Paper: arxiv.org/abs/2610.07511
Ria Doshi retweeted
Human fingers move in coordinated patterns. Can those patterns help robots explore?
Excited to share EigenDEXplore! 🤖✋
Key idea: add exploration noise along directions learned from human hand motion, while leaving robots free to discover motions of their own
See @harshgupta's 🧵
Ria Doshi retweeted
Task and motion planning (TAMP) excels at multi-step, semantic, and geometric reasoning. VLAs excel at deformable object manipulation, which TAMP can't do. Can one VLA do both?
DATAFARM fine-tunes VLAs on TAMP demos aligned to the pre-training distribution.
(1/9)
Ria Doshi retweeted
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. 🧵
Ria Doshi retweeted
Excited to share our work on a model for mapping molecules to olfactory receptors to perception, out today! Check out the link in thread ⬇️
Out today in Cell Systems: the final version of our work on biologically-inspired models for predicting how molecules smell!
With @SeyoneC and @jdthamores
Ria Doshi retweeted
Why do Vision-Language-Action (VLA) models still struggle with contact-rich manipulation? 🤖
Excited to share our new paper: Demystifying When and Why VLAs Fail in Contact-Rich Tasks and How to Fix Them. 🧵 (1/8)
Such a meaningful application of home robotics. So inspired by @marionlepert always, go check out her awesome work, OpenDerm!
Catching skin cancer early is a home robotics problem.
Melanoma is highly treatable when detected early, yet today’s screening process depends heavily on patients noticing tiny changes across their entire skin surface. This requires patients to solve a near-impossible visual-memory and registration problem.
I built OpenDerm, an open-source 4-DOF robot that captures high-resolution images of the skin and uses them to reconstruct and track the skin surface in 3D over time.
The best way to make skin screening truly routine is to bring it into the home. OpenDerm shows that inexpensive robotic skin imaging is possible, but the path to scale is not a dedicated screening robot in every household—it is to make skin screening one of the many useful things a general-purpose home robot can do.
Read more about why I built OpenDerm and how it works here:
Blog: marionlepert.github.io/blog/…
Project: openderm.github.io/
Great time chatting about CHORUS & multi-robot collab on RoboPapers with @leto__jean :)
Thanks for having us on the pod 😁 @chris_j_paxton @DJiafei @micoolcho
Many tasks cannot be completed by one robot alone. But coordinating multiple robots performing complex manipulation tasks is very difficult. Many solutions rely on complicated centralized control, which tends towards bespoke methods that do not scale well with team size.
Enter CHORUS by @riadoshi21, @leto__jean, and team. They train a single VLA to control multiple, diverse robots, given only local observations and identifying information. This allows robots to collaborate on tasks like using a tape measure, handing over a book, or lifting a laundry basket.
To learn more, watch Episode #93 of Robopapers now, with @micoolcho, @DJiafei, and @chris_j_paxton!
Ria Doshi retweeted
Full episode dropping soon!
Geeking out with @riadoshi21 @leto__jean on CHORUS: Decentralized Multi-Embodiment Collaboration with One VLA Policy chorus-model.github.io/
Co-hosted by @micoolcho @DJiafei
Ria Doshi retweeted
Introducing Real-time RL.
In the real world, time isn't free. The environment keeps "moving" even when you're computing your next action.
We show how RL agents can learn to adaptively think in real-time games.
1/🧵
Ria Doshi retweeted
How can generalist policies adapt to new challenges at deployment using skills they already have?
We optimize VLA *prompt inputs* with reinforcement learning, enabling efficient real-robot adaptation on complex tasks where existing methods struggle. 🧵
semantic-action-rl.github.io
Ria Doshi retweeted
Seeing multiple, mobile robots collaborate on manipulation tasks was my dream since I started at Stanford.
@riadoshi21 made it happen.
CHORUS is a single decentralized VLA policy whose architecture stays fixed regardless of team size.
