Assistant CS Professor at UT Austin. Former Stanford and TUBerlin. Researching at the intersection of vision, learning and robotics 🏳️🌈
- Tweets 193
- Following 283
- Followers 2,564
- Likes 570
Very honored and humbled to receive the 2026 IROS Toshio Fukuda Young Professional Award! 🏆🤖
Grateful to all the students, collaborators, and mentors who have been part of this journey; and to the robotics community that has made it such a fun one.
Thank you, IROS! 🙏
20
6
147
4,413
Roberto retweeted
🤖 Coming to @corl_conf 2026: The first workshop on imperfect robotics data! We’ll explore how to collect, curate & use failures 💢, OOD events❓, and unexpected human behavior 🤔 - data every lab produces but rarely documents, shares, or reuses. Check out workshop.oopsie-data.com
2
5
20
7,389
Roberto retweeted
I'm incredibly excited to lead the new NSF Center for Human and Robot Co-Adaptation!
It is one of three new $30M, 5yr Centers launched under the @NSF STC program, and is led by @UTAustin , with partners @IUBloomington , @MIT , @TuftsUniversity , @UUtah , and @Yale
A new $30 million @NSF award will establish the Center for Human and Robot Co-Adaptation at UT Austin.
Led by Texas researchers, the new center will advance groundbreaking research into how humans and robots can learn to live and work together.
Another bold step forward for research at Texas. 🤘
Read more: utex.as/4zIvi3w
ALT UT to lead new $30M NSF robotics center.\n\nNew five-year award will establish the Center for Human and Robot Co-Adaptation.
ALT The center will bring together 39 researchers from six universities to study how people and robots adapt to one another over time in everyday environments.
ALT \u201CThe next leap in robotics is not just getting robots to perform more tasks,\u201D said Joydeep Biswas, an associate professor of computer science who will serve as the center\u2019s director. \n\n\u201CIt is enabling robots to understand the people around them: their needs, preferences, values and constraints, while recognizing that people also adapt their behavior when they integrate robots into their environment.\u201D
ALT The research explores how robots and people learn from each other \u2014 robots adapting to individual needs and abilities, and people discovering new ways to live more independently.
10
15
81
10,080
Roberto retweeted
Very excited to share that our CRL-VLA paper has won the outstanding paper award at the Reinforcement Learning Conference (also best paper at the ICRA RL4IL workshop)! The full list can be found at rl-conference.cc/RLC2026Awar….
This is my first time attending @RL_Conference, and RLC has already became my favorite conference (alongside CoRL). The community, the great review process, the hot takes... Everything is amazing!
Congratulations to all co-authors: @jayjshim @ChenTangMark @yoonchangsung @cranialxix @PeterStone_TX @RobobertoMM
VLA models are capable generalists. But can they continually self-improve?
Such Continual Reinforcement Learning (CRL) problems are traditionally considered very challenging.
Surprisingly, we found that with the right setup, the simplest CRL recipe can work really well!
arxiv.org/abs/2603.11653
3
11
71
5,440
Thrilled to share that I've received an NSF CAREER Award for "Dual-Axis Continual Learning for Adaptive Mobile Manipulation Skills in Household Environments"! Grateful to my students, mentors, and collaborators, and excited to build robots that learn without starting over. 🤖🎉
6
2
48
2,630
Another step in our lab's Oopsie- line of research: after OopsieVerse (our simulator with damage aware capabilities) we now focus on failures in the real world. I'm excited call-for-contributions to OopsieData, the first large dataset of robot failures! This has the potential to be a game-changer for safety in robotics. Please, consider contributing
Really excited for this initiative!
Failure data is becoming very useful, and the best part, every robot lab collects them; they're just rarely shared. OopsieData aims to change that by pooling real-world robot failures across labs, making a collective dataset for all to use! 👇
1
3
8
2,546
Roberto retweeted
1/N Long horizon, complex tasks that truly matter in everyday life are not solved problems by today’s robotics, requiring planning, object detection, object manipulation, and failure recovery.
That's why Stanford's BEHAVIOR Challenge is back for year 2! Last year, the winning solution reached only 12.4% full task success. This year, the BEHAVIOR challenge has more tasks, better evaluation, and is easier to use. 🚨
⏰ Submission deadline: 10/16/2026
📣 Winners announced: 11/04/2026
🏆 Prize pool: $11,000
22
91
531
115,344
Roberto retweeted
📢 The 5th Workshop on Mobile Manipulation and Embodied Intelligence (MOMA.v5)
@IROS2026 — Call for Papers! 🚀
This time, we are focusing on contact-rich mobile manipulation for robust real-world deployments: whole-body manipulation, compliant control, multimodal perception, contact-rich sim2real, generalizable skill learning, & more ✨
📝 Submit your work & join us! 🙌
🔗 Website: mobile-manipulation.net/even…
Deadline: August 20th
#IROS2026 #MOMA
1
6
14
1,701
Do you want to develop SAFE robots?
Today, we release OopsieVerse, our simulation framework that let you know how much damage is done in real time. Multiple damage sources: mechanical, thermal, liquid 🦾🔥💧... And many ways to use it: for control, RL, IL, VLAs... Including 32 new tasks + access/integration with Robocasa/Mujoco and B1K/Omniverse. Amazing work by @ArpitBahety, Arnav and the team to be presented at #RSS2026
This is a normal day in our lab, but don't tell our advisor! Simulation provides a way to avoid such expensive behaviors, but the consequences of actions, like fluid damage or breakage, aren't observable in sim, making it hard to train and evaluate robot policies for safety.
🧵👇
2
11
1,727
Roberto retweeted
Tell a robot “spray the plant” 🪴— how does that translate into dexterous action? It must grasp the bottle stably, aim it at the leaves, and squeeze the trigger.
Excited to share CoDex(#ICRA2026): A framework for dexterous manipulation of functional objects WITHOUT demonstrations using VLM guidance + optimization + RL!
2
13
45
4,681
Excited to share that HALO was accepted to #RSS2026. Hope to reconnect with friends and meet new ones in Sydney
Robots need to remember what they saw and did, like where they just put your car keys or when they set the water to boil. We introduce our work HALO 🧵👇
🍿🍿🍿🍿 Enjoy the robot making popcorn using HALO from scratch with kernels and a pan, beats the microwave one haha
1
7
996
Roberto retweeted
We extended the deadline to *June 22nd*! Submit your coolest and craziest (in-progress or completed) works on generalist robot safety 😎
Workshop co-organized with the great team: @ArpitBahety @kensukenk @imp_aa @RobobertoMM @ianabraha @LihanZha
Excited to announce our #RSS2026 workshop: "Rethinking What It Means to be 'Safe' for Generalist Robots"! 🛡️🤖
Have new work or videos of robot safety failures? Submit by June 12! 👇
1
5
12
2,099
I'll be giving two talks at ICRA today: 2:30pm on "Frugal Imitation Learning" (beyond telop workshop) and on 5:30pm on "Closing the Understanding Gap Between Humans and Robots" (robot learning + HRI). Come visit!
4
394
Roberto retweeted
🤖 How can robots learn long-horizon object state change tasks like mashing a banana 🥣🍌, spreading ketchup on bread 🍅🍞, or slicing a cucumber 🔪🥒?
Introducing SPARTA: object state-change manipulation via visual spatial progress 👇
🌐 vision.cs.utexas.edu/project…
2
7
29
5,016
Roberto retweeted
Don’t miss our poster at #ICRA!
June 3rd 3-4:30 WeI2I.312 and June 5th 10:45-11:45 in the Uncertainty in Open-World Robotics Workshop!
1
3
398
Roberto retweeted
Robots can’t do everything.
How can they effectively work with us?
We present MiCoBot, a flexible human-robot collaborative framework where both🧑🦱+🤖can initiate 💬verbal and🦾physical actions.
To be presented at ICRA tomorrow 6/3!
Poster 9-10:30am @ I.126
(1/8)
1
5
20
1,541
How to learn how things sound? Interacting with them! We are presenting CAVER at ICRA, a really fun work
Can you guess the object by its sound? 🔊
Humans learn to correlate sight and sound through exploration from infancy. We want robots to learn the same way.
Meet CAVER: the first Curious Audio-Visual Exploring Robot, learning about the world through interactive exploration. 🤖✨
4
804
Roberto retweeted
Excited to announce our #RSS2026 workshop: "Rethinking What It Means to be 'Safe' for Generalist Robots"! 🛡️🤖
Have new work or videos of robot safety failures? Submit by June 12! 👇
1
4
14
5,987
How do we turn a decent generalist VLA into a great multitask specialist? RL can turn experience into one fine-tuned policy. The challenge is doing it continuously as new tasks arrive: without forgetting old ones or limiting future learning.
Surprisingly simple. Check this out.
VLA models are capable generalists. But can they continually self-improve?
Such Continual Reinforcement Learning (CRL) problems are traditionally considered very challenging.
Surprisingly, we found that with the right setup, the simplest CRL recipe can work really well!
arxiv.org/abs/2603.11653
9
762