Are you a #computervision PhD student close to graduating? Consider participating in the #CVPR2024 Doctoral Consortium event. See link for eligibility details and application: cvpr.thecvf.com/Conferences/20…

will it nerf? yep ✅ congrats to Tim Brooks Bill Peebles and colleagues, absolutely incredible results!!

Our lab's work was featured in local news coverage of Penn's new BSE degree in AI: fox29.com/news/universit… Including cool live demos of Jason Ma's latest trick, a quadruped dog walking on a yoga ball!

After two years, it is my pleasure to introduce “DROID: A Large-Scale In-the-Wild Robot Manipulation Dataset” DROID is the most diverse robotic interaction dataset ever released, including 385 hours of data collected across 564 diverse scenes in real-world households and offices

I was skeptical that we'd get our quadruped to turn circus performer and walk on a yoga ball. Turns out it can (mostly)! Check out Jason's thread for how he together with our MS students Hungju Wang and undergrads Will Liang and Sam Wang managed to train this skill, and others!

People need to carefully sense & process lots of info when we're novices at a skill, e.g. driving/tying shoelaces. Having learned it, we can do it "with our eyes closed." Ed has built an integrative framework for robots to also benefit from privileged training-time sensing!

You enjoyed #ICRA2024 as much as we did? I may have another opportunity to meet and exchange ideas for you: the Conference on Robot Learning (#CoRL) will take place in Munich in November this year! corl.org/home ** Deadline for papers: June 6, 2024**

Congratulations to the ROBO class of 2024! #GRASP #GRASPLab #ROBOGrad #ROBO24

We are organizing a workshop on task specification at #RSS2024! Consider submitting your latest work to our workshop and attending!

Had fun speaking with Alok and showing off our group's latest and greatest work for this podcast episode on the rise of robot learning. Have a listen! Work led by Jason Ma, Aurora Qian, Junyao Shi.

How can large language models be used in robotics? Dinesh Jayaraman joins our “Babbage” podcast to explain how AI is helping make robots more capable econ.st/3RscW2l 🎧

Congratulations to my colleague Rajeev Alur on winning the 2024 Knuth Prize for foundational contributions to CS! sigact.org/prizes/knuth/c…

Check out the list of Invited Talks at Michigan AI 2024 Symposium! 🤖✨ Thrilled that Joyce Chai (Michigan AI), Dinesh Jayaraman (UPenn), Guanya Shi (CMU Robotics Institute), and Bernadette Bucher (@Umich) join us to share their insights on the future of #AI. ai.engin.umich.edu/events/2024-ai…

Introducing Eurekaverse 🌎, a path toward training robots in infinite simulated worlds! Eurekaverse is a framework for automatic environment and curriculum design using LLMs. This iterative method creates useful environments designed to progressively challenge the policy during

Excited to share the recordings from Michigan AI Symposium 2024 - Session 2. Revisit your favorite talks or explore what you missed—anytime, anywhere! 🗣️Gabe Margolis Gabe Margolis Dinesh Jayaraman Ilija Radosavovic Ilija Radosavovic youtu.be/uutQ1lMado0

IEEE RAS conferences like IEEE ICRA not always fun to attend and I often wonder whether to go despite seeing many friends there. This year, Tamim Asfour+Serena Ivaldi showed in both #ICRA@40 + IEEE-RAS Int. Conf. on Humanoid Robots (HUMANOIDS) 2024 that we can do much better! Here are some key lessons:

To Singapore for ICLR'25! A demonstration of the awesome power of simple retrieval-style biases (RAG-style) for generalizing across many wildly different robotics / game-playing tasks, with a single "generalist" agent.

A new demonstration of autonomous iterative design guided by a VLM (a la Eureka, DrEureka, Eurekaverse), this time for actual physical design of tools for manipulation. My personal tagline for this paper is: if you can't perform a task well, blame (and improve) your tools! ;)

Vibe testing for robots. My students had a lot of fun helping with this effort!

Excited to share our recent progress on adapting pretrained VLAs to imbue them with in-context learning capabilities!