Very prod to be part of the Khoury Story Khoury College of Computer Sciences! youtu.be/B9g2yhHs5Wg?si…

Awesome talks from great speakers and panelist Prof. Gregory Chirikjian, Robert Platt, Georgia Chalvatzaki, Katerina Fragkiadaki, Jeannette Bohg, Lawson Wong, and amazing posters from participants today at the Geometric and Algebraic Structure in Robot Learning workshop #RSS2024

12/ 📄 Correct, Incorrect and Extrinsic Equivariance? ✍️ Dian Wang, Jung Yeon Park, Xupeng Zhu, Neel Sortur, Mingxi Jia, Guanang Su, Lawson L.S. Wong, Robert Platt, Robin Walters 🔗 gram-blogposts.github.io/blog/2024/extr…

🔍 Equivariant model success relies on symmetric ground truth functions. This post explains correct, incorrect, and extrinsic equivariance, showing how extrinsic equivariance can enhance performance and how symmetry mismatches affect learning, with many cool animations! 🦆

We have released the YouTube recording of our #RSS2024 workshop on "Geometric and Algebraic Structure in Robot Learning"! 🎥Youtube: youtube.com/playlist?list=… 🏠Webpage: sites.google.com/view/gas-rl-rs…

We recently launched umi-data.github.io as a community-driven effort to pool UMI-related data together. 🦾 If you are using a UMI-like system, please consider adding your data here. 🤩🤝 No dataset is too small; small data WILL add up!📈

Join us on Monday October. 14th at 2pm (UTC+4) in #IROS2024 Workshop on Equivariant Robotics. A great lineup of keynote speakers will discuss how symmetry penetrates each and every subfield of robotics. Website and Zoom Link: equirob2024.github.io

📢 NeurReps Speaker Series goes to Massachusetts Institute of Technology (MIT) 🇺🇸 🎙️ Robin Walters & Dian Wang (Northeastern U.) 🏷️ Pushing the Limits of Equivariant Neural Networks ⏰ October 28, 11 AM EST 📍 Room 32-G575 Massachusetts Institute of Technology (MIT) 🔗 Zoom link: shorturl.at/kO3Ja Don't miss it! #NeurReps2024

🚀 Diffusion Policy is great, but how can we achieve category-level generalization? 🤖 Our answer: use explicit 3D and semantic representation to enable category-level generalization capabilities in our recent work GenDP. 🔗 robopil.github.io/GenDP/ #CoRL2024 👇 Threads (1/9)

Check out our new grasping work, OrbitGrasp! It achieved a 98% grasping success rate by learning the SE(3)-equivariant grasp quality distribution using spherical harmonics. I’ll be at #CoRL2024 to present this paper.

📢New Release📢 We are excited to announce **robosuite v1.5**, supporting more robots, teleoperation interfaces, and controllers ➕ real-time ray tracing rendering! We continue our commitment to building open-source research software. Try it out at github.com/ARISE-Initiati…

Does equivariance matter when you have lots of data and compute? In a new paper with Sönke Behrends, Pim de Haan, and Taco Cohen, we collect some evidence. arxiv.org/abs/2410.23179 1/7

📹 Missed our NeurReps Speaker Series talk at Massachusetts Institute of Technology (MIT) last week? Watch Robin Walters & Dian Wang's presentation on "Pushing the Limits of Equivariant Neural Networks" now on YouTube! 🔗 youtu.be/MU6wpz_8kEA #NeurReps2024

Had a great time at the symposium at TUDarmstadt yesterday! Thanks Snehal Jauhri @ CoRL 2024 Firas Al-Hafez and Georgia Chalvatzaki so much for organizing, it’s a putty that I missed the group photo in the end!

#CoRL2024 Looking forward to presenting Equivariant Diffusion Policy at Oral Session 1 on Nov 6 and Poster Session 2 on Nov 7! Also checkout equidiff.github.io for the paper and code.

#CoRL2024 Humans can imagine the outcome of an action, maybe robots can do the same? In imagination policy, we achieve this through generating a target scene point cloud then use SVM to calculate actions. Haojie Huang will present this in poster session 4#36, I’ll be there too!

Honored to receive my first best paper nomination from Conference on Robot Learning! Had such a great time at #CoRL2024, huge thanks to the organizing committee and all my co-authors: Steve, David, Tarik Kelestemur @CoRL (Hiring), Haojie Huang, Haibo Zhao, Mark, JW, Robin Walters, Robert Platt!

While demoing our tactile sensor at #CoRL2024 Conference on Robot Learning, I received many inquiries about how to get one yourself. Great news— Binghao Huang has shared a complete guide for sensor fabrication and PCB assembly! Key highlights: 1. The entire build process takes just 30 minutes.

I gave an Early Career Keynote at CoRL 2024 on Robot Learning from Embodied Human Data Recording: youtube.com/watch?v=H-a748… Slides: faculty.cc.gatech.edu/~danfei/corl24… Extended summary thread 1/N