Accepted to ICRA 2025! 🎉 We introduce MI-HGNN, a morphology-informed heterogeneous graph neural network built directly from a robot’s URDF. By embedding robot morphological constraints, MI-HGNN significantly enhances model efficiency and learning performance. Applied to contact estimation for legged robots, it outperforms the SOTA by 8.4% while using only 0.21% of the parameters. It can also be seamlessly applied to other types of multi-body dynamical systems. Check it out for more details. - project: - paper: - code: Led by @DanielCButter, with Sandilya Sai Garimella, Nai-Jen Cheng, @ganlumomo.

It is just so sad that the #NeurIPS2024 main conference ended with such a racist remark by a faculty when talking about ethics. How ironic! I also want to commend the Chinese student who spoke up right on spot. She was respectful, decent, and courageous. Her response was exemplary: she began by acknowledging the speaker’s efforts, then gave the speaker an opportunity to clarify (though, regrettably, the speaker’s reply only reinforced her bias), and ultimately called attention to the inappropriate racial bias and offered constructive suggestions. Thank you for speaking out!

I'm happy to announce that we will organize the LocoLearn Workshop at @corl_conf 2024 in Munich! If you are interested in learning, active perception, or bioinspired locomotion, join us on Saturday, November 9th, 2024.

The Lunar Lab at @GeorgiaTech is actively looking for multiple highly motivated Ph.D. students to join us in Fall 2024. We are interested in robot perception, robot learning, and autonomous navigation. Please repost to share widely! Detailed information:

.@RoboJackets Calling all #Robotics Students! Get your research viewed by faculty and industry 👀👀! Register to present a poster at the IRIM Fall Robotics #Research #Symposium Come to present, stay to enjoy the meet-up after 🤖👩‍🔬👨‍🔬🥳 Deets: