Ruihan (Multy) Xu 徐睿涵

Band practice at SMTD,

University of Michigan,

Ann Arbor, MI 48105

I am an undergratue student at the University of Michigan, pursuing degree of Computer Science focusing in Robotics with Math minor.

I feel fortuntate to work in CURLY lab directed by Prof. Maani Ghaffari we aims to discover methods for computational reasoning and perception that will enable robots to effectively assist people in common human environments. Besides, I also work closely with Prof. Chad Jenkins in The Lab for Progress.

My research interests mainly lie in robot perception for better scene to inform decision-making and planning. Especially, I’m interested in the intersection of probability theory and deep learning, aiming to bring exlainable component into neural network through quantifiable uncertainty.

“君子和而不同” – “Scholars seek harmony in diversity”. Therefore, I’m excited to make friends with diversified interest and background, form collabration, and pursue great ideas. Feel free to contact me through email.

news

Oct 03, 2024	Our work Latent BKI has been submitted to RA-L for review.
Jul 10, 2024	Our work Single-View 3D Reconstruction via SO(2)-Equivariant Gaussian Sculpting Networks has been accepted to RSS workshop on Geometric and Algebraic Structure in Robot Learning!
Jan 15, 2024	Our work Stein Variational Belief Propagation for Multi-Robot Coordination is accepted to RA-L!
Oct 15, 2023	One paper submitted and is under review!

selected publications

arXiv

Latent BKI: Open-Dictionary Continuous Mapping in Visual-Language Latent Spaces with Quantifiable Uncertainty

Joey Wilson*, Ruihan Xu*, Yile Sun, and 4 more authors

2024

Bib PDF

@misc{wilson2024latentbkiopendictionarycontinuous,
  title = {Latent BKI: Open-Dictionary Continuous Mapping in Visual-Language Latent Spaces with Quantifiable Uncertainty},
  author = {Wilson*, Joey and Xu*, Ruihan and Sun, Yile and Ewen, Parker and Zhu, Minghan and Barton, Kira and Ghaffari, Maani},
  year = {2024},
  eprint = {2410.11783},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
  url = {https://arxiv.org/abs/2410.11783},
}

RSS Workshop

Single-View 3D Reconstruction via SO(2)-Equivariant Gaussian Sculpting Networks

Ruihan Xu, Anthony Opipari, Joshua Mah, and 4 more authors

In RSS 2024 Workshop on Geometric and Algebraic Structure in Robot Learning , 2024

Bib PDF Video

@inproceedings{xu2024soequivariant,
  title = {Single-View 3D Reconstruction via {SO}(2)-Equivariant Gaussian Sculpting Networks},
  author = {Xu, Ruihan and Opipari, Anthony and Mah, Joshua and Lewis, Stanley Robert and Zhang, Haoran and Guo, Hanzhe and Jenkins, Odest Chadwicke},
  booktitle = {RSS 2024 Workshop on Geometric and Algebraic Structure in Robot Learning},
  year = {2024},
  url = {https://arxiv.org/abs/2409.07245},
}

RA-L

Stein Variational Belief Propagation for Multi-Robot Coordination

Jana Pavlasek, Joshua Jing Zhi Mah, Ruihan Xu, and 2 more authors

IEEE Robotics and Automation Letters, 2024

Bib PDF Video Website

@article{10465621,
  author = {Pavlasek, Jana and Mah, Joshua Jing Zhi and Xu, Ruihan and Jenkins, Odest Chadwicke and Ramos, Fabio},
  journal = {IEEE Robotics and Automation Letters},
  title = {Stein Variational Belief Propagation for Multi-Robot Coordination},
  year = {2024},
  volume = {9},
  number = {5},
  pages = {4194-4201},
  keywords = {Robots;Robot kinematics;Belief propagation;Trajectory;Planning;Collision avoidance;Service robots;Distributed robot systems;probabilistic inference},
  doi = {10.1109/LRA.2024.3375708},
}