Yuheng Qiu

I am a Ph.D. candidate at Carnegie Mellon University, advised by Sebastian Scherer and affiliated with the AirLab. I received my B.Eng. degree in Computer Science and Engineering from the Chinese University of Hong Kong, Shenzhen in 2019.
I have an innate passion for advancing spatial AI to enhance robot autonomy. One specific area I focus on is creating generalized learning-based SLAM systems. Currently, engineers need to manually tune hyperparameters when applying these systems to new platforms, datasets, or sensors. I believe data-driven methods and uncertainty modeling are key to solving this problem. I hope that one day, SLAM will be fully automated—so much so that SLAM engineers like me will become unnecessary. (And I’ll happily “fire” myself when that day comes! 😂)
News
May 22, 2025 | 🥇 MAC-VO won the ICRA 2025 Best Conference Paper Award and Best Paper Award on Robot Perception. |
May 19, 2025 | 🖥️ MAC-VO is selected as ICRA 2025 Best Paper Finalist. Join our talk with live demo [1] [2] on May 20 Atlanta! |
Jul 06, 2024 | 📝 Prior to today, many papers were accepted, while more were rejected. |
Publications
2025
- Imperative MPC: An End-to-End Self-Supervised Learning with Differentiable MPC for UAV Attitude Control
- MAC-VO: Metrics-aware Covariance for Learning-based Stereo Visual Odometry
2024
2023
- PyPose: A library for robot learning with physics-based optimization