Heng Yang and Luca Carlone, Certifiable Outlier-Robust Geometric Perception: Exact Semidefinite Relaxations and Scalable Global Optimization, 2021. (Code) — The paper to read about the line of research in designing certifiable and trustworthy algorithms for robot perception.
Heng Yang, Ling Liang, Luca Carlone, and Kim-Chuan Toh, An Inexact Projected Gradient Method with Rounding and Lifting by Nonlinear Programming for Solving Rank-One Semidefinite Relaxation of Polynomial Optimization, 2021. (Code) — Introduce STRIDE, the first method that can solve large-scale rank-one semidefinite relaxations of polynomial optimization problems to high accuracy, even in the presence of millions of constraints.
Jingnan Shi, Heng Yang, and Luca Carlone, Optimal Pose and Shape Estimation for Category-level 3D Object Perception, in Robotics: Science and Systems (RSS), 2021. Best Paper Award Finalist. (Spotlight Video) — Introduce PACE, a state-of-the-art optimal method for solving category-level object pose estimation such as estimating the pose of a car with unknown 3D CAD model.
Heng Yang, Chris Doran, and Jean-Jacques Slotine, Dynamical Pose Estimation, 2021. (Video) — Introduce DAMP, the first general and practical algorithm for solving a class of pose estimation problems by simulating rigid body dynamics arising from virtual springs and damping.
Heng Yang, Wei Dong, Luca Carlone, and Vladlen Koltun, Self-supervised Geometric Perception, In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2021. Oral presentation. (Code) —The first general and practical framework for learning feature descriptors without ground-truth supervision from geometric models.
Jingnan Shi, Heng Yang, and Luca Carlone, ROBIN: a Graph-Theoretic Approach to Reject Outliers in Robust Estimation using Invariants, In International Conference on Robotics and Automation (ICRA), 2021. —Boost the performance of robust solvers (RANSAC, GNC) like a charm!
Pasquale Antonante, Vasileios Tzoumas, Heng Yang, and Luca Carlone, Outlier-Robust Estimation: Hardness, Minimally-Tuned Algorithms, and Applications, IEEE Transactions on Robotics (T-RO), 2020. —The one paper to read to learn about robust estimation in robot perception.
Heng Yang and Luca Carlone, One Ring to Rule Them All: Certifiably Robust Geometric Perception with Outliers, in Conference on Neural Information Processing Systems (NeurIPS), 2020. (Video)(Code) —Beyond TEASER: we extend the success of TEASER to solve a class of robust geometric perception problems with outliers. This is the first work in literature that can certifiably solve robust geometric perception problems.
Heng Yang, A Dynamical Perspective on Point Cloud Registration, arXiv Preprint, 2020.
Heng Yang, Jingnan Shi and Luca Carlone, TEASER: Fast and Certifiable Point Cloud Registration, in IEEE Transactions on Robotics (T-RO), 2020. (Code)(Video)(Tutorial) —TEASER is robust against over 99% outlier correspondences; TEASER is certifiably correct; TEASER runs in milliseconds.
Heng Yang and Luca Carlone, In Perfect Shape: Certifiably Optimal 3D Shape Reconstruction from 2D Landmarks, In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2020. —We present Shape*, the first certifiably optimal non-minimal solver for 3D shape reconstruction from 2D landmarks in a single image, and Shape#, a robust shape reconstruction algorithm that tolerates a large amount of outliers in the 2D measurements. We demonstrate the power of Sums-of-Squares (SOS) relaxations in solving challenging geometric perception.
Heng Yang, Pasquale Antonante, Vasileios Tzoumas and Luca Carlone, Graduated Non-Convexity for Robust Spatial Perception: From Non-Minimal Solvers to Global Outlier Rejection, IEEE Robotics and Automation Letters (RA-L), 2020. (Video) Best Paper Award in Robot Vision at ICRA 2020, Best Paper Award Honorable Mention from RA-L 2020. —A general-purpose robust estimation framework called graduated non-convexity (GNC) that can be applied to any problem where a globally optimal non-minimal solver (e.g. from SDP and SOS relaxations) for the outlier-free case is available. Empirically robust againts 70-80% outliers across applications. As an alternative to RANSAC, GNC robustifies non-minimal solvers, while RANSAC robustifies minimal solvers.
Heng Yang and Luca Carlone, A Quaternion-based Certifiably Optimal Solution to the Wahba Problem with Outliers, International Conference on Computer Vision (ICCV), 2019. Oral presentation (4% acceptance rate) (Video) —Introducing QUASAR (QUAternion-based Semidefinite relAxation for Robust alignment), a quaternion-based SDP relaxation that is tight and returns the certifiable global optima to the Wahba problem (aka rotation search) in the presence of large noise and 95% outliers.
Heng Yang and Luca Carlone, A Polynomial-time Solution for Robust Registration with Extreme Outlier Rates, Robotics: Science and Systems (RSS), 2019. Spotlight talk + Poster (Video) (Poster)—Introducing TEASER (Truncated least squares Estimation And SEmidefinite Relaxation), a robust point cloud registration algorithm that is robust against 99% outliers.
- Heng Yang, Carolina Amador Carrascal, Hua Xie, Vijay Shamdasani and Brian W Anthony, Design and Experimental Validation of Miniature External Mechanical Vibrators Towards Clinical Ultrasound Shear Wave Elastography. 2018 IEEE International Ultrasonics Symposium (IUS). — Enabling low-cost, miniature and portable ultrasound shear wave elastography imaging with external mechanical vibration.
- Felix Van De Donk, Heng Yang and Brian W Anthony, Miniaturization of external mechanical vibration for shear wave elastography imaging. 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). — Preliminary concept design of miniature external mechanical vibration device for portable ultrasound shear wave elastography imaging.
- Heng Yang, Man M Nguyen, Sheng-Wen Huang, Vijay Shamdasani, Hua Xie and Brian W Anthony, Simulation, design, and implementation of external mechanical vibration for ultrasound shear wave elastography. 2017 IEEE International Ultrasonics Symposium (IUS). — We propose to induce shear waves using a multi-point-source external mechanical vibration concept. Simulation and experimental prototype show promising results on liver phantoms.
- Julian Chacon-Castano, Daniel R Rathbone, Rachel Hoffman, Heng Yang, Dimitrios Pantazis, Jason Yang, Erik Hornberger and Nevan C Hanumara, Music and the brain-design of an MEG compatible piano. 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). — A piano design by optical fiber encoder that can be used in MEG room to study human brian activity induced by playing music.
- Yiwei Zhao, Jianing Wu, Heng Yang and Shaoze Yan, The morphology and reciprocation movement of Honeybee's hairy tongue for nectar uptake. Journal of Bionic Engineering. 2016.
- Jianing Wu, Heng Yang and Shaoze Yan, Energy saving strategies of honeybees in dipping nectar. Scientific reports, 2015. — Through observing how honeybees drink, we get engineering insights of designing energy-saving micropumps.
- Zelin Linghu, Chenjia Zhao, Heng Yang and Xinqian Zheng, Beetle wing folding facilitated by micro-protrusions on the body surface: a case of Allomyrina dichotoma. Science bulletin, 2015.
- Heng Yang, Jianing Wu and Shaoze Yan, Effects of erectable glossal hairs on a honeybee's nectar-drinking strategy. Applied Physics Letters, 2014. — A mathematical model with delicate experimental observation that explains a very interesting phenomenon in nature: why all the flowers pollinated by honeybees have nectar concentration 35%?
[Last edit: 07/16/2021]