I submitted my master's thesis to the department on Friday, May 16. It's focused on fundamental algorithms for estimating the position, orientation, and shape of objects. When available, you can download a draft here. Here's a brief outline:
Preliminaries. A review of the mathematics, including Shor's relaxation, conformal prediction, and quaternion algebra.
Certifiable Object Tracking. We propose an algorithm to track objects and estimate their shape over multiple observations. It's globally optimal in the certifiable sense. Compared to the publication, we add a world-frame motion model which is significantly faster.
Conformal Pose Uncertainty. Pose estimation with statistically valid translation and rotation bounds. We propagate conformal prediction bounds from the measurements (keypoints) to a pose uncertainty set, and efficiently bound the set using an ellipse.
Sub-Millisecond Local Pose and Shape Estimates. We rewrite the first-order optimality conditions as a nonlinear eigenproblem which can be solved in less than a millisecond using self-consistent field iteration. Solutions are local (no certificate), but can update quickly.
Some examples of conformal uncertainty sets (rotational uncertainty for fixed translation):
A video showing the central pose estimate for the "duck" object:
@misc{Coming soon!}
Master's Thesis: Optimization Techniques for Trustworthy 3D Object Understanding
Lorenzo Shaikewitz
D-Space / bibTeX
A Certifiable Algorithm for Simultaneous Shape Estimation and Object Tracking
Lorenzo Shaikewitz, Samuel Ubellacker, and Luca Carlone
RA-L / arXiv / code / video / bibTeX