I gave a talk about certifiable perception at the research seminar at UNC Charlotte College of Computing and Informatics

Title: 

Certifiable Outlier-Robust Geometric Perception: Robots that See through the Clutter with Confidence

Abstract:

Geometric perception is the task of estimating geometric models from sensor measurements and priors. The ubiquitous existence of outliers —measurements that tell no or little information about the models to be estimated— makes it theoretically intractable to perform estimation with guaranteed optimality. Despite this theoretical intractability, safety-critical robotic applications still demand trustworthiness and performance guarantees on perception algorithms. In this talk, I present certifiable outlier-robust geometric perception, a new paradigm to design tractable algorithms that enjoy rigorous performance guarantees, i.e., they commonly return an optimal estimate with a certificate of optimality, but declare failure and provide a measure of suboptimality on worst-case instances. Particularly, I present three algorithms in the certifiable perception toolbox: (i) a pruner that uses graph theory to filter out gross outliers and boost robustness to against over 95% outliers; (ii) an estimator that leverages graduated non-convexity to compute the optimal estimate with high probability of success; and (iii) a certifier that employs sparse semidefinite programming (SDP) relaxation and a novel SDP solver to endow the estimator with an optimality certificate or escape local minima otherwise. I showcase certifiable outlier-robust perception on real robotic applications such as scan matching, satellite pose estimation, and vehicle pose and shape estimation.