Equivariant Visual Odometry in the Wild

Robert Mahony, Pieter van Goor, Mina Henein, Ryan Pike, Jun Zhang, and Yonhon Ng

2020 59th IEEE conference on decision and control (CDC), 2020

Abstract

Visual Odometry is a core problem in robotics. Recent advances in equivariant systems theory, and the discovery of symmetries for the visual odometry problem, has provided a new perspective that is leading to new algorithms. This paper provides an overview of the geometry of visual odometry problem and an algorithm that results from this perspective.