IDEAS Seminar: “Equivariant Neural Inertial Odometry”
October 17 at 11:00 AM - 12:00 PM
Abstract:
In this talk, we introduce a new class of problems related to integrating inertial measurements obtained from an IMU that play a significant role in navigation combined with visual data. While there have been tremendous technological advances in the precision of instrumentation, integrating acceleration and angular velocity still suffers from drift in the displacement estimates. Neural networks have come to the rescue in estimating displacement and the associated uncertainty covariance. However, such networks do not consider the physical roto-reflective symmetries inherent in IMU data, leading to the need to memorize the same priors for every possible motion direction, which hinders generalization. In this work, we characterize these symmetries and show that the IMU data and the resulting displacement and covariance transform equivariantly when rotated around the gravity vector and reflected with respect to arbitrary
planes parallel to gravity. We propose a network for predicting an equivariant gravity-aligned frame from equivariant vectors and invariant scalars derived from IMU data, leveraging expressive linear and non-linear layers tailored to commute with the underlying symmetry transformation. Such a canonical frame can precede existing architectures that are end-to-end or filter-based. We will include an introduction to the inertial filtering problem and we will present
results in real-world datasets.
Zoom link: https://caltech.zoom.us/j/88141815847?pwd=ayPBbwoDE91IWysv1P4Oxp6zbamrSQ.1
Prof. Kostas Daniilidis & Yinshuang Xu, PhD student
Kostas Daniilidis is the Ruth Yalom Stone Professor of Computer and
Information Science at the University of Pennsylvania where he has been faculty since 1998. He is an IEEE Fellow. He obtained his undergraduate degree in Electrical Engineering from the National Technical University of Athens, 1986, and his PhD in Computer Science from the University of Karlsruhe, 1992, under the supervision of Hans-Hellmut Nagel. He received the Best Conference Paper Award at ICRA 2017. He co-chaired ECCV 2010 and 3DPVT 2006. His most cited works have been on event based vision, equivariant learning, 3D human pose, and hand-eye calibration.
Yinshuang Xu is currently pursuing her fifth year of PhD studies in Computer and Information Science at the University of Pennsylvania, where she is advised by Prof. Kostas Daniilidis. She previously graduated from Shanghai Jiao Tong University with a bachelor’s degree in Engineering Mechanics and later received her master’s in Robotics from the University of Pennsylvania. Her research interests include equivariance and geometric deep learning, with a focus on their use in computer vision and machine learning.