no code implementations • 30 Nov 2022 • Yuxuan Chen, Timothy D. Barfoot
Visual localization is the task of estimating camera pose in a known scene, which is an essential problem in robotics and computer vision.
no code implementations • 22 Feb 2021 • David J. Yoon, Haowei Zhang, Mona Gridseth, Hugues Thomas, Timothy D. Barfoot
Though the framework is general to any form of parameter learning and sensor modality, we demonstrate application to feature and uncertainty learning with a deep network for 3D lidar odometry.
Variational Inference Robotics
no code implementations • 10 Feb 2021 • Mollie Bianchi, Timothy D. Barfoot
This trained autoencoder is used to compress a real UAV image, which is then compared to the precollected, nearby, autoencoded GE images using an inner-product kernel.
no code implementations • 13 Jan 2021 • Benjamin Congram, Timothy D. Barfoot
Adding additional absolute sensors such as Global Navigation Satellite Systems (GNSS) has the potential to expand the domain of Visual Teach and Repeat to environments where the ability to visually localize is not guaranteed.
2 code implementations • 10 Dec 2020 • Hugues Thomas, Ben Agro, Mona Gridseth, Jian Zhang, Timothy D. Barfoot
We provide insights into our network predictions and show that our approach can also improve the performances of common localization techniques.
no code implementations • 14 May 2020 • Timothy D. Barfoot, Gabriele M. T. D'Eleuterio
The goal is to find an approximate probability density function (PDF) from a chosen family that is in some sense 'closest' to the full Bayesian posterior.
no code implementations • 21 Mar 2020 • Jeremy N. Wong, David J. Yoon, Angela P. Schoellig, Timothy D. Barfoot
Our contribution is to additionally learn parameters of our system models (which may be difficult to choose in practice) within the ESGVI framework.
no code implementations • 27 Jan 2020 • Timothy D. Barfoot
This short note reviews so-called Natural Gradient Descent (NGD) for multivariate Gaussians.
no code implementations • 9 Nov 2019 • Timothy D. Barfoot, James R. Forbes, David Yoon
We present a Gaussian Variational Inference (GVI) technique that can be applied to large-scale nonlinear batch state estimation problems.
no code implementations • 19 Sep 2018 • David J. Yoon, Tim Y. Tang, Timothy D. Barfoot
This paper presents a model-free, setting-independent method for online detection of dynamic objects in 3D lidar data.
no code implementations • 22 May 2014 • Jonathan D. Gammell, Siddhartha S. Srinivasa, Timothy D. Barfoot
In this paper, we present Batch Informed Trees (BIT*), a planning algorithm based on unifying graph- and sampling-based planning techniques.
1 code implementation • 8 Apr 2014 • Jonathan D. Gammell, Siddhartha S. Srinivasa, Timothy D. Barfoot
We present the algorithm as a simple modification to RRT* that could be further extended by more advanced path-planning algorithms.