Compressed Gaussian Estimation under Low Precision Numerical Representation
Open Access
Abstract
This paper introduces a novel method for computationally efficient Gaussian estimation of high-dimensional problems such as Simultaneous Localization and Mapping (SLAM) processes and for treating certain Stochastic Partial Differential Equations (SPDEs). The authors have presented the Generalized Compressed Kalman Filter (GCKF) framework to reduce the computational complexity of the filters by partitioning the state vector into local and global and compressing the global state updates. The compressed state update, however, still suffers from high computational costs, making it challenging to implement on embedded processors. We propose a low-precision numerical representation for the global filter, such as 16-bit integer or 32-bit single-precision formats for the global covariance matrix, instead of the expensive double-precision, floating-point representation (64 bits). This truncation can inevitably cause filter instability since the truncated covariance matrix becomes overoptimistic or even turns to be an invalid covariance matrix. We introduce a Minimal Covariance Inflation (MCI) method to make the filter consistent while minimizing the truncation errors. Simulation-based experiments results show significant improvement of the proposed method with a reduction in the processing time with minimal loss of accuracy.Keywords
All Related Versions
Funding Information
- NAUSS (NAUSS-23-R23)
This publication has 18 references indexed in Scilit:
- The Generalized Compressed Kalman FilterRobotica, 2016
- Compressed Unscented Kalman filter-based SLAM2014
- An Iterative EnKF for Strongly Nonlinear SystemsMonthly Weather Review, 2012
- Convergence properties of a decentralized Kalman filter2008
- Distributed Kalman filtering for sensor networks2007
- Marginalized particle filters for mixed linear/nonlinear state-space modelsIEEE Transactions on Signal Processing, 2005
- The Ensemble Kalman Filter: theoretical formulation and practical implementationOcean Dynamics, 2003
- Solving computational and memory requirements of feature-based simultaneous localization and mapping algorithmsIEEE Transactions on Robotics and Automation, 2003
- Optimization of the simultaneous localization and map-building algorithm for real-time implementationIEEE Transactions on Robotics and Automation, 2001
- A singular evolutive extended Kalman filter for data assimilation in oceanographyJournal of Marine Systems, 1998