Journal
IEEE TRANSACTIONS ON ROBOTICS
Volume 39, Issue 2, Pages 1496-1508Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TRO.2022.3208503
Keywords
Optimization; Cameras; Cost function; Robots; State estimation; Robot vision systems; Tracking; Depth-inertial odometry (DIO); evolution strategy; simultaneous localization and mapping; state estimation
Categories
Ask authors/readers for more resources
This paper focuses on the problem of high-dimensional nonlinear state estimation in inertial-aided navigation systems. The authors propose a method based on random optimization and active subspace to tackle the challenges posed by large interframe transformations. The method efficiently explores the state space and achieves accurate and robust depth inertial odometry.
High-dimensional nonlinear state estimation is at the heart of inertial-aided navigation systems (INS). Traditional methods usually rely on good initialization and find difficulty in handling large interframe transformations due to fast camera motion. We opt to tackle these challenges by solving the depth inertial odometry (DIO) problem with random optimization. To address the exponentially increased amount of candidate states sampled for the high-dimensional state space, we propose a highly efficient variant of random optimization based on the idea of active subspace. Our method identifies the active dimensions, which contribute most significantly to the decrease of the cost function in each iteration, and samples candidate states only within the corresponding subspace. This allows us to efficiently explore the 18D state space of DIO and achieve good optimality by sampling and evaluating only thousands of candidate states. Experiments show that our method attains highly robust and accurate DIO under fast camera motions and low light conditions, without needing a slow-motion warm-up for initialization.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available