Get Started
Research questionHow can visual–inertial navigation filters maintain consistency without expensive non-block-diagonal covariance operations?Filter coordinate choices affect whether unobservable directions remain consistent, while the Jacobians needed for that consistency can make covariance operations computationally expensive.
Computer Vision
Robotics
Latest papersRecent research connected to this question, newest first.Equivariant Filter Transformations for Consistent and Efficient Visual--Inertial NavigationThe source concerns equivariant filters for visual–inertial navigation, including transformations between local error states, consistency through state-independent unobservable subspaces, and implementations that exploit simpler block-diagonal Jacobians. Evidence comes from Monte Carlo simulations and real-world experiments.research paper · Sep 2, 2026
Related questions
How can fixed 3D Gaussian-splatting reconstructions support valid, traversable, closed-loop visual-navigation evaluation?How can camera-controlled video generation preserve spatial consistency over long horizons despite noisy 3D memory?How can vision-only BEV perception remain accurate while meeting real-time constraints on production hardware?How can indoor robots prevent glare-corrupted RGB-D measurements from creating phantom obstacles in navigation costmaps?
Home
Topics
Search
Library