NOCT: Nonlinear Observability with Constraints and Time Offset

TL;DR

This paper introduces a method to analyze the observability of nonlinear affine control systems with constraints and time offsets, extending classical approaches and validating findings through visual inertial odometry applications.

Contribution

It presents a procedure to convert constrained nonlinear models into standard forms suitable for classic observability analysis, specifically addressing constraints and time offsets.

Findings

Unobservable variables under degenerate motion match previous linearized VIO results.

Extended observability analysis for time offset beyond prior studies.

Validated findings through simulation experiments.

Abstract

Nonlinear systems of affine control inputs overarch many sensor fusion instances. Analyzing whether a state variable in such a nonlinear system can be estimated (i.e., observability) informs better estimator design. Among the research on local observability of nonlinear systems, approaches based on differential geometry have attracted much attention for the solid theoretic foundation and suitability to automated deduction. Such approaches usually work with a system model of unconstrained control inputs and assume that the control inputs and observation outputs are timestamped by the same clock. To our knowledge, it has not been shown how to conduct the observability analysis with additional constraints enforced on the system's observations or control inputs. To this end, we propose procedures to convert a system model of affine control inputs with linear constraints into a constraint-free standard model which is apt to be analyzed by the classic observability analysis procedure. Then, the whole analysis procedure is illustrated by applying to the well-studied visual inertial odometry (VIO) system which estimates the camera-IMU relative pose and time offset. The findings about unobservable variables under degenerate motion concur with those obtained with linearized VIO systems in other studies, whereas the findings about observability of time offset extend those in previous studies. These findings are further validated by simulation.