ASPIRE-VINS: Adaptive Spline-based Visual-inertial Navigation System With Robust 3D Measurement Residuals

2026-08-13

AI Summary

This work addresses the limitations of conventional visual-inertial navigation systems, which often suffer from insufficient flexibility or parameter redundancy when handling observations with arbitrary timestamps and dynamic motion. To overcome these challenges, the authors propose a continuous-time visual-inertial navigation framework that employs motion-adaptive trajectory modeling. This framework integrates adaptive knot placement (AKP), multi-resolution splines (MRS), and 3D measurement-space residuals (3D-MSR) to enable local optimization in the tangent space while enforcing measurement consistency constraints. The resulting approach significantly enhances estimation accuracy and robustness in dynamic environments, achieving trajectory errors that are either superior or comparable to those of state-of-the-art baseline methods across a variety of motion profiles and perceptual conditions.

Abstract

Visual-inertial navigation systems estimate six-degree-of-freedom motion by fusing visual and inertial data. Modern discrete-time methods with IMU preintegration provide strong accuracy and efficiency, but keyframe-based representations can be less flexible when residuals must be evaluated at arbitrary timestamps or when motion-dependent temporal resolution is needed. Continuous-time splines address this issue by representing the trajectory as a smooth temporal function, but uniformly spaced knots can under-represent rapid dynamics or over-parameterize static intervals. This letter proposes ASPIRE-VINS, a continuous-time VINS framework that combines adaptive knot placement (AKP), multi-resolution splines (MRS), and 3D measurement-space residuals (3D-MSR). AKP allocates knots according to local motion variation, MRS adds bounded local refinement in tangent space, and 3D-MSR provides bearing consistency by aligning transformed features with calibrated observation rays in 3D measurement space. Experiments show that ASPIRE-VINS achieves competitive or lower trajectory errors than the compared baselines, demonstrating the effectiveness of motion-adaptive continuous-time trajectory modeling under diverse motion and sensing conditions.

Problem

• visual-inertial navigation
• continuous-time trajectory
• adaptive knot placement
• motion-dependent resolution
• 3D measurement residuals

Innovation

• adaptive knot placement
• multi-resolution splines
• 3D measurement-space residuals
• continuous-time VINS
• motion-adaptive trajectory modeling