Physical spline for denoising object trajectory data by combining splines, ML feature regression and model knowledge
This work addresses the need for accurate trajectory data as reference inputs in machine learning models, particularly for vehicle dynamics, but it appears incremental as it builds on existing spline and regularization techniques.
The paper tackles the problem of estimating dynamic driving states from noisy trajectory data by combining splines, machine learning feature regression, and model knowledge, producing refined trajectories with kinematic consistency and orientation constraints. It demonstrates effectiveness with both complete and partial observations, implemented as a configurable Python library.
This article presents a method for estimating the dynamic driving states (position, velocity, acceleration and heading) from noisy measurement data. The proposed approach is effective with both complete and partial observations, producing refined trajectory signals with kinematic consistency, ensuring that velocity is the integral of acceleration and position is the integral of velocity. Additionally, the method accounts for the constraint that vehicles can only move in the direction of their orientation. The method is implemented as a configurable python library that also enables trajectory estimation solely based on position data. Regularization is applied to prevent extreme state variations. A key application is enhancing recorded trajectory data for use as reference inputs in machine learning models. At the end, the article presents the results of the method along with a comparison to ground truth data.