Learning Vehicle Trajectory Uncertainty

TL;DR

This paper introduces a hybrid adaptive Kalman filter that leverages recurrent neural networks to learn vehicle kinematic features, improving trajectory estimation accuracy under uncertainty in real-time scenarios.

Contribution

It presents a novel hybrid approach combining neural networks with Kalman filtering to adaptively learn process noise covariance for vehicle tracking.

Findings

Outperforms traditional adaptive Kalman filters on Oxford RobotCar dataset.

Effectively learns process noise covariance in real-time.

Improves vehicle trajectory estimation accuracy.

Abstract

A novel approach for vehicle tracking using a hybrid adaptive Kalman filter is proposed. The filter utilizes recurrent neural networks to learn the vehicle's geometrical and kinematic features, which are then used in a supervised learning model to determine the actual process noise covariance in the Kalman framework. This approach addresses the limitations of traditional linear Kalman filters, which can suffer from degraded performance due to uncertainty in the vehicle kinematic trajectory modeling. Our method is evaluated and compared to other adaptive filters using the Oxford RobotCar dataset, and has shown to be effective in accurately determining the process noise covariance in real-time scenarios. Overall, this approach can be implemented in other estimation problems to improve performance.