Learning Vehicle Trajectory Uncertainty

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.

References in corpus (2)

• A Hybrid Model and Learning-Based Adaptive Navigation Filter
• BeamsNet: A data-driven Approach Enhancing Doppler Velocity Log Measurements for Autonomous Underwater Vehicle Navigation

Cited by in corpus (7)

• A Hybrid Model and Learning-Based Adaptive Navigation Filter
• Adaptive Kalman-Informed Transformer
• VIO-DualProNet: Visual-Inertial Odometry with Learning Based Process Noise Covariance
• Data-Driven Meets Navigation: Concepts, Models, and Experimental Validation
• DeepUKF-VIN: Adaptively-tuned Deep Unscented Kalman Filter for 3D Visual-Inertial Navigation based on IMU-Vision-Net
• Learning Position From Vehicle Vibration Using an Inertial Measurement Unit
• Deep Learning for Inertial Sensor Alignment