Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Schlangen, Isabel, Brandenburger, André, Sun, Mengwei, Hopgood, James R.
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2410.10538
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912072499986432
author Schlangen, Isabel
Brandenburger, André
Sun, Mengwei
Hopgood, James R.
author_facet Schlangen, Isabel
Brandenburger, André
Sun, Mengwei
Hopgood, James R.
contents The performance of tracking algorithms strongly depends on the chosen model assumptions regarding the target dynamics. If there is a strong mismatch between the chosen model and the true object motion, the track quality may be poor or the track is easily lost. Still, the true dynamics might not be known a priori or it is too complex to be expressed in a tractable mathematical formulation. This paper provides a comparative study between three different methods that use machine learning to describe the underlying object motion based on training data. The first method builds on Gaussian Processes (GPs) for predicting the object motion, the second learns the parameters of an Interacting Multiple Model (IMM) filter and the third uses a Long Short-Term Memory (LSTM) network as a motion model. All methods are compared against an Extended Kalman Filter (EKF) with an analytic motion model as a benchmark and their respective strengths are highlighted in one simulated and two real-world scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2410_10538
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Data-Driven Approaches for Modelling Target Behaviour
Schlangen, Isabel
Brandenburger, André
Sun, Mengwei
Hopgood, James R.
Machine Learning
Methodology
The performance of tracking algorithms strongly depends on the chosen model assumptions regarding the target dynamics. If there is a strong mismatch between the chosen model and the true object motion, the track quality may be poor or the track is easily lost. Still, the true dynamics might not be known a priori or it is too complex to be expressed in a tractable mathematical formulation. This paper provides a comparative study between three different methods that use machine learning to describe the underlying object motion based on training data. The first method builds on Gaussian Processes (GPs) for predicting the object motion, the second learns the parameters of an Interacting Multiple Model (IMM) filter and the third uses a Long Short-Term Memory (LSTM) network as a motion model. All methods are compared against an Extended Kalman Filter (EKF) with an analytic motion model as a benchmark and their respective strengths are highlighted in one simulated and two real-world scenarios.
title Data-Driven Approaches for Modelling Target Behaviour
topic Machine Learning
Methodology
url https://arxiv.org/abs/2410.10538