# Data-Driven Approaches for Modelling Target Behaviour

arXiv: https://arxiv.org/abs/2410.10538 · HTML: https://mlsanity.com/paper/2410.10538/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 33 references that are in the map.
- First posted on arXiv 14 Oct 2024.

## Builds on (most cited first, 7 of 7)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Long Short-Term Memory Kalman Filters:Recurrent Neural Estimators for Pose Regularization](https://mlsanity.com/paper/1708.01885/) (2017)
- [Neural Enhanced Belief Propagation for Multiobject Tracking](https://mlsanity.com/paper/2212.08340/) (2022)
- [Fitting a Kalman Smoother to Data](https://mlsanity.com/paper/1910.08615/) (2019)
- [The Fragility of Noise Estimation in Kalman Filter: Optimization Can Handle Model-Misspecification](https://mlsanity.com/paper/2104.02372/) (2021)
- [A Gaussian Process Regression based Dynamical Models Learning Algorithm for Target Tracking](https://mlsanity.com/paper/2211.14162/) (2022)
- [Learning IMM Filter Parameters from Measurements using Gradient Descent](https://mlsanity.com/paper/2307.06618/) (2023)

## Abstract (arXiv)

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.