TrackDiffuser: Nearly Model-Free Bayesian Filtering with Diffusion Model
This provides a practical solution for real-world state estimation problems where perfect models and prior knowledge are unavailable, though it appears incremental as it builds on existing diffusion model techniques.
The paper tackles the challenge of state estimation in domains like autonomous driving and quantum control by addressing limitations of classical Bayesian filtering, which struggles with inaccurate state space models and requires extensive noise knowledge. The result is TrackDiffuser, a generative framework that reformulates Bayesian filtering as a conditional diffusion model, substantially outperforming classical and hybrid methods in non-linear scenarios with non-Gaussian noises.
State estimation remains a fundamental challenge across numerous domains, from autonomous driving, aircraft tracking to quantum system control. Although Bayesian filtering has been the cornerstone solution, its classical model-based paradigm faces two major limitations: it struggles with inaccurate state space model (SSM) and requires extensive prior knowledge of noise characteristics. We present TrackDiffuser, a generative framework addressing both challenges by reformulating Bayesian filtering as a conditional diffusion model. Our approach implicitly learns system dynamics from data to mitigate the effects of inaccurate SSM, while simultaneously circumventing the need for explicit measurement models and noise priors by establishing a direct relationship between measurements and states. Through an implicit predict-and-update mechanism, TrackDiffuser preserves the interpretability advantage of traditional model-based filtering methods. Extensive experiments demonstrate that our framework substantially outperforms both classical and contemporary hybrid methods, especially in challenging non-linear scenarios involving non-Gaussian noises. Notably, TrackDiffuser exhibits remarkable robustness to SSM inaccuracies, offering a practical solution for real-world state estimation problems where perfect models and prior knowledge are unavailable.