arXiv cs.LG
· Papers
Population-Aware Physics-Informed Neural Particle Flow for Robust Spacecraft Bayesian Navigation
arXiv:2606.10959v2 Announce Type: replace Abstract: Spacecraft navigation often requires Bayesian inference from sparse nonlinear measurements that produce curved, multimodal, or geometrically constrained posterior distributions. Physics-informed neural particle flow (PINPF) addresses such problems by learning a determ