Mitigating Error Accumulation in Continuous Navigation via Memory-Augmented Kalman Filtering
This addresses state drift in UAV navigation, which is a domain-specific problem, but the approach appears incremental as it builds on classical control theory and existing VLN models.
The paper tackles error accumulation in continuous navigation for UAVs by proposing NeuroKalman, a memory-augmented Kalman filtering framework that decouples navigation into prior prediction and likelihood correction, and it demonstrates clear outperformance over baselines on the TravelUAV benchmark with only 10% fine-tuning data.
Continuous navigation in complex environments is critical for Unmanned Aerial Vehicle (UAV). However, the existing Vision-Language Navigation (VLN) models follow the dead-reckoning, which iteratively updates its position for the next waypoint prediction, and subsequently construct the complete trajectory. Then, such stepwise manner will inevitably lead to accumulated errors of position over time, resulting in misalignment between internal belief and objective coordinates, which is known as "state drift" and ultimately compromises the full trajectory prediction. Drawing inspiration from classical control theory, we propose to correct for errors by formulating such sequential prediction as a recursive Bayesian state estimation problem. In this paper, we design NeuroKalman, a novel framework that decouples navigation into two complementary processes: a Prior Prediction, based on motion dynamics and a Likelihood Correction, from historical observation. We first mathematically associate Kernel Density Estimation of the measurement likelihood with the attention-based retrieval mechanism, which then allows the system to rectify the latent representation using retrieved historical anchors without gradient updates. Comprehensive experiments on TravelUAV benchmark demonstrate that, with only 10% of the training data fine-tuning, our method clearly outperforms strong baselines and regulates drift accumulation.