🤖 AI Summary
To address the insufficient robustness and sharp accuracy degradation of motion trajectory classification models under post-disaster distribution shifts, this paper proposes a neuro-symbolic, rule-driven framework. The method introduces the first explainable error-correction paradigm for trajectory classification, integrating a domain-knowledge-based rule engine, error-pattern modeling, and a distribution-shift-aware correction algorithm to enable real-time detection and rectification of prediction errors. It guarantees formal verifiability and achieves zero-shot out-of-distribution generalization—overcoming the adaptability bottleneck of purely deep learning approaches in dynamic environments. Experiments demonstrate an error detection F1-score of 0.984 and an 8.51% improvement in zero-shot out-of-distribution accuracy over baseline models, establishing significant gains in both reliability and generalization under distributional shift.
📝 Abstract
Classification of movement trajectories has many applications in transportation and is a key component for large-scale movement trajectory generation and anomaly detection which has key safety applications in the aftermath of a disaster or other external shock. However, the current state-of-the-art (SOTA) are based on supervised deep learning - which leads to challenges when the distribution of trajectories changes due to such a shock. We provide a neuro-symbolic rule-based framework to conduct error correction and detection of these models to integrate into our movement trajectory platform. We provide a suite of experiments on several recent SOTA models where we show highly accurate error detection, the ability to improve accuracy with a changing test distribution, and accuracy improvement for the base use case in addition to a suite of theoretical properties that informed algorithm development. Specifically, we show an F1 scores for predicting errors of up to 0.984, significant performance increase for out-of distribution accuracy (8.51% improvement over SOTA for zero-shot accuracy), and accuracy improvement over the SOTA model.