MobiWave: Dispatch-Oriented Graph Wavelets and Drift-Guided Selective Optimization for Autonomous Fleet Rebalancing

2026-07-27

AI Summary

This work addresses the challenges in autonomous vehicle fleet rebalancing caused by the entanglement of regional and local traffic patterns, which obscures effective dispatching routes, and by environmental drift that leads to policy degradation. To tackle these issues, the authors propose a multi-scale graph wavelet representation combined with a drift-guided hierarchical optimization mechanism. By leveraging graph spectral decoupling through wavelet-based state representations, the approach mitigates state aliasing, while a dispatch-weighted spectral drift detection module enables selective, fast-slow layered policy updates. This facilitates efficient policy transfer and optimization under resource constraints. Experimental results on both real-world and simulated datasets demonstrate that the proposed method significantly outperforms existing approaches, achieving higher dispatching rewards while maintaining service quality and safety constraints.

Abstract

Autonomous fleets enable mobility platforms to coordinate idle vehicles directly, making fleet-wide rebalancing possible. However, two obstacles limit reliable deployment: overlapping regional and local traffic patterns can hide roads that remain useful for dispatch, and mobility drift can make a trained policy unreliable. Existing spatial aggregation mixes these patterns, while updating all parameters from limited recent data is costly and can damage stable knowledge. We propose \name, a framework that connects a dispatch-oriented multi-scale graph wavelet module with Drift-Guided Layer-Selective Optimization (DGLS). The first module addresses the representation challenge by separating graph-frequency patterns and weighting each scale according to its value for demand prediction and feasible rebalancing. DGLS addresses the adaptation challenge by measuring Dispatch-weighted Spectral Drift, selecting affected layers within a resource budget, and separating short shocks from persistent changes through a drift-aware fast--slow update. Candidate validation further rejects updates that fail to improve held-out dispatch reward without worsening monitored service or safety constraints. Experiments on both real-world datasets and simluated environments demonstrate the effectiveness of \name\ in comparing with state-of-the-art methods. The source code and datasets are available at https://anonymous.4open.science/r/MobiWave-40F8/.

Problem

• autonomous fleet rebalancing
• traffic pattern overlap
• mobility drift
• spatial representation
• policy reliability

Innovation

• graph wavelets
• selective optimization
• spectral drift
• autonomous fleet rebalancing
• multi-scale representation