PathletRL++: Optimizing Trajectory Pathlet Extraction and Dictionary Formation via Reinforcement Learning
Gian Alix, Arian Haghparast, Manos Papagelis
TL;DR
The paper tackles the challenge of representing large-scale trajectory data with a compact pathlet dictionary by adopting a bottom-up, edge-disjoint pathlet merging strategy. It introduces PathletRL, a Deep Q-Network–based framework that learns a utility function for merging unit-length pathlets into longer, more informative ones, achieving dramatic memory reductions and high trajectory representability. To further improve performance, PathletRL++ adds richer state representations and enhanced reward shaping, yielding smaller dictionaries with faster convergence while preserving reconstruction quality. The approach outperforms state-of-the-art top-down methods, reducing dictionary size by up to 65.8% and enabling reconstruction of about 85% of trajectories with half of the dictionary, while delivering memory savings up to ~24,000×. Overall, the work offers a scalable, learning-driven solution for trajectory compression, route planning, and offline analysis, with open-source tooling to support reproducibility.
Abstract
Advances in tracking technologies have spurred the rapid growth of large-scale trajectory data. Building a compact collection of pathlets, referred to as a trajectory pathlet dictionary, is essential for supporting mobility-related applications. Existing methods typically adopt a top-down approach, generating numerous candidate pathlets and selecting a subset, leading to high memory usage and redundant storage from overlapping pathlets. To overcome these limitations, we propose a bottom-up strategy that incrementally merges basic pathlets to build the dictionary, reducing memory requirements by up to 24,000 times compared to baseline methods. The approach begins with unit-length pathlets and iteratively merges them while optimizing utility, which is defined using newly introduced metrics of trajectory loss and representability. We develop a deep reinforcement learning framework, PathletRL, which utilizes Deep Q-Networks (DQN) to approximate the utility function, resulting in a compact and efficient pathlet dictionary. Experiments on both synthetic and real-world datasets demonstrate that our method outperforms state-of-the-art techniques, reducing the size of the constructed dictionary by up to 65.8%. Additionally, our results show that only half of the dictionary pathlets are needed to reconstruct 85% of the original trajectory data. Building on PathletRL, we introduce PathletRL++, which extends the original model by incorporating a richer state representation and an improved reward function to optimize decision-making during pathlet merging. These enhancements enable the agent to gain a more nuanced understanding of the environment, leading to higher-quality pathlet dictionaries. PathletRL++ achieves even greater dictionary size reduction, surpassing the performance of PathletRL, while maintaining high trajectory representability.