Error-Bounded Online Trajectory Simplification with Multi-Agent Reinforcement Learning
Authors:
Open Access
- 14 August 2021
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1758-1768
Abstract
Trajectory data has been widely used in various applications, including taxi services, traffic management, mobility analysis, etc. It is usually collected at a sensor's side in real time and corresponds to a sequence of sampled points. Constrained by the storage and/or network bandwidth of a sensor, it is common to simplify raw trajectory data when it is collected by dropping some sampled points. Many algorithms have been proposed for the error-bounded online trajectory simplification (EB-OTS) problem, which is to drop as many points as possible subject to that the error is bounded by an error tolerance. Nevertheless, these existing algorithms rely on pre-defined rules for decision making during the trajectory simplification process and there is no theoretical ground supporting their effectiveness. In this paper, we propose a multi-agent reinforcement learning method called MARL4TS for EB-OTS. MARL4TS involves two agents for different decision making problems during the trajectory simplification processes. Besides, MARL4TS has its objective equivalent to that of the EB-OTS problem, which provides some theoretical ground of its effectiveness. We conduct extensive experiments on real-world trajectory datasets, which verify that MARL4TS outperforms all existing algorithms in effectiveness and provides competitive efficiency.Keywords
This publication has 17 references indexed in Scilit:
- COMPRESSACM Transactions on Database Systems, 2017
- One-pass error bounded trajectory simplificationProceedings of the VLDB Endowment, 2017
- Trajectory simplificationProceedings of the VLDB Endowment, 2014
- Direction-preserving trajectory simplificationProceedings of the VLDB Endowment, 2013
- Reinforcement learning in robotics: A surveyThe International Journal of Robotics Research, 2013
- Compression of trajectory data: a comprehensive evaluation and new approachGeoInformatica, 2013
- Efficient real-time trajectory trackingThe VLDB Journal, 2011
- SQUISH2011
- On-line data reduction and the quality of history in moving objects databases2006
- On the approximation of curves by line segments using dynamic programmingCommunications of the ACM, 1961