Trajectory Simplification with Reinforcement Learning

Trajectory data is used in various applications including traffic analysis, logistics, and mobility services. It is usually collected continuously by sensors and accumulated at a server resulting in big volume. A common practice is to conduct trajectory simplification which is to drop some points of a trajectory when they are being collected (online mode) and/or after they are accumulated (batch mode). Existing algorithms usually involve some decision making tasks (e.g., deciding which point to drop), for which, some human-crafted rules are used. In this paper, we propose to learn a policy for the decision making tasks via reinforcement learning (RL) and develop trajectory simplification methods based on the learned policy. Compared with existing algorithms, our RL-based methods are data-driven and can adapt to different dynamics underlying the problem. We conduct extensive experiments to verify that our RL-based methods compute simplified trajectories with smaller errors while running comparably fast (and faster in the batch mode) compared with existing methods.