pith. sign in

arxiv: 1811.08069 · v1 · pith:CVXJ4523new · submitted 2018-11-20 · 💻 cs.LG · stat.ML

Representation Learning of Pedestrian Trajectories Using Actor-Critic Sequence-to-Sequence Autoencoder

classification 💻 cs.LG stat.ML
keywords representationtrajectorylearningpedestriantrajectoriescharacteristicssequence-to-sequencespatiotemporal
0
0 comments X
read the original abstract

Representation learning of pedestrian trajectories transforms variable-length timestamp-coordinate tuples of a trajectory into a fixed-length vector representation that summarizes spatiotemporal characteristics. It is a crucial technique to connect feature-based data mining with trajectory data. Trajectory representation is a challenging problem, because both environmental constraints (e.g., wall partitions) and temporal user dynamics should be meticulously considered and accounted for. Furthermore, traditional sequence-to-sequence autoencoders using maximum log-likelihood often require dataset covering all the possible spatiotemporal characteristics to perform well. This is infeasible or impractical in reality. We propose TREP, a practical pedestrian trajectory representation learning algorithm which captures the environmental constraints and the pedestrian dynamics without the need of any training dataset. By formulating a sequence-to-sequence autoencoder with a spatial-aware objective function under the paradigm of actor-critic reinforcement learning, TREP intelligently encodes spatiotemporal characteristics of trajectories with the capability of handling diverse trajectory patterns. Extensive experiments on both synthetic and real datasets validate the high fidelity of TREP to represent trajectories.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.