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

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.

[1]  Stan Matwin,et al.  TrajectoryNet: an embedded GPS trajectory representation for point-based classification using recurrent neural networks , 2017, CASCON.

[2]  Yu Zheng,et al.  Trajectory Data Mining , 2015, ACM Trans. Intell. Syst. Technol..

[3]  Nitish Srivastava,et al.  Unsupervised Learning of Video Representations using LSTMs , 2015, ICML.

[4]  Qiang Gao,et al.  Trajectory-User Linking via Variational AutoEncoder , 2018, IJCAI.

[5]  Mao Ye,et al.  Mining GPS Data for Trajectory Recommendation , 2014, PAKDD.

[6]  Pengpeng Zhao,et al.  LC-RNN: A Deep Learning Model for Traffic Speed Prediction , 2018, IJCAI.

[7]  Joelle Pineau,et al.  An Actor-Critic Algorithm for Sequence Prediction , 2016, ICLR.

[8]  Agathoniki Trigoni,et al.  Lightweight map matching for indoor localisation using conditional random fields , 2014, IPSN-14 Proceedings of the 13th International Symposium on Information Processing in Sensor Networks.

[9]  Kuldip K. Paliwal,et al.  Bidirectional recurrent neural networks , 1997, IEEE Trans. Signal Process..

[10]  Wang-Chien Lee,et al.  Semantic trajectory mining for location prediction , 2011, GIS.

[11]  Jae-Gil Lee,et al.  Mining Discriminative Patterns for Classifying Trajectories on Road Networks , 2011, IEEE Transactions on Knowledge and Data Engineering.

[12]  Ranga Raju Vatsavai,et al.  Spatiotemporal data mining in the era of big spatial data: algorithms and applications , 2012, BigSpatial '12.

[13]  Jure Leskovec,et al.  node2vec: Scalable Feature Learning for Networks , 2016, KDD.

[14]  Qiang Gao,et al.  Identifying Human Mobility via Trajectory Embeddings , 2017, IJCAI.

[15]  Ling Liu,et al.  A Systematic Approach to Clustering Whole Trajectories of Mobile Objects in Road Networks , 2017, IEEE Transactions on Knowledge and Data Engineering.

[16]  Tom Schaul,et al.  Dueling Network Architectures for Deep Reinforcement Learning , 2015, ICML.

[17]  Charu C. Aggarwal,et al.  You Are How You Drive: Peer and Temporal-Aware Representation Learning for Driving Behavior Analysis , 2018, KDD.

[18]  Yuki Endo,et al.  Classifying spatial trajectories using representation learning , 2016, International Journal of Data Science and Analytics.

[19]  Weiwei Sun,et al.  Modeling Trajectories with Recurrent Neural Networks , 2017, IJCAI.

[20]  Chao Zhang,et al.  Trajectory clustering via deep representation learning , 2017, 2017 International Joint Conference on Neural Networks (IJCNN).

[21]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[22]  Philip S. Yu,et al.  Transportation mode detection using mobile phones and GIS information , 2011, GIS.

[23]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[25]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[26]  Takayuki Kanda,et al.  Person Tracking in Large Public Spaces Using 3-D Range Sensors , 2013, IEEE Transactions on Human-Machine Systems.