Spatiotemporal Models for Motion Planning in Human Populated Environments

Home / Publications / 2017 / Spatiotemporal Models for Motion Planning in Human Populated Environments

Tomáš Vintr, Sergi Molina, Grzegorz Cielniak, Tom Duckett, and Tomáš Krajník
Spatiotemporal Models for Motion Planning in Human Populated Environments
Proceedings of the Student Conference on Planning in Artificial Intelligence and Robotics (PAIR)

Abstract

In this paper we present an effective spatiotemporal model for motion planning computed using a novel representation known as the temporary warp space-hypertime continuum. Such a model is suitable for robots that are expected to be helpful to humans in their natural environments. This method allows to capture natural periodicities of human behavior by adding additional time dimensions. The model created thus represents the temporal structure of the human habits within a given space and can be analysed using regular analytical methods. We visualize the results on a real-world dataset using heatmaps.

@inproceedings{vintr2017pair,
  author={Vintr, Tom\'{a}\v{s} and Molina Mellado, Sergi and Cielniak, Grzegorz and Duckett, Tom and Krajn\'{i}k, Tom\'{a}\v{s}},
  title={Spatiotemporal Models for Motion Planning in Human Populated Environments},
  booktitle={Student Conference on Planning in Artificial Intelligence and Robotics (PAIR)},
  date = sep~{17}, 
  address = {Žilina, Slovakia},
  year=2017,
  note = {organized by Czech Technical University in Prague, Faculty of Electrical Engineering},
}