Intent-aware long-term prediction of pedestrian motion

Vasiliy Karasev; Alper Ayvaci; Bernd Heisele; Stefano Soatto

ICRA 2016156 citations

Intent-aware long-term prediction of pedestrian motion

Vasiliy Karasev, Alper Ayvaci, Bernd Heisele, Stefano Soatto

Abstract

We present a method to predict long-term motion of pedestrians, modeling their behavior as jump-Markov processes with their goal a hidden variable. Assuming approximately rational behavior, and incorporating environmental constraints and biases, including time-varying ones imposed by traffic lights, we model intent as a policy in a Markov decision process framework. We infer pedestrian state using a Rao-Blackwellized filter, and intent by planning according to a stochastic policy, reflecting individual preferences in aiming at the same goal.

BibTeX

@inproceedings{icra2016_intentawarelongt,
  title = {Intent-aware long-term prediction of pedestrian motion},
  author = {Vasiliy Karasev and Alper Ayvaci and Bernd Heisele and Stefano Soatto},
  booktitle = {ICRA 2016},
  year = {2016}
}