Goal-Oriented Pedestrian Motion Prediction

Jingyuan Wu, Johannes Ruenz, Hendrik Berkemeyer, Liza Dixon, Matthias Althoff

Research output: Contribution to journalArticlepeer-review

Abstract

Forecasting the motion of others in shared spaces is a key for intelligent agents to operate safely and smoothly. We present an approach for probabilistic prediction of pedestrian motion incorporating various context cues. Our approach is based on goal-oriented prediction, yielding interpretable results for the predicted pedestrian intention, even without the prior knowledge of goal positions. By using Markov chains, the resulting probability distribution is deterministic—a beneficial property for motion planning or risk assessment in automated and assisted driving. Our approach outperforms a physics-based approach and improves over state-of-the-art approaches by reducing standard deviations of prediction errors and improving robustness against realistic, noisy measurements.

Original languageEnglish
Pages (from-to)1-17
Number of pages17
JournalIEEE Transactions on Intelligent Transportation Systems
DOIs
StateAccepted/In press - 2023

Keywords

  • Behavioral sciences
  • Markov processes
  • Markov processes
  • Mathematical models
  • Pedestrians
  • Planning
  • Trajectory
  • Vehicle dynamics
  • motion planning
  • pedestrian motion prediction
  • probabilistic model
  • road safety

Fingerprint

Dive into the research topics of 'Goal-Oriented Pedestrian Motion Prediction'. Together they form a unique fingerprint.

Cite this