Real-Time Predictive Modeling and Robust Avoidance of Pedestrians with Uncertain, Changing Intentions

  title={Real-Time Predictive Modeling and Robust Avoidance of Pedestrians with Uncertain, Changing Intentions},
  author={Sarah Ferguson and Brandon Luders and Robert C. Grande and J. How},
  • Sarah Ferguson, Brandon Luders, +1 author J. How
  • Published in WAFR 2014
  • Computer Science, Engineering
  • To plan safe trajectories in urban environments, autonomous vehicles must be able to quickly assess the future intentions of dynamic agents. Pedestrians are particularly challenging to model, as their motion patterns are often uncertain and/or unknown a priori. This paper presents a novel changepoint detection and clustering algorithm that, when coupled with offline unsupervised learning of a Gaussian process mixture model (DPGP), enables quick detection of changes in intent and online learning… CONTINUE READING
    SILA: An Incremental Learning Approach for Pedestrian Trajectory Prediction
    Context-Aware Pedestrian Motion Prediction In Urban Intersections
    • 15
    • PDF
    Robust sampling-based motion planning for autonomous vehicles in uncertain environments
    • 8
    Human motion trajectory prediction: a survey
    • 76
    • Highly Influenced
    • PDF
    A general, context-aware pedestrian trajectory prediction model


    Publications referenced by this paper.
    Model based vehicle detection and tracking for autonomous urban driving
    • 343
    • PDF
    Planning-based prediction for pedestrians
    • 380
    • PDF
    Intention-Aware Motion Planning
    • 131
    • PDF
    Hidden Markov model for dynamic obstacle avoidance of mobile robot navigation
    • 165
    Motion Planning in Complex Environments using Closed-loop Prediction
    • 107
    • PDF