The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction

Abstract

This paper studies the problem of predicting the distribution over multiple possible future paths of people as they move through various visual scenes. We make two main contributions. The first contribution is a new dataset, created in a realistic 3D simulator, which is based on real world trajectory data, and then extrapolated by human annotators to achieve different latent goals. This provides the first benchmark for quantitative evaluation of the models to predict multi-future trajectories. The second contribution is a new model to generate multiple plausible future trajectories, which contains novel designs of using multi-scale location encodings and convolutional RNNs over graphs. We refer to our model as Multiverse.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 14, 2020
Accession Number
AD1152495

Entities

People

  • Alexander Hauptmann
  • Junwei Liang
  • Kevin Murphy
  • Lu Jiang
  • Ting Yu

Organizations

  • Carnegie Mellon University
  • Google

Tags

Communities of Interest

  • Air Platforms
  • Autonomy

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Artificial Intelligence Software
  • Coders
  • Coding
  • Computational Science
  • Computer Graphics
  • Computer Programs
  • Computer Vision
  • Computers
  • Decoders
  • Machine Learning
  • Models
  • Neural Networks
  • Probabilistic Models
  • Probability
  • Recurrent Neural Networks
  • Reliability
  • Robotics
  • Simulations
  • Simulators
  • Test And Evaluation

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.
  • Parallel and Distributed Computing.
  • Theoretical Analysis.