Skip to main content

No project description provided

Project description

pedestrian_prediction

Realtime, confidence-varying trajectory prediction for "Probabilistically Safe Robot Planning with Confidence-Based Human Predictions". RSS '18

Installation

git clone https://github.com/sirspinach/pedestrian_prediction.git
cd pedestrian_prediction
pip install -e .

Module contents

  • pp.mdp: Data structures and value iteration algorithms for two types of GridWorlds -- a standard GridWorld with only lateral and diagonal movement, and a GridWorldExpanded in which actions operate in "gridless" continuous space but are snapped to the nearest grid cell.
  • pp.inference: Algorithms for inferring destinations, occupancies, and states given a GridWorld, a list of destinations, and the pedestrian's trajectory so far.
  • pp.util: Utilities for parsing and trajectory manipulation.
  • pp.plots: Plot simulated trajectories, overlayed with heatmaps of predicted states. Produce some test plots by executing python -m pp.plot. (Requires plotly)

Project details


Release history Release notifications | RSS feed

This version

0.1

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for pedestrian-prediction, version 0.1
Filename, size File type Python version Upload date Hashes
Filename, size pedestrian_prediction-0.1.tar.gz (1.9 kB) File type Source Python version None Upload date Hashes View

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring DigiCert DigiCert EV certificate Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page