SPNets: Human-like Navigation Behaviors with Uncertain Goals

Nicholas Sohre, Stephen J. Guy

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Most path planning techniques use exact, global information of the environment to make optimal or near-optimal plans. In contrast, humans navigate using only local information, which they must augment with their understanding of typical building layouts to guess what lies ahead, while integrating what they have seen already to form mental representations of building structure. Here, we propose Scene Planning Networks (SPNets), a neural network based approach for formulating the long-range navigation problem as a series of local decisions similar to what humans face when navigating. Agents navigating using SPNets build additive neural representations of previous observations to understand local obstacle structure, and use a network-based planning approach to plan the next steps towards a fuzzy goal region. Our approach reproduces several important aspects of human behavior that are not captured by either full global planning or simple local heuristics.

Original languageEnglish (US)
Title of host publicationProceedings - MIG 2020
Subtitle of host publication13th ACM SIGGRAPH Conference on Motion, Interaction, and Games
EditorsStephen N. Spencer
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9781450381710
DOIs
StatePublished - Oct 16 2020
Event13th ACM SIGGRAPH Conference on Motion, Interaction, and Games, MIG 2020 - Virtual, Online, United States
Duration: Oct 16 2020Oct 18 2020

Publication series

NameProceedings - MIG 2020: 13th ACM SIGGRAPH Conference on Motion, Interaction, and Games

Conference

Conference13th ACM SIGGRAPH Conference on Motion, Interaction, and Games, MIG 2020
CountryUnited States
CityVirtual, Online
Period10/16/2010/18/20

Bibliographical note

Funding Information:
This work was supported in part by the National Science Foundation under grants IIS-1748541 and CHS-1526693.

Keywords

  • Path planning
  • character simulation
  • deep neural networks
  • navigation

Fingerprint Dive into the research topics of 'SPNets: Human-like Navigation Behaviors with Uncertain Goals'. Together they form a unique fingerprint.

Cite this