Spatial and Temporal Abstractions in POMDPs Applied to Robot Navigation

Abstract

Partially observable Markov decision processes (POMDPs) are a well studied paradigm for programming autonomous robots, where the robot sequentially chooses actions to achieve long term goals efficiently. Unfortunately, for real world robots and other similar domains, the uncertain outcomes of the actions and the fact that the true world state may not be completely observable make learning of models of the world extremely difficult, and using them algorithmically infeasible. In this paper we show that learning POMDP models and planning with them can become signifcantly easier when we incorporate into our algorithms the notions of spatial and temporal abstraction. We demonstrate the superiority of our algorithms by comparing them with previous flat approaches for large scale robot navigation.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 27, 2005
Accession Number
ADA466737

Entities

People

  • Georgios Theocharous
  • Leslie P. Kaelbling
  • Sridhar Mahadevan

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Autonomy
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Artificial Intelligence Software
  • Autonomous Navigation
  • Bayesian Networks
  • Computational Science
  • Hidden Markov Models
  • Information Processing
  • Information Systems
  • Language
  • Machine Learning
  • Markov Models
  • Navigation
  • Neural Networks
  • Operations Research
  • Probability
  • Probability Distributions
  • Robot Navigation

Fields of Study

  • Computer science

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • AI & ML - Machine Learning Algorithms
  • Autonomy
  • Autonomy - Autonomous System Control