Planning under Uncertainty for Robotic Tasks with Mixed Observability

  • Authors:

  • Sylvie C. W. Ong; Shao Wei Png;David Hsu; Wee Sun Lee

  • Affiliations:

  • Department of Computer Science, National Universityof Singapore, Singapore 117417, Singapore;School of Computer Science, McGill University, Montreal,Quebec H3A 2A7, Canada;Department of Computer Science, National Universityof Singapore, Singapore 117417, Singapore;Department of Computer Science, National Universityof Singapore, Singapore 117417, Singapore

  • Venue:
  • International Journal of Robotics Research
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Partially observable Markov decision processes (POMDPs) provide a principled, general framework for robot motion planning in uncertain and dynamic environments. They have been applied to various robotic tasks. However, solving POMDPs exactly is computationally intractable. A major challenge is to scale up POMDP algorithms for complex robotic tasks. Robotic systems often have mixed observability : even when a robotâ聙聶s state is not fully observable, some components of the state may still be so. We use a factored model to represent separately the fully and partially observable components of a robotâ聙聶s state and derive a compact lower-dimensional representation of its belief space. This factored representation can be combined with any point-based algorithm to compute approximate POMDP solutions. Experimental results show that on standard test problems, our approach improves the performance of a leading point-based POMDP algorithm by many times.