An Empirical Evaluation of the Effectiveness of Local Search for Replanning

  • Authors:
  • Steve Chien;Russell Knight;Gregg Rabideau

  • Affiliations:
  • -;-;-

  • Venue:
  • ECAI '00 Proceedings of the Workshop on Local Search for Planning and Scheduling-Revised Papers
  • Year:
  • 2000

Quantified Score

Hi-index 0.00

Visualization

Abstract

Local search has been proposedas a means of responding to changes in problem context requiring replanning. Iterative repair and iterative improvement have desirable properties of preference for plan stability (e.g., non-disruption, minimizing change), and have performed well in a number of practical applications. However, there has been little real empirical evidence to support this case. This paper focuses on the use of local search to support a continuous planning process (e.g., continuously replanning to account for problem changes) as is appropriate for autonomous spacecraft control. We describe results from ongoing empirical tests using the CASPER system to evaluate the effectiveness of local search to replanning using a number of spacecraft scenario simulations including landed operations on a comet and rover operations.