AAAI Publications, Twenty-Eighth International Conference on Automated Planning and Scheduling

Font Size: 
AD*-Cut: A Search-Tree Cutting Anytime Dynamic A* Algorithm
Maciej Przybylski

Last modified: 2018-06-15


This paper presents a new anytime incremental search algorithm, AD*-Cut. AD*-Cut is based on two algorithms, namely, Anytime Repairing A* (ARA*) and the novel incremental search algorithm, D* Extra Lite. D* Extra Lite reinitializes (cuts) entire search-tree branches that have been affected by changes in an environment, and D* Extra Lite appears to be quicker than the reinitialization during the search utilized by the popular incremental search algorithm, D* Lite. The search-tree branch cutting is a simple and robust technique that can be easily applied to ARA*. Consequently, AD*-Cut extends D* Extra Lite in the same manner, as the state-of-the-art Anytime D* (AD*) algorithm extends D* Lite. The benchmark results suggest that AD*-Cut is quicker and achieves shorter paths than AD* when used for path planning on 3D state-lattices (a 2D position with rotation).


path planning; anytime incremental search

Full Text: PDF