Integration of Hierarchical Goal Network Planning and Autonomous Path Planning

Report No. ARL-MR-0926
Authors: Nicholas C Fung
Date/Pages: March 2016; 16 pages
Abstract: Automated planning has become an increasingly influential area of research in the realm of artificial intelligence. Task-based planning algorithms provide a number of advantages, including the ease of human readability when creating mission-length plans. However, such planning algorithms are rarely implemented on real-world robotic systems. This report documents work to integrate a hierarchical goal network planning algorithm with low-level path planning. The system uses the Goal Decomposition with Landmarks (GoDeL) low-level path planner to create a plan, consisting of a sequence of actions, to attain the goals state. The domain is a robot operating in a known office environment with labeled rooms and doors that can be manipulated. The report goes on to discuss future improvement of the system with the goal of creating a robust system that can operate on a robotic platform in a dynamic environment.
Distribution: Approved for public release
  Download Report ( 0.300 MBytes )
If you are visually impaired or need a physical copy of this report, please visit and contact DTIC.

Last Update / Reviewed: March 1, 2016