Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks


  • Tom Silver Massachusetts Institute of Technology
  • Rohan Chitnis Massachusetts Institute of Technology
  • Aidan Curtis Massachusetts Institute of Technology
  • Joshua B. Tenenbaum Massachusetts Institute of Technology
  • Tomás Lozano-Pérez Massachusetts Institute of Technology
  • Leslie Pack Kaelbling Massachusetts Institute of Technology


Planning/Scheduling and Learning


Real-world planning problems often involve hundreds or even thousands of objects, straining the limits of modern planners. In this work, we address this challenge by learning to predict a small set of objects that, taken together, would be sufficient for finding a plan. We propose a graph neural network architecture for predicting object importance in a single inference pass, thus incurring little overhead while greatly reducing the number of objects that must be considered by the planner. Our approach treats the planner and transition model as black boxes, and can be used with any off-the-shelf planner. Empirically, across classical planning, probabilistic planning, and robotic task and motion planning, we find that our method results in planning that is significantly faster than several baselines, including other partial grounding strategies and lifted planners. We conclude that learning to predict a sufficient set of objects for a planning problem is a simple, powerful, and general mechanism for planning in large instances. Video: Code:




How to Cite

Silver, T., Chitnis, R., Curtis, A., Tenenbaum, J. B., Lozano-Pérez, T., & Kaelbling, L. P. (2021). Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 35(13), 11962-11971. Retrieved from



AAAI Technical Track on Planning, Routing, and Scheduling