arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.05613cs.LGcs.AI
收藏

基于图神经网络的大规模问题求解中的学习对象重要性规划

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

MIT Computer Science and Artificial Intelligence Laboratory(麻省理工学院计算机科学与人工智能实验室)

Tom Silver, Rohan Chitnis, Aidan Curtis, Joshua Tenenbaum, Tomas Lozano-Perez, Leslie Pack Kaelbling

摘要:

现实世界中的规划问题往往涉及数百甚至数千个对象,这使现代规划者的极限变得紧张。在这项工作中,我们通过学习预测一小部分对象来应对这一挑战,这些对象放在一起就足以找到一个计划。我们提出了一个图神经网络架构预测对象的重要性,在一个单一的推理通过,从而产生很少的开销,同时大大减少了规划者必须考虑的对象的数量。我们的方法将规划器和过渡模型视为黑盒,并且可以与任何现成的规划器一起使用。从经验上讲,在经典规划,概率规划,机器人任务和运动规划,我们发现,我们的方法的结果规划,是显着快于几个基线,包括其他部分接地策略和解除规划。我们的结论是,学习预测一个规划问题的足够的一组对象是一个简单的,强大的,和一般的机制,在大的情况下规划。视频:https://youtu.be/FWsVJc2fvCE代码:https://git.io/JIsqX

英文摘要:

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: https://youtu.be/FWsVJc2fvCE Code: https://git.io/JIsqX

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑