Scene mover: Automatic Move Planning for Scene Arrangement by Deep Reinforcement Learning

Hanqing Wang, Wei Liang*, Lap Fai Yu

*此作品的通讯作者

科研成果: 期刊稿件文章同行评审

23 引用 (Scopus)

摘要

We propose a novel approach for automatically generating a move plan for scene arrangement.1 Given a scene like an apartment with many furniture objects, to transform its layout into another layout, one would need to determine a collision-free move plan. It could be challenging to design this plan manually because the furniture objects may block the way of each other if not moved properly; and there is a large complex search space of move action sequences that grow exponentially with the number of objects. To tackle this challenge, we propose a learning-based approach to generate a move plan automatically. At the core of our approach is a Monte Carlo tree that encodes possible states of the layout, based on which a search is performed to move a furniture object appropriately in the current layout. We trained a policy neural network embedded with a LSTM module for estimating the best actions to take in the expansion step and simulation step of the Monte Carlo tree search process. Leveraging the power of deep reinforcement learning, the network learned how to make such estimations through millions of trials of moving objects. We demonstrated our approach for moving objects under different scenarios and constraints. We also evaluated our approach on synthetic and real-world layouts, comparing its performance with that of humans and other baseline approaches.

源语言英语
文章编号233
期刊ACM Transactions on Graphics
39
6
DOI
出版状态已出版 - 26 11月 2020

指纹

探究 'Scene mover: Automatic Move Planning for Scene Arrangement by Deep Reinforcement Learning' 的科研主题。它们共同构成独一无二的指纹。

引用此