arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.00786cs.CL
收藏

基于视觉目标预测的三维环境中指令到动作的映射

Mapping Instructions to Actions in 3D Environments with Visual Goal Prediction

Cornell University(康奈尔大学)

Dipendra Misra, Andrew Bennett, Valts Blukis, Eyvind Niklasson, Max Shatkhin, Yoav Artzi

摘要:

我们建议将指令执行分解为目标预测和动作生成。我们设计了一个模型,使用LINGUNET(一种语言调节的图像生成网络)将原始视觉观察映射到目标,然后生成完成它们所需的动作。我们的模型是在没有外部资源的情况下从演示中训练出来的。为了评估我们的方法,我们引入两个基准指令指令遵循:LANI,导航任务和柴,代理执行家庭指令。我们的评估展示了我们的模型分解的优势,并说明了我们的新基准所带来的挑战。

英文摘要:

We propose to decompose instruction execution to goal prediction and action generation. We design a model that maps raw visual observations to goals using LINGUNET, a language-conditioned image generation network, and then generates the actions required to complete them. Our model is trained from demonstration only without external resources. To evaluate our approach, we introduce two benchmarks for instruction following: LANI, a navigation task; and CHAI, where an agent executes household instructions. Our evaluation demonstrates the advantages of our model decomposition, and illustrates the challenges posed by our new benchmarks.

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。

↑