arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1707.03804cs.CLcs.AIcs.LGcs.RO
收藏

空间指令理解的源-目标推理模型

Source-Target Inference Models for Spatial Instruction Understanding

University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校)

Hao Tan, Mohit Bansal

摘要:

可以执行自然语言指令的模型,用于机器人任务,如装配和导航,在家庭,办公室和远程场景中有几个有用的应用。基于Bisk-2016 blank-labeled block数据集,研究了空间相关配置和排列指令的语义。该任务涉及找到源块并将其移动到目标位置(通过参考块和偏移量提及),其中块没有名称或颜色,仅通过空间位置特征提及。我们提出了新的模型的源块分类和目标位置回归的子任务,基于联合损失语言和空间世界表示学习,以及基于CNN和双注意力模型来计算世界块和指令短语之间的对齐。对于目标位置预测,我们比较了两种推理方法:退火抽样通过策略梯度与期望推理通过监督回归。我们的模型在这项任务上达到了最先进的水平,源块精度提高了47%,目标位置距离提高了22%。

英文摘要:

Models that can execute natural language instructions for situated robotic tasks such as assembly and navigation have several useful applications in homes, offices, and remote scenarios. We study the semantics of spatially-referred configuration and arrangement instructions, based on the challenging Bisk-2016 blank-labeled block dataset. This task involves finding a source block and moving it to the target position (mentioned via a reference block and offset), where the blocks have no names or colors and are just referred to via spatial location features. We present novel models for the subtasks of source block classification and target position regression, based on joint-loss language and spatial-world representation learning, as well as CNN-based and dual attention models to compute the alignment between the world blocks and the instruction phrases. For target position prediction, we compare two inference approaches: annealed sampling via policy gradient versus expectation inference via supervised regression. Our models achieve the new state-of-the-art on this task, with an improvement of 47% on source block accuracy and 22% on target position distance.

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。

↑