Grounding Robot Plans from Natural Language Instructions with Incomplete World Knowledge

Grounding Robot Plans from Natural Language Instructions with Incomplete World Knowledge
复制标题

利用不完整的世界知识根据自然语言指令制定机器人计划

DOI:
--
复制
发表时间:
2018
期刊:
Conference on Robot Learning
影响因子:
--
通讯作者:
N. Roy
N. Roy
中科院分区:
--
文献类型:
--
作者:
D. Nyga;Subhro Roy;Rohan Paul;Daehyung Park;M. Pomarlan;M. Beetz;N. Roy

文献摘要

参考文献

被引文献

相似文献

我们的目标是使机器人能够解释和执行使用自然语言指令传达的高级任务。例如,考虑给家用机器人分配任务,“准备我的早餐”,“清理桌子上的盒子”或“给我做水果奶昔”。解释这种未被指定的艾德指令需要环境背景和关于如何完成复杂任务的背景知识。此外,机器人的工作空间知识可能不完整:环境可能只被部分观察到,或者背景知识可能缺失,导致计划合成失败。我们引入了一个概率模型,利用背景知识来推断潜在的或缺失的计划成分的基础上,从嘈杂的文本语料库的任务描述的语义共同协会。推断缺失的计划成分的能力使信息寻求行动,如视觉探索或与人类对话,以获得新的知识来填补不完整的计划。结果表明,在部分已知的世界中,根据未指定的艾德指令进行鲁棒的计划推断。
: Our goal is to enable robots to interpret and execute high-level tasks conveyed using natural language instructions. For example, consider tasking a household robot to, “prepare my breakfast”, “clear the boxes on the table” or “make me a fruit milkshake”. Interpreting such underspecified instructions requires environmental context and background knowledge about how to accomplish complex tasks. Further, the robot’s workspace knowledge may be incomplete: the environment may only be partially-observed or background knowledge may be missing causing a failure in plan synthesis. We introduce a probabilistic model that utilizes background knowledge to infer latent or missing plan constituents based on semantic co-associations learned from noisy textual corpora of task descriptions. The ability to infer missing plan constituents enables information-seeking actions such as visual exploration or dialogue with the human to acquire new knowledge to fill incomplete plans. Results indicate robust plan inference from under-specified instructions in partially-known worlds.
DOI: --
发表时间: 2017-10
期刊: --
影响因子: --
作者:
Jesse Thomason;Aishwarya Padmakumar;Jivko Sinapov;Justin W. Hart;P. Stone;R. Mooney
通讯作者: Jesse Thomason;Aishwarya Padmakumar;Jivko Sinapov;Justin W. Hart;P. Stone;R. Mooney