用于取放任务中双重指代表达理解的 Switching Head-Tail Funnel UNITER
Switching Head-Tail Funnel UNITER for Dual Referring Expression Comprehension with Fetch-and-Carry Tasks
AI总结：
针对家庭机器人依据自然语言完成取放任务时双重指代表达组合推理成本高的问题，提出单一模型 Switching Head-Tail Funnel UNITER 分别预测目标与目的地，并在仿真和实体实验中验证其准确率与超过90%的抓放成功率。
摘要：
本文描述了一种家庭服务机器人（DSR），它能够根据自由形式的自然语言指令拿取日常物品，并将其搬运到指定目的地。对于诸如“把盘子左侧的瓶子移到空椅子上”这样的指令，DSR 需要从环境中的多个候选对象中识别出瓶子和椅子，并将目标物体搬运到目的地。大多数现有多模态语言理解方法在计算复杂度上并不实用，因为它们需要对目标物体候选与目的地候选的所有组合进行推理。我们提出 Switching Head-Tail Funnel UNITER，通过使用单一模型分别预测目标物体和目的地来解决该任务。我们的方法在一个新建数据集上得到验证，该数据集由物体操作指令和在标准 Embodied AI 仿真器中捕获的半照片级真实感图像组成。结果表明，我们的方法在语言理解准确率方面优于基线方法。此外，我们还进行了物理实验，其中 DSR 按照带有指代表达的指令，在标准化家庭环境中递送标准化日常物品。实验结果表明，物体抓取和放置动作均以超过 90% 的成功率完成。
英文摘要：
This paper describes a domestic service robot (DSR) that fetches everyday objects and carries them to specified destinations according to free-form natural language instructions. Given an instruction such as "Move the bottle on the left side of the plate to the empty chair," the DSR is expected to identify the bottle and the chair from multiple candidates in the environment and carry the target object to the destination. Most of the existing multimodal language understanding methods are impractical in terms of computational complexity because they require inferences for all combinations of target object candidates and destination candidates. We propose Switching Head-Tail Funnel UNITER, which solves the task by predicting the target object and the destination individually using a single model. Our method is validated on a newly-built dataset consisting of object manipulation instructions and semi photo-realistic images captured in a standard Embodied AI simulator. The results show that our method outperforms the baseline method in terms of language comprehension accuracy. Furthermore, we conduct physical experiments in which a DSR delivers standardized everyday objects in a standardized domestic environment as requested by instructions with referring expressions. The experimental results show that the object grasping and placing actions are achieved with success rates of more than 90%.
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。
