arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.07268cs.CVcs.AIcs.CLcs.RO
收藏

探索与解释:自监督导航与复述

Explore and Explain: Self-supervised Navigation and Recounting

University of Modena and Reggio Emilia(摩德纳和雷焦艾米利亚大学)

Roberto Bigazzi, Federico Landi, Marcella Cornia, Silvia Cascianelli, Lorenzo Baraldi, Rita Cucchiara

AI总结:

本文提出一种新型具身智能体设置,结合带惩罚的自监督探索模块与全注意力字幕模型,研究环境与导航驱动的解释时机选择策略,在Matterport3D数据集上验证了导航、解释能力及二者交互的作用。

摘要:

具身AI(Embodied AI)因旨在推动自主智能体的发展,近来受到广泛关注。本文提出了一种全新的具身任务设置:智能体需要探索此前未知的环境,同时复述其在路径中看到的内容。在该场景下,智能体需在探索目标的驱动下在环境中导航,选择合适的时机进行描述,并输出相关物体与场景的自然语言描述。我们的模型整合了一个带惩罚机制的新型自监督探索模块,以及一个用于解释的全注意力字幕生成模型。此外,我们还研究了由环境与导航信息共同驱动的、用于选择合适解释时机的不同策略。实验在Matterport3D数据集的照片级真实环境中开展,考察了智能体的导航与解释能力,以及二者交互的作用。

英文摘要:

Embodied AI has been recently gaining attention as it aims to foster the development of autonomous and intelligent agents. In this paper, we devise a novel embodied setting in which an agent needs to explore a previously unknown environment while recounting what it sees during the path. In this context, the agent needs to navigate the environment driven by an exploration goal, select proper moments for description, and output natural language descriptions of relevant objects and scenes. Our model integrates a novel self-supervised exploration module with penalty, and a fully-attentive captioning model for explanation. Also, we investigate different policies for selecting proper moments for explanation, driven by information coming from both the environment and the navigation. Experiments are conducted on photorealistic environments from the Matterport3D dataset and investigate the navigation and explanation capabilities of the agent as well as the role of their interactions.

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。

↑