在体现的AI工作室上的回顾

论文标题

在体现的AI工作室上的回顾

Retrospectives on the Embodied AI Workshop

论文作者

Deitke, Matt, Batra, Dhruv, Bisk, Yonatan, Campari, Tommaso, Chang, Angel X., Chaplot, Devendra Singh, Chen, Changan, D'Arpino, Claudia Pérez, Ehsani, Kiana, Farhadi, Ali, Fei-Fei, Li, Francis, Anthony, Gan, Chuang, Grauman, Kristen, Hall, David, Han, Winson, Jain, Unnat, Kembhavi, Aniruddha, Krantz, Jacob, Lee, Stefan, Li, Chengshu, Majumder, Sagnik, Maksymets, Oleksandr, Martín-Martín, Roberto, Mottaghi, Roozbeh, Raychaudhuri, Sonia, Roberts, Mike, Savarese, Silvio, Savva, Manolis, Shridhar, Mohit, Sünderhauf, Niko, Szot, Andrew, Talbot, Ben, Tenenbaum, Joshua B., Thomason, Jesse, Toshev, Alexander, Truong, Joanne, Weihs, Luca, Wu, Jiajun

论文摘要

我们提出了有关体现AI研究状态的回顾。我们的分析重点是CVPR的体现AI研讨会上提出的13个挑战。这些挑战分为三个主题：（1）视觉导航，（2）重排和（3）体现的视觉和语言。我们讨论了每个主题中的主要数据集，挑战的评估指标以及最先进的模型的性能。我们强调了挑战的顶级方法之间的共同点，并确定了体现AI研究的潜在未来方向。

We present a retrospective on the state of Embodied AI research. Our analysis focuses on 13 challenges presented at the Embodied AI Workshop at CVPR. These challenges are grouped into three themes: (1) visual navigation, (2) rearrangement, and (3) embodied vision-and-language. We discuss the dominant datasets within each theme, evaluation metrics for the challenges, and the performance of state-of-the-art models. We highlight commonalities between top approaches to the challenges and identify potential future directions for Embodied AI research.

下载PDF全文

下载文献需遵守相关版权规定

论文标题