EgoPet: 動物視点の自己運動とインタラクションデータセット
EgoPet: Egomotion and Interaction Data from an Animal's Perspective
ペットの視点から撮影した映像で自己運動とマルチエージェント相互作用を同時に含むデータセットを構築し、四足歩行ロボットの事前学習に有効であることを示した。
著者: Amir Bar, Arya Bakhtiar, Danny Tran, Antonio Loquercio, Jathushan Rajasegaran, Yann LeCun, Amir Globerson, Trevor Darrell
分類: cs.RO, cs.CV
原文アブストラクト
Animals perceive the world to plan their actions and interact with other agents to accomplish complex tasks, demonstrating capabilities that are still unmatched by AI systems. To advance our understanding and reduce the gap between the capabilities of animals and AI systems, we introduce a dataset of pet egomotion imagery with diverse examples of simultaneous egomotion and multi-agent interaction. Current video datasets separately contain egomotion and interaction examples, but rarely both at the same time. In addition, EgoPet offers a radically distinct perspective from existing egocentric datasets of humans or vehicles. We define two in-domain benchmark tasks that capture animal behavior, and a third benchmark to assess the utility of EgoPet as a pretraining resource to robotic quadruped locomotion, showing that models trained from EgoPet outperform those trained from prior datasets.
