Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration

Xavier Puig · Tianmin Shu · Shuang Li · Zilin Wang · Yuan-Hong Liao · Joshua B Tenenbaum · Sanja Fidler · Antonio Torralba

[ Abstract ] [ Livestream: Visit Oral Session 2 ] [ Paper ]
Mon 3 May 1:50 p.m. — 2 p.m. PDT
[ Paper ]

In this paper, we introduce Watch-And-Help (WAH), a challenge for testing social intelligence in agents. In WAH, an AI agent needs to help a human-like agent perform a complex household task efficiently. To succeed, the AI agent needs to i) understand the underlying goal of the task by watching a single demonstration of the human-like agent performing the same task (social perception), and ii) coordinate with the human-like agent to solve the task in an unseen environment as fast as possible (human-AI collaboration). For this challenge, we build VirtualHome-Social, a multi-agent household environment, and provide a benchmark including both planning and learning based baselines. We evaluate the performance of AI agents with the human-like agent as well as and with real humans using objective metrics and subjective user ratings. Experimental results demonstrate that our challenge and virtual environment enable a systematic evaluation on the important aspects of machine social intelligence at scale.

Chat is not available.