TY - JOUR AU - Netanyahu, Aviv AU - Shu, Tianmin AU - Katz, Boris AU - Barbu, Andrei AU - Tenenbaum, Joshua B. PY - 2021/05/18 Y2 - 2024/03/28 TI - PHASE: PHysically-grounded Abstract Social Events for Machine Social Perception JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 35 IS - 1 SE - AAAI Technical Track on Cognitive Modeling and Cognitive Systems DO - 10.1609/aaai.v35i1.16167 UR - https://ojs.aaai.org/index.php/AAAI/article/view/16167 SP - 845-853 AB - The ability to perceive and reason about social interactions in the context of physical environments is core to human social intelligence and human-machine cooperation. However, no prior dataset or benchmark has systematically evaluated physically grounded perception of complex social interactions that go beyond short actions, such as high-fiving, or simple group activities, such as gathering. In this work, we create a dataset of physically-grounded abstract social events, PHASE, that resemble a wide range of real-life social interactions by including social concepts such as helping another agent. PHASE consists of 2D animations of pairs of agents moving in a continuous space generated procedurally using a physics engine and a hierarchical planner. Agents have a limited field of view, and can interact with multiple objects, in an environment that has multiple landmarks and obstacles. Using PHASE, we design a social recognition task and a social prediction task. PHASE is validated with human experiments demonstrating that humans perceive rich interactions in the social events, and that the simulated agents behave similarly to humans. As a baseline model, we introduce a Bayesian inverse planning approach, SIMPLE (SIMulation, Planning and Local Estimation), which outperforms state-of-the-art feed-forward neural networks. We hope that PHASE can serve as a difficult new challenge for developing new models that can recognize complex social interactions. ER -