‘Intuitive physics’ enables our pragmatic engagement with the physical world and forms a key component of ‘common sense’ aspects of thought. Current artificial intelligence systems pale in their understanding of intuitive physics, in comparison to even very young children. Here we address this gap between humans and machines by drawing on the field of developmental psychology. First, we introduce and open-source a machine-learning dataset designed to evaluate conceptual understanding of intuitive physics, adopting the violation-of-expectation (VoE) paradigm from developmental psychology. Second, we build a deep-learning system that learns intuitive physics directly from visual data, inspired by studies of visual cognition in children. We demonstrate that our model can learn a diverse set of physical concepts, which depends critically on object-level representations, consistent with findings from developmental psychology. We consider the implications of these results both for AI and for research on human cognition.

“直觉物理学”使我们能够务实地参与物理世界，并构成思想“常识”方面的关键组成部分。与非常年幼的孩子相比，当前的人工智能系统对直觉物理学的理解显得苍白无力。在这里，我们通过借鉴发展心理学领域来解决人与机器之间的这种差距。首先，我们引入并开源了一个机器学习数据集，该数据集旨在评估对直觉物理学的概念理解，采用发展心理学的预期违背 (VoE) 范式。其次，受儿童视觉认知研究的启发，我们构建了一个直接从视觉数据中学习直觉物理学的深度学习系统。我们证明我们的模型可以学习一组不同的物理概念，这严重依赖于对象级表示，与发展心理学的发现一致。我们考虑了这些结果对人工智能和人类认知研究的影响。