Free-falling paper shapes exhibit rich, complex and varied behaviours that are extremely challenging to model analytically. Physical experimentation aids in system understanding, but is time-consuming, sensitive to initial conditions and reliant on subjective visual behavioural classification. In this study, robotics, computer vision and machine learning are used to autonomously fabricate, drop, analyse and classify the behaviours of hundreds of shapes. The system is validated by reproducing results for falling discs, which exhibit four falling styles: tumbling, chaotic, steady and periodic. A previously determined mapping from a non-dimensional parameter space to behaviour groups is shown to be consistent with these new experiments for tumbling and chaotic behaviours. However, steady or periodic behaviours are observed in previously unseen areas of the parameter space. More complex hexagon, square and cross shapes are investigated, showing that the non-dimensional parameter space generalizes to these shapes. The system highlights the potential of robotics for the investigation of complex physical systems, of which falling paper is one example, and provides a template for future investigation of such systems.

自由落体的纸张形状表现出丰富，复杂和多样的行为，这对于分析建模极具挑战性。物理实验有助于系统理解，但耗时，对初始条件敏感且依赖于主观视觉行为分类。在这项研究中，机器人技术，计算机视觉和机器学习被用于自主制造，掉落，分析和分类数百种形状的行为。该系统通过重现掉落圆盘的结果进行了验证，该结果显示出四种掉落样式：翻滚，混乱，稳定和周期性。先前确定的从无量纲参数空间到行为组的映射显示与这些关于翻滚和混乱行为的新实验一致。然而，在参数空间以前看不见的区域中观察到稳定或周期性的行为。研究了更复杂的六边形，正方形和十字形，这表明无量纲参数空间可以推广到这些形状。该系统突出了机器人技术研究复杂物理系统的潜力，其中下降的纸张就是一个例子，并为将来对此类系统的研究提供了模板。