Researchers have compiled a dataset that captures the detailed behavior of a robotic system physically pushing hundreds of different objects. Using the dataset — the largest and most diverse of its kind — researchers can train robots to ‘learn’ pushing dynamics that are fundamental to many complex object-manipulation tasks, including reorienting and inspecting objects, and uncluttering scenes.

Original source: https://www.sciencedaily.com/releases/2019/10/191022124914.htm