Mobile manipulation Why are humans so much better? And how can we change that?

There is a significant performance gap between human agents and robotic agents. Closing this gap has been the goal or robotics research for many years now. There are different opinions on how much progress the community as a whole has made in this regard. In this talk, I would like to speculate on characteristics of solutions capable of closing that gap — as opposed to the development of increasingly competent skills that serve specific applications but do not achieve the generality required to be part of closing the gap. I will propose several characteristics and support their importance with experiments from the areas of grasping, interactive perception, and learning from interaction. As these experiments can only be considered circumstantial evidence for my claims, I prefer to refer to these characteristics as “tricks”. But my hope is, of course, that these tricks will develop into foundational components for the generation of versatile autonomous robot behavior.