Semantic gap in a DIKW pyramid

 Before the situation for robotics is explained, the situation for computing in general should be explained. An example for a semantic gap in computer is the missing layer between hardware and software. The hardware of a computer consists of a CPU, a floppy drive, a graphics card and other elements, while the software is formujlated on a high level layer and describe the appearance of a GUI, contains of algorithms and specify the data.

Its not possible to run directly software on the hardware because a dedicated operating system is needed. For today's computer user its common sonse to decide for such an operating system. Someboy prefers MS Dos, another user likes Linux while the next one has installed Windows 11 on his machine.

It was a slow development until operating systems became the standard. During the 1980s most homecomputer didn't had a dedicated operating system or it was very tiny. The situation changed in the 1990s and the situation today is, that operating systems are a standard component of every computer.

In case of robotics there is also a semantic gap available between low level and high level layer. The low level layer is in the DIKW pyramid the sensory data for example a camera picture or a lidar sensor. The high level layer in the dikw pyramid is a textual description of a scene, provided by a chatbot. Between both layers there is gap available, because a camera picture can't be directly converted into a text description. What is needed is a converter, some sort of robot operating system which closes the gap.

The common name for such a tool is "Vision language action model" be definition such a model, realized as a neural network, is able to translate back and forth between images and text. The prediction is that future robotics after the year 2030 will have such a VQA module built in as default, similar to an operating system in a computer. The VQA module ensures that robot tasks can be specified in natural language.