The core idea of MARII is to pick two of the most important mediums of human communication, voice and gestures, and combine them to create a significantly better interaction experience than the current state of text-based prompting. By delivering context over two different modalities simultaneously, the user can express intent much faster and more naturally than typing.
For example, instead of typing "Move ship 1 to the windfarm located at coordinates 54.32°N, 10.14°E", the user can simply point at the ship, point at the windfarm, and say "Move this ship here." The gesture provides the spatial reference, and the voice provides the action and intent. This division of labor is precisely how humans naturally communicate about physical spaces.

.

.

.

.

.

.

.

.

.

.

.

.

.

.

.

.

MARII (Maritime Intelligent Interface) transforms human-AI communication by replacing text prompting with real-time 3D hand gesture tracking and natural voice commands. By eliminating coordinate typing and back-and-forth prompt iterations (ping-pong prompting), MARII empowers operators to command complex maritime fleets through intuitive pointing and speaking—delivering sub-second, zero-typing execution.

.

.

OUR TEAM

.