You can often infer someone's intent from what they're looking at, or in other words, their gaze. For example, people normally direct conversation by looking at the person they're conversing with (most of the time). Here, we are interested in where the user would like to place the bin; we will do this by attaching the bin to their gaze and follow it around, hugging the surface of the floor; when it is in a valid location, we will allow the user to place the bin by performing the tap gesture.
We will implement gaze using two components. The first will be responsible for inferring and updating the gaze based on the user's head position and orientation as well as assigning the gaze endpoint (where it hits the surface) to a ...
