In the current evaluation code for NavDP/X-NavDP, the reference distance used for SPL is the 2D Euclidean distance between the start and goal points, rather than the geodesic shortest path (which, in most cases, corresponds to the A* shortest path). However, the SPL formula defined in the 2018 paper "On Evaluation of Embodied Navigation Agents" (arXiv:1807.06757) explicitly specifies the use of the geodesic shortest path in the numerator. I would like to know why the formula used here differs from that definition.
This is a matter of detail; I would be extremely grateful if you could answer this for me.
In the current evaluation code for NavDP/X-NavDP, the reference distance used for SPL is the 2D Euclidean distance between the start and goal points, rather than the geodesic shortest path (which, in most cases, corresponds to the A* shortest path). However, the SPL formula defined in the 2018 paper "On Evaluation of Embodied Navigation Agents" (arXiv:1807.06757) explicitly specifies the use of the geodesic shortest path in the numerator. I would like to know why the formula used here differs from that definition.
This is a matter of detail; I would be extremely grateful if you could answer this for me.