InternRobotics / InternRobotics/NavDP

About the calculation formula for SPL

Open
#121 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
793
Forks
69
PR merge metrics
No merged PRs in 30d

Description

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.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading the evaluation code for NavDP/X-NavDP alongside the cited 2018 SPL paper. Identify where the reference distance is calculated and compare the implemented 2D Euclidean distance with the paper's geodesic definition. Done means documenting a maintainer-confirmed explanation for the discrepancy or clarifying which formula should be used.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Documentation
Difficulty
3/5
Estimated time
1-2 days
Activity status
Active
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.