InternRobotics / InternRobotics/NavDP
Imagegoal Evaluation
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 793
- Forks
- 69
- PR merge metrics
- No merged PRs in 30d
Description
Hello, when I used the provided navdp-cross-modal.ckpt to evaluate in the easy scenes with eval_imagegoal_wheeled.py, I found that the success rate was only around 30%. The evaluation results for the easy_2 scene are shown below (31%) is far from the data normally reported in the paper, and I'm really puzzled about what went wrong.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the evaluation with navdp-cross-modal.ckpt using eval_imagegoal_wheeled.py, focusing on the easy_2 scene and its reported 31% success rate. Compare the evaluation result with the data reported in the paper and inspect the run configuration or inputs for a concrete discrepancy. Done means the cause of the low success rate is identified and the evaluation matches the expected result or is explained.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, robotics
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 38/100