GraphCanon updated 3w · GitHub synced 3w · 26 views this month
Decision brief
VLN-CE provides Python-based resources for Vision-and-Language Navigation research using Habitat. It uses the MIT license but the datasets adhere to Matterport3D terms.
Good fit when
- When aiming to advance robotics navigation by training models on vision-language tasks with habitat-sim.
- If focusing on research that aligns with continuous environments and requires detailed annotation under MP_TOS.
Avoid when
- Avoid if your project needs fully open datasets, as some VLN-CE components are restricted by Matterport3D license terms.
- Steer clear if you prefer tools with built-in support for environments other than those within the Habitat simulation framework.
Observed Jul 17, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (569d since push)
- As of 3w
- Provenance
- Not a fork · Personal account
- As of 3w
- Security (OSV)
- 640 low (640 low)
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install VLN-CESimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
A Python-based codebase for Vision and Language Navigation research in robotics with Habitat.
Capability facts
- Languages
- python
Source: github.language+pyproject.toml · Jul 31, 2026
Categories
Tags
README
License
The VLN-CE codebase is MIT licensed. Trained models and task datasets are considered data derived from the mp3d scene dataset. Matterport3D based task datasets and trained models are distributed with Matterport3D Terms of Use and under CC BY-NC-SA 3.0 US license.
For agents
This page has a .md twin and JSON over the API.