zd11024/NaviLLM

[CVPR 2024] The code for paper 'Towards Learning a Generalist Model for Embodied Navigation'

37
/ 100
Emerging

This project helps roboticists and AI researchers develop smarter autonomous agents that can navigate and interact with complex 3D environments. It takes various forms of instructions (like "go to the kitchen" or "find the red mug") and visual information from a 3D space, then outputs navigation paths, answers to questions about the environment, or descriptions of objects. It's designed for those building embodied AI agents for robotics or virtual environments.

229 stars. No commits in the last 6 months.

Use this if you need a single AI model to handle multiple embodied navigation tasks, like following instructions or answering questions about a 3D space, rather than building separate models for each task.

Not ideal if you're looking for a simple plug-and-play solution for a single, highly specialized navigation task, as it's designed for broad generalizability across many tasks.

robotics-navigation embodied-ai 3d-environment-interaction autonomous-agents computer-vision-navigation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

229

Forks

15

Language

Python

License

MIT

Last pushed

Jun 18, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/zd11024/NaviLLM"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.