vidhiJain/SpatialEmbeddings

Learning Embeddings that Capture Spatial Semantics for Indoor Navigation, NeurIPS ORLR 2020

21
/ 100
Experimental

This project helps roboticists and AI researchers develop embodied AI agents capable of smart indoor navigation. It takes common object names and spatial relationships to create an 'understanding' of where things are likely to be found. The output helps an AI agent search for objects more intelligently and efficiently in complex indoor environments, similar to how a human would.

No commits in the last 6 months.

Use this if you are developing AI agents or robots that need to efficiently find specific objects within indoor settings like homes or offices, by leveraging semantic spatial awareness.

Not ideal if your navigation task involves outdoor environments, abstract objects, or relies purely on geometric pathfinding without semantic object knowledge.

Robotics Indoor Navigation Embodied AI Object Search Spatial Reasoning
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 8 / 25

How are scores calculated?

Stars

9

Forks

1

Language

Python

License

Last pushed

Dec 23, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/vidhiJain/SpatialEmbeddings"

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