Zeying-Gong/ascent

[RAL‘26] Stairway to Success: An Online Floor-Aware Zero-Shot Object-Goal Navigation Framework via LLM-Driven Coarse-to-Fine Exploration

37
/ 100
Emerging

This project helps autonomous robots navigate complex indoor environments to find specific objects, even across different floors, without needing prior training for that exact object or location. It takes in a general object description and a 3D environment map, then outputs a navigation path for the robot to successfully locate the item. This tool is for robotics engineers and researchers working on advanced autonomous navigation systems for service robots or exploration.

Use this if you need an autonomous robot to find a specified object in a multi-floor indoor setting without pre-training for every possible target.

Not ideal if your robot operates solely on a single floor or if you have a fixed set of target objects that can be pre-programmed.

robot-navigation service-robotics autonomous-exploration 3D-mapping object-search
No Package No Dependents
Maintenance 6 / 25
Adoption 9 / 25
Maturity 15 / 25
Community 7 / 25

How are scores calculated?

Stars

84

Forks

4

Language

Python

License

MIT

Last pushed

Jan 11, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Zeying-Gong/ascent"

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