bagh2178/UniGoal

[CVPR 2025] UniGoal: Towards Universal Zero-shot Goal-oriented Navigation

38
/ 100
Emerging

This project helps roboticists and autonomous system developers enable robots to navigate to specific destinations without prior training in new environments. You provide images from a robot's camera or descriptive text for a goal, and the system generates the precise actions the robot needs to take to reach it. This is ideal for researchers and engineers developing next-generation autonomous robots for dynamic, unfamiliar settings.

311 stars. No commits in the last 6 months.

Use this if you need a robotic agent to navigate to a goal specified by an image or text in an unfamiliar indoor environment without extensive pre-training.

Not ideal if your robot operates exclusively in pre-mapped, static environments or if your navigation tasks require only simple waypoint following.

robotics autonomous-navigation zero-shot-learning scene-understanding robot-control
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

311

Forks

12

Language

Python

License

MIT

Last pushed

Sep 16, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/bagh2178/UniGoal"

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