Xiaoming-Zhao/PointNav-VO

[ICCV 2021] Official implementation of "The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation"

39
/ 100
Emerging

This project helps roboticists and AI researchers develop embodied agents that can navigate to specific points in a 3D environment using visual information. It takes simulated sensor data, like camera images, and outputs improved navigation decisions, helping the agent reach its target more effectively. This is for researchers working on autonomous navigation for robots or virtual agents.

No commits in the last 6 months.

Use this if you are developing or evaluating point-goal navigation agents and want to integrate advanced visual odometry to improve their pathfinding accuracy.

Not ideal if you are looking for a physical robot deployment solution, as this project is focused on simulation environments like Habitat.

robotics embodied-ai autonomous-navigation computer-vision pathfinding
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

84

Forks

11

Language

Python

License

Apache-2.0

Last pushed

Feb 23, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Xiaoming-Zhao/PointNav-VO"

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