peteanderson80/Matterport3DSimulator

AI Research Platform for Reinforcement Learning from Real Panoramic Images.

51
/ 100
Established

This platform helps AI researchers develop and test intelligent agents that learn to navigate real-world 3D indoor environments using visual input. You input real panoramic RGB-D images from diverse spaces like homes and offices, and the platform outputs data about the agent's visual observations (like what it 'sees') and its movements. This is primarily for AI researchers working on reinforcement learning, computer vision, natural language processing, and robotics to train agents to follow instructions or find specific locations.

683 stars. No commits in the last 6 months.

Use this if you are an AI researcher developing agents that need to interpret visual information and follow navigation instructions in realistic indoor settings.

Not ideal if you need synthetic environments or only require simple 2D navigation tasks.

AI-research robotics-navigation computer-vision reinforcement-learning natural-language-interaction
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

683

Forks

138

Language

C++

License

Last pushed

Jul 12, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/peteanderson80/Matterport3DSimulator"

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