decisionforce/pgdrive

PGDrive: an open-ended driving simulator with infinite scenes from procedural generation

51
/ 100
Established

PGDrive provides an open-ended driving simulator that generates infinite unique road networks, traffic patterns, and environmental settings. It takes in vehicle control inputs and simulates realistic physics, outputting sensory data for training and evaluating autonomous driving systems. This tool is for researchers and engineers developing self-driving car algorithms or intelligent transportation systems.

132 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need a lightweight, efficient, and realistic simulation environment to test and train autonomous driving agents in a wide variety of road conditions without manual map creation.

Not ideal if you need a highly detailed, photorealistic graphics simulator for human-in-the-loop driving or require a specific, non-randomized real-world map.

autonomous-driving robotics-simulation reinforcement-learning transportation-research vehicle-dynamics
Stale 6m No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 16 / 25

How are scores calculated?

Stars

132

Forks

18

Language

Python

License

Apache-2.0

Last pushed

Jun 20, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/decisionforce/pgdrive"

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