basiclab/TTSG
Traffic Scene Generation from Natural Language Description for Autonomous Vehicles with Large Language Models
This project helps autonomous vehicle developers create realistic traffic scenarios for testing and simulation. You provide a natural language description, and it generates a complete traffic scene, including vehicles and their behaviors, for use in a simulator like Carla. This is designed for engineers and researchers working on autonomous driving systems.
Use this if you need to rapidly generate diverse and specific traffic scenarios from text descriptions to test autonomous vehicle control systems without manual scene construction.
Not ideal if you need to simulate pedestrian interactions that require precise sidewalk positioning, as there's a known crash issue with Carla's pedestrian API.
Stars
55
Forks
7
Language
Python
License
—
Category
Last pushed
Nov 13, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/basiclab/TTSG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
chrisliu298/awesome-llm-unlearning
A resource repository for machine unlearning in large language models
worldbench/awesome-vla-for-ad
🌐 Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future
hijkzzz/Awesome-LLM-Strawberry
A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.
zjukg/KG-MM-Survey
Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey
worldbench/awesome-spatial-intelligence
🌐 Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems