Hello Robotaxi has introduced its generative driving world model, HelloWorld. The system is designed to support autonomous driving research by focusing on on-demand driving data construction and interactive strategy testing.

The model integrates scene control, continuous generation, multi-sensor observation, and efficient inference. It allows developers to generate multi-view videos and LiDAR observations based on specific requirements.

Users can modify scenarios by editing vehicle and pedestrian movements or adjusting environmental conditions such as rain, snow, and lighting. The model also supports natural language prompts to create complex traffic situations.

This tool aims to expand the coverage of long-tail scenarios that are difficult to capture through real-world data collection. Developers can use it to simulate construction zones, dense traffic, and pedestrian crossings.