Baidu Apollo releases Apollo World world model
The story so far
No overview yet — start with the coverage timeline below.
Coverage timeline
Follow the coverage to see every side of the story.
- QbitAIBaidu ApolloWorld's world model performs real-time simulation of the global environment, enhancing virtual road test efficiency by three years.
Baidu ApolloWorld's world model uses AI to simulate virtual traffic environments in real-time, enabling autonomous vehicles to complete full Robotaxi trips. One day of virtual testing mileage is equivalent to three years of real-world testing for a real test vehicle. This model has been applied to the global testing of Luobu Kuaipao. Through multi-agent driving technology, it achieves autonomous decision-making and interaction among traffic participants, combined with a new generation of L4 end-to-end model architecture, significantly improving testing efficiency.
- ITHome · AIBaidu Apollo World's world model unveiled: Using AI to teach AI to drive
Baidu Apollo first reveals physical AI intelligent body-driven full-modal world model Apollo World, can generate realistic videos following real-world laws and support autonomous vehicles to complete complete travel tasks from start to finish. The model proposes a '2+3' judgment standard for world models, requiring causality, interactivity, physical accuracy, persistence, and real-time performance, supporting AI intelligent body decision-making and interaction in virtual cities, already used in Luobo Fast global testing and verification.
- 36Kr · AIBaidu Apollo World World Model Unveiled
Baidu Apollo first reveals the intelligent agent-driven, multimodal world model Apollo World for physical AI, proposing a '2+3' judgment standard for world models. In the virtual city constructed by Apollo World, traffic participants such as vehicles and pedestrians have decision-making and interaction capabilities.