# Baidu Says Apollo World Can Simulate 100,000 Kilometers Daily By Simon Yoon Canonical URL: https://www.tokenpost.com/news/technology/48201 Published: 2026-11-04T03:52:19.000Z Updated: 2026-11-04T03:52:19.000Z Section: Technology > Baidu says Apollo Go is already using the system in global testing. It can model complete trips with vehicles and pedestrians responding to traffic changes. Baidu unveiled Apollo World at its AI Day·Apollo event in Shenzhen on Tuesday, Nov. 3, describing it as a world model for training and validating Apollo Go robotaxis. The company puts Apollo World’s daily simulation capacity at up to 100,000 kilometers (62,000 miles). Baidu says Apollo Go is already using it in testing and validation work around the world. In the simulated settings, vehicles and pedestrians act as AI agents that make decisions and respond to traffic changes. Baidu says Apollo World can generate camera and lidar observations in real time and represent a continuous trip from pickup through drop-off. Real-road data helps identify situations for virtual testing, and results from those tests are fed back into the driving system. Baidu likened a day of simulated mileage to the road testing a single autonomous vehicle with a safety driver might complete in about three years. The comparison is the company’s estimate of the system’s simulation capacity. At the event, Baidu outlined a “2+3” framework for world models. Causality and interaction are the two baseline qualities; physical accuracy, persistence and real-time performance are three additional measures. The announcement gives Apollo Go a confirmed role for the model after Baidu’s earlier [plan to disclose its world-model research](), which did not specify an autonomous-driving application. As of the event, Apollo Go had reached 28 cities and served more than 23 million rides, Baidu said. The service had accumulated more than 350 million kilometers of autonomous driving, including more than 240 million kilometers with no driver in the vehicle. The launch comes as robotaxi operators face high development and fleet costs. Chinese companies have partnered overseas with automakers, ride-hailing platforms and local fleet operators to avoid bearing the full cost of owning and running vehicles. Training models and acquiring vehicles remain costly parts of the work. “They still have the capex of training models ... and vehicles, a challenge that every autonomous vehicle company is going to face,” said Frank McCleary, an autonomous mobility and urban transportation expert at Arthur D. Little. ## Links in this article - [plan to disclose its world-model research](https://www.tokenpost.com/news/technology/42515)