China's Baidu Launches AI Model Simulating Road Environment for Robotaxis
Apollo World can generate up to 100,000 km of simulated driving daily, Baidu said, as automakers seek cheaper robotaxi development.
- On Tuesday, Baidu launched Apollo World, an AI system designed to simulate real-world environments for training robotaxis and reducing development costs for the Baidu-owned Apollo fleet's global deployment.
- Automakers currently face high costs developing autonomous vehicles, prompting firms to seek efficiency. Apollo World addresses this by generating multimodal data streams—camera and lidar observations—enabling self-driving systems to navigate simulated environments.
- Apollo World can generate "up to 100,000 km" of simulated driving daily, equivalent to three years of real-world testing. Frank McCleary, autonomous mobility expert at Arthur D. Little, said "the speed at which you can launch" depends on technology adaptation.
- Baidu-Owned Apollo competes with rivals WeRide, Pony, and Momenta Global in China's robotaxi market. Tesla uses an "end-to-end neural network" trained on human driving video to develop self-driving technology as competition intensifies globally.
- Morgan Stanley has estimated China's robotaxi fleet could grow to 1 million vehicles by 2035. Chinese firms pursue asset-light expansion strategies, partnering with automakers and operators rather than bearing full fleet ownership costs.
15 Articles
15 Articles
Baidu launches Apollo World model to train robotaxis in simulated environments · TechNode
Baidu unveiled Apollo World on November 3, a world model that simulates interactive road environments to train and test autonomous vehicles. The company said the system is already being used to support Apollo Go’s global robotaxi development and can generate up to 100,000 kilometers of simulated driving per day. Apollo World produces real-time camera and […]
From cyclists to wild dogs: Baidu’s new AI preps robotaxis for rare road hazards
For autonomous vehicles, the hardest lessons to learn are the ones that can test the skills of even the most experienced human drivers: an errant cyclist darting through a red light, or an animal bolting into oncoming traffic from behind a corner. The Chinese tech giant Baidu has developed a new AI-driven simulator to prepare its Apollo robotaxis for just such rare but high-stakes road hazards, as the firm looks to gain an edge in the fast-growi…
China's Baidu launches AI model simulating road environment for robotaxis
Baidu’s Apollo World trains robotaxis on cyclists and dogs that never existed
Baidu has built Apollo World, an AI world model that fills a virtual city with cyclists, pedestrians and drivers who react to its robotaxis as they move. The company says its Apollo Go fleet already trains and tests there, but it has published nothing on how closely the simulation matches real streets.
Coverage Details
Bias Distribution
- 75% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
