Baidu Discloses Apollo World World Model; Apollo Go Has Surpassed One Million Kilometers of Fully Unmanned Operations

Related topics top start Related topics top end Futures promotion begin Futures promotion end Miaopai begin Miaopai end Video player start Video player end Market chart begin Market chart end

Sina Tech News, November 4 afternoon — At Baidu AI Day's Apollo special session, Baidu Apollo for the first time disclosed Apollo World, an agent-driven omni-modal world model for physical AI, and proposed a "2+3" criteria for judging world models. Currently, the model has been used in the global testing and validation of Apollo Go (Luobo Kuaipao), with end-to-end fully driverless operations exceeding one million kilometers, helping to bring autonomous driving to scale.

It is reported that Apollo World can model all traffic participants in a virtual scene as AI agents with decision-making and interaction capabilities, supporting driverless vehicles to travel between any origin and destination in a virtual city, and creating virtual-scenario orders that verify the "infinite future" in advance. Based on the virtual training environment provided by Apollo World, the AI Driver can learn, validate, and iterate.

In traditional simulation, other traffic participants are more like props running according to scripts. But in the virtual city built by Apollo World, traffic participants such as vehicles and pedestrians are all modeled as AI agents with decision-making and interaction capabilities, able to adjust their actions according to changes in the surrounding traffic. A driverless vehicle slowing down, changing lanes, or yielding may trigger different reactions from other participants, enabling the autonomous driving system to be trained and tested in a continuously changing traffic environment.

Some industry observers analyze that Apollo World can "travel 100,000 kilometers a day," and the virtual road-test mileage it completes in one day is equivalent to about three years of continuous testing by a real road-test vehicle equipped with a safety driver. Relying on the capability leap brought by the world model, combined with the data flywheel effect, the industry will show a pattern where the strong get stronger, and this trend is also pushing the industry toward the long-awaited "AGI moment."

For autonomous driving to scale, it must simultaneously balance safety, intelligence, and scale, and among these three there exists an "impossible triangle." Long-tail scenarios are difficult to fully cover through real-vehicle mileage, deploying in new areas involves testing costs and trial-and-error risks, and continuous driving capability across road segments and scenarios requires large-scale validation. Apollo World transforms the complex interactions and risk scenarios in real operations into a repeatable, controllable, and scalable virtual test environment, and generates new scenarios not yet covered by reality, allowing driverless vehicles to complete driving simulations in the virtual world before real-vehicle deployment, absorbing testing costs and deployment risks in the virtual world first, and letting AI teach AI to drive.

It is reported that Apollo Go has currently launched in 28 cities worldwide, completed over 23 million trips in total, with total autonomous driving mileage exceeding 350 million kilometers, of which fully driverless mileage exceeds 240 million kilometers, and has carried out driverless practices in both left-hand and right-hand drive markets. Relying on real driving data, Apollo World extracts high-value scenarios, and virtual test results in turn feed back into vehicle-side iteration, forming a closed loop in which real operations and virtual validation reinforce each other. (Wen Meng) news_keyword_pub,stock, iframe below body iframe below body General statement General statement QR code at end start QR code at end start

QR code at end start QR code at end start Editor name and work code

Editor name and work code