On August 30, Ideal announced the latest developments in the end-to-end model, VLM visual language model and world model, as well as autonomous driving technology architecture at the Chengdu Auto Show.
Officials said that it is ideally expected to reach 3 billion kilometers by the end of this year, and new functions for AES secondary avoidance and AES scenario expansion are currently being developed.
At the same time, it announced that it had entered a new phase, named supervised autonomous driving.
In addition, the end-to-end +VLM 10,000-person experience group began recruiting today, and OTA 6.
2 will be launched today.
, 
, , , , end-to-end models are used to process conventional driving behavior.
Only one model passes through from sensor input to driving trajectory output.
Information transfer, inference calculation and model iteration are more efficient, and driving behavior is more humanoid.
, the VLM visual language model has strong logical thinking capabilities, can understand complex road conditions, navigation maps and traffic rules, and deal with difficult unknown scenarios.
, 
and .
At the same time, the autonomous driving system will conduct ability learning and testing in a virtual environment built based on the world model.
The world model combines reconstruction and generation of two paths.
The test scenarios constructed not only conform to the real laws, but also have excellent generalization capabilities.
(Text/Picture Car Home Tang Dynasty), return to the first electric network home page>,.
