Information prediction method, autonomous driving model training method and apparatus

The information prediction method in autonomous driving systems uses a generative model to encode image and driving data, addressing the need for accurate annotations by incorporating image generation as an auxiliary task, thereby enhancing environmental perception and scalability.

JP7876022B2Active Publication Date: 2026-06-18BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
BEIJING BAIDU NETCOM SCI & TECH CO LTD
Filing Date
2025-03-14
Publication Date
2026-06-18

AI Technical Summary

⚠Technical Problem

End-to-end autonomous driving systems face challenges in establishing robust environmental perception and representation due to the reliance on expensive and labor-intensive accurate perception annotations, limiting scalability and practicality.

⚗Method used

An information prediction method that uses a generative model to predict control information by encoding image and driving data, where image generation serves as an auxiliary task, reducing the need for accurate perception annotations and enabling scalable deployment.

🎯Benefits of technology

Enables robust environmental perception and representation in autonomous driving without relying on complex perception tasks, providing a low-cost and scalable solution for end-to-end autonomous driving technology.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007876022000014
    Figure 0007876022000014
  • Figure 0007876022000015
    Figure 0007876022000015
  • Figure 0007876022000016
    Figure 0007876022000016
Patent Text Reader

Abstract

To provide an information prediction method to be applied to a scenario of autonomous driving, etc., a method of training an autonomous driving model, a device, an apparatus, a medium, a program product, and an autonomous driving vehicle.SOLUTION: An information prediction method includes acquiring perception data including image data collected by a sensor in a vehicle and driving data of the vehicle, encoding the image data to obtain an image token sequence corresponding to the image data, encoding the driving data to obtain a driving feature corresponding to the driving data, and generating a prediction token sequence corresponding to the image token sequence and a control information for the vehicle by using a generative model on the basis of the driving feature and the image token sequence.SELECTED DRAWING: Figure 2
Need to check novelty before this filing date? Find Prior Art