Artificial intelligence modeling techniques for vision-based surface determination.

JP2025532890APending Publication Date: 2025-10-03TESLA INC
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
JP2025518216
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2022-09-30
Filing Date
2023-09-28
Publication Date
2025-10-03

AI Technical Summary

Technical Problem

Autonomous vehicles and robots face challenges in navigating complex and dynamic environments due to the need for accurate prediction of occupancy and surface attributes in their surroundings, which is crucial for safe navigation and decision-making.

Method used

A trained artificial intelligence (AI) model analyzes image data from cameras to predict occupancy and surface attributes, generating a 3D representation of the ego's surroundings, including navigable surfaces, slopes, and obstacles, without requiring prior image data for training.

Benefits of technology

Enables autonomous navigation by instantly predicting surroundings, allowing vehicles and robots to navigate safely and efficiently without relying on pre-captured image data, enhancing their ability to handle unknown environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2025532890000001_ABST
    Figure 2025532890000001_ABST
Patent Text Reader

Abstract

Disclosed herein are methods and systems for using artificial intelligence modeling techniques to train and run an artificial intelligence model to analyze camera feeds received from an ego and predict surface data for various surfaces surrounding the ego. The method includes inputting image data of the space surrounding the ego object into the artificial intelligence model using one or more cameras of the ego object, predicting surface attributes of one or more surfaces in the space surrounding the ego object by running the artificial intelligence model, and generating a dataset based on the one or more surfaces and their corresponding surface attributes.
Need to check novelty before this filing date? Find Prior Art