公开(公告)号：US20250153711A1

公开(公告)日：2025-05-15

申请号：US18523918

申请日：2023-11-30

Applicant: INSTITUTE FOR INFORMATION INDUSTRY

Inventor： I-Heng MENG ,  Jun-Dong CHANG ,  Ai-Ting CHANG

IPC: B60W30/095 ,  G06V10/774 ,  G06V20/58 ,  G08G1/01

Abstract: A decision generating device is configured to execute the following operations. A driving image of a vehicle and a driving status corresponding to the driving image are obtained. An image recognition is performed on the driving image by using an image recognition model to generate object information of objects in the driving image. A predictive driving information is generated based on the object information and the driving status by using a prediction model, the predictive driving information includes object movement predictions of the objects and a movement prediction of the vehicle, and the prediction model is generated based on a trained generative content model. A driving decision is generated based on the predictive driving information.

公开(公告)号：US20230062694A1

公开(公告)日：2023-03-02

申请号：US17450071

申请日：2021-10-05

Applicant: INSTITUTE FOR INFORMATION INDUSTRY

Inventor： I-Heng MENG ,  Ching-Wen LIN ,  Ai-Ting CHANG

IPC: G01C21/00

Abstract: A navigation apparatus and method are provided. The apparatus receives an input data and at least a piece of positioning information. The apparatus performs a semantic analysis on the input data to generate a plurality of pieces of semantic information. The apparatus selects at least one of the semantic information as a filtering condition. The apparatus compares the filtering condition with a plurality of semantic tags in the map data to determine whether the semantic tags have at least one first semantic tag that meets the filtering condition. When determining that the semantic tags have the at least one first semantic tag, the apparatus generates a comparison result, wherein the comparison result is related to an object corresponding to the at least one first semantic tag. The apparatus generates a navigation route according to the comparison result and the at least a piece of positioning information.