公开(公告)号：US20250074453A1

公开(公告)日：2025-03-06

申请号：US18457609

申请日：2023-08-29

Applicant: GM Global Technology Operations LLC

Inventor： Ramesh Sethu ,  Rami Ismail Debouk ,  Joseph D'Ambrosio

IPC: B60W60/00

Abstract: The method for autonomous driving includes receiving vehicle data about an autonomous vehicle, creating, using the vehicle data, a multi-domain ontology data structure. The multi-domain ontology data structure includes information about tasks, objects, missions, events, and responses of the autonomous vehicle in a plurality of operational design domains. The method further includes generating use cases, requirements, and test cases for the autonomous vehicle based on the multi-domain ontology data structure. The method may include controlling the autonomous vehicle in accordance with the use cases generated using the multi-domain ontology data structure.

公开(公告)号：US20240168748A1

公开(公告)日：2024-05-23

申请号：US18057001

申请日：2022-11-18

Applicant: GM Global Technology Operations LLC

Inventor： Ramesh Sethu ,  Rami Ismail Debouk ,  Paolo Giusto ,  Azeem Sarwar

IPC: G06F8/65 ,  G06F8/33

CPC classification number: G06F8/65 ,  G06F8/33

Abstract: A system for CI/CD of AI/ML based components includes a cloud infrastructure which receives multiple new requirements from a vehicle designer or a developer, with the new requirements adapted for artificial intelligence/machine learning (AI/ML) based components of a vehicle. A dataset is provided. A metamorphic relations (MR) module receives input information from the dataset and sends MR information to the dataset. A components requirements database includes the new requirements in addition to existing requirements for the AI/ML based components. The MR module also receives components requirements data from the components requirements database and sends the MR information to the components requirements database. An AI/ML algorithm analyzes the input information from the dataset and prepares an updated component dataset.