Marelli and AWS pioneer AI-driven system test generation for software-defined vehicle validation
Marelli, with AWS, has developed an AI-driven System Test Generation Agent that automates the creation of test cases from engineering requirements, accelerating validation for software-defined vehicles.
What Happened
Marelli, a global automotive supplier, has partnered with AWS to create the AI-driven System Test Generation (STG) Agent. This tool automates the generation of system test cases from engineering system requirements, a critical step in validation. As vehicles become more software-defined, managing large volumes of requirements and ensuring traceability has become challenging. The STG Agent helps improve efficiency and consistency, reducing validation time.
“The STG Agent represents an important step forward in how we validate solutions for software-defined vehicles. By combining our engineering expertise with advanced AI capabilities from AWS, we significantly accelerate validation cycles and ensure consistent quality across global programs.”
“Marelli's approach to automating system validation demonstrates the transformative potential of generative AI in automotive engineering. By leveraging Amazon Nova foundation models and Amazon Bedrock, companies are setting new standards for how software-defined vehicles are developed and validated.”
Why this matters
The AI-powered tool reduces validation time and improves consistency, helping automakers deliver new features faster and more reliably as vehicles become increasingly software-defined.
Terms in This Story
- Software-defined vehicle
- A vehicle whose features and functions are primarily enabled by software, allowing for updates and new capabilities over time.
- System test cases
- Specific scenarios or conditions used to verify that a system meets its requirements.
- Validation
- The process of checking that a product meets the needs and requirements of its users and stakeholders.
- Generative AI
- A type of artificial intelligence that can generate new content, such as text, images, or test cases, based on patterns learned from data.
Summarised from the linked release; details can be imperfect — always verify against the original source.