dSpace, a provider of simulation and validation solutions for automated and connected vehicles, is working with Amazon Web Services (AWS) to develop an advanced scenario generation solution using generative AI technologies.
The new feature, supported by the AWS Generative AI Innovation Center, will be integrated into the dSpace portfolio for software-in-the-loop (SIL) and hardware-in-the-loop (HIL) testing and data-driven development.
It employs a large language model (LLM) available on Amazon Bedrock and a retrieval-augmented generation (RAG) architecture, using scenario data from dSpace. This technology is designed to enable users to create numerous complex and realistic scenarios, including edge cases in line with the ASAM OpenScenario standard, by entering textual descriptions.
Both companies says that this capability enables automotive manufacturers and suppliers to simulate and validate autonomous driving systems more comprehensively.
“dSpace is an AWS Automotive Competency Partner. In this new initiative, we are creating innovative capabilities in scenario generation for autonomous vehicle validation. Using generative AI technologies, we ensure that our customers can easily create realistic and diverse simulation scenarios to develop safer and more reliable autonomous vehicles,” explained André Rolfsmeier, director of strategic product management at dSpace.
dSpace is demonstrating these capabilities for the first time at the AWS Automotive Symposium in Munich, Germany, on June 26.