AI in Vehicle Development – How Porsche is Using Large Language Models
At Porsche Centre South Lakes, we love seeing how cutting-edge technology is shaping the future of Porsche engineering. Artificial Intelligence (AI) is already playing a major role in vehicle development, and Large Language Models (LLMs) are now being used to streamline processes, improve efficiency, and enhance precision in car design and testing.
A Modern Rosetta Stone for Engineering
Back in 1799, the Rosetta Stone unlocked the secrets of Egyptian hieroglyphics. Today, LLMs are doing something similar for natural language processing, allowing AI to interpret and process human language in ways we’ve never seen before.
A large language model is based on neural networks and is able to decode the meaning of natural language in context and machine-process it. LLMs can understand, process, and translate language, but also generate new texts, explains Dr. Joachim Schaper, Senior Manager AI and Big Data at Porsche Engineering.
Porsche Engineering is already using AI-powered tools like ChatGPT and LLaMa to increase efficiency in the development process. But unlike standard AI chatbots, Porsche trains its models using its own engineering data, ensuring these systems understand the intricacies of vehicle development.
Making Vehicle Development Smarter
One of the first applications for LLMs at Porsche Engineering is in the revision of customer specifications. Every vehicle development project is different, and requirements often come in varying formats from clients. Before engineers can begin work, they need to translate these requirements into precise technical specifications.
Until recently, this was a manual and time-consuming task, but with the help of AI-driven specification templates, the process has become much faster and more reliable. LLMs help identify patterns, check for completeness, and ensure clarity, reducing the chance of errors creeping into development.
AI That Learns and Improves Over Time
Unlike traditional software, LLMs can infer meaning from context, making them incredibly powerful for interpreting technical documentation. “As a demonstration project, we revised the requirements catalog for a vehicle component,” says Volker Reber, Senior Manager High-Voltage System Development at Porsche Engineering.
After training ona dataset of just a few hundred items, the AI was able to quickly convert thousands of individual specifications into a standardised format, slashing processing times. Engineers now spend less time on tedious paperwork and more time on innovation.
The more the system is used, the better it gets. Feedback from engineers helps to refine the AI’s understanding, making it faster and more accurate with each project. In fact, initial testing showed a 50% reduction in workload, and future optimisations are expected to improve efficiency even further.
AI Enhancing Everyday Engineering Tasks
LLMs aren’t just helping with specification processing – they’re also being used in data management during vehicle testing. When test drivers detect a fault in a new system, they log the issue in a central database. But with thousands of tests happening across multiple projects, similar issues can sometimes be recorded multiple times under slightly different descriptions, making troubleshooting harder than it needs to be.
Now, LLMs are being trained to compare test logs in real-time. Engineers can enter an issue, and the AI will instantly cross-check it with existing reports to highlight related faults. “The AI gives real-time feedback on similar errors that have been logged before,” explains Dr. Fabian Hinder, Lead Engineer at Porsche Engineering. “This makes it easier to spot recurring issues across different vehicle models, reducing duplication and improving troubleshooting.”
The Future of AI at Porsche
Porsche’s innovation teams are continuously exploring new ways to integrate AI into vehicle development, helping engineers work faster, smarter, and more effectively. “Developers today have to manually query the aggregated data for a problem in the central database. In our lighthouse project, we are creating a concept with which the LLM will carry out this activity in the future,” says Antoon Versteeg, Innovation Manager at Porsche.
By combining AI-driven insights with Porsche’s world-class engineering expertise, the brand is setting a new standard for data-driven vehicle development. While AI is making huge strides, human expertise remains irreplaceable. Porsche is committed to ensuring that AI tools complement engineers, not replace them, so they can focus on what they do best – building some of the finest sports cars in the world.
The automotive industry is just scratching the surface of what AI can do, and at Porsche Centre South Lakes, we can’t wait to see how these advancements shape the future of driving.