Audi unveils humanoid proof of concept to automate parts sequencing in Ingolstadt

Audi and Agile Robots, together with Dassault Systèmes and NVIDIA, made the announcement at Nvidia GTC Berlin that their joint project to automate parts sequencing with humanoid robots is already underway.

Audi emphasised that demand-driven material supply relies on highly complex sequencing operations, noting that approximately 1 million picks each day are necessary to ensure that the right parts reach the right workstation in the right order for assembly.

In an effort to automate this process, the four companies are working to deploy mobile humanoids from Agile Robots to pick parts from material containers and place them in the correct sequence for final assembly of Audi vehicles.

“The future of manufacturing will be defined by how successfully we combine industrial expertise with artificial intelligence," said Gerd Walker, Audi board member for production and logistics. "For decades, picking within the sequencing process has remained one of the toughest automation challenges in automotive logistics. Together with our partners, we are now exploring how AI-powered robotics can help solve this challenge and unlock a new level of productivity in our Audi factories."

The humanoids are currently operating within the Audi Production Lab – the company's innovation space for testing future production and logistics technologies – but the proof of concept is designed to automate parts sequencing at Audi's plant in Ingolstadt, Germany.

Testing in a virtual environment

Before the robots are deployed within Audi's Ingolstadt facility, a virtual twin of the "smart intralogistics environment" is being created using Dassault Systèmes' Delmia application – a software platform designed to build three-dimensional visualisations of real environments.

“Audi and Agile Robots are using Dassault Systèmes Delmia and Nvidia Omniverse physical AI libraries to simulate and validate mobile humanoids for parts sequencing, tackling one of automotive logistics’ toughest workflows with minimal changes to existing operations," said Deepu Talla, vice president of robotics and edge AI at Nvidia.

Testing will take use Dassault Systèmes’ 3DExperience platform, which combines the company's own virtual modelling tools with those from Nvidia to simulate how the humanoid will perform its tasks before being deployed in the factory. This digital twin will be used to test the feasibility, ergonomics, safety and timings of the humanoid's tasks.

“The breakthrough is not simply bringing humanoid robots into the factory at high pace," said Philippe Laufer, executive vice president of 3DS global brands at Dassault Systèmes. "It is being able to engineer and validate their mission and role before they ever enter it physically."

The project will be supported by both human expertise and artificial intelligence. Audi supply chain experts are contributing their sequencing expertise and helping to define the operational requirements for testing the use case under real-world conditions. And looking ahead, Dassault Systèmes’ AI-powered virtual companion, Leo, will be used to assist engineers and accelerate the testing process from months to days.

Addressing a pressing issue

Read more: Why do so many AI projects fail and what does effective scaled use look like?

According to research, it is estimated that more than 80% of AI projects fail – twice the rate of corporate IT projects that do not involve AI. Experts at ALSC Global 2026 shared insight into why so many AI projects in automotive logistics fail to reach their full potential and what is needed to effectively scale AI.

As Nitin Sethi, vic president and head of IT at Autoliv Americas, emphasised on stage at the ALSC Global conference this year, the most common issue when deploying AI or new digital tools is a disconnect between the solution and the problems they are deployed to address.

This point was also made by John Rich, director of AI transformation at Mazda North American Operations on the Red Sofa at ALSC Digital Strategies North America in June. "I think it's so important to connect AI to what the business is trying to accomplish," he said.

But in this case, Audi has been very clear about the problems it intends to solve through the use of these humanoids. It noted that two of the most persistent challenges in automation have been the handling of high-variant or semi-rigid parts and the reliable picking of unsorted components from containers. It noted that Agile Robots' mobile humanoids are designed to address both.

According to Audi, the robots' dual-arm manipulation capabilities enable them to handle large and flexible parts, while AI-powered perception allows them to identify, grasp and manipulate a wide variety of components with precision, even when stored in mixed containers or presented in varying positions and packaging.

Operating at human height, the robots are able to slot into Audi's existing environment without the need for modifications. Audi has said that this proof of concept supports its vision of highly automated in-house logistics within the thinking factory, where AI and robotics work hand-in-hand with employees.

It noted that by automating complex and repetitive sequencing tasks, the technology can help reduce manual workload, increase efficiency and enable employees to focus on higher-value activities.

"For decades, picking within the sequencing process has remained one of the toughest automation challenges in automotive logistics," said Audi's Walker. "Together with our partners, we are now exploring how AI-powered robotics can help solve this challenge and unlock a new level of productivity in our Audi factories."

Working together on this proof of concept, Audi, Agile Robots, Dassault Systèmes and Nvidia are aiming to demonstrate how humanoid robots powered by physical AI can become a game-changer for the future of logistics, enabling the automation of tasks that have long been beyond the reach of traditional robotics while paving the way for high-volume series production.