Industrial AI Podcast
Latest Episodes
Industrial AI and Motion Control - how do we reduce engineering time?
Two Siemens engineers described us their reinforcement approach in a chocolate factory. One important asset is the digital twin of the plant.
LSTM for ABB's Augmented Operator
In this episode we have three guests from ABB and talk about the Augmented Operator - what is it supposed to do, how was it built and where will it be used?
How an Ex-MAN-employee uses reinforcement learning for factories
Ramakrishna Nanjundaiah from Phantasma simulated the driving behaviour of vehicles. Now he wants to bring the knowledge to the shop floor. Reinforcement learning is supposed to make factories more eff
SDK for machine learning on the edge
Lamin from Infineon recommended that we talk to Jon Linden from Ekkono. The Swede explains his ML on the edge approach and why Volvo, Siemens and ABB work with him.
More than an interface for open source AI-tools - what is AIUI?
Peter has written many letters and now Ernst Dieter Dickmanns is receiving The Order of Merit of Germany. We are very happy for him. In the main part we talk to Martin Schiele about his company and th
IABG: How to safeguard AI?
Peter Seeberg discusses runtime assurance, safe AI and how IABG is working on it with Dr. Lukas Hhndorf.
What is Volkswagen's AI research working on?
Shortly before the end of 2022, we met with Patrick van der Smagt. He is Director of AI Research at VW Group.
The Festo AI strategy on products and processes
We spoke with Jan R. Seyler, Director Adv. Dev. AI and Controls at Festo, about generative AI, reinforcement learning and the role AI will play in the development of products and processes at Festo.
NeurIPS Special - more than ChatGPT
NeurIPS is one of the most important AI conferences. Prof. Dr. Gnter Klambauer from JKU Linz was on site and reports for us.
How do you make data accountable? With an AI model.
Michael Welsch is a mechanical engineer. His approach makes data accountable. A neural network learns to decompose and reconstruct a company's data lake, which it can only do if it learns to model the