KI in der Industrie

In this episode of the Industrial AI Podcast we talk about MAN TruckScenes: the world's first freely available sensor and driving data for autonomous trucks. In the newspart Peter and Robert discuss their plans and their news.

In the interview with Peter Seeberg, Sepp Hochreiter explains how he did it, what state tracking is, how he came up with the devices and what the next steps are.

In this episode, Robert Weber talks to Tom Zehle from Airbus. He explains how he stays up to date, how he analyzes papers, and what he wants from research. The Industrial AI Podcast reports weekly on the latest developments in AI and Machine Learning for the engineering, robotics, automotive, process and automation industries. The podcast features industrial users, scientists, vendors and startups in the field of Industrial AI and Machine Learning. The podcast is hosted by Peter Seeberg, Industrial AI consultant and Robert Weber, tech journalist.

Peter Seeberg talks to Thomas Dhollander, Co-founder & CPO at Timeseer.AI about Trusted IIoT Data as the Key to Proactive Operations.

In this episode, we talk to Lucas from MathWorks about their Safe AI Approach and how it can be used to make money, think about the Pope, and introduce our new US correspondent.

MAGS harness the creative potential of generative models while enabling intelligent agents to collaborate, adapt, and solve complex problems in real time. This new synergy elevates AI systems beyond traditional automation, pushing them into the realm of autonomous problem-solving, creative thinking, and adaptive decision-making. The development of MAGS marks a significant shift in the way organizations approach challenges in rapidly evolving environments. By integrating Large Language Models (LLMs) and other advanced generative models with agents capable of learning and interacting independently, MAGS enable organizations to address problems that are not only multifaceted but also constantly changing. This guide explores the foundational elements of MAGS, their architecture, and why they matter for industries that need to navigate complexity, unpredictability, and scale.

We need to talk about talents – AI talents. We lack them in companies (really?), but also in universities, and, "Now that Trump is in power in America, it is easy to poach them and bring them to Europe," according to some politicians. The idea is not far-fetched, but Trump bashing alone will not attract anyone to Europe. Europe first has to do its homework.

Many of you still remember the fieldbus wars, then peace came and we solved industrial communication with TSN and many other technologies. But now the agents are coming. What are they – “just” a new layer?

In the Newspart we talk about Hannover Messe, Agents, MCP and a lot more. Robert talked to Miroslaw Bartecki from Kyp.ai about Data, Supply Chains and AI, EPR-Systems and Agents and a lot more.

We needed to discuss the topic because AI plays a crucial role in it and the guys from Fraunhofer IPA are the experts when it comes to robotics in Europe.

We're starting to feel like we're a CNC podcast. Two weeks ago, Sandvik was a guest, today Limitless CNC. The industry is highly innovative when it comes to industrial AI.

Peter Seeberg talks to Prof. Dr. Jay Lee not only about the past and the special features of industrial AI, but also looks to the future with him.

We have already had an episode with the Sandvik CTO, but this time we go into detail. We talk about agents and how Sandvik uses them, what is needed for them and what they can ultimately do.

The system enables companies to generate precise, process-specific motion trajectories that optimize production parameters and enhance adaptability, efficiency and user-friendliness. No wonder the Canadian company won the prestigious ROBOTICS AWARD 2025 by Hannover Messe.

DeepSeek has impressed many and reinforcement learning is getting new attention. However, it was never gone, but is now celebrating a revival. Jan Kountik is one of the most prominent AI experts in the field. We talk to him. We talk to Jan Koutnik about prejudices, approaches and new ideas in reinforcement learning and why new ideas are needed.

Frank Hutter and his team were recently able to secure nine million euros. They are now embarking on timeseries and their first industrial projects. What are the Freiburg-based company's plans?

Andrii Zadaianchuk's CV is impressive: ETH Zurich, Max Planck and University of Amsterdam. We spoke to the exceptional researcher from the Netherlands. It's all about industrial AI and world robotics models.

We wanted to know who Cusp AI's customers are, what the platform looks like and how it brings together AI and domain knowledge. And Max explains what his product looks like in the end.

Prof. Dr. Günter Klambauer explains Deepseek and evaluates the new model for us. Prof. Dr. Daniel Leidner from DLR, Anders Billesø Beck from Universal Robots and Dr. Karsten Roscher from Fraunhofer IKS discuss robotics, AI and safety with us.

We repeatedly see individual companies rolling out AutoML as a product, but the technology has not yet fulfilled the great promise of empowering domain experts. Why?

An exploration into the intersection of artificial intelligence and manufacturing, where complex challenges meet innovative solutions. Expect insights that go beyond buzzwords to the heart of what drives efficiency and transformation in the manufacturing sector.

Together, we explore the evolution of agent technology, its practical use cases, and the profound impact it may have on industrial workflows. This is a thought-provoking discussion about the intersection of AI, industry, and the human-first design approach that drives innovation forward.

The episode was recorded on the fringes of the Beyond Safety Forum at the beginning of December. Safety experts and AI thought leaders discussed the interplay between the two disciplines on site. Conclusion: It won't be easy.

At the end of the year, Sepp Hochreiter looks back on the NeurIPS. We talk about the most interesting episodes and what may come next.

From grounded AI models to explainable AI and overcoming data silos, the conversation dives into the nuts and bolts of creating domain-specific AI solutions. Balancing people, processes, and technology, this episode sheds light on the challenges and opportunities in leveraging AI for manufacturing reliability, maintenance, and optimization.

Our guest is Joern Steinbeck and we discuss his GenAI approach with LLaMA. Joern explains in the podcast how he uses the LLM for OEE optimisation and what he has learned.

From silos in the food industry to fluidized bed reactors in the chemical sector, Johannes explains how neural networks are pushing the boundaries of numerical simulation, why real-time engineering could soon become a reality, and what this means for digital twins. A conversation about science, visions, and the potential to rethink entire industries.

Spleenlab is a highly specialized AI software company founded with the Idea to redefine Safety and AI. Since April 2018, the company has been primarily engaged in the development and distribution of safe Machine Learning algorithms for the semi- and fully autonomous mobility, especially the flight of unmanned aerial vehicles (UAV), helicopters, Air Taxis, driving vehicles and beyond. The groundbreaking fusion of different sensors, such as camera, laser and radar by means of Machine Learning is the core business of the company. The generated SLAM (Simultaneous Localization and Mapping) enables completely new applications and products for any kind of autonomous mobility.

This episode unpacks how AI isn't just about futuristic robotics but is already reshaping industries as unassuming as brooms and brushes. What makes a self-learning system adaptable in such high-stakes settings? Why does it matter that AI “never stops learning”? Join us as we uncover the unexpected depth behind automation and explore how cutting-edge AI is changing MedTech manufacturing from the ground up.

In a fascinating conversation, Dr. Christian Gilcher guides us through the differences between RPA (Robotic Process Automation) and the more advanced APA approach, which uses AI agents to dynamically manage complex processes in a compliant and efficient manner. They discuss how APA not only solves cost and capacity issues in regulated industries but also provides an innovation boost within the industry. A highlight: APA's potential goes far beyond optimization, paving the way for entirely new industrial processes in the future.

We talk about AI research at ASML, new generations of machines, federated learning, MLOps and many more topics. In the news part Peter Seeberg and Robert Weber discussed the RosCon, NVIDIAs show and Microsoft´s engagement in Germany, Honeywell and Siemens.

From explainable AI to organizing massive AI projects, this isn't just about tech; it's about solving real-world challenges. Listen in as they share candid discussions, lessons learned, and visions for the future, all without the buzzword hype—just real insights from people making AI work in industry. Thanks for listening. We welcome suggestions for topics, criticism and a few stars on Apple, Spotify and Co. We thank our partner **SIEMENS** https://www.siemens.de/de/ Our event in January in Frankfurt ([more](https://www.hannovermesse.de/de/rahmenprogramm/special-events/ki-in-der-industrie/))

He explains the need for widespread AI knowledge across departments to enable data-driven innovation, starting with young apprentices and dual-study students. Ottnad highlights the importance of understanding data quality, hands-on experience, and interdisciplinary collaboration. Thanks for listening. We welcome suggestions for topics, criticism and a few stars on Apple, Spotify and Co. We thank our partner **SIEMENS** https://www.siemens.de/de/ Our event in January in Frankfurt ([more](https://www.hannovermesse.de/de/rahmenprogramm/special-events/ki-in-der-industrie/)) Our guests are [Dr. Jens Ottnad](https://www.linkedin.com/in/dr-jens-ottnad-9b308418b?originalSubdomain=de)

The basis for the discussion is a paper by Prof. Dr. Marco Huber, which was published a few weeks ago: How should AI decisions be explained? Requirements for Explanations from the Perspective of European Law. Thanks for listening. We welcome suggestions for topics, criticism and a few stars on Apple, Spotify and Co. We thank our partner **SIEMENS** https://www.siemens.de/de/ Our event in January in Frankfurt ([more](https://www.hannovermesse.de/de/rahmenprogramm/special-events/ki-in-der-industrie/)) Our guests are [Marco Huber ](https://www.linkedin.com/in/marco-huber-78a1a151/) and [Tom Cadera ](https://www.linkedin.com/in/tom-cadera-05948636/) #machinelearning #ai #aimodel #industrialautomation #manufacturing #automation #genai #datascience #mlops #llm #IndustrialAI #artificialintelligence #Safety #NVIDIA #xLSTM #IndustrialAI #bluecollar #Transformer #HPE #Compute #Hardware #robotics #vision #PLC #Automation #Robotics #IndustrialAIPodcast #Vanderlande #Warehouse #Logistics #XAI #FraunhoferIPA

Bas shares insights on how AI is enhancing control rooms, optimizing operational workflows, and addressing challenges like data sharing. The discussion also explores future trends, including the potential of AI-based simulation and reinforcement learning for fully automated warehouses. Thanks for listening. We welcome suggestions for topics, criticism and a few stars on Apple, Spotify and Co. We thank our partner **SIEMENS** https://www.siemens.de/de/ Our event in January in Frankfurt ([more](https://www.hannovermesse.de/de/rahmenprogramm/special-events/ki-in-der-industrie/)) Our guest is [Bas Coenen ](https://www.linkedin.com/in/samcoenen/) #machinelearning #ai #aimodel #industrialautomation #manufacturing #automation #genai #datascience #mlops #llm #IndustrialAI #artificialintelligence #Safety #NVIDIA #xLSTM #IndustrialAI #bluecollar #Transformer #HPE #Compute #Hardware #robotics #vision #PLC #Automation #Robotics #IndustrialAIPodcast #Vanderlande #Warehouse #Logistics

Xia is doing his doctorate at the University of Stuttgart at the Institute for Industrial Automation and Software Engineering. He investigates how to apply the LLM reasoning capability to make the simulation models more intelligent. Based on our research exploration, he proposed a concept design consisting of LLM-agents system and digital twins to enhance the intelligence and user-friendliness of industrial software systems.

Rainer Brehm is the CEO of the Factory Automation Business Unit at Siemens. His team is behind the Industrial Copilot. We talk to Rainer about the monetization of GenAI, development challenges, price-sensitive customers and the next stage of development towards AI agents. Thanks for listening. We welcome suggestions for topics, criticism and a few stars on Apple, Spotify and Co. We thank our partner **SIEMENS** https://www.siemens.de/de/ Our event in January in Frankfurt ([more](https://www.hannovermesse.de/de/rahmenprogramm/special-events/ki-in-der-industrie/)) Our guest is [Rainer Brehm ](https://www.linkedin.com/in/rainer-brehm/) #machinelearning #ai #aimodel #industrialautomation #manufacturing #automation #genai #datascience #mlops #llm #IndustrialAI #artificialintelligence #Safety #NVIDIA #xLSTM #IndustrialAI #bluecollar #Transformer #HPE #Compute #Hardware #robotics #vision #PLC #Automation #Robotics #IndustrialAIPodcast

Only a few people in the region embody the Eindhoven ecosystem like Albert van Breemen. He studied there, worked for Philips, ASML and then set up his own company. We talk about robotics, vision and AI for the food industry. Thanks for listening. We welcome suggestions for topics, criticism and a few stars on Apple, Spotify and Co. We thank our partner **SIEMENS** https://www.siemens.de/de/ Our guest is [Albert van Breemen ](https://www.linkedin.com/in/albertvanbreemen/) #machinelearning #ai #aimodel #industrialautomation #manufacturing #automation #genai #datascience #mlops #llm #IndustrialAI #artificialintelligence #Safety #NVIDIA #xLSTM #IndustrialAI #bluecollar #Transformer #HPE #Compute #Hardware #robotics #vision

In the news section, we talk about humanoids, about Aleph Alpha, about XAI and HMI and the demands of the AI Act for explainability. We talk about AI agents, robotics and bit about AI operations systems. Thanks for listening. We welcome suggestions for topics, criticism and a few stars on Apple, Spotify and Co. We thank our partner **SIEMENS** https://www.siemens.de/de/ Our guests: [Kathrin Hoesli ](https://www.linkedin.com/in/kathrinhoesli/) [Max Schönsteiner ](https://www.linkedin.com/in/max-sch%C3%B6nsteiner-aa55a977/) [XAI Paper](https://arxiv.org/abs/2404.12762v1) [AI Agents Article by McKinsey](https://www.mckinsey.com/capabilities/mckinsey-digital/our-insights/why-agents-are-the-next-frontier-of-generative-ai) [Robots on Hugging Face](https://www.linkedin.com/posts/bartdewitte_wow-the-democratisation-of-robotics-has-ugcPost-7233096511486627840-OqaP?utm_source=share&utm_medium=member_desktop) #machinelearning #ai #aimodel #industrialautomation #manufacturing #automation #genai #datascience #mlops #llm #IndustrialAI #artificialintelligence #Safety #NVIDIA #xLSTM #IndustrialAI #bluecollar #Transformer #Compute #Hardware

We still have something for the summer break! One prompt and the song is ready. This will change the music industry. Peter is a big Prince fan, so we came up with something for the summer. Kudos to Tristan Behrens and Suno.AI. Try it out. We were fascinated by it.

Facilis.AI developed a transformative GenAI product and is working with 10 top tier manufacturers. They help manufacturers turn AI into tangible ROI in just weeks, by transforming real-time manufacturing data and domain knowledge into actionable insights within minutes. Thanks for listening. We welcome suggestions for topics, criticism and a few stars on Apple, Spotify and Co. We thank our partner **SIEMENS** https://www.siemens.de/de/ Our guest is [Yousef Mohassab ](https://www.linkedin.com/in/yousefmohassab/) #machinelearning #ai #aimodel #industrialautomation #manufacturing #automation #genai #datascience #mlops #llm #IndustrialAI #artificialintelligence #Safety #NVIDIA #xLSTM #IndustrialAI #bluecollar #Transformer #HPE #Compute #Hardware

Utz-Uwe Haus takes us with him and explains what the industrial sector will need in terms of infrastructure in the coming years. But Uwe doesn't just talk about hardware, we also talk about models, new architecture and computing power. Thanks for listening. We welcome suggestions for topics, criticism and a few stars on Apple, Spotify and Co. We thank our partner **SIEMENS** https://www.siemens.de/de/ Our guest is [Utz-Uwe Haus ](https://www.linkedin.com/in/uuhaus/) #machinelearning #ai #aimodel #industrialautomation #manufacturing #automation #genai #datascience #mlops #llm #IndustrialAI #artificialintelligence #Safety #NVIDIA #xLSTM #IndustrialAI #bluecollar #Transformer #HPE #Compute

Our guest is Prof. Dr. Johannes Brandstetter. We met Johannes Brandstetter at the AI with purpose summit by Siemens. Peter Seeberg discussed with him the latest developments in simulation and AI. In the newspart we talk about a timeseries paper using xLSTM, Robert Weber talks about a new tool by Continental using a vision approach for sidewall readings and the new company by Fei-Fei Li Xdash.ai.

Jan Koutnik “Czeched out” in 2009 to improve recurrent neural networks and scale evolutionary reinforcement learning as a postdoc at IDSIA. At NNAISENSE, he directed the division of the company responsible for the “learning to park” NeurIPS 2016 demo with Audi, the “learning to run” NeurIPS competition win in 2017, and the Festo Softhand in-hand manipulation demo at Hannover Messe in 2019. We take a brief look back with Jan Koutnik at his time at NNAISENSE and the beginnings of Industrial AI. Then we switch to the present. Jan explains his Industrial AI approach, why he doesn't realize GenAI use cases and where he sees the sweet spot for himself and his new company. Spoiler: It's all about vision systems. Thanks for listening. We welcome suggestions for topics, criticism and a few stars on Apple, Spotify and Co. We thank our partner **SIEMENS** https://www.siemens.de/de/ Our guest is [Jan Koutnik ](https://www.linkedin.com/in/jan-koutn%C3%ADk-b7b6872/) #machinelearning #ai #aimodel #industrialautomation #manufacturing #automation #genai #datascience #mlops #llm #IndustrialAI #artificialintelligence #Safety #NVIDIA #LSTM #IndustrialAI #bluecollar

The EU Machinery Regulation and the topic of AI are closely linked. But other regulations also play a role. For example, machine manufacturers must also keep an eye on the AI Act. Is the regulation a breakthrough? Sascha Steinkrauß remains skeptical. Thanks for listening. We welcome suggestions for topics, criticism and a few stars on Apple, Spotify and Co. We thank our partner **SIEMENS** https://www.siemens.de/de/ Our guest is [Sascha Steinkrauß ](https://www.linkedin.com/in/sascha-steinkrau%C3%9F-6b3248117/) #machinelearning #ai #aimodel #industrialautomation #manufacturing #automation #genai #datascience #mlops #llm #IndustrialAI #artificialintelligence #Sandvik #CAM #Safety #NVIDIA #xLSTM

Our guest is Magnus Malmström. He is the CTO of Sandvik. He explains to us what his customers demand from him in the area of AI, why his day-to-day work is dominated by AI and how he enriches his CAM systems. And he reveals the new AI based products by Sandvik. Thanks for listening. We welcome suggestions for topics, criticism and a few stars on Apple, Spotify and Co. We thank our partner **SIEMENS** https://www.siemens.de/de/ [More about Sandvik's AI for manufacturing:](https://bit.ly/3XHPfXH) Our guest is [Magnus Malmström](https://www.linkedin.com/in/magnusmalmstrom/) #machinelearning #ai #aimodel #industrialautomation #manufacturing #automation #genai #datascience #mlops #llm #IndustrialAI #artificialintelligence #CAM

Prof. Dr. Jakub Tomczak published a sensational article on GenAI Systems a few weeks ago. We immediately realised that he had to explain it to us. His outlook: The idea of using LLMs as a backbone for Operating Systems and agents as applications has attracted a lot of attention. Here, we consider general systems with various GenAI-based components, not only LLM-based compartments. Either way, moving towards GenAI-based (operating) systems seems like the future, and the next step of cloud-based systems. Indeed, GenAISys can be deployed locally, but also in a cloud server; or as a hybrid (e.g., a GeM, a cache storage, and DEs are local but external tools and storage are in a cloud). The last option can be especially appealing for manufacturing since all real-life operations must be executed in real-time while data storage and other operations are carried out by external services (or agents). Thanks for listening. We welcome suggestions for topics, criticism and a few stars on Apple, Spotify and Co. We thank our partner **SIEMENS** https://www.siemens.de/de/ Our guest is [Jakub Tomczak](https://www.linkedin.com/in/jakub-tomczak-04305314a/) We highly recommend his [short article ](https://jmtomczak.github.io/blog/21/21_genaisys.html) #machinelearning #ai #aimodel #industrialautomation #manufacturing #automation #genai #datascience #mlops #llm #IndustrialAI #artificialintelligence

Shadow's robotic hand is in high demand - among others at Google DeepMind - but the British company wants to scale its hand and is also eyeing other markets. In the podcast, Rich Walker explains what role AI plays in this and why he is happy with hardware. Thanks for listening. We welcome suggestions for topics, criticism and a few stars on Apple, Spotify and Co. We thank our partner **SIEMENS** https://www.siemens.de/de/ Our guest is [Rich Walker](https://www.linkedin.com/in/walkerrich/) #machinelearning #ai #aimodel #industrialautomation #manufacturing #automation #genai #datascience #mlops #llm #IndustrialAI #artificialintelligence

Peter and Robert report on their highlights from the AI with Purpose Summit and feature some topics that will be published in the coming weeks. For Robert, Rainer Brehm's ‘Industrial Copilot' development journey was the highlight of the event. Peter spoke to NXAI and Rocket Science. And this is what the event host says? Boris Scharinger shares his impressions with us. In the main section, we learn from the shipping industry how GenAI can be used to develop fundamentally new designs. Our guest: Shahroz Khan from Bar Technologies. Thanks for listening. We welcome suggestions for topics, criticism and a few stars on Apple, Spotify and Co. We thank our partner **SIEMENS** https://www.siemens.de/de/ Some Links Embraceable AI [more](https://embraceable.ai/) Rocket Science [more](https://www.rocket-science.ch/press-releases) NXAI [more](https://www.nx-ai.com/de) Our guest [Shahroz Khan ](https://www.linkedin.com/in/shahrozkhan2020/) Our guest [Boris Scharinger ](https://www.linkedin.com/in/borisscharinger/) #machinelearning #ai #aimodel #industrialautomation #manufacturing #automation #genai #datascience #mlops #llm #IndustrialAI #artificialintelligence

In this episode we talk about Timeseries and in the main part Prof. Dr. Marco Huber from IPA and Marc Zöller from GFT explain how their Timeseries AutoML tool works. In the news part we offer an an overview from Statistical (ARIMA) through ML (Random Forest, gradient boosting, ...), Neural Networks (LSTM), AutoML and lately Transformers approaches. Thanks for listening. We welcome suggestions for topics, criticism and a few stars on Apple, Spotify and Co. We thank our partner **SIEMENS** https://www.siemens.de/de/ xLSTM Github ([mehr](https://lnkd.in/eG3HWJrs)) auto-sktime ([mehr](https://github.com/Ennosigaeon/auto-sktime)) Our guest [Marco Huber ](https://www.linkedin.com/in/marco-huber-78a1a151/) Our guest [Marc Zöller ](https://www.linkedin.com/in/marc-zoeller/) #machinelearning #ai #aimodel #industrialautomation #manufacturing #automation #genai #datascience #mlops #llm #IndustrialAI #artificialintelligence #sklearn

Robert Weber met Danny at Harting's IoT Week. A discussion quickly broke out about the future of European start-ups in the field of industrial AI. Unfortunately, the conversation was not recorded. That's why we tried again and arranged a recording date. We talked about AI models, data, use cases and the role of AWS. Thanks for listening. We welcome suggestions for topics, criticism and a few stars on Apple, Spotify and Co. We thank our partner **SIEMENS** https://www.siemens.de/de/ Our guest [Danny Smith ](https://www.linkedin.com/in/bdannysmith/)