We talk IoT – The Internet of Things Business Podcast

When an older person falls at home, help often arrives late. A broken leg can end independent living for good, and care outside the home costs well over €10,000 a year per person. Detecting the fall is only the start. The harder question is whether technology can spot the warning signs earlier. Christophe Arnaud, CEO of Telecom Design, explains how the Bordeaux company’s wristband raises an alarm via a home hub and a call centre. He describes how gait analysis and months of activity data build a personal movement profile, why the battery has to last three years, and why the company hired a doctor to check that the data matches real life. The second half of the episode turns to home security. Jammers costing a few euros can silence wireless alarms, door sensors and outdoor cameras at the push of a button. #AgeTech #Telecare #FallDetection #SmartHome #IoT #WeTalkIoT   Summary of this week’s episode: 01:34 From a corporate career to telecare and home security 02:33 The Vibby Oak: from fall detection to fall prevention 05:47 Why detecting a fall is harder than it looks 06:36 Home security and jammers: the second business 08:11 Who pays: telecare providers, the Red Cross and families 10:54 Gait analysis: spotting a decline before a fall 14:26 Three years on one battery: what runs on the wrist and in the cloud 17:33 The business case: what a fall that never happens is worth 20:38 From data to KPIs, and why a doctor joined the team 24:22 Technology from the 1990s: the industry’s slow upgrade 26:55 Jammers for a few euros: how burglars blind wireless alarms 29:12 Jam detection: alerting the call centre anyway   Show notes: Christophe Arnaud: https://www.linkedin.com/in/christophearnaud/ Telecom Design: https://telecom-design.com/   Listen to the "We Talk IoT" Soundtrack on: Spotify: https://open.spotify.com/playlist/05MOV4OV2MH2in2txsAGtG?si=ad08112cb8d443f4 YouTube: https://www.youtube.com/watch?v=D-NvQ6VJYtE&list=PLLqgVFfZhDRVYmpEqbgajzDvGL4kACRDp   About Avnet Silica: This podcast is brought to you by Avnet Silica – the Engineers of Evolution. Subscribe to our newsletters here: https://my.avnet.com/silica/resources/newsletter/ You can connect with us on LinkedIn: https://www.linkedin.com/company/silica-an-avnet-company/. Or find us at http://www.avnet-silica.com.

Warehouses run on data, yet that data often lags behind reality. The system shows a pallet on the shelf. The shelf stands empty. In this episode, Oana Jinga, co-founder and Chief Commercial and Product Officer of Dexory, explains what physical AI means. Digital AI is really good at giving answers, physical AI needs to sense, reason and act in the real world. And pressing Ctrl+Z is not an option. Dexory’s robots reach up to 18 metres, scan between 10,000 and 12,000 pallet locations an hour with cameras and lidar, and feed a live digital twin of the warehouse. Oana describes a site where 350 picking robots kept stalling at empty locations. A month after Dexory started scanning continuously, the site posted three record days. We also discuss who signs off on warehouse automation, why scaling from one site to hundreds is the real test for physical AI start-ups, and why Dexory sees its future as a data company rather than a robot maker. #PhysicalAI #WarehouseAutomation #Robotics #DigitalTwin #Logistics #Dexory #WeTalkIoT   Summary of this week’s episode: 01:20 From a home robot to the warehouse floor 03:11 What physical AI means – and why there is no Ctrl+Z 04:44 Sense, reason, act: physical AI in the warehouse 06:06 What warehouse management systems miss 07:26 Data-driven automation vs conveyor belts and picking robots 09:33 The universal problem: data that is worse than you think 11:23 Use case: 350 picking robots and three record days 14:12 Why warehouse space is the industry’s currency 15:46 A 24/7 shift: 18 metres, cameras and lidar 18:02 Built to blend in on the warehouse floor 19:18 Adoption: who decides and what convinces them 20:47 The most common objection 21:34 The real test: scaling from one site to hundreds 23:21 How warehouse workers react to the robot 25:22 From robotics company to data company 27:44 Global customers and messy spaces   Show notes: Oana Jinga: https://www.linkedin.com/in/oanajinga/ Dexory: https://www.dexory.com/ Read more about connected devices and physical AI: https://my.avnet.com/silica/resources/article/from-connected-devices-to-physical-ai/   Listen to the "We Talk IoT" Soundtrack on: Spotify: https://open.spotify.com/playlist/05MOV4OV2MH2in2txsAGtG?si=ad08112cb8d443f4 YouTube: https://www.youtube.com/watch?v=D-NvQ6VJYtE&list=PLLqgVFfZhDRVYmpEqbgajzDvGL4kACRDp   About Avnet Silica: This podcast is brought to you by Avnet Silica—the Engineers of Evolution. Subscribe to our newsletters here: https://my.avnet.com/silica/resources/newsletter/ You can connect with us on LinkedIn: https://www.linkedin.com/company/silica-an-avnet-company/. Or find us at www.avnet-silica.com.

Airports run on machines many passengers don’t even notice. Tugs, loaders, de-icing truck, hundreds of vehicles are moving across the tarmac every hour. If only one gets it wrong, the cost is not just downtime, it’s safety. Matthias Moulinier, VP of Product and Customer Success at Adveez, explains how connected ground support equipment (GSE) is changing life on the ramp. He walks us through the system that tracks who drives what, when and how. From badge-scan access control to automatic speed reductions when a seatbelt is not engaged. We explore how airports balance their fleets in summer and winter seasons, and how data helps operators avoid over-buying equipment. We talk electrification, autonomous GSE and what you learn from tracking more than 30.000 vehicles across 280 airports. #GSE #airport #IoT #fleetmanagement #saftey #wetalkiot Summary of this week’s episode: 01:34  Matthias's background and role at Adveez 02:08  How airports are evolving as GSE gets connected 03:41  What Adveez actually builds: hardware, cloud, and platform 05:47  Life before Adveez: paper-based, or no tracking at all 06:40  Badge-scan access control and driver authorisation 08:36  Seatbelt monitoring and automatic speed reduction 09:47  Fleet management: real-time visibility and utilisation data 13:58  Electrification: state-of-charge alerts and charger data 18:48  What's next: autonomous GSE on the ramp 23:04  Adveez by the numbers: 32,000+ tracked assets, 280+ airports   Show notes: Matthias Moulinier: https://www.linkedin.com/in/matthias-moulinier-1a8b5359/ Adveez: https://adveez.com   Listen to the “We Talk IoT” Soundtrack on: Spotify: https://open.spotify.com/playlist/05MOV4OV2MH2in2txsAGtG?si=ad08112cb8d443f4 YouTube: https://www.youtube.com/watch?v=D-NvQ6VJYtE&list=PLLqgVFfZhDRVYmpEqbgajzDvGL4kACRDp About Avnet Silica: This podcast is brought to you by Avnet Silica — the Engineers of Evolution. Subscribe to our newsletters here: https://my.avnet.com/silica/resources/newsletter/ You can connect with us on LinkedIn: https://www.linkedin.com/company/silica-an-avnet-company/. Or find us at www.avnet-silica.com.

Harvesters, buses and mining machines are becoming rolling computers. The hardware inside them has to last decades. Yet the AI running on top of it changes every quarter. Ralf Kapahnke from Tria Technologies and Frank Neelen from Avnet Silica discuss where the CAV CAV (Commercial and Agricultural Vehicles) market is heading. Cameras that spot-treat pesticide or milking robots that turn farmers into a roboticists, are just two use cases we cover. And the decision facing every OEM: solder the processor onto your own board, or fit a module. #CAV #embedded #functionalsafety #agritech #edgeai #iot #wetalkiot   Summary of this week’s episode: 01:30 What CAV means 03:20 Why AI and connectivity change the requirements 04:10 Functional safety: when a tractor meets a human being 06:30 Talking to your machine: LLMs moving from cloud to chip 07:15 AI-driven autonomy, from drone irrigation to predictive maintenance 09:00 Spot-treating pesticide with camera-based systems 10:45 Autonomous milking robots 13:30 Beyond agriculture: street cleaning, buses and people counting 15:20 Mining: robots underground 16:30 What keeps developers awake — and why software now leads hardware 19:00 What chip-down actually means 20:30 The module case: less risk, faster time to market 23:00 Where scalability pays off for an OEM 24:00 Volume, ARM versus x86, and the OSM trend 26:30 Modularity as a business strategy   Show notes: Ralf Kapahnke: https://www.linkedin.com/in/ralf-kapahnke-a713b912b/ Frank Neelen: https://www.linkedin.com/in/frank-neelen-93008376/ Tria Technologies — commercial and agricultural vehicles: https://www.tria-technologies.com/commercial-agricultural-vehicles/ The episode with AGCO Fendt is called “From the cab to the cloud: How AGCO Fendt is making smart farming real”: https://my.avnet.com/silica/resources/podcast/episode-86-agco-fendt-makes-smart-farming-real/   Listen to the “We Talk IoT” Soundtrack on: Spotify: https://open.spotify.com/playlist/05MOV4OV2MH2in2txsAGtG?si=ad08112cb8d443f4 YouTube: https://www.youtube.com/watch?v=D-NvQ6VJYtE&list=PLLqgVFfZhDRVYmpEqbgajzDvGL4kACRDp About Avnet Silica: This podcast is brought to you by Avnet Silica — the Engineers of Evolution. Subscribe to our newsletters here: https://my.avnet.com/silica/resources/newsletter/ You can connect with us on LinkedIn: https://www.linkedin.com/company/silica-an-avnet-company/. Or find us at www.avnet-silica.com.

AI data centres have a problem that no one talks about enough. When GPUs synchronise and fire together, power demand spikes exponentially, in milliseconds. Legacy backup systems were never built for this. Oversizing the grid is expensive. Throttling GPU utilisation wastes the very infrastructure operators are paying for. Ramesh Narasimhan, EVP, CCO and CFO at Nyobolt, explains how the Cambridge deep-tech startup evolved from a university materials lab into a full solutions provider. And how its Dynamic Response System addresses the power spike problem at the rack level, in real time. Ramesh discusses Nyobolt's journey from a vacuum cleaner prototype to a partnership with Symbotic's warehouse robots, the case for ultra-fast charging over high energy density, and why the company's core lesson applies as much to startups as to battery chemistry: don't confuse your product with your purpose. #battery #fastcharging #AIDataCentre #robotics #IoT #WeTalkIoT   Summary of this week's episode: 01:08 From automotive to deep-tech: Ramesh's background 02:00 Nyobolt's origin: Cambridge materials lab to commercial company 03:03 What forced the shift from materials to solutions provider 05:05 The secret sauce: what Nyobolt's battery does differently 06:47 Charging a car in under five minutes, and why range obsession misses the point 09:42 The AI data centre power problem explained 12:25 The Dynamic Response System vs. conventional UPS 13:55 Off-grid in Rajasthan: what the MoU actually means 14:50 Symbotic and the warehouse robot use case 16:02 Humanoids, trade-offs, and scaling the supply chain 17:55 Where Nyobolt focuses and why 19:05 Looking ahead: changing how industries think about operations 20:05 The talent ecosystem around Cambridge   Show notes: Ramesh Narasimhan: https://www.linkedin.com/in/ramesh-narasimhan-201ab3a/ Nyobolt Dynamic Response System: https://nyobolt.com/ai-data-centre-power-solutions/   Listen to the "We Talk IoT" Soundtrack on: Spotify: https://open.spotify.com/playlist/05MOV4OV2MH2in2txsAGtG?si=ad08112cb8d443f4 YouTube: https://www.youtube.com/watch?v=D-NvQ6VJYtE&list=PLLqgVFfZhDRVYmpEqbgajzDvGL4kACRDp   About Avnet Silica: This podcast is brought to you by Avnet Silica — the Engineers of Evolution. Subscribe to our newsletters here: https://my.avnet.com/silica/resources/newsletter/ You can connect with us on LinkedIn: https://www.linkedin.com/company/silica-an-avnet-company/. Or find us at www.avnet-silica.com.