Alstom’s Journey to Safe, Reliable AI Mobility
summary
Alstom deploys AI across non‑safety systems (about 20% of business) with a 250‑person global team, reusing camera, odometry and signaling data to build features like passenger counts, luggage detection and HVAC filter predictive maintenance; pilots show 7–15% energy savings, 20% fewer maintenance activities and 25% fewer needless checks. Work includes track‑circuit signal‑shape analysis, a mix of simulations and generated data, early use of formal methods for resilience and ongoing digital‑twin efforts.
AI-written summary · about
chapters (11)
- 0:00Alstom and AI journey
- 2:59Safe and reliable AI in mobility
- 4:08AI in non-safety critical apps
- 5:11Trust in AI via robustness
- 7:19Explainability and fairness in AI
- 10:49AI for predictive maintenance
- 14:24Reusing data for AI use cases
- 18:01AI for signaling infrastructure
- 20:54Data science to business impact
- 23:43Collaboration for trustworthy AI
- 24:52Q&A
related talks
31mWant to adopt AI in your business: Good luck!
18mExtending Mobility - How AI Contributes towards the Future of Railway Transportation
08mHuman–AI Collab for Reliable Automotive Control Systems
20mThe Transformative Role of AI in Aerospace
35mDriving Societal Change Through AI Innovation
16mEnterprise and industrial AI: The great threat of complacency
15mFrom Alarms to Action — AI for Conveyor Reliability
06mAI in production: The droids you’re looking for