Extending Mobility - How AI Contributes towards the Future of Railway Transportation
summary
Central unit builds and deploys concrete systems: a centralized construction-site platform (prototype finished April) feeding capacity planning; a reinforcement-learning multi-agent dispatching system live around Stuttgart that uses simulation and real-world data and saves 30,000 minutes of delay in 2022 for commuter trains; and post-trip analytics ingesting black-box tachograph data to do black-box tachograph clustering for infrastructure hot spots. Systems follow a four-stage MLops pipeline (feasibility 3–6 weeks → prototype → MVP → ops) and provide about a 30–40 minute lookahead for dispatch decisions.
AI-written summary · about
chapters (8)
- 0:00Intro
- 0:46Welcome
- 2:01The Vision
- 3:30Expect Delays
- 5:50Reinforcement Learning
- 8:12XPost Analysis
- 9:42Vision
- 12:15Questions
related talks
22mMicrodosing the Economy
29mAlstom’s Journey to Safe, Reliable AI Mobility
21mML Infrastructure for Autonomous Vehicles
31mDriving Trust and Addressing Ethical Challenges in Transportation through Explainable AI
31mWant to adopt AI in your business: Good luck!
27mBuilding Reliable Human-AI Warehouse Operations at Scale
27mAI at Scale in the Enterprise
21mFrom Reactive to Proactive: How AI is Redefining Resilience in Modern Networks