AI in Public Transport
How to use AI in urban mobility
The hype around AI can get in the way of finding practical, effective solutions. That’s inevitable, given that AI technologies are advancing so fast and we’re still exploring how to use them. Let’s get down to the reality on the ground by exploring examples of AI success in public transport.
Today, AI is mainly used to assist data analysis, anomaly detection, and predictive modelling. With new, cutting-edge technologies like large language models (LLMs) and AI-driven video analytics, more opportunities are opening up. Already, many public transport organisations around the globe use the power of AI tools to make operations safer, more efficient, and more comfortable for passengers.
Society is being increasingly shaped by AI. And public transport, as a public service, is no different.
“New opportunities are opening up. On the one hand, to facilitate operations, and on the other hand, to change the way that we communicate with customers. In the end, this should create a new business model that impacts us internally and externally. Our customers are demanding this more and more.”
17 use cases of AI technology to improve urban mobility
AI is already changing mobility. Discover 17 ways how public transport operators, authorities, researchers, and other stakeholders are using AI to generate all sorts of benefits.
- Passenger announcements with AI – PostBus, Switzerland
- Sign language virtual assistant – SBS Transit, Singapore
- Incident chatbot – Chicago Transit Authority, USA
- Chatbot helper – Club Italia, Italy
- Employee chatbot – AC Transit, USA
- Customer chatbot – Tokyo Metro, Japan
- Bus safety – Land Transport Authority, Singapore
- Safety & trespassing – New York Metropolitan Transportation Authority, USA
- Bus occupancy levels – Sofia Urban Mobility Centre, Bulgaria
- Bus lane enforcement – AC Transit, USA
- Fare evasion enforcement – FGC Barcelona, Spain
- Accessible guidance for bus stops – Schepens Institute, USA
- Driver efficiency – Alsa Morocco, Morocco
- Smart charging – Arriva Spain, Spain
- Real-time fleet data – National Transport Authority, Ireland
- Mobility forecasts – Hamburg Police Traffic Control, Germany
- Ventilation – Barcelona Metro (TMB & FGC), Spain
A sneak peek at some results:
- 25% reduction in electricity costs
from smart e-charging
- 13% increase in prediction accuracy
for modelling of demand and arrival times
- As high as 40% reduction in improper vehicle use
from AI-powered driving assistance and training
Contents:
- Introduction
- The hype & the reality
- Large language models (LLMs)
- Customer assistance use cases
- Staff assistance use cases
- Video analytics
- Tackling new challenges
- Additional insights and future developments
- Weaknesses associated with operational use of AI models
- Use cases
- Predictive modelling with AI
- Benefits and limitations
- Predictive modelling for public transport
- Human resources use case
- Vehicle fleets use case
- Service design and real-time disruptions use cases
- Infrastructure use case
- Regulatory landscape and privacy protection
- Success factors in AI projects
- Energy usage and model sizes
- Conclusions and next steps
AI use case on a bus in Singapore.
Related Resources
publication Data4PT Project Brief
news Unlocking the power of data for sustainable mobility: DATA4PT project concludes
news The digital revolution gets smarter: IT-TRANS 2024 concludes with a focus on the future
news How technology can improve passenger flow and crowd management
publication Investing in Technologies for Passenger Flow and Crowd Management
publication Large Scale Bus Electrification: IT Systems Checklist
news Making the most of digitalisation in public transport
- publication
Capturing Digital Value Within Public Transport