AI in Public Transport

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.

Dive into examples of AI

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.

1. Passenger announcements with AI – PostBus, Switzerland
2. Sign language virtual assistant – SBS Transit, Singapore
3. Incident chatbot – Chicago Transit Authority, USA
4. Chatbot helper – Club Italia, Italy
5. Employee chatbot – AC Transit, USA
6. Customer chatbot – Tokyo Metro, Japan
7. Bus safety – Land Transport Authority, Singapore
8. Safety & trespassing – New York Metropolitan Transportation Authority, USA
9. Bus occupancy levels – Sofia Urban Mobility Centre, Bulgaria
10. Bus lane enforcement – AC Transit, USA
11. Fare evasion enforcement – FGC Barcelona, Spain
12. Accessible guidance for bus stops – Schepens Institute, USA
13. Driver efficiency – Alsa Morocco, Morocco
14. Smart charging – Arriva Spain, Spain
15. Real-time fleet data – National Transport Authority, Ireland
16. Mobility forecasts – Hamburg Police Traffic Control, Germany
17. Ventilation – Barcelona Metro (TMB & FGC), Spain

Hitachi Rail has the need for rapid identification of infrastructure failure causes and the provision of effective recovery instructions during railway disruptions. Traditional methods, which depended heavily on the experience and knowledge of dispatchers, were often insufficient for managing promptly rare or complex incidents.

To address this issue, an AI-based system utilising Hitachi’s proprietary Recommendation AI technology was developed. This system analyses extensive historical records of infrastructure failures to identify similar past events. By extracting and presenting information from previous fault reports, the AI assists dispatchers in narrowing down potential causes and suggesting appropriate recovery actions. The learning model used was BERT. Around 3,000 historical data points related to failures and malfunctions were used to train the model.

A field trial was conducted using data from JR East, a rail operator in Japan, from 2020 to 2022 to confirm the effectiveness of the AI-based system. During the proof-of-concept phase, a significant reduction in recovery time was demonstrated. When applied to significant past incidents that typically require around two hours for recovery, it reduced the recovery time by approximately 50%, shortening it to about one hour. Following these successful trials, the system commenced full operation.

• 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

Explore the use cases of AI