Mobilising AI: Data driven transport solutions
Artificial Intelligence (AI) is in the spotlight as one of the emerging fields with the potential to transform and revolutionize the transport sector. But what do we mean by AI? Artificial Intelligence is not reduced to one type of machine or robot, but it is actually a series of approaches, methods, and technologies that display intelligent behavior by analyzing their environments and taking actions—with some degree of autonomy—to achieve specific targets in various contexts.
AI in a nutshell
Considering there is not one common definition for Artificial Intelligence, AI can be defined as a broad branch of computer science, the study of processes that interact with data and that can be represented as data in the form of programs. The main objective of Artificial Intelligence is to make systems function intelligently and independently. Depending on the complexity of the system and the tasks to be performed by AI, it can be classified in weak or strong AI.
There are different ways in which AI can be achieved: symbolic AI, data-driven AI and future technologies.
- Symbolic AI refers to systems where a human expert creates precise rules, transcribed in algorithms, which machines can follow to decide how to respond to a given situation. As symbolic AI requires human experts encoding their knowledge, there are significant constraints in their degree of autonomy and complexity.
- Data-driven AI is an AI that combines learning systems with technologies used for searching and analyzing large quantities of data. Learning systems refer to algorithms that autonomously improve their performance, without humans directly encoding their expertise. Data-driven AI requires a large amount of computer processing capacity as well as a large amount of tagged data to understand the task at hand. It can thus achieve the highest degree of accuracy in data (bigger the amount of -training- data for the algorithms, higher the accuracy and precision).
- Future technologies refer to the potential various developments where AI could display a wider range of human capacities (such as creativity or intuition) or even where AI outperforms humans.
AI in transport
From assistance and automation systems already implemented to the use of AI for operations and asset management, AI is not completely unknown and has long been present in the field of mobility and transport.
The final goal of transport planning is to make multimodal mobility sustainable, efficient, safe and user-friendly, exploiting the optimization potential of each service and between them. Such an optimization requires a stronger connection of each other’s systems, with all that this would imply at the technical and regulatory level (in particular regarding data protection). There is certainly a need to look at transport in a global way since all the modes are linked and it is these services as a whole that we want to understand and plan better. The challenge of AI lies in the complexity of the systems and the increasing volumes of data the mobility sector produces - AI methods can be presented as a smart solution for complex systems that cannot be managed using traditional methods.
Some examples of AI uses in transport are:
-Cybersecurity: anomaly detection, cyber-attack prediction, system optimization, pattern detections.
-Traffic Management: estimation of real-time traffic flow data in urban environments, fleet management, traffic signaling.
-Route Planning: optimization of route planning for public transport, ride-sharing services, logistics.
-Smart Grids Management: energy load forecasting, assessment of new power generation.
Are you a local or regional authority interested in the application of Artificial Intelligence in the field of transport? Get in touch with Laura Babío.
 Artificial intelligence in transport: Current and future developments, opportunities and challenges, Niestadt, Maria et al. 2019.