safe.trAIn: Safe AI for driverless trains

Artificial intelligence for automated rail transport

Autonomous rail transport with the maximum amount of automation possible is a key component in establishing a climate-neutral and attractive mix of transport options. A high degree of train automation on the existing rail network can, for example, result in higher train frequencies and therefore shorter intervals, as well as improved train reliability. Based on the current state of technology, this goal is simply not feasible using conventional automation methods alone.

However, enormous progress is currently being made in developing systems for autonomous driving on both rail and road that harness the benefits of artificial intelligence (AI). Nevertheless, it remains to be seen just how AI processes can be linked to rail transport requirements and approval procedures. This is where the safe.trAIn project comes in.

safe.trAIn: Safe AI for driverless regional trains

The safe.trAIn project was launched with the intention of establishing the groundwork for using AI safely in driverless rail vehicles to make regional rail transport more efficient and sustainable. Unlike existing driverless rail transport, used exclusively in closed and controlled environments, regional transport represents a more open environment where obstacles such as people on the track or fallen trees must be detected safely and reliably.

Therefore, the safe.trAIn project is developing testing standards and methods to be applied when using AI for rail transport automation. Furthermore, this project will demonstrate the suitability of the testing standards with an application example, the driverless regional train. The safe.trAIn project will focus primarily on:

  •  AI-based methods for a driverless regional train
  •  Approval-relevant evidence of product safety for AI components
  •  Test procedures and test methods for verification

Test procedures and tools for AI-based approaches will be investigated while taking the specifications for proof of safety into account. For one use case, a fully automated system (GoA4) will be conceptually built and tested in a virtual test field, while a safety architecture will be defined using the example of the autonomous regional train. 

The safe.trAIn project consortium consists of 17 partners, including companies from the rail industry, technology providers, research institutions and also standardization and testing organizations. The project is funded with approx. 23 million euros by the German Federal Ministry for Economic Affairs and Climate Action (BWMK).

Fraunhofer IKS as part of the safe.trAIn project

Fraunhofer IKS is focusing on three particular topics in the safe.trAIn project:

  • Proof of safety for AI functions in the perception of the train
  • Robustness of AI and monitoring mechanisms for AI-based systems
  • Operational design domain (ODD) specification and monitoring for rail transport

In this context, Fraunhofer is involved in two work packages in particular:

Proof of safety for AI methods

Within the safe.trAIn project, one of the responsibilities of Fraunhofer IKS include the test methods and tools that prove the reliability of AI methods. Fraunhofer IKS is developing methods and tools based on the properties and acceptance criteria for AI systems specified in the project to demonstrate the explainability, robustness and compliance with safety requirements. Special metrics and concrete methods are being researched, such as the reliable detection of humans or the detection of unknown situations (out-of-distribution detection).

Fraunhofer IKS is also working on methods that assure the quality of AI functions as early as during the development phase. A key point of research is on methods that increase the transparency and interpretability of AI applications.

Safety architecture for AI-based functions

Fraunhofer IKS is researching the safety architecture for AI-based functions in fully automated operation (GoA4). In order to do this, the requirements for the driverless regional train are first defined and then a Technical Safety Plan (TESIP) is created. The operational design domain (ODD) must also be determined, which records the environmental conditions, including individuals and other systems interacting with the system, as well as the operational, climate and weather conditions. The ODD specification is pivotal for the driverless regional train’s safety justification and vehicle architecture. Fraunhofer IKS is concentrating its efforts in this area on researching a method for specifying and monitoring the ODD for rail transport. The ultimate goal is a safe, reliable, available, and efficiently maintainable overall system. 

Expected results

The safe.trAIn project will make an important contribution to the further development of rail transport thanks to its research. By safely applying AI in the rail sector, the safe.trAIn project will lay the foundation for further automation solutions for the highly automated and driverless operation of rail vehicles. Furthermore, safe.trAIn will provide important contributions to ongoing standardization efforts.

The project is funded by the European Union and the German Federal Ministry for Economic Affairs and Climate Action (BMWK) as part of the “New Vehicle and System Technologies” program.