-04.png){kind=small}
Applications
The following sections illustrate how Resembler can support the deployment and verification of autonomous systems across different mobility and infrastructure environments.
Autonomous Vehicles
Human drivers often avoid accidents through intuitive reasoning that occurs before a hazard fully materializes. This cognitive process—anticipating risk, interpreting subtle cues, and adjusting behaviour—is largely invisible and therefore difficult to model directly in perception, prediction, planning, or control algorithms.
Resembler addresses this challenge by converting real-world incidents into A–B verification tests. Automated systems can be placed in the exact same situation experienced by a human driver and their behaviour can be compared against the human outcome. This allows developers and regulators to evaluate whether an automated system demonstrates comparable risk-anticipating behaviour.
Smart Cities
Cities introducing autonomous mobility must manage where and how systems operate within the urban environment. This requires clear definitions of operational design domains (ODDs) and structured methods for expanding deployments over time.
Resembler supports cities by analyzing infrastructure conditions, defining operational domains, and enabling incremental ODD expansion. The platform also allows ODD comparisons across different areas, helping authorities understand how risk changes between deployment zones. In practice, digital infrastructure and governance platforms may become the primary mechanism through which cities coordinate and supervise multiple mobility providers.
Insurance
Infrastructure design, careful selection of deployment areas, and controlled operational domains can significantly reduce accident risk. However, accidents can never be completely eliminated.
Insurance providers will therefore play a central role in the introduction of autonomous mobility. Resembler supports this ecosystem by providing structured accident intelligence and scenario analysis that help insurers understand risk exposure, evaluate deployment environments, and support the development of appropriate insurance models for automated systems.
Fleet Management
Operators deploying fleets of automated vehicles must monitor system behaviour across large operational areas and diverse traffic conditions.
​
Resembler enables fleet operators to analyze incidents, review system responses, and identify patterns that may indicate elevated risk within specific operational domains. This allows operators to refine deployment areas, adjust operational parameters, and improve the safety performance of autonomous fleets over time.