top of page
-04.png){kind=small}
Access 500 million km of real-world accident data to verify the robustness of automated driving systems
What is Resembler
Resembler is a verification and deployment governance platform for automated driving systems. It transforms larege-scale real-world accident data into structured verification scenarios that allow developers, cities and regulators to evaluate whether automated systems achieve safety outcomes comparable to human drivers.
Human drivers are remarkably good at avoiding accidents - even when others make mistakes.
Resembler captures and models these human-level avoidance behaviors to help you measure how your AV or ADAS system performs using real-world data.
Through our unique A–B verification tests, you can directly compare your algorithm’s responses against real human data in identical traffic scenarios.
Human danger recognition recognition follows univerdal behaviour patterns - people instinctively react to occlusion, sudden intrusions and speed differences.
Resembler models this behavior using Singapore as its living testbed - a uniquely dense, multi-modal city where every traffic scenario converges, from urban and industrial zones to ports, airports, and highways - providing the perfect foundation to validate safety in any city worldwide.
Incremental Deployment Governance Cycle
Automated mobility is deployed incrementally and under structured governance.
For a selected Operational Design Domain (ODD), the Resembler platform automatically generates a Verification Test Plan linking deployment parameters to nominal scenarios and real accident archetypes derived from over 500 million km of traffic exposure.
Vehicles initially operate under controlled conditions before transitioning into monitored deployment, where operational data and incidents are continuously evaluated against the approved safety baseline.
Resembler Platform Modules
The Resembler platform provides integrated modules that support each stage of the deployment governance cycle — from accident intelligence search and ODD assessment to verification testing and monitored deployment.
RIQL Accident Search
Verification Test Report (Parameterized Real World Accidents)
Monitored Deployment
ODD Assessment
Risk Balance
(Human-AV Assessment Tool)
Synthetic DataBase Cross Check
Verification Test Report (Nominal Scenarios)
Open Drive / Open Scenario
Upload Public Incident
Our Numbers
5
Years of Data
km Coverage
657,248,520
Europe, US and Asia
3
bottom of page