As autonomous robots increasingly navigate complex and unpredictable\nenvironments, ensuring their reliable behavior under uncertainty becomes a\ncritical challenge. This paper introduces a digital twin-based runtime\nverification for an autonomous mobile robot to mitigate the impact posed by\nuncertainty in the deployment environment. The safety and performance\nproperties are specified and synthesized as runtime monitors using TeSSLa. The\nintegration of the executable digital twin, via the MQTT protocol, enables\ncontinuous monitoring and validation of the robot's behavior in real-time. We\nexplore the sources of uncertainties, including sensor noise and environment\nvariations, and analyze their impact on the robot safety and performance.\nEquipped with high computation resources, the cloud-located digital twin serves\nas a watch-dog model to estimate the actual state, check the consistency of the\nrobot's actuations and intervene to override such actuations if a safety or\nperformance property is about to be violated. The experimental analysis\ndemonstrated high efficiency of the proposed approach in ensuring the\nreliability and robustness of the autonomous robot behavior in uncertain\nenvironments and securing high alignment between the actual and expected speeds\nwhere the difference is reduced by up to 41\\% compared to the default robot\nnavigation control.\n