Fuzzing is increasingly used to test ROS-based robotic systems, yet results remain difficult to compare because studies exercise different ROS layers and define failures in different ways. We analyze 92 selected works on ROS/ROS-based fuzzing and closely related robotic, cyber-physical, and autonomous-system testing. The corpus was built through a documented search, screening, and snowballing process. Each work is interpreted by its role in the fuzzing workflow and by the strength of its ROS-specific evidence, which separates direct ROS results from near-domain evidence that can be transferred only under explicit assumptions. Thereview shows a shift from message-validity testing toward runtime behavior and task-level failures, but the evidence profile is uneven: input modeling, feedback, and oracle construction have advanced more clearly than repeatable execution and diagnosable failure analysis. Treating ROS fuzzing as an evidence-bound workflow clarifies which claims can be compared, where evidence remains weak, and what support is needed for reproducible and repairable ROS fuzzing results.