Formal verification (of cyber-physical systems) — supplies the rigor asimov lacked → Asimov's first law of robotics

The paper places these at opposite ends of a twenty-year gap between aspiration and achievement. Asimov's first law is cited as an early, informal call — fiction, not engineering — that the research community nonetheless took seriously enough for Weld and Etzioni to attempt formalizing it within classical AI planning over two decades before this paper was written (concrete-problems, §"Other Calls for Work on Safety:", p. 21). Formal verification of the federal aircraft collision-avoidance system is offered as what actually rigorous, machine-checked harm-avoidance looks like once a community commits to it (concrete-problems, §"Cyber-Physical Systems Community:", p. 20). The pairing sets up a contrast the paper immediately undercuts: this level of rigor exists for cyber-physical systems built on formal models, but the same section notes it "has not focused much on modern machine learning systems, where formal verification is often not feasible" — Asimov's aspiration remains largely unmet for ML.