>Skeptics of robo-policing, including Tu, say these debates need to happen today to preempt the abuses of tomorrow, especially because of the literal and figurative distance robotic killing affords. Guariglia said, “It in many ways lowers the psychological hurdle for enacting that violence when it’s just a button on a remote control.” > >... > >With thousands of Andros robots operated by hundreds of police department across the country, those concerned by the prospect of shotgun robots on the streets of Oakland or elsewhere refer to what they say is a clear antecedent with other militarized hardware: mission creep. > >Once a technology is feasible and permitted, it tends to linger. Just as drones, mine-proof trucks, and Stingray devices drifted from Middle Eastern battlefields to American towns, critics of the PAN disruptor proposal say the Oakland police’s claims that lethal robots would only be used in one-in-a-million public emergencies isn’t borne out by history. The recent past is littered with instances of technologies originally intended for warfare mustered instead against, say, constitutionally protected speech, as happened frequently during the George Floyd protests. > >“As you do this work for a few years, you come to realize that we’re not really talking about a slippery slope. It’s more like a well-executed playbook to normalize militarization,” said O’Sullivan, of Parity. There’s no reason to think the PAN disruptor will be any different: “One can imagine applications of this particular tool that may seem reasonable, but with a very few modifications, or even just different kinds of ammunition, these tools can easily be weaponized against democratic dissent.”

A full and proper public debate on whether these kinds of technologies are appropriate for police forces is best done before they are adopted, rather than after. Recent history and recent speculative fiction are both littered with instances of what could go wrong in these kinds of scenarios.