An architecture for ethical robots
This addresses the safety and ethical decision-making challenge for autonomous robots, though it is incremental as it builds on existing robot controllers with a supplementary layer.
The authors tackled the problem of ensuring autonomous robots behave ethically by developing an Ethical Layer control architecture that predicts action outcomes and evaluates them against predetermined ethical rules, and they validated it on a humanoid robot using Asimov's laws, demonstrating in experiments that it prevented harm to a human proxy.
Robots are becoming ever more autonomous. This expanding ability to take unsupervised decisions renders it imperative that mechanisms are in place to guarantee the safety of behaviours executed by the robot. Moreover, smart autonomous robots should be more than safe; they should also be explicitly ethical -- able to both choose and justify actions that prevent harm. Indeed, as the cognitive, perceptual and motor capabilities of robots expand, they will be expected to have an improved capacity for making moral judgements. We present a control architecture that supplements existing robot controllers. This so-called Ethical Layer ensures robots behave according to a predetermined set of ethical rules by predicting the outcomes of possible actions and evaluating the predicted outcomes against those rules. To validate the proposed architecture, we implement it on a humanoid robot so that it behaves according to Asimov's laws of robotics. In a series of four experiments, using a second humanoid robot as a proxy for the human, we demonstrate that the proposed Ethical Layer enables the robot to prevent the human from coming to harm.