The effort to "align" AI with human values is falling dangerously short in robotic systems, according to researchers from Penn Engineering, Carnegie Mellon University (CMU) and the University of Oxford. In a new paper appearing in Science Robotics, the researchers highlight the need to develop more thorough frameworks for ensuring that AI-enabled robots embody a core principle famously articulated by science fiction author Isaac Asimov: "A robot may not injure a human being."
