Akratic robots and the computational logic thereof

Are Autonomous-and-Creative Machines Intrinsically Untrustworthy?

“…Such "trust-aware" machines would have not only ToM-creativity, but, if you will, "ToM prudence." 22 For more detailed use, and technical presentation, of a cognitive calculus that is only a slightly different dialect than D e CEC, see [10]. The results given there are now greatly improved performancewise by the use of ShadowProver.…”

“…Unfortunately, such ascriptions are -as of the typing of the present sentence in late 2016 -issued in the absence of a formal definition of what autonomy is. 10 What might a formal definition of autonomy look like? Presumably such an account would be developed along one or both of two trajectories.…”

Machine Ethics: The Design and Governance of Ethical AI and Autonomous Systems [Scanning the Issue]

“…The earliest proposal for a practical ethical governor for robots -a mechanism for moderating or inhibiting a robot's behavior to prevent it from acting unethically -was from Arkin [20], 1 although not tested on real robots. At the time of writing the number of experimental demonstrations of ethical robots remains very small indeed; to the best of our knowledge there have been only five such demonstrations to date: (i) the GenEth system of Anderson and Anderson [22], (ii) the Asimovian ethical robots of Winfield et al [23] and Vanderelst and Winfield [24], (iii) Bringsjord et al's Akratic robot [25], (iv) the "sorry I can't do that" robot of Briggs and Scheutz [26], and (v) the Intervening robot mediator in healthcare of Shim, Arkin and Pettinatti [27]. Papers which review and update the approaches of (i) and (ii) are included in this issue; we now briefly review (iii -v).…”

“…in scenarios in which it is charged with guarding a prisoner of war and must choose between retaliating with violence to an attack (thus satisfying a self-defense goal) or refraining from retaliation [25]. The robot's "ethical substrate model" incorporates logic that specifies which actions are forbidden under certain circumstances, or which are permitted or obligatory; importantly that logic, a deontic cognitive event calculus (DCEC), can be formally verified.…”

“…Briggs and Scheutz [26] demonstrate a robot capable of declining to carry out an instruction, if it reasons that to do so would harm itself. The robot may more properly be described as implicitly ethical since it is designed only to avoid unethical outcomes to itself, but the cognitive machinery it uses to avoid such outcomes is, like Bringsjord et al's robot [25], based on reasoning about obligation and permissibility.…”