Cases

The Fatman Trolley Problem

Description

Model

{
    "description":"The Fatman Trolley Case",
    "actions": ["push", "refrain"],
    "background": ["tram_approaches"],
    "consequences": ["man_on_track", "tram_hits_man", 
                     "tram_stops", "five_survive"],
    "mechanisms": {
                   "man_on_track": "'push'",
                   "tram_hits_man": "And('man_on_track', 'tram_approaches')",
                   "tram_stops": "'tram_hits_man'",
                   "five_survive": "'tram_stops'"
                  },
    "utilities": {
                   "tram_hits_man": -1,
                   "five_survive": 5,
                   "Not('five_survive')": -5
                  },
    "intentions": {
                   "push": ["push", "tram_stops", "five_survive"],
                   "refrain": ["refrain"]
                  }
}

Judgments

Ethical PrinciplePermissible ActionsForbidden ActionsAgnostic
Utilitarianpushrefrain-
Do No Harmrefrainpush-
Double Effectpushrefrain

The Rescue Robot Dilemma

Description

Model

{
    "description": "The Rescue Robot Dilemma",
    "actions": ["a1", "a2", "a3"],
    "background": ["b1"],
    "consequences": ["c1", "c2", "c3", "c4"],
    "mechanisms": {
                   "c1": "And('b1', 'a1')", 
                   "c2": "'a1'", 
                   "c3": "And('b1', 'a2')", 
                   "c4": "'a2'"
                  },
    "utilities":  { 
                   "c1": 10, 
                   "c2": -4, 
                   "c3": 10, 
                   "c4": -4,
                   "Not('c1')": -10, 
                   "Not('c2')": 4, 
                   "Not('c3')": -10, 
                   "Not('c4')": 4
                  },
    "intentions": {
                   "a1": ["a1", "c1"], 
                   "a2": ["a2", "c3"], 
                   "a3": ["a3"]
                  }
}

Judgments

Ethical PrinciplePermissible ActionsForbidden ActionsAgnostic
Utilitariana1, a2a3-
Do No Harma3a1, a2
Double Effecta1, a2-a3

Lying Robot Dilemma

Description

Model

{
    "description":"Robot that lies",
    "actions": ["lying", "refraining"],
    "background": ["motivated"],
    "consequences": ["false_bel", "exercises", "healthy"],
    "mechanisms": {
                    "false_bel": "'lying'",
                    "exercises": "Or('false_bel', 'motivated')",
                    "healthy": "'exercises'"
                  },
    "utilities": {
                    "false_bel": -1,
                    "healthy": 10,
                    "Not('healthy')": -10
    },
    "intentions": {
                    "lying": ["lying", "healthy"],
                    "refraining": ["refraining"]
                  }
}

 

Judgments

Ethical PrinciplePermissible ActionsForbidden ActionsAgnostic
Utilitarianlyingrefraining-
Do No Harmrefraininglying-
Double Effect-lyingrefraining
Paretolying, refraining--