Robots Learning Altruism and Cooperation – Interesting by Itself and Seems to Echo a Human Mod
It feels like science fiction. But, here is the ScienceDaily summary of an experiment – and success – in robots learning altruism and cooperation. The experiment was undertaken to test "Hamilton’s Rule" on why humans act altruistically. The full paper is here in PLoS.
The experiment involved researchers at the Ecole Polytechnique Fédérale de Lausanne, Lausanne, Switzerland, and the Department of Ecology and Evolution, Biophore, University of Lausanne. The Swiss researchers used small "Alice" robots previously developed at the University. The robots seek out food. The robots started with 33 "genes" of code. They evolved and improved over 500 generations of robots. The authors now want to put the results to work to see if flying robots will better cooperate in swarming.
The law side? Who knows. But this article caught my eye because somewhere an article set out the idea that some day robots could be used to clean up debris at nuclear power plants, but current design standards make that harder because power plant designs assume human mobility and dexterity. Will it some day be negligent to design a nuclear plant without providing for robotic clean up?
Here’s the conclusion from the article:
"Because the 33 genes were initially set to random values, the robots’ behaviors were completely arbitrary in the first generation. However, the robots’ performance rapidly increased over the 500 generations of selection (Figure 2). The level of altruism also rapidly changed over generations with the final stable level of altruism varying greatly depending on the within-group relatedness and c/b ratio (Figure 3). When the c/b value was very small (0.01), the level of altruism was very high in the populations where within-group relatedness was positive (i.e., 0.25, 0.5, 0.75, and 1.00) and close to zero when robots were unrelated (Figure 4). In the treatments with other c/b values, the level of altruism was also very low when the relatedness was close to 0 and the level of altruism also rapidly increased when the relatedness became higher than a given value. In all cases, the transition occurred when r became greater than c/b, as predicted by Hamilton’s rule."