As research expands in multiagent intelligent systems, investigators need n
ew tools for evaluating the artificial societies they study. It is impossib
le, for example, to correlate heterogeneity with performance in multiagent
robotics without a quantitative metric of diversity. Currently diversity is
evaluated on a bipolar scale with systems classified as either heterogeneo
us or homogeneous, depending on whether any of the agents differ. Unfortuna
tely, this labeling doesn't tell us much about the extent of diversity in h
eterogeneous teams. How can it be determined if one system is more or less
diverse than another? Heterogeneity must be evaluated on a continuous scale
to enable substantive comparisons between systems. To enable these types o
f comparisons, we introduce: (1) a continuous measure of robot behavioral d
ifference, and (2) hierarchic social entropy, an application of Shannon's i
nformation entropy metric to robotic groups that provides a continuous, qua
ntitative measure of robot team diversity. The metric captures important co
mponents of the meaning of diversity, including the number and size of beha
vioral groups in a society and the extent to which agents differ. The utili
ty of the metrics is demonstrated in the experimental evaluation of multiro
bot soccer and multirobot foraging teams.