GLM Error in R - Getting the message: "Error: no valid set of coefficients has been found: please supply starting values"

Question

I am trying to assign a poisson distribution to the random component of a GLM in R, however I keep getting the message "Error: no valid set of coefficients has been found: please supply starting values" when I try the following code:

normal.poisson.glm <- glm(Incidents ~ Temp, family=poisson(link=identity), data=O.Ring_Problems)

The formula works when I change "identity" to "log" or when I change "poisson" to "gaussian", but I can't figure out how to plug starting values in to make the formula. Does anyone know how to fix the issue?

My original dataframe is:

O.Ring_Problems <- data.frame(
"Temp" = c(53,56,57,63,66,67,67,67,68,69,70,70,70,70,72,73,75,75,76,76,78,79,80,81),
"Incidents" = c(3,1,1,0,0,0,0,0,0,0,0,1,1,1,0,0,0,2,0,0,0,0,0,0))