XXooptRobotics

Discrete Bayes Filter: One Measurement Update

mediumnumerical

General

A robot moving along a 1D hallway estimates which of 3 discrete cells it occupies. Its current belief (prior) over cells (c1,c2,c3)(c_1, c_2, c_3) is (0.2,0.5,0.3)(0.2, 0.5, 0.3). A door sensor fires, and the likelihood of getting this exact sensor reading given the robot is in each cell is P(zc1)=0.6P(z \mid c_1)=0.6, P(zc2)=0.2P(z \mid c_2)=0.2, P(zc3)=0.9P(z \mid c_3)=0.9. Applying one discrete Bayes filter measurement (correction) update, what is the posterior probability that the robot is in cell c2c_2? Give your answer as a probability (round to 2 decimal places).

probability