“…2) Process Noise Distribution: We model [w t n t ] as a product of 6 (2 for agent, 2×2 for obstacles) independent uni-variate truncated normal random variables (cf. [9], [10]), truncNorm(µ, σ, a, b), with µ = 0, a = −2, b = 2 and σ = 0.01 for w t , σ = 0.1 for n t . The resulting distribution for [w t n t ] has mean 0, variance Σ = 7.7 • blkdiag(10 −5 I 2×2 , 10 −3 I 4×4 ) and support D = ([−0.02, 0.02]) 2 × ([−0.2, 0.2]) 4 (with Γ = blkdiag(10 2 I2×2, 10I4×4), γ = 2 ), which is used for defining the uncertainty descriptions D1, D2, D3.…”