Table 2 Reduplicate experiments results of all approaches within the Zara dataset.

From: Goal-oriented autonomous decision-making for social robots via collaborative interactive inverse reinforcement learning approach

Method

Success rate [%]

Disturbance score

minimal social distance

Disturbance score

comfortable social distance

LM-SARL

83 ± 1

0.09 ± 0.01

2.46 ± 0.34

det-MEDIRL

78 ± 6

0.27 ± 0.03

1.89 ± 0.18

GAIfO

72 ± 3

0.26 ± 0.06

1.16 ± 0.11

SAIfO

79 ± 9

0.22 ± 0.03

1.42 ± 0.14

GO-ADM

91 ± 2

0.03 ± 0.02

0.99 ± 0.23

Back to article page