A New Terrain Classification Framework Using Proprioceptive Sensors for Mobile Robots

Figure 9

Accuracies obtained using the proposed terrain classification framework as a function of number of optimal features: (a) Accuracies of SVM; (b) accuracies of RF; (c) accuracies of kNN; and (d) accuracies of NB. The horizontal axis indicates the number of selected optimal features (dimension of optimal feature vector). The accuracies were measured for three different driving speeds.

(a)

(b)

(c)

(d)