Table 3 Quality comparisons of proposed and existing path planning systems for static and dynamic Obstacles environments.
Path planning system | Accuracy | Precision | Recall | F- Measure | Accuracy | Precision | Recall | F-measure |
|---|---|---|---|---|---|---|---|---|
Measure (%) – Static obstacles | Measure (%) – Dynamic obstacles | |||||||
Random forest | 79.714 | 75.715 | 75.138 | 75.426 | 67.739 | 66.740 | 66.399 | 66.569 |
Linear regression | 82.070 | 78.071 | 77.494 | 77.782 | 71.301 | 70.302 | 69.961 | 70.131 |
K-nearest neighbor | 84.426 | 80.427 | 79.850 | 80.138 | 74.863 | 73.864 | 73.523 | 73.693 |
Support vector machine | 86.782 | 82.783 | 82.206 | 82.494 | 78.425 | 77.426 | 77.085 | 77.255 |
Decision tree | 89.138 | 85.139 | 84.562 | 84.850 | 81.987 | 80.988 | 80.647 | 80.817 |
XG boosting | 91.494 | 87.495 | 86.918 | 87.206 | 85.549 | 84.550 | 84.209 | 84.379 |
Deep neural network | 93.850 | 89.851 | 89.274 | 89.562 | 89.111 | 88.112 | 87.771 | 87.941 |
Artificial neural network | 96.206 | 92.207 | 91.630 | 91.918 | 92.673 | 91.674 | 91.333 | 91.503 |
MAMO + CLS + HS-RNN | 98.562 | 94.563 | 93.986 | 94.274 | 96.235 | 95.236 | 94.895 | 95.065 |
