A Path-Planning Approach Based on Potential and Dynamic Q-Learning for Mobile Robots in Unknown Environment

Figure 3

Path planning (solution) for MR in different test environments (each map shows the best path obtained by the PDQL algorithm, S is the starting point, and G is the goal point). (a) M01. (b) M02. (c) M03. (d) M04. (e) M05. (f) M06. (g) M07. (h) M08. (i) M09.