Path Planning Algorithm for Unmanned Surface Vessel Based on Multiobjective Reinforcement Learning

Table 4

Performance of various path planning methods.

Method of path planning	Success rate of path planning (%)	Success rate of goal approaching (%)	Success rate of dynamic obstacle avoidance (%)	Length of the path (m)
A ^∗ + ORCA	42	100	42	16.43
Dueling DQN	82	97	85	18.32
PER-DDQN	80	98	81	18.57
Proposed method	93	96	97	17.96