Fig 1.
Flow of the REINFORCE algorithm.
Fig 2.
Schematic diagram of ACA in VN of ADRs.
Fig 3.
Parallel ACA for VN of an autonomous robot.
Fig 4.
Flowchart of improved REINFORCE algorithm based on ACA.
Fig 5.
ResBlock structure diagram.
Fig 6.
Module combining CAM and SAM.
Fig 7.
Diagram of the ADR-VN model based on the improved REINFORCE algorithm.
Table 1.
Experimental settings.
Fig 8.
Comparison of ACC and recall rates of several algorithms.
Fig 9.
Comparison of convergence and runtime of several algorithms.
Fig 10.
Comparison of RMSE and MAE of several algorithms.
Fig 11.
Accuracy of the algorithm in the value function and the policy function.
Fig 12.
Average reward value of VN of autonomous robot in simulated environment and real scene.
Table 2.
NSR between simulated environment and real scenario.
Table 3.
NDT between simulated environment and real scenario.
Table 4.
Comparison of Navigation Performance of various algorithms in Extreme Scenarios.
Table 5.
Statistical significance analysis results of performance indicators for each algorithm.
Table 6.
Performance comparison table of ablation experiments.
Table 7.
Performance comparison of improved algorithm and modern DRL methods.
Table 8.
Cross-validation comparison of algorithm robustness and resource consumption.
Table 9.
Comparison of algorithm deployment and computational efficiency on mainstream embedded platforms.
Table 10.
Comparison of navigation performance of various algorithms in chaotic urban street environments.