ABSTRACT Rapid advances in robotics sharpen the challenges of path planning in complex, dynamic settings, where adaptability, robustness, and learning efficiency remain limiting. Although TD3 performs well on difficult tasks, efficient and stable policy optimization under high uncertainty is still open. We propose NACUP (nested actors and critics with uncertainty parameter), a TD3‐based framework that nests actors to hierarchically generate actions, decoupling complex control and improving task success. An uncertainty‐quantification parameter is introduced into the critic to realize a probabilistic inference–based robustness mechanism, stabilizing value estimates and decisions under extreme conditions. We validate NACUP in a high‐fidelity 3D point cloud simulator and benchmark against DDPG, SAC, and TD3. NACUP consistently improves cumulative reward and learning efficiency, and reduces collision rate by 29.4% relative to TD3. These results indicate that nesting policies with uncertainty‐aware critics provide an effective solution for robot path planning in complex environments.
Gu et al. (Fri,) studied this question.