Research on trajectory prediction and tracking methods for underwater cleaning robots based on PA-MDP

To address cleaning operations in high-interference power cooling ponds, this paper proposes a physics-aware Markov decision process (PA-MDP) framework. This framework is designed to mitigate trajectory deviations caused by the decoupling of decision-making logic and physical dynamics in dynamically constrained underwater environments. The core innovation lies in the explicit coupling of computational fluid dynamics (CFD) prior fields with stochastic differential equation integration, enabling the quantitative physical characterization of robot motion uncertainty. On this basis, a multi-objective reward function—balancing cleaning coverage gains and nonlinear flow field energy costs—is reconstructed to induce physically consistent optimal operational paths. To handle non-stationary disturbances, an asynchronous replanning mechanism based on Mahalanobis distance monitoring is introduced. Furthermore, within the stochastic model predictive control framework, the mean-square ultimate boundedness of the closed-loop system is proved using Lyapunov theory. Simulation and prototype experiments demonstrate that, compared to NMPC and DOB-ALC algorithms, PA-MDP reduces steady-state error by approximately 33% under strong disturbances and shortens recovery time by 44% following sudden disruptions. The proposed method achieves a superior performance balance between dynamic robustness and energy efficiency optimization. These findings provide an integrated solution characterized by theoretical rigor and engineering resilience for autonomous robotic operation and maintenance in complex, constrained aquatic environments.