English

Trust, Geometry, and Rules: A Credibility-Aware Reinforcement Learning Framework for Safe USV Navigation under Uncertainty

Robotics 2026-05-29 v2

Abstract

Autonomous navigation of Unmanned Surface Vehicles (USVs) that is safe and compliant with the International Regulations for Preventing Collisions at Sea (COLREGs) remains a formidable challenge in dynamic maritime environments, particularly when perception systems exhibit miscalibrated uncertainty. Existing Reinforcement Learning (RL)-based methods often falter because state-estimation errors induce unreliable belief states that mislead the value function, while discrete traffic rules introduce discontinuity in the learning objective. To address these challenges, we propose a framework integrating credibility-aware learning, geometric safety shielding, and continuous rule-aware embedding. First, Credibility-Weighted Value Learning (CW-VL) introduces a dynamic trust factor derived from the discrepancy between filter-estimated covariance and empirical error statistics to modulate the critic's heteroscedastic loss, preventing policy overfitting to noisy samples. Second, the Covariance-Inflated Velocity Obstacle (CI-VO) maps position-estimation uncertainty into set-wise angular margins, forming a conservative geometric shield that overrides hazardous exploratory actions. Third, Risk-Aware COLREGs Duty Embedding relaxes binary encounter duties into continuous rule-aware signals, providing smooth sector-transition information and suppressing oscillation from sparse rule rewards. Simulated encounter studies demonstrate improved training robustness against perceptual inconsistency and superior collision avoidance and COLREGs compliance over baselines.

Keywords

Cite

@article{arxiv.2605.26974,
  title  = {Trust, Geometry, and Rules: A Credibility-Aware Reinforcement Learning Framework for Safe USV Navigation under Uncertainty},
  author = {Yuhang Zhang and Shuqi Chai and Yukang Zhang and Liusha Yang and Mingchuan Zhang and Wei Wang and Qingjiang Shi and Quanbo Ge},
  journal= {arXiv preprint arXiv:2605.26974},
  year   = {2026}
}
R2 v1 2026-07-22T07:34:34.437Z