aiqbench analysis
This research advances safe autonomous navigation for unmanned surface vehicles by integrating credibility-weighted value learning with uncertainty-aware control barrier functions. The approach dynamically adjusts trust in sensor data and expands safety boundaries based on estimation errors, ensuring robust compliance with maritime traffic rules even when perception is miscalibrated. Simulations demonstrate significantly improved collision avoidance success rates in dynamic environments beyond the training distribution.
Credibility-Aware Learning and Control for Safe USV Navigation under Perception Uncertainty
arXiv:2605.26974v4 Announce Type: replace Abstract: Safe navigation for Unmanned Surface Vehicles (USVs) under the International Regulations for Preventing Collisions at Sea (COLREGs) remains challenging in dynamic maritime environments, especially when perception uncertainty is miscalibrated. Errors in state estimation can produce unreliable belief states that mislead value learning, while logic based on discrete traffic rules can cause abrupt action corrections. To address these challenges, we integrate Credibility-Weighted Value Learning (CWVL) with Covariance- and Recovery-Aware Control Barrier Function Quadratic Programming (CoReCBF-QP). CWVL derives a dynamic trust factor from the discrepancy between the covariance estimated by the filter and empirical error statistics. This factor modulates the critic's heteroscedastic loss and limits overfitting to miscalibrated observations. CoReCBF expands the collision geometry according to uncertainty and incorporates terms for braking and turning recovery. The resulting hyperbolic safety boundary preserves feasible avoidance velocities and supplies the QP safety constraint. A continuous COLREGs-aware reference in the objective promotes starboard maneuvers in Rule 14 head-on and Rule 15 give-way crossing encounters. Simulations show improved robustness in collision avoidance and COLREGs event compliance, achieving an 82.0\% success rate with ten target ships beyond the training range.
Abstract:Safe navigation for Unmanned Surface Vehicles (USVs) under the International Regulations for Preventing Collisions at Sea (COLREGs) remains challenging in dynamic maritime environments, especially when perception uncertainty is miscalibrated. Errors in state estimation can produce unreliable belief states that mislead value learning, while logic based on discrete traffic rules can cause abrupt action corrections. To address these challenges, we integrate Credibility-Weighted Value Learning (CWVL) with Covariance- and Recovery-Aware Control Barrier Function Quadratic Programming (CoReCBF-QP). CWVL derives a dynamic trust factor from the discrepancy between the covariance estimated by the filter and empirical error statistics. This factor modulates the critic's heteroscedastic loss and limits overfitting to miscalibrated observations. CoReCBF expands the collision geometry according to uncertainty and incorporates terms for braking and turning recovery. The resulting hyperbolic safety boundary preserves feasible avoidance velocities and supplies the QP safety constraint. A continuous COLREGs-aware reference in the objective promotes starboard maneuvers in Rule 14 head-on and Rule 15 give-way crossing encounters. Simulations show improved robustness in collision avoidance and COLREGs event compliance, achieving an 82.0\% success rate with ten target ships beyond the training range.
Robotics (cs.RO)
arXiv:2605.26974 [cs.RO]
(or arXiv:2605.26974v4 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2605.26974 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 273 words
Related coverage
Game Design Creativity evals
LessWrong · Oct 12, 2026
SemSafe-3DGS: Semantic Risk-Aware Active Navigation in Uncertain 3D Gaussian Splatting Maps
arXiv · Sep 18, 2026
Trust, Geometry, and Rules: A Credibility-Aware Reinforcement Learning Framework for Safe USV Navigation under Uncertainty
arXiv · Jun 8, 2026
End-to-End Safe Social Navigation via Multi-Task Reinforcement Learning and Probabilistic Perception
arXiv · Oct 6, 2026