VORRT-COLREG：一种基于速度障碍和RRT的COLREG兼容的自主水面舰艇路径规划器
VORRT-COLREGs: A Hybrid Velocity Obstacles and RRT Based COLREGs-Compliant Path Planner for Autonomous Surface Vessels
摘要：
本文介绍了VORRT-COLREG，一种混合技术，结合速度障碍（VO）和快速探索随机树（RRT），以生成安全的轨迹自主水面船只（ASV），同时遵循航海规则的道路。RRT生成一组路径点，速度障碍方法确保路径点之间的安全行驶。我们还确保ASV的行动不违反海上碰撞准则。早期的工作分别使用RRT和VO来生成ASV的路径。然而，RRT不能很好地处理高度动态的情况，并且VO似乎最适合作为本地路径规划器。结合这两种方法，VORRT-COLREG是一个全局路径规划器，它使用联合正向仿真来确保生成的路径在情况变化时保持有效和无冲突。实验是在不同类型的碰撞情况下进行的，并使用了不同数量的ASV。结果表明，VORRT-COLREGS生成碰撞规则（COLREG）投诉路径在开放的海洋场景。此外，VORRT-COLREGS成功地在交通分离方案中生成了符合要求的路径。这些结果表明，我们的技术在不同的碰撞情况下生成ASV的路径的适用性。据我们所知，这是第一个结合速度障碍和RRT为ASV产生安全和COLREG投诉路径的工作。
英文摘要：
This paper presents VORRT-COLREGs, a hybrid technique that combines velocity obstacles (VO) and rapidly-exploring random trees (RRT) to generate safe trajectories for autonomous surface vessels (ASVs) while following nautical rules of the road. RRT generates a set of way points and the velocity obstacles method ensures safe travel between way points. We also ensure that the actions of ASVs do not violate maritime collision guidelines. Earlier work has used RRT and VO separately to generate paths for ASVs. However, RRT does not handle highly dynamic situations well and and VO seems most suitable as a local path planner. Combining both approaches, VORRT-COLREGs is a global path planner that uses a joint forward simulation to ensure that generated paths remain valid and collision free as the situation changes. Experiments were conducted in different types of collision scenarios and with different numbers of ASVs. Results show that VORRT-COLREGS generated collision regulations (COLREGs) complaint paths in open ocean scenarios. Furthermore, VORRT-COLREGS successfully generated compliant paths within traffic separation schemes. These results show the applicability of our technique for generating paths for ASVs in different collision scenarios. To the best of our knowledge, this is the first work that combines velocity obstacles and RRT to produce safe and COLREGs complaint path for ASVs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
