Optimal policies for autonomous navigation in strong currents using fast marching trees

IF 3.7 3区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Autonomous Robots Pub Date : 2024-10-22 DOI:10.1007/s10514-024-10179-z

Bernardo Martinez Rocamora Jr., Guilherme A. S. Pereira

{"title":"Optimal policies for autonomous navigation in strong currents using fast marching trees","authors":"Bernardo Martinez Rocamora Jr., Guilherme A. S. Pereira","doi":"10.1007/s10514-024-10179-z","DOIUrl":null,"url":null,"abstract":"<div><p>Several applications require that unmanned vehicles, such as UAVs and AUVs, navigate environmental flows. While the flow can improve the vehicle’s efficiency when directed towards the goal, it may also cause feasibility problems when it is against the desired motion and is too strong to be counteracted by the vehicle. This paper proposes the flow-aware fast marching tree algorithm (FlowFMT*) to solve the optimal motion planning problem in generic three-dimensional flows. Our method creates either an optimal path from start to goal or, with a few modifications, a vector field-based policy that guides the vehicle from anywhere in its workspace to the goal. The basic idea of the proposed method is to replace the original neighborhood set used by FMT* with two sets that consider the reachability from/to each sampled position in the space. The new neighborhood sets are computed considering the flow and the maximum speed of the vehicle. Numerical results that compare our methods with the state-of-the-art optimal control solver illustrate the simplicity and correctness of the method.</p></div>","PeriodicalId":55409,"journal":{"name":"Autonomous Robots","volume":null,"pages":null},"PeriodicalIF":3.7000,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Autonomous Robots","FirstCategoryId":"94","ListUrlMain":"https://link.springer.com/article/10.1007/s10514-024-10179-z","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}

引用次数: 0

Abstract

Several applications require that unmanned vehicles, such as UAVs and AUVs, navigate environmental flows. While the flow can improve the vehicle’s efficiency when directed towards the goal, it may also cause feasibility problems when it is against the desired motion and is too strong to be counteracted by the vehicle. This paper proposes the flow-aware fast marching tree algorithm (FlowFMT*) to solve the optimal motion planning problem in generic three-dimensional flows. Our method creates either an optimal path from start to goal or, with a few modifications, a vector field-based policy that guides the vehicle from anywhere in its workspace to the goal. The basic idea of the proposed method is to replace the original neighborhood set used by FMT* with two sets that consider the reachability from/to each sampled position in the space. The new neighborhood sets are computed considering the flow and the maximum speed of the vehicle. Numerical results that compare our methods with the state-of-the-art optimal control solver illustrate the simplicity and correctness of the method.

Abstract Image

查看原文本刊更多论文

利用快速行进树在强水流中实现自主导航的最佳策略

在一些应用中，无人飞行器（如无人潜航器和自动潜航器）需要导航环境流。当环境流指向目标时，可以提高飞行器的效率，但当环境流与飞行器的运动目标相悖且强度过大时，也可能导致可行性问题。本文提出了流量感知快速行进树算法（FlowFMT*）来解决一般三维流中的最优运动规划问题。我们的方法既可以创建一条从起点到目标的最优路径，也可以在稍作修改后创建一个基于矢量场的策略，引导车辆从其工作空间的任意位置到达目标。所提方法的基本思想是用两个考虑空间中每个采样位置的可达性的邻域集取代 FMT* 使用的原始邻域集。新的邻域集在计算时考虑了流量和车辆的最大速度。将我们的方法与最先进的最优控制求解器进行比较的数值结果表明了该方法的简便性和正确性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Autonomous Robots 工程技术-机器人学

CiteScore

7.90

自引率

5.70%

发文量

审稿时长

3 months

期刊介绍： Autonomous Robots reports on the theory and applications of robotic systems capable of some degree of self-sufficiency. It features papers that include performance data on actual robots in the real world. Coverage includes: control of autonomous robots · real-time vision · autonomous wheeled and tracked vehicles · legged vehicles · computational architectures for autonomous systems · distributed architectures for learning, control and adaptation · studies of autonomous robot systems · sensor fusion · theory of autonomous systems · terrain mapping and recognition · self-calibration and self-repair for robots · self-reproducing intelligent structures · genetic algorithms as models for robot development. The focus is on the ability to move and be self-sufficient, not on whether the system is an imitation of biology. Of course, biological models for robotic systems are of major interest to the journal since living systems are prototypes for autonomous behavior.