Research on scheduling path planning of multi-objective unmanned tractor based on reinforcement learning method

2022 IEEE 8th International Conference on Cloud Computing and Intelligent Systems (CCIS) Pub Date : 2022-11-26 DOI:10.1109/ccis57298.2022.10016314

Haichen Wang, Huarui Wu, Ning Zhang

{"title":"Research on scheduling path planning of multi-objective unmanned tractor based on reinforcement learning method","authors":"Haichen Wang, Huarui Wu, Ning Zhang","doi":"10.1109/ccis57298.2022.10016314","DOIUrl":null,"url":null,"abstract":"In order to improve the efficiency of unmanned tractor ridge operation and save land costs, hence, a multi-objective optimization model is established in this paper, with the goal of minimizing the reserved turning distance and turning scheduling time at the headland. The model is solved by the improved reinforcement learning method according to the tractor’s turning action and motion state, and the optimal turning decision-making method that satisfies the multi-objective optimization conditions is obtained by using the TOPSIS method. On this basis, with the shortest global tractor turning time, the ant colony algorithm is used to plan the ridge operation path of the unmanned tractor. According to the experiment, the optimized unmanned tractor can save 17.8% of the turning time and 23.9% of the reserved length of the headland by operating in the shuttle operation mode; the total turning time of planning the global operation path combined with the ant colony algorithm can be saved by 48.22%.","PeriodicalId":374660,"journal":{"name":"2022 IEEE 8th International Conference on Cloud Computing and Intelligent Systems (CCIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE 8th International Conference on Cloud Computing and Intelligent Systems (CCIS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ccis57298.2022.10016314","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

In order to improve the efficiency of unmanned tractor ridge operation and save land costs, hence, a multi-objective optimization model is established in this paper, with the goal of minimizing the reserved turning distance and turning scheduling time at the headland. The model is solved by the improved reinforcement learning method according to the tractor’s turning action and motion state, and the optimal turning decision-making method that satisfies the multi-objective optimization conditions is obtained by using the TOPSIS method. On this basis, with the shortest global tractor turning time, the ant colony algorithm is used to plan the ridge operation path of the unmanned tractor. According to the experiment, the optimized unmanned tractor can save 17.8% of the turning time and 23.9% of the reserved length of the headland by operating in the shuttle operation mode; the total turning time of planning the global operation path combined with the ant colony algorithm can be saved by 48.22%.

查看原文本刊更多论文

基于强化学习方法的多目标无人驾驶拖拉机调度路径规划研究

因此，为了提高无人驾驶拖拉机垄沟作业效率，节约土地成本，本文建立了以海岬预留转弯距离和转弯调度时间最小为目标的多目标优化模型。根据拖拉机的转向动作和运动状态，采用改进的强化学习方法对模型进行求解，利用TOPSIS方法得到满足多目标优化条件的最优转向决策方法。在此基础上，以全局拖拉机转弯时间最短为目标，采用蚁群算法规划无人驾驶拖拉机的山脊作业路径。实验结果表明，优化后的无人驾驶拖拉机在穿梭运行模式下，转弯时间节省17.8%，海岬预留长度节省23.9%;结合蚁群算法规划全局运行路径的总转弯时间可节省48.22%。

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

2022 IEEE 8th International Conference on Cloud Computing and Intelligent Systems (CCIS)

自引率

0.00%

发文量