摘要
农业机器人采用深度强化学习算法进行路径规划时存在难以找到目标点、稀疏奖励、收敛缓慢等问题,为此提出基于多目标点导航融合改进深度Q网络算法(MPN-DQN)的路径规划方法.利用激光同步定位与建图(SLAM)扫描全局环境以构建先验地图,划分行走行和作物行区域;对地图边界进行膨胀拟合处理,形成前向弓字形作业走廊.利用中间目标点分割全局环境,将复杂环境划分为多阶段短程导航环境以简化目标点搜索过程.从动作空间、探索策略和奖励函数3个方面改进深度Q网络算法以改善奖励稀疏问题,加快算法收敛速度,提高导航成功率.实验结果表明,搭载MPN-DQN的农业机器人自主行驶的总碰撞次数为1,平均导航时间为104.27 s,平均导航路程为16.58 m,平均导航成功率为95%.
In order to solve the problems of difficulty in finding target points,sparse rewards,and slow convergence when using deep reinforcement learning algorithms for path planning of agricultural robots,a path-planning method based on multi-target point navigation integrated improved deep Q-network algorithm(MPN-DQN)was proposed.The laser simultaneous localization and mapping(SLAM)was used to scan the global environment to construct a prior map and divide the walking row and crop row areas,and the map boundary was expanded and fitted to form a forward bowshaped operation corridor.The middle target point was used to segment the global environment,and the complex environment was divided into a multi-stage short-range navigation environment to simplify the target point search process.The deep Q-network algorithm was improved from three aspects:action space,exploration strategy and reward function to improve the reward sparsity problem,accelerate the convergence speed of the algorithm,and improve the navigation success rate.Experimental results showed that the total number of collisions of agricultural robots equipped with the MPN-DQN algorithm was 1,the average navigation time was 104.27 s,the average navigation distance was 16.58 m,and the average navigation success rate was 95%.
作者
赵威
张万枝
侯加林
侯瑞
李玉华
赵乐俊
程进
ZHAO Wei;ZHANG Wanzhi;HOU Jialin;HOU Rui;LI Yuhua;ZHAO Lejun;Cheng Jin(College of Mechanical and Electronic Engineering,Shandong Agricultural University,Taian 271018,China;Shandong Engineering Research Center of Agricultural Equipment Intelligentization,Taian 271018,China;School of Artificial Intelligence,Beijing University of Posts and Telecommunications,Beijing 100876,China;Shandong Key Laboratory of Intelligent Production Technology and Equipment for Facility Horticulture,Taian 271018,China)
出处
《浙江大学学报(工学版)》
北大核心
2025年第7期1492-1503,共12页
Journal of Zhejiang University(Engineering Science)
基金
山东省重点研发计划(重大科技创新工程)项目(2022CXGC020703)
山东省重点研发计划(乡村振兴科技创新提振行动计划)项目(2022TZXD006)
山东省薯类产业技术体系农业机械岗位专家项目(SDAIT-16-10)。
