基于视觉机器人障碍点云映射避障规划及仿真  

Visual Robot Obstacle Avoidance Planning and Simulation Using Mapped Point Clouds

作　　者：霍韩淋 邹湘军[1,2] 陈燕 周馨曌[2] 陈明猷 李承恩 潘耀强 唐昀超 Huo Hanlin;Zou Xiangjun;Chen Yan;Zhou Xinzhao;Chen Mingyou;Li Chengen;Pan Yaoqiang;Tang Yunchao(College of Engineering,South China Agricultural University,Guangzhou 510000,China;Foshan-Zhongke Innovation Research Institute of Intelligent Agriculture and Robotics,Foshan 528000,China;College of Urban and rural Construction,Zhongkai College of Agricultural Engineering,Guangzhou 510080,China)

机构地区：[1]华南农业大学工程学院,广东广州510000 [2]佛山市中科农业机器人与智慧农业创新研究院,广东佛山528000 [3]仲恺农业工程学院城乡建设学院,广东广州510080

出　　处：《系统仿真学报》2024年第9期2149-2158,共10页Journal of System Simulation

基　　金：国家自然科学基金(32171909);东莞市2021年度省乡村振兴战略专项资金“大专项+任务清单”(20211800400013);广东省科学技术厅计划(2021A1313030016)。

摘　　要：针对复杂非结构化果园环境下的视觉点云障碍物识别的数据量大、冗杂度高,严重影响采摘作业的实时性及效率,基于点云分割提出了一种点云压缩算法,旨在提升了点云障碍物的识别效率及环境自适应性。采用了基于Informed RRT^(*)及结合逆投影算法Mapping-based Informed RRT^(*)(M-Informed RRT^(*))降维求解采摘路径。通过构建一个强实时性和高鲁棒性的机器人“采样-感知-避障”一体化作业系统,实现了高效的障碍物识别和路径规划。ROS采摘机器人的实验数据证明了本算法的可行性,显著提升了采摘作业的效率。In response to the large and complex data volume and high redundancy of visual point cloud obstacle recognition in complex unstructured orchard environments,which severely impacts the real-time performance and efficiency of harvesting operations,a point cloud compression algorithm is proposed based on point cloud segmentation to enhance the efficiency of point cloud obstacle recognition and environmental adaptability.An Informed RRT^(*)based approach is used combined with an inverse projection algorithm,mapping-based informed RRT^(*)(M-Informed RRT^(*))to solve the harvesting path problem.By constructing a highly real-time and robust integrated robot system for sampling,perception,and obstacle avoidance,efficient obstacle recognition and path planning are achieved.Experimental data from ROS based picking robots demonstrates the feasibility of this algorithm and significantly improves the efficiency of harvesting operations.

关 键 词：双目视觉 路径规划 点云映射 ROS仿真 采摘避障 

分 类 号：TP249[自动化与计算机技术—检测技术与自动化装置] TP242.3[自动化与计算机技术—控制科学与工程] TP391