A Generalized Voronoi Diagram-Based Efficient Heuristic Path Planning Method for RRTs in Mobile Robots

运动规划 沃罗诺图 启发式 计算机科学 特征(语言学) 任意角度路径规划 移动机器人 人工智能 算法 特征提取 数学优化 机器人 数学 几何学 语言学 哲学
作者
Wenzheng Chi,Zhiyu Ding,Jiankun Wang,Guodong Chen,Lining Sun
出处
期刊:IEEE Transactions on Industrial Electronics [Institute of Electrical and Electronics Engineers]
卷期号:69 (5): 4926-4937 被引量:110
标识
DOI:10.1109/tie.2021.3078390
摘要

The rapidly exploring random tree and its variants (RRTs) have been widely adopted as the motion planning algorithms for mobile robots. However, the trap space problem, such as mazes and S-shaped corridors, hinders their planning efficiency. In this article, we present a generalized Voronoi diagram (GVD)-based heuristic path planning algorithm to generate a heuristic path, guide the sampling process of RRTs, and further improve the motion planning efficiency of RRTs. Different from other heuristic algorithms that only work in certain environments or depend on specified parameter setting, the proposed algorithm can automatically identify the environment feature and provide a reasonable heuristic path. First, the given environment is initialized with a lightweight feature extraction from the GVD, which guarantees that any state in the free space can be connected to the feature graph without any collision. Second, to remove the redundancy of feature nodes, a feature matrix is proposed to represent connections among feature nodes and a corresponding feature node fusion technique is utilized to delete the redundant nodes. Third, based on the GVD feature matrix, a heuristic path planning algorithm is presented. This heuristic path is then used to guide the sampling process of RRTs and achieve real-time motion planning. The proposed GVD feature matrix can be also utilized to improve the efficiency of the replanning. Through a series of simulation studies and real-world implementations, it is confirmed that the proposed algorithm achieves better performance in heuristic path planning, feature extraction of free space, and real-time motion planning.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
顺心磬完成签到 ,获得积分10
刚刚
1秒前
半个桃子发布了新的文献求助30
1秒前
2秒前
2秒前
娜娜发布了新的文献求助10
4秒前
猪猪hero发布了新的文献求助10
5秒前
王www发布了新的文献求助10
7秒前
8秒前
沙世平完成签到,获得积分10
8秒前
小h发布了新的文献求助20
10秒前
11秒前
12秒前
13秒前
飞飞发布了新的文献求助10
15秒前
17秒前
学术不难发布了新的文献求助30
17秒前
18秒前
丘比特应助猪猪hero采纳,获得10
18秒前
22秒前
24秒前
席河木鱼发布了新的文献求助10
26秒前
淡定小白菜完成签到,获得积分10
26秒前
朝朝发布了新的文献求助10
29秒前
29秒前
30秒前
麦苗果果发布了新的文献求助10
31秒前
量子星尘发布了新的文献求助10
31秒前
31秒前
王www完成签到,获得积分10
32秒前
32秒前
1751587229发布了新的文献求助10
33秒前
tao完成签到 ,获得积分10
34秒前
孙皮皮完成签到 ,获得积分10
35秒前
猪猪hero发布了新的文献求助10
36秒前
泡面完成签到 ,获得积分10
37秒前
彭于彦祖应助刘玉采纳,获得30
37秒前
大模型应助席河木鱼采纳,获得10
38秒前
热心市民小红花应助骑骑采纳,获得10
38秒前
chy发布了新的文献求助10
38秒前
高分求助中
The Mother of All Tableaux Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 2400
Ophthalmic Equipment Market by Devices(surgical: vitreorentinal,IOLs,OVDs,contact lens,RGP lens,backflush,diagnostic&monitoring:OCT,actorefractor,keratometer,tonometer,ophthalmoscpe,OVD), End User,Buying Criteria-Global Forecast to2029 2000
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Cognitive Neuroscience: The Biology of the Mind (Sixth Edition) 1000
Optimal Transport: A Comprehensive Introduction to Modeling, Analysis, Simulation, Applications 800
Official Methods of Analysis of AOAC INTERNATIONAL 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3959210
求助须知:如何正确求助?哪些是违规求助? 3505538
关于积分的说明 11124306
捐赠科研通 3237248
什么是DOI,文献DOI怎么找? 1789010
邀请新用户注册赠送积分活动 871512
科研通“疑难数据库(出版商)”最低求助积分说明 802824