SIA OpenIR  > 机器人学研究室
动态环境下移动机器人自适应路径规划方法研究
Alternative TitleResearch on Adaptive Path Planning of Mobile Robot in Dynamic Environmen
董淑娴
Department机器人学研究室
Thesis Advisor卜春光
Keyword路径规划 动态环境 移动机器人 鲸鱼优化算法 人工势场法
Pages72页
Degree Discipline控制工程
Degree Name专业学位硕士
2021-05-21
Degree Grantor中国科学院沈阳自动化研究所
Place of Conferral沈阳
Abstract当移动机器人在复杂环境下作业时,如何快速高效地规划一条安全路径是其完成任务的关键。本文分析和研究了动态环境下移动机器人的路径规划方法,提出了一种混合路径规划方法以解决全局和局部路径规划的不足,并在仿真环境下验证了该混合算法的有效性。本文的主要工作如下:1)若已知环境中的障碍物信息,在运动之前对机器人进行静态的全局路径规划。针对鲸鱼优化算法收敛速度慢、收敛精度低、易陷入局部最优等问题,本文提出了一种多策略改进的鲸鱼优化算法。首先,在种群初始化时引入Piecewise混沌映射,增强了初始化群体的多样性;其次,在收敛因子中引入非线性调整策略,加入贝塔分布,平衡了算法的全局搜索能力和局部开发能力,加快算法的收敛速度;最后,采用非线性自适应权重对鲸鱼位置更新公式进行了修正,提高算法的寻优精度。仿真结果表明,改进后的鲸鱼优化算法比原始算法更有效,并且可以应用于机器人的全局路径规划中。2)针对传统人工势场法进行局部路径规划时的缺陷进行了改进。针对引力不平衡问题,对引力势场函数进行修改,设置不同的作用域,避免机器人由于引力过大与障碍物相撞;对斥力势场函数进行重新设计,当机器人靠近目标点位置时,将斥力减小到约为零,从而使机器人目标点为全局势场中最小的位置,解决目标不可达问题;引入模拟退火法解决机器人局部最小值、振荡等问题。利用改进的人工势场法,在模拟的复杂环境中进行仿真实验,通过仿真实验,验证了该方法在局部路径规划上的有效性。3)对于在动态环境中机器人的路径规划问题,本文提出了一种混合算法,搭建CoppeliaSim仿真实验平台并进行实验验证。首先使用多策略鲸鱼优化算法生成静态的全局路径,在沿着已生成的全局路径运动时,机器人可以持续感知周围的环境信息并用人工势场法进行障碍物的避碰。如果机器人不与动态障碍物发生碰撞,那么继续按照之前的全局路径前进;如果与障碍物产生碰撞,则利用改进的人工势场法为机器人规划一条避开动态障碍物的局部路径。仿真实验结果表明该混合算法具体可行,可以使机器人较好的避开环境中的静态以及动态障碍物到达期望目标点。
Other AbstractWhen a mobile robot is operating in a complex environment, how to plan a safe path quickly and efficiently is the key to its task. This paper analyzes and studies the path planning method of mobile robots in a dynamic environment, proposes a hybrid path planning method to solve the shortcomings of global and local path planning, and verifies the effectiveness of the hybrid algorithm in a simulation environment. The main work of this paper is as follows: 1.Under the premise of obstacles in environment are observed and detected, we start to plan statical global path before sending moving information to the object vehicle. Aiming at the problems of slow convergence speed, low convergence precision and easy to fall into local optimum of whale optimization algorithm, an creative whale optimization algorithm is proposed with multi-variable stategies. To start with, aiming to enhance the diversity of population during initialization, a kind of chaotic map is introduced called Piecewise. Then, beta distribution is used to disturb the value of convergence factor, which is one of nonlinear adjustment methods. Additionally, this nonlinear adjustment method can accelerate the speed of convergence in whole progress of optimization. Simultaneity, the global search ability and local development ability of the algorithm are balanced. Finally, we amend the formula of position updating by using nonlinear adaptive weight factor, which improve the accuracy of the algorithm. The simulation results show that the improved whale optimization algorithm is more effective than the original algorithm and can be applied to the robot's global path planning. 2.The traditional artificial potential field method is used to adjust the problems of some paths. To solve the problem of gravitational imbalance, modify the gravitational potential field function to set different scopes to prevent the robot from colliding with obstacles due to excessive gravity; redesign the repulsive potential field function. When the robot is close to the target point, the The repulsive force is reduced to 0, so that the target point of the robot is the smallest position in the whole situation, which solves the problem of unreachable targets; the simulated annealing method is introduced to solve the problems of robot local minimum and oscillation. Using the improved artificial potential field method, a simulation experiment is carried out in a simulated complex environment, and the effectiveness of the method is verified through the simulation local path planning experiment. 3.For the problem of robot path planning in a dynamic environment, this paper proposes a hybrid algorithm, builds a CoppeliaSim simulation experimental platform and conducts experimental verification. First, a multi-strategy whale optimization algorithm is used to generate a static global path. When moving along the generated global path, the robot can continuously perceive the surrounding environment information and use the artificial potential field method to avoid obstacles. If the robot does not collide with the dynamic obstacle, it will continue to follow the previous global path; if it collides with the obstacle, the improved artificial potential field method is used to plan a local path for the robot to avoid the dynamic obstacle. The simulation experiment results show that the hybrid algorithm is concrete and feasible, and it can make the robot avoid static and dynamic obstacles in the environment to reach the desired target point.
Language中文
Contribution Rank1
Document Type学位论文
Identifierhttp://ir.sia.cn/handle/173321/28989
Collection机器人学研究室
Affiliation中国科学院沈阳自动化研究所
Recommended Citation
GB/T 7714
董淑娴. 动态环境下移动机器人自适应路径规划方法研究[D]. 沈阳. 中国科学院沈阳自动化研究所,2021.
Files in This Item:
File Name/Size DocType Version Access License
动态环境下移动机器人自适应路径规划方法研(3445KB)学位论文 开放获取CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[董淑娴]'s Articles
Baidu academic
Similar articles in Baidu academic
[董淑娴]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[董淑娴]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.