A Real-Time Collision-Free Path Planning of a Rust Removal Robot Using an Improved Neural Network

doi:10.1007/s12204-017-1881-x

摘要/Abstract

摘要： In this paper, a real-time collision-free path planning of the rust removal robot in a ship environment is proposed, which is based on an improved biologically inspired neural network algorithm. This improved algorithm is based on the biologically inspired neural network and modified with obstacle detection sensors and kinematic state templates, and is implemented in a ship rust removal robot planning system for dynamic trajectory generation. The real-time optimal trajectory is generated by the biologically inspired neural network, and the moving obstacle detection process of a ship robot working on the wall is simulated with the obstacle detection sensors models. The local real-time trajectory can be re-planned by the updated local map information, where the obstacle detection sensors are used to inspect partial environment information and update the robot nearby information in real time in the original neural network algorithm. At the same time, the method of the kinematic state templates matching and searching is used to solve the pipes’ influence of the rust removal robot climbing on the wall, which can not only provide a smooth path, but also can judge the motion direction and turning angle of the robot. Comparison of the proposed approach with the simulation shows that the improved algorithm is capable of planning a real-time collision-free path with achieving the local environmental information and judging the rust removal robot’s motion direction and turning angle. This proposed algorithm can be good used in the ship rust removal robot.

关键词: real-time path planning, ship rust removal robot, biologically inspired neural network, obstacle detection sensors, kinematics state template matching

Abstract: In this paper, a real-time collision-free path planning of the rust removal robot in a ship environment is proposed, which is based on an improved biologically inspired neural network algorithm. This improved algorithm is based on the biologically inspired neural network and modified with obstacle detection sensors and kinematic state templates, and is implemented in a ship rust removal robot planning system for dynamic trajectory generation. The real-time optimal trajectory is generated by the biologically inspired neural network, and the moving obstacle detection process of a ship robot working on the wall is simulated with the obstacle detection sensors models. The local real-time trajectory can be re-planned by the updated local map information, where the obstacle detection sensors are used to inspect partial environment information and update the robot nearby information in real time in the original neural network algorithm. At the same time, the method of the kinematic state templates matching and searching is used to solve the pipes’ influence of the rust removal robot climbing on the wall, which can not only provide a smooth path, but also can judge the motion direction and turning angle of the robot. Comparison of the proposed approach with the simulation shows that the improved algorithm is capable of planning a real-time collision-free path with achieving the local environmental information and judging the rust removal robot’s motion direction and turning angle. This proposed algorithm can be good used in the ship rust removal robot.

Key words: real-time path planning, ship rust removal robot, biologically inspired neural network, obstacle detection sensors, kinematics state template matching

中图分类号:

TP 242

SUN Ling (孙玲). A Real-Time Collision-Free Path Planning of a Rust Removal Robot Using an Improved Neural Network[J]. 上海交通大学学报（英文版）, 2017, 22(5): 633-640.

SUN Ling (孙玲). A Real-Time Collision-Free Path Planning of a Rust Removal Robot Using an Improved Neural Network[J]. Journal of shanghai Jiaotong University (Science), 2017, 22(5): 633-640.

参考文献 14

[1]	LU T, YUAN K, ZOU W. Study on navigation strategyof intelligent wheel chair in narrow spaces [C]//World Congress on Intelligent Control & Automation.Dalian: [s. n.], 2006: 9252-9256 (in Chinese).
[2]	ZHANG G L. Survey on path planning for mobilerobot under dynamic environment [J]. Machine Tool& Hydraulics, 2013, 1(41): 157-162.
[3]	GAO X, SU Q. Multi-robot path planning and collisionavoidance based on double fuzzy logic [J]. ComputerTechnology and Development, 2014, 11(24): 79-82.
[4]	LI Y J. The research of intelligent car path planningbased on the genetic algorithm [D]. Jinzhou: LiaoningTechnical University, 2011.
[5]	HE S J, DENG Z X, GAO Y F, et al. Path planningresearch for fire-fighting robot based on improved antcolony algorithm [J]. Microcomputer & Its Application,2014, 13(33): 81-84.
[6]	QU H, HUANG L W, KE X. Research of improvedant colony based robot path planning under dynamicenvironment [J]. Journal of University of ElectronicScience and Technology of China, 2015, 2(44): 260-265.
[7]	ZHANG W X, ZHANG X L, LI Y. Path planningfor intelligent robots based on improved particleswarm optimization algorithm [J]. Journal of ComputerApplications, 2014, 34(2): 510-513.
[8]	WEI G W, FU M Y. An algorithm based on neuralnetwork for mobile robot path planning [J]. ComputerSimulation, 2010, 27(7): 112-116.
[9]	YAO Y, CHEN G J, JIA J L. Study on the robot pathplanning based on fuzzy neural network algorithm [J].Journal of Sichuan University of Science & Engineering(Natural Science Edition), 2014, 27(6): 30-33.
[10]	YANG S X, LUO C M, MENG M. A neural computationalalgorithm for coverage path planning in changingenvironments [J]. IEEE Transactions on Systems,Man, and Cybernetics, 2002, 2: 1174-1178.
[11]	YANG S X, LUO C M. A neural network approach tocomplete coverage path planning [J]. IEEE Transactionson Systems, Man, and Cybernetics, 2004, 34(1):718-725.
[12]	NI J J, LI X Y, FAN X N, et al. A dynamic risk levelbased bio-inspired neural network approach for robotpath planning [C]//World Automation Congress Proceedings.Waikoloa.: TSI Press, 2014: 829-833.
[13]	LUO C M, YANG S X. A bio-inspired neural networkfor real-time concurrent map building and completecoverage robot navigation in unknown environments[J]. IEEE Translations on Neural Networks,2008, 19(7): 1279-1298.
[14]	YANG X Y. Neural network approaches to real-timemotion planning and control of robotic systems [D].Canada: University of Alberta, 1999.

[1]	. [J]. J Shanghai Jiaotong Univ Sci, 2022, 27(3): 383-392.
[2]	. [J]. J Shanghai Jiaotong Univ Sci, 2022, 27(2): 231-239.
[3]	. [J]. J Shanghai Jiaotong Univ Sci, 2022, 27(1): 1-6.
[4]	. [J]. J Shanghai Jiaotong Univ Sci, 2022, 27(1): 7-14.
[5]	. [J]. J Shanghai Jiaotong Univ Sci, 2022, 27(1): 15-23.
[6]	. [J]. J Shanghai Jiaotong Univ Sci, 2022, 27(1): 24-35.
[7]	. [J]. J Shanghai Jiaotong Univ Sci, 2022, 27(1): 36-44.
[8]	. [J]. J Shanghai Jiaotong Univ Sci, 2022, 27(1): 45-54.
[9]	. [J]. J Shanghai Jiaotong Univ Sci, 2021, 26(5): 569-576.
[10]	. [J]. J Shanghai Jiaotong Univ Sci, 2021, 26(5): 690-698.
[11]	. [J]. J Shanghai Jiaotong Univ Sci, 2021, 26(5): 722-730.
[12]	. [J]. J Shanghai Jiaotong Univ Sci, 2021, 26(5): 731-738.
[13]	. [J]. J Shanghai Jiaotong Univ Sci, 2021, 26(5): 739-746.
[14]	ZHENG Dongdong, LI Pengcheng, XIE Wenfang, LI Dan . Identification and Control of Flexible Joint Robot Using Multi-Time-Scale Neural Network[J]. Journal of Shanghai Jiao Tong University(Science), 2020, 25(5): 553-560.
[15]	XIANG Jiawei, ZHANG Jinyi, WANG Bin, MA Yongbin . Low Data Overlap Rate Graph-Based SLAM with Distributed Submap Strategy[J]. Journal of Shanghai Jiao Tong University(Science), 2020, 25(5): 650-658.