For the basic ant colony algorithm in the robot welding path planning, some problems such as too long searching time, low efficiency and falling into local optimum in the process of searching were found. For the basic ant colony algorithm, Adadelta algorithm was introduced in this paper. By updating the parameters of Adadelta algorithm, the update of ant pheromones was improved and the volatility coefficient of pheromones was improved. The adaptive method was adopted to update pheromones. The improved algorithm was simulated with MATLAB and the result analysis show that the improved ant colony algorithm in this paper had better search capability than the basic ant colony algorithm and higher algorithm efficiency, which was about 20 generations ahead of the basic ant colony algorithm. The method in this paper effectively solved the local optimization and slow convergence speed of the basic ant colony algorithm and made the search results better.
WU Minghui
,
HUANG Haijun
,
WANG Xianwei
. Robot welding path planning based on improved ant colony algorithm[J]. Transactions of The China Welding Institution, 2018
, 39(10)
: 113
-118
.
DOI: 10.12073/j.hjxb.2018390259
[1] Wu M H, Pan G, Zhang T, et al. Design and optimal research of non-contact variable magnetic adsorption mechanism for wall-climbing welding robot[J]. International Journal of Advanced Robotic Systems, 2013, 63(10):1-10.
[2] Zhang T, Wu M H, Zhao Y Z, et al. Optimal motion planning of mobile welding robot based on multivariable for broken line seams[J]. International Journal of Robotics and Automation, 2014, 29(2):215-223.
[3] Yan X, Wu Q, Yan J, et al. A fast evolutionary algorithm for robot path planning[C]//2007 IEEE International Conference on Control and Automation, Guangzhou:IEEE, 2007:84-87.
[4] 张春伟, 刘海江, 姜冬冬. 基于遗传算法的白车身机器人焊接路径规划[J]. 同济大学学报:自然科学版, 2011, 39(4):576-598 Zhang Chunwei, Liu Haijiang, Jiang Dongdong. Robot welding route planning in car-body welding process based on genetic algorithm[J]. Journal of Tongji University:Natural Science, 2011, 39(4):576-598
[5] Wang X, Shi Y, Ding D, et al. Double global optimum genetic algorithm-particle swarm optimization-based welding robot path planning[J]. Engineering Optimization, 2016, 48(2):299-316.
[6] Yang H, Shao H. Distortion-oriented welding path optimization based on elastic net method and genetic algorithm[J]. Journal of Materials Processing Technology, 2009, 209(9):4407-4412.
[7] 王春华, 邱立鹏, 潘德文. 改进蚁群算法的机器人焊接路径规划[J]. 传感器与微系统, 2017, 36(2):75-77 Wang Chunhua, Qiu Lipeng, Pan Dewen. Robot welding route planning based on improved ant colony algorithm[J]. Transducer and Microsystem Technologies, 2017, 36(2):75-77
[8] 金嘉琦, 刘畅, 徐振伟. 基于改进蚁群算法的焊接机器人路径规划[J]. 重型机械, 2017(1):44-46 Jin Jiaqi, Liu Chang, Xu Zhenwei. Path planning of welding robot based on improved ant colony optimization[J]. Heavy Machinery, 2017(1):44-46
[9] Hu J, Zhu Q B. Multi-objective mobile robot path planning based on improved genetic algorithm[C]//2010 International Conference on Intelligent Computation Technology and Automation, Changsha:IEEE Press, 2010:752-756.
[10] 林哲骋, 许力. 一种应用于激光焊接轨迹规划的改进蚁群算法[J]. 焊接学报, 2018, 39(1):107-110 Lin Zhecheng, Xu Li. An improved ant colony optimization applied in programing laser welding path[J]. Transactions of the China Welding Institution, 2018, 39(1):107-110
[11] Kong M. Solving path planning problem based on ant colony algorithm[C]//Control and Decision Conference, IEEE, 2017:5391-5395.
[12] Zeiler M D. ADADELTA:An adaptive learning rate method[J]. Computer Science, 2012:42-47.
[13] 韦峰. 推荐系统中矩阵分解算法研究[D]. 合肥:中国科学技术大学, 2017.
[14] Li H C, Shi Y H, Wang G R. Automatic teaching of stereovision-guided welding robot using ant colony optimization algorithm[J]. China Welding, 2010, 19(1):37-42.
[15] 游晓明, 刘升, 吕金秋. 一种动态搜索策略的蚁群算法及其在机器人路径规划中的应用[J]. 控制与决策, 2017, 32(3):552-556 You Xiaoming, Liu Sheng, Lü Jinqiu. Ant colony algorithm based on dynamic search strategy and its application on path planning of robot[J]. Control and Decision, 2017, 32(3):552-556
