Obstacle avoidance and model-free tracking control for home automation using bio-inspired approach

被引：34
作者：
Khan A.T. [1 ]
Li S. [2 ]
Li Z. [3 ]
机构：
[1] Department of Computing, The Hong Kong Polytechnic University, Hung Hom
[2] Department of Electrical Engineering, Swansea University, Swansea
[3] School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu
来源：
Advanced Control for Applications: Engineering and Industrial Systems | 2022年 / 4卷 / 01期
关键词：
bio-inspired algorithm; home automation; obstacle avoidance; redundant manipulator; smart-home;
D O I：
10.1002/adc2.63
中图分类号：
学科分类号：
摘要：
This article proposes a control algorithm for obstacle avoidance and trajectory tracking for a redundant-manipulator in smart-homes. The redundancy provides dexterity and flexibility for the applications like picking, dropping, and transporting objects, tracking predefined paths while avoiding obstacles. The obstacle avoidance is one of the critical problems that need to be addressed. Our proposed algorithm, zeroing neural network with beetle antennae search (ZNNBAS), unifies these two problems into a single constrained optimization problem, which includes a penalty function to reward the optimizer on avoiding obstacles while tracking the reference trajectory. The penalty function is based on the principle of maximizing the minimum distance between the joints of the manipulator and the obstacles. Gilbert Johnson Keerthi (GJK) algorithm is used to calculate the distance between the manipulator and the obstacle as it uses the 3D geometry of the object and manipulator. To test the working of ZNNBAS, we simulated the model of the KUKA LBR robotic manipulator. We used two reference trajectories, that is, hypotrochoid and a character “M,” with an arbitrarily shaped obstacle. The simulation results show that ZNNBAS was able to trace the reference path while successfully avoiding the obstacle accurately. © 2020 John Wiley & Sons, Ltd.
引用
收藏
相关论文
共 49 条
[1]  
Wang J., Li Y., Zhao X., Inverse kinematics and control of a 7-DOF redundant manipulator based on the closed-loop algorithm, Int J Adv Robot Syst, 7, 4, (2010)
[2]  
Chirikjian G.S., Burdick J.W., A modal approach to hyper-redundant manipulator kinematics, IEEE Trans Robot Automat, 10, pp. 343-354, (1994)
[3]  
Mirza M.A., Li S., Jin L., Simultaneous learning and control of parallel Stewart platforms with unknown parameters, Neurocomputing, 266, pp. 114-122, (2017)
[4]  
El-laithy R.A., Huang J., Yeh M., (2012)
[5]  
Ayres R.U., Miller S.M., (1983)
[6]  
Chen D., Zhang Y., Li S., Tracking control of robot manipulators with unknown models: a Jacobian-matrix-adaption method, IEEE Trans Ind Inform, 14, 7, pp. 3044-3053, (2017)
[7]  
Li S., Lou Y., Liu B., Bluetooth aided mobile phone localization: a nonlinear neural circuit approach, ACM Transactions on Embedded Computing Systems (TECS), 13, 4, pp. 1-15, (2014)
[8]  
Li S., Guo Y., Distributed source seeking by cooperative robots: All-to-all and limited communications, 2012 IEEE International Conference on Robotics and Automation, pp. 1107-1112, (2012)
[9]  
Benzaoui M., Chekireb H., Tadjine M., Boulkroune A., Trajectory tracking with obstacle avoidance of redundant manipulator based on fuzzy inference systems, Neurocomputing, 196, pp. 23-30, (2016)
[10]  
Mohammed A.M., Li S., Dynamic neural networks for kinematic redundancy resolution of parallel stewart platforms, IEEE Trans Cybern, 46, 7, pp. 1538-1550, (2015)
12345