logo

SCIENCE CHINA Information Sciences, Volume 64 , Issue 1 : 112208(2021) https://doi.org/10.1007/s11432-019-2749-0

A population randomization-based multi-objective genetic algorithm for gesture adaptation in human-robot interaction

More info
  • ReceivedJul 18, 2019
  • AcceptedDec 2, 2019
  • PublishedDec 24, 2020

Abstract


Acknowledgment

This work was supported by National Natural Science Foundation of China (Grant Nos. 61973286, 61603356, 61733016, 61773353), 111 Project (Grant No. B17040), Hubei Provincial Natural Science Foundation (Grant No. 2015CFA010), Fundamental Research Funds for the Central Universities, China University of Geosciences (Wuhan) (Grant No. 2018039), and Wuhan Science and Technology Project (Grant No. 2017010201010133).


References

[1] Zhang J, Wang L, Xing L. Large-scale medical examination scheduling technology based on intelligent optimization. J Comb Optim, 2019, 37: 385-404 CrossRef Google Scholar

[2] Yue M, Ning Y, Yu S. Composite following control for wheeled inverted pendulum vehicles based on human-robot interaction. Sci China Inf Sci, 2019, 62: 50206 CrossRef Google Scholar

[3] Du G, Chen M, Liu C. Online Robot Teaching With Natural Human-Robot Interaction. IEEE Trans Ind Electron, 2018, 65: 9571-9581 CrossRef Google Scholar

[4] Hwang J, Kim J, Ahmadi A. Dealing With Large-Scale Spatio-Temporal Patterns in Imitative Interaction Between a Robot and a Human by Using the Predictive Coding Framework. IEEE Trans Syst Man Cybern Syst, 2018, : 1-14 CrossRef Google Scholar

[5] Chen L, Zhou M, Wu M. Three-Layer Weighted Fuzzy Support Vector Regression for Emotional Intention Understanding in Human-Robot Interaction. IEEE Trans Fuzzy Syst, 2018, 26: 2524-2538 CrossRef Google Scholar

[6] Chen L, Wu M, Zhou M. Information-Driven Multirobot Behavior Adaptation to Emotional Intention in Human-Robot Interaction. IEEE Trans Cogn Dev Syst, 2018, 10: 647-658 CrossRef Google Scholar

[7] Jang Y, Jeon I, Kim T K. Metaphoric Hand Gestures for Orientation-Aware VR Object Manipulation With an Egocentric Viewpoint. IEEE Trans Human-Mach Syst, 2017, 47: 113-127 CrossRef Google Scholar

[8] Ding I J, Chang C W. An eigenspace-based method with a user adaptation scheme for human gesture recognition by using Kinect 3D data. Appl Math Model, 2015, 39: 5769-5777 CrossRef Google Scholar

[9] Yang H, Li X, Wang Y. Control of Single-Cell Migration Using a Robot-Aided Stimulus-Induced Manipulation System. IEEE/ASME Trans Mechatron, 2017, 22: 815-825 CrossRef Google Scholar

[10] Zhijun Zhang , Beck A, Magnenat-Thalmann N. Human-Like Behavior Generation Based on Head-Arms Model for Robot Tracking External Targets and Body Parts.. IEEE Trans Cybern, 2015, 45: 1390-1400 CrossRef PubMed Google Scholar

[11] Lou Y, Wu W, Vatavu R D. Personalized gesture interactions for cyber-physical smart-home environments. Sci China Inf Sci, 2017, 60: 072104 CrossRef Google Scholar

[12] K?l?boz N, Güdükbay U. A hand gesture recognition technique for human-computer interaction. J Visual Communication Image Representation, 2015, 28: 97-104 CrossRef Google Scholar

[13] Ding I J, Chang C W. An adaptive hidden Markov model-based gesture recognition approach using Kinect to simplify large-scale video data processing for humanoid robot imitation. Multimed Tools Appl, 2016, 75: 15537-15551 CrossRef Google Scholar

[14] Obo T, Loo C K, Seera M. Hybrid evolutionary neuro-fuzzy approach based on mutual adaptation for human gesture recognition. Appl Soft Computing, 2016, 42: 377-389 CrossRef Google Scholar

[15] Huang C M, Chen Y R, Fu L C. Visual Tracking of Human Head and Arms Using Adaptive Multiple Importance Sampling on a Single Camera in Cluttered Environments. IEEE Sens J, 2014, 14: 2267-2275 CrossRef ADS Google Scholar

[16] Emgin S E, Aghakhani A, Sezgin T M. HapTable: An Interactive Tabletop Providing Online Haptic Feedback for Touch Gestures.. IEEE Trans Visual Comput Graphics, 2019, 25: 2749-2762 CrossRef PubMed Google Scholar

[17] Jevtic A, Flores Valle A, Alenya G. Personalized Robot Assistant for Support in Dressing. IEEE Trans Cogn Dev Syst, 2019, 11: 363-374 CrossRef Google Scholar

[18] Li Y, Ge S S. Human-Robot Collaboration Based on Motion Intention Estimation. IEEE/ASME Trans Mechatron, 2014, 19: 1007-1014 CrossRef Google Scholar

[19] Wakita K, Huang J, Di P. Human-Walking-Intention-Based Motion Control of an Omnidirectional-Type Cane Robot. IEEE/ASME Trans Mechatron, 2013, 18: 285-296 CrossRef Google Scholar

[20] Chen L, Wu M, Zhou M. Dynamic Emotion Understanding in Human-Robot Interaction Based on Two-Layer Fuzzy SVR-TS Model. IEEE Trans Syst Man Cybern Syst, 2020, 50: 490-501 CrossRef Google Scholar

[21] T. Motoki, “A New Method for Modeling the Behavior of Finite Population Evolutionary Algorithms," Evolutionary Computation, vol. 18, no. 3, pp. 451-489, 2010. Google Scholar

[22] Fang H, Shang C, Chen J. An optimization-based shared control framework with applications in multi-robot systems. Sci China Inf Sci, 2018, 61: 014201 CrossRef Google Scholar

[23] Chevtchenko S F, Vale R F, Macario V. Multi-objective optimization for hand posture recognition. Expert Syst Appl, 2018, 92: 170-181 CrossRef Google Scholar

[24] Saremi S, Mirjalili S, Lewis A. Enhanced multi-objective particle swarm optimisation for estimating hand postures. Knowledge-Based Syst, 2018, 158: 175-195 CrossRef Google Scholar

[25] Wang J W, Wang H F, Ip W H. Predatory Search Strategy Based on Swarm Intelligence for Continuous Optimization Problems. Math Problems Eng, 2013, 2013(3): 1-11 CrossRef Google Scholar

[26] Yi J H, Xing L N, Wang G G. Behavior of crossover operators in NSGA-III for large-scale optimization problems. Inf Sci, 2020, 509: 470-487 CrossRef Google Scholar

[27] Tarokh M, Zhang X. Real-Time Motion Tracking of Robot Manipulators Using Adaptive Genetic Algorithms. J Intell Robot Syst, 2014, 74: 697-708 CrossRef Google Scholar

[28] Datta R, Pradhan S, Bhattacharya B. Analysis and Design Optimization of a Robotic Gripper Using Multiobjective Genetic Algorithm. IEEE Trans Syst Man Cybern Syst, 2016, 46: 16-26 CrossRef Google Scholar

[29] Chen C H, Liu T K, Chou J H. A Novel Crowding Genetic Algorithm and Its Applications to Manufacturing Robots. IEEE Trans Ind Inf, 2014, 10: 1705-1716 CrossRef Google Scholar

[30] Zacharia P T, Tsirkas S A, Kabouridis G. Planning the construction process of a robotic arm using a genetic algorithm. Int J Adv Manuf Technol, 2015, 79: 1293-1302 CrossRef Google Scholar

[31] Wang R, Lai S, Wu G. Multi-clustering via evolutionary multi-objective optimization. Inf Sci, 2018, 450: 128-140 CrossRef Google Scholar

[32] Xiang S, Xing L, Wang L. Comprehensive learning pigeon-inspired optimization with tabu list. Sci China Inf Sci, 2019, 62: 70208 CrossRef Google Scholar

[33] Liang X, Jiang Z, Wang B. Recognition Algorithm and Optimization Experiments on Tomato Picking Robots. IJSIP, 2016, 9: 389-400 CrossRef Google Scholar

[34] Mohamed Z, Kitani M, Kaneko S. Humanoid robot arm performance optimization using multi objective evolutionary algorithm. Int J Control Autom Syst, 2014, 12: 870-877 CrossRef Google Scholar

[35] Mukhopadhyay A, Maulik U, Bandyopadhyay S. A Survey of Multiobjective Evolutionary Algorithms for Data Mining: Part I. IEEE Trans Evol Computat, 2014, 18: 4-19 CrossRef Google Scholar

[36] Mahmoodabadi M J, Safaie A A, Bagheri A. A novel combination of Particle Swarm Optimization and Genetic Algorithm for Pareto optimal design of a five-degree of freedom vehicle vibration model. Appl Soft Computing, 2013, 13: 2577-2591 CrossRef Google Scholar

[37] Chen D, Gao Z. A multi-objective generic algorithm approach for optimization of building energy performance. In: Computing in Civil Engineering. Reston: American Society of Civil Engineers, 2011. 51--58. Google Scholar

[38] Gupta H P, Chudgar H S, Mukherjee S. A Continuous Hand Gestures Recognition Technique for Human-Machine Interaction Using Accelerometer and Gyroscope Sensors. IEEE Sens J, 2016, 16: 6425-6432 CrossRef ADS Google Scholar

[39] Han H, Lu W, Zhang L. Adaptive Gradient Multiobjective Particle Swarm Optimization.. IEEE Trans Cybern, 2018, 48: 3067-3079 CrossRef PubMed Google Scholar

[40] E. Creaco and G. Pezzinga, “Embedding linear programming in multi objective genetic algorithms for reducing the size of the search space with application to leakage minimization in water distribution networks," Environmental Modelling $\&$ Software, 2015, vol. 69: 308-318. Google Scholar

[41] K. Deb, “Multi-objective optimization," Search methodologies. Springer US, 2014, pp. 403-449. Google Scholar

[42] Chen L, Zhou M, Su W. Softmax regression based deep sparse autoencoder network for facial emotion recognition in human-robot interaction. Inf Sci, 2018, 428: 49-61 CrossRef Google Scholar

  • Figure 1

    (Color online) Kinematic model of a human arm gesture.

  • Figure 2

    (Color online) The gesture adaptation system.

  • Figure 3

    (Color online) Optimal angle values of the three joints.

  • Figure 4

    (Color online) Experimental environment. 1: the human arm, 2: the data-processing PC used to obtain the gesture data, 3: Kinect, 4: robotic arm.

  • Figure 5

    (Color online) Experimental comparison of objective angle values at (a) angle1, (b) angle2, and (c) angle3.

  • Figure 6

    (Color online) Experimental comparison of the variance at (a) angle1, (b) angle2, and (c) angle3.

  • Figure 7

    (Color online) Comparison of (a) energy consumption, (b) end errors, and (c) imitation errors.

  • Table 1  

    Table 1Parameters of the human arm gesture kinematic model

    JointLength (cm)AngleWeight (kg)
    117$-\pi/2-\pi/2$0.8
    210$-\pi/2-\pi/2$0.6
    317$-\pi/2-\pi/2$0.4
  • Table 2  

    Table 2Verification results of angle data produced by the multi-objective genetic algorithm

    $(\theta_{1}^{o},\theta_{2}^{o},\theta_{3}^{o})$$(\theta_{1},\theta_{2},\theta_{3})$$R1$$R2$$R3$
    $(1.4516,1.1898,-1.0741)$$(1.4525,1.1919,-1.0632)$0.99970.31060.0896
    $(1.4686,1.0338,-1.3264)$$(1.4853,1.0282,-1.3178)$0.95110.09900.0196
    $(0.7142,-0.1139,-0.6549)$$(0.7375,-0.1496,-0.6615)$0.98500.40620.0432
    $(-0.2800,-0.4277,-0.3330)$$(-0.2987,-0.4233,-0.3254)$0.99670.14590.0207
    ($1.5347,-0.5657,-1.2554$)($1.5677,-0.6260,-1.1946$)0.89410.15550.0918
    $(-0.9016,1.0417,-0.8502)$$(-1.0350,0.9896,-0.7193)$0.90320.14820.1940
    $(1.0270,0.3269,0.5976)$$(1.0589,0.4945,0.4887)$0.95710.28670.2024
    $(0.6138,-0.2058,-0.7063)$$(0.6396,-0.3152,-0.6449)$0.98520.16000.1280
    $(1.5058,-0.7557,-0.2540)$$(1.5230,-0.7449,-0.2590)$0.96370.23990.0209
    $(0.7108,0.2231,-1.2131)$$(0.7408,0.1680,-1.2036)$0.98590.12890.0635
    $(-0.4804,-0.8168,-0.7634)$$(-0.5372,-0.7622,-0.7419)$0.98810.25450.0817
    $(1.0961,-1.1386,-1.2963)$$(1.116,-1.1493,-1.2733)$0.97050.22660.0328
    $(-1.1527,1.4562,-0.3654)$$(-1.1864,1.4285,-0.3434)$0.96190.15300.0488
    $(-1.1481,0.3165,1.1845)$$(-1.1871,0.3711,1.1546)$0.94980.33030.0735
  • Table 3  

    Table 3Comparison results calculated by four different algorithms

    AlgorithmEnergyEnd errorTracking errorComputation time (s)
    PSO0.91543.39240.26820.043449
    SOGA1.62771.96660.29330.066131
    TMOGA1.0336$-$0.53120.10370.069721
    PRMOGA0.83110.14970.05500.073386
  • Table 4  

    Table 4Comparative analysis of the existing methods

    AlgorithmEnergyEnd errorTracking errorComputation time (s)
    CHG-EP [38]1.82310.41060.09320.076231
    AGMOPSO [39]0.90621.87410.10130.062146
    PRMOGA0.83110.14970.05500.073386