Journal of the Korean Society of Industry Convergence (한국산업융합학회 논문집)

The Korean Society of Industry Convergence (한국산업융합학회)
권호 표지
DOI QR코드

DOI QR Code

Optimization of Posture for Humanoid Robot Using Artificial Intelligence

인공지능을 이용한 휴머노이드 로봇의 자세 최적화

  • 최국진 (한국폴리텍대학 창원캠퍼스)
  • Received : 2018.10.10
  • Accepted : 2019.03.05
  • Published : 2019.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

This research deals with posture optimization for humanoid robot against external forces using genetic algorithm and neural network. When the robot takes a motion to push an object, the torque of each joint is generated by reaction force at the palm. This study aims to optimize the posture of the humanoid robot that will change this torque. This study finds an optimized posture using a genetic algorithm such that torques are evenly distributed over the all joints. Then, a number of different optimized postures are generated from various the reaction forces at the palm. The data is to be used as training data of MLP(Multi-Layer Perceptron) neural network with BP(Back Propagation) learning algorithm. Humanoid robot can find the optimal posture at different reaction forces in real time using the trained neural network include non-training data.

Keywords

SOOOB6_2019_v22n2_87_f0001.png 이미지

Fig. 1 Architecture of the proposed methods.

SOOOB6_2019_v22n2_87_f0002.png 이미지

Fig. 2 Degree of freedoms of the robot

SOOOB6_2019_v22n2_87_f0003.png 이미지

Fig. 3 Photograph of the robot.

SOOOB6_2019_v22n2_87_f0004.png 이미지

Fig. 4 Experimental setup.

SOOOB6_2019_v22n2_87_f0005.png 이미지

Fig. 5 Block diagram of motion control.

SOOOB6_2019_v22n2_87_f0006.png 이미지

Fig. 6 Change of the fitness function

SOOOB6_2019_v22n2_87_f0007.png 이미지

Fig. 7 Comparison of torque ratio for Exp. 1

SOOOB6_2019_v22n2_87_f0008.png 이미지

Fig. 8 Comparison of torque ratio for Exp. 2

Table 1. Objective functions.

SOOOB6_2019_v22n2_87_t0001.png 이미지

Table 2. Specifications of the robot

SOOOB6_2019_v22n2_87_t0002.png 이미지

Table 3. Comparison of optimized results between Exp. 1 and Exp. 2표 18

SOOOB6_2019_v22n2_87_t0003.png 이미지

References

  1. I. Kato, S. Ohteru, H. Kobayashi, K. Shirai and A. Uchiyama, "Information-power machine with senses and limbs (WABOT-1)," Proc. of the 1st CISM-IFoMM Symposium on Theory and Practice of Robots and Manipulators, pp. 11-24, (1973).
  2. Arakawa and T. Fukuda, "Natural motion generation of biped locomotion using hierarchical trajectory generation method consisting of GA, EP layers," Proc. of IEEE Int. Conf. on Robotics and Automation, pp. 211-216, (1997).
  3. D. Katic and M. Vukobratovic. "Intelligent soft-computing paradigms for humanoid robot," Proc. of IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, pp. 2533-2538, (2002).
  4. Y. K. Hwang, K. J. Choi and D. S. Hong, "Self-learning control of cooperative motion for humanoid robots," Int. Journal of Control, Automation, and Systems, pp. 725-735, (2006). https://doi.org/10.1007/s12555-014-0126-0
  5. K. J. Choi and D. S. Hong, "Posture Optimization for a Humanoid Robot using a Simple Genetic Algorithm," Int. Journal of Precision Engineering and Manufacturing, pp. 381-390, (2010).