Neural Network Based Configuring of Linear Delta Robots with Reduced Energy Consumption   V. Vodovozov, Z. Raud and E. Petlenkov   2024/07/20

Abstract

In this paper, a neural network based methodology of joints configuring is proposed for linear Delta robots, optimal in terms of minimizing the consumed energy. Since the techniques developed for serial robots are severely limited in parallel robotics, where many parameters affecting robot behaviour are either unstable or absent, a new purely data-driven approach has been developed and studied in the conditions of incomplete prior knowledge of robot geometric and mass properties. In the current research, the forward and inverse kinematics solvers are designed, the workspace of the robot is estimated, forward and inverse statics problems are resolved, and the most economical joint configurations are found with the help of the neural network robot model validated experimentally on the linear Delta robot EXPT-45-E1. The method offered in this study can be used in many other robotics applications, especially for the pick-and-place operations, where energy saving comes out on top.

Authors and affiliations

V. Vodovozov(1), Z. Raud(1) and E. Petlenkov(2)

1. Department of Electrical Power Engineering and Mechatronics

2 Department of Computer Systems. Tallinn University of Technology. Ehitajate tee 5, 19086, Tallinn (Estonia)

Key words

Energy consumption, linear Delta robots neural network based model, pick-and-place robotics.

References

[1] C. Müller, World Robotics 2023 – Industrial Robots, IFR Statistical Department, VDMA Services GmbH, Frankfurt am Main, Germany (2023). Available:https://ifr.org/img/worldrobotics/Executive_Summary_WR_Industrial_Robots_2023.pdf.

[2] R. A. Kampa, What is a Serial Robot. Available: https://www.easytechjunkie.com/what-is-a-serial-robot.htm.

[3] Web Parallel Robots: The High-Speed Robotics Platform (2021). Available: https://howtorobot.com/expert-insight/parallel-robots.

[4] W. Khalil and E Dombre, “Introduction to geometric and kinematic modeling of parallel robots,” In: Modeling, Identification and Control of Robots (2002), pp. 171 – 190. https://doi.org/10.1016/B978-190399666-9/50008-7.

[5] M. Bouri and R. Clavel, “The linear Delta: Developments and applications,” 41st International Symposium on Robotics (ISR) and 6th German Conference on Robotics (ROBOTIK) (2010), pp. 1 – 8. Available: https://ieeexplore.ieee.org/document/5756938?arnumber=5756938.

[6] S. Ahangar, M. V. Mehrabani, A. P. Shorijeh and M. T. Masouleh, “Design a 3-DOF Delta parallel robot by one degree redundancy along the conveyor axis: A novel automation approach,” 5th Conference on Knowledge Based Engineering and Innovation (KBEI), Tehran, Iran (2019), pp. 413 – 418. https://doi.org/10.1109/KBEI.2019.8734975.

[7] X. Yang, S. Wang, Y. Dong and H. Yang, “D2 Delta robot structural design and kinematics analysis,” IOP Conf. Series: Materials Science and Engineering (2017), 274, pp. 1 – 12. https://doi,org/10.1088/1757-899X/274/1/012009.

[8] S. C. T. Filho and E. L. L. Cabra, “Dynamics and Jacobian analysis of a parallel architecture robot: The Hexa,” 18th International Congress of Mechanical Engineering, Ouro Preto, Brasilia (2005), pp. 1 – 8. Available: https://abcm.org.br/symposium-series/SSM_Vol2/Section_III_Robotics/SSM2_III_02.pdf.

[9] A. Csiszar, J. Eilers and A. Verl, “On solving the inverse kinematics problem using neural networks,” 24th International Conference on Mechatronics and Machine Vision in Practice (M2VIP), Auckland, New Zealand (2017), pp. 1 – 6. https://doi,org/10.1109/M2VIP.2017.8211457.

[10] C. Urrea, L. Valenzuela and J. Kern, “Design, simulation, and control of a hexapod robot in Simscape Multibody,” In: Applications from Engineering with MATLAB Concepts (2016). https://doi,org/10.5772/63388.

[11] C. C. Aggarwal, Neural Networks and Deep Learning, Springer, Yorktown Heights, NY, USA (2018), 510 p. https://doi.org/10.1007/978-3-319-94463-0.

[12] V. Vodovozov, A. Aksjonov, E. Petlenkov and Z. Raud, “Neural network-based model reference control of braking electric vehicles,” Energies (2021), 14, 2373. https://doi.org/10.3390/en14092373.

[13] Fit Data with a Shallow Neural Network (2023). Available: https://se.mathworks.com/help/deeplearning/gs/fit-data-with-a-neural-network.html#f9-43356.

[14] H. P. Gavin, “The Levenberg-Marquardt Algorithm for Nonlinear Least Squares Curve-Fitting Problems. Durham: NC, Duke University (2020), 19 p.

[15] V. Vodovozov, Z. Raud and E. Petlenkov, “Intelligent control of robots with minimal power consumption in pick-and-place operations,” Energies (2023), 16, 7418. https://doi.org/10.3390/en16217418.

[16] Electrical Tripod EXPT. 3D High Speed Pick & Place. Festo (2010) Available: https://www.festo.com/net/SupportPortal/Files/13547/EXPT-PSI-US.pdf.