Hostname: page-component-7bb8b95d7b-pwrkn Total loading time: 0 Render date: 2024-09-20T12:37:43.406Z Has data issue: true hasContentIssue false
  • English
  • Français

DDPG-based path planning for cable-driven manipulators in multi-obstacle environments

Published online by Cambridge University Press:  13 September 2024

Dong Zhang Open the ORCID record for Dong Zhang [Opens in a new window] ,
Renjie Ju Open the ORCID record for Renjie Ju [Opens in a new window]  and
Zhengcai Cao
Dong Zhang
Affiliation:
College of Information Science and Technology, Beijing University of Chemical Technology, Beijing, China
Renjie Ju
Affiliation:
College of Information Science and Technology, Beijing University of Chemical Technology, Beijing, China
Zhengcai Cao*
Affiliation:
The State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Harbin, China
*
Corresponding author: Zhengcai Cao; Email: caozc@hit.edu.cn
Get access Rights & Permissions [Opens in a new window]

Abstract

Hyper-redundant cable-driven manipulators (CDMs) are widely used for operations in confined spaces due to their slender bodies and multiple degrees of freedom. Most research focuses on their path following but not path planning. This work investigates a deep deterministic policy gradient (DDPG)-based path-planning algorithm for CDMs in multi-obstacle environments. To plan passable paths under many constraints, a DDPG algorithm is modified according to features of CDMs. To improve adaptability of planned paths, a specialized reward function is newly designed. In this function, such factors as smoothness, arrival time and distance are taken into account. Results of simulations and physical experiments are presented to demonstrate the performances of the proposed methods for planning paths of CDMs.

Keywords

cable-driven manipulatorpath planningdeep deterministic policy gradient
Type
Research Article
Information
Robotica , First View , pp. 1 - 13
Copyright
© The Author(s), 2024. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Li, D., Zhang, B., Xiu, Y., Deng, H., Zhang, M., Tong, W., Law, R., Zhu, G., Wu, E. Q. and Zhu, L., “Snake robots play an important role in social services and military needs,” Innovation 3(6), 100333 (2022).Google Scholar
Robert, J. W. and Bryan, A., “Design and kinematic modeling of constant curvature continuum robots: A review,” Int J Robot Res 29(13), 1661–1683 (2010).Google Scholar
Li, T., Ma, S. G., Li, B., Wang, M. H. and Wang, Y. C., “Axiomatic design method to design a screw drive in-pipe robot passing through varied curved pipes,” Sci China Technol Sci 59(2), 191–202 (2016).Google Scholar
Peng, J., Zhang, C., Meng, D. and Liang, B., “Trajectory optimization methods of a space hyper-redundant robot based on effective arm-shape measurement,” IEEE Trans Instrum Meas 72(5017914), 1–14 (2023).Google Scholar
Walker, I. D., Choset, H. and Chirikjian, G. S., “Snake-Like and Continuum Robots,” In: Springer Handbook of Robotics (Siciliano, B. and Khatib, O., eds.) (Springer International Publishing, Berlin, Heidelberg, 2016) pp. 481–498.Google Scholar
Dong, X., Raffles, M., Cobos-Guzman, S., Axinte, D. and Kell, J., “A novel continuum robot using twin-pivot compliant joints: Design, modeling, and validation,” J Mech Robot 8(2), 021010 (2015).Google Scholar
Shigeo, H., Peter, C. and Charles, G., Biologically Inspired Robots: Snake-Like Locomotors and Manipulators (Oxford University Press, Oxford, 1993).Google Scholar
Buckingham, R., Chitrakaran, V., Conkie, R., Ferguson, G., Graham, A., Lazell, A., Lichon, M., Parry, N., Pollard, F., Kayani, A., Redman, M., Summers, M. and Green, B., Snake-arm robots: A new approach to aircraft assembly, (2007). SAE technical paper, 01–3870.Google Scholar
Kang, R., Guo, Y., Chen, L., Branson, D. and Dai, J., “Design of a pneumatic muscle based continuum robot with embedded tendons,” IEEE/ASME Trans Mechatro 22(2), 751–761 (2017).Google Scholar
Yang, C., Geng, S., Walker, I., Branson, D. T., Liu, J., Dai, J. S. and Kang, R., “Geometric constraint-based modeling and analysis of a novel continuum robot with shape memory alloy initiated variable stiffness,” Int J Robot Res 39(14), 1620–1634 (2020). doi: 10.1177//0278364920913929.Google Scholar
Dong, X., Axinte, D., Palmer, D., Cobos, S., Raffles, M., Rabani, A. and Kell, J., “Development of a slender continuum robotic system for on-wing inspection/repair of gas turbine engines,” Robot Comp Integ Manuf 44, 218–229 (2017).Google Scholar
Mohammad, A., Russo, M., Fang, Y., Dong, X., Axinte, D. and Kell, J., “An efficient follow-the-leader strategy for continuum robot navigation and coiling,” IEEE Robot Automa Lett 6(4), 7493–7500 (2021).Google Scholar
Buckingham, R. and Graham, A., “Dexterous Manipulators for Nuclear Inspection and Maintenance; Case Study,” In: IEEE International Conference on Applied Robotics for the Power Industry, (2010) pp. 1–6.Google Scholar
Dong, X., Wang, M., Mohammad, A., Ba, W., Russo, M., Norton, A., Kell, J. and Axinte, D., “Continuum robots collaborate for safe manipulation of high-temperature flame to enable repairs in extreme environments,” IEEE/ASME Trans Mechatro 27(5), 4217–4220 (2022).Google Scholar
Lau, D., Oetomo, D. and Halgamuge, S. K., “Inverse dynamics of multilink cable-driven manipulators with the consideration of joint interaction forces and moments,” IEEE Trans Robot 31(2), 479–488 (2015).Google Scholar
Tang, L., Ji, L. Z., Zhu, X. and Gu, G., “Path tracking of a cable-driven snake robot with a two-level motion planning method,” IEEE/ASME Trans Mechatro 24(3), 935–946 (2019).Google Scholar
Conkur, E. S., “Path following algorithm for highly redundant manipulators,” Robot Auton Syst 45(1), 1–22 (2003).Google Scholar
Palmer, D., Cobos-Guzman, S. and Axinte, D., “Real-time method for tip following navigation of continuum snake arm robots,” Robot Auton Syst 62(10), 1478–1485 (2014).Google Scholar
Wang, J., Tang, L., Gu, G. and Zhu, X., “Tip-following path planning and its performance analysis for hyper-redundant manipulators,” J Mech Eng 54(3), 18–25 (2018).Google Scholar
Tang, L., Zhu, L. M., Zhu, X. Y. and Gu, G. Y., “Confined spaces path following for cable-driven snake robots with prediction lookup and interpolation algorithms,” Sci China Technol Sci 63(2), 255–264 (2020).Google Scholar
LaValle, S. M., Planning Algorithms (Cambridge University Press, 2006). doi: 10.1017/CBO9780511546877.Google Scholar
Luo, M., Li, E., Zhang, A., Tan, M. and Liang, Z., “A bioinspired coiled cable-driven manipulator: Mechatronic design and kinematics planning with multiconstraints,” IEEE/ASME Trans Mechatro 28(6), 3155–3166 (2023).Google Scholar
Wei, H., Zheng, Y. and Gu, G., “RRT-Based Path Planning for Follow-the-Leader Motion of Hyper-Redundant Manipulators,” In: IEEE/RSJ International Conference on Intelligent Robots and Systems, (2021) pp. 3198–3204.Google Scholar
Jia, L., Huang, Y., Chen, T., Guo, Y., Yin, Y. and Chen, J., “MDA+RRT: A general approach for resolving the problem of angle constraint for hyper-redundant manipulator,” Exp Syst Appl 193, 116379 (2021).Google Scholar
Zhang, D., Gai, Y., Ju, R., Miao, Z. and Lao, J., “RRT-A* Path Planning Algorithm for Cable-Driven Manipulators,” In: IEEE International Conference on Robotics and Biomimetics, (2022) pp. 451–456.Google Scholar
Ji, H., Xie, H., Wang, C. and Yang, H., “E-RRT*: Path planning for hyper-redundant manipulators,” IEEE Robotics and Automa Lett 8(12), 8128–8135 (2023).Google Scholar
Sangiovanni, B., Rendiniello, A., Incremona, G. P., Ferrara, A. and Piastra, M., “Deep Reinforcement Learning for Collision Avoidance of Robotic Manipulators,” In: European Control Conference, (2018) pp.2063–2068.Google Scholar
Hua, X., Wang, G., Xu, J. and Chen, K., “Reinforcement learning-based collision-free path planner for redundant robot in narrow duct,” J Intell Manuf 32(2), 471–482 (2021).Google Scholar
Ju, R., Zhang, D., Xu, J., Yuan, H., Miao, Z., Zhou, M. and Cao, Z., “Design, modeling, and kinematics analysis of a modular cable-driven manipulator,” J Mech Robot 14(6), 064501 (2022).Google Scholar
Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D. and Wierstra, D., Continuous Control with Deep Reinforcement Learning, Computer Science, (2015).Google Scholar
Aimedee, F., Gogu, G., Dai, J. S., Bouzgarrou, C. and Bouton, N., “Systematization of morphing in reconfigurable mechanisms,” Mech Mach Theory 96, 215–224 (2016).Google Scholar
Salerno, M., Zhang, K., Menciassi, A. and Dai, J. S., “A novel 4-DOFs Origami Enabled, SMA Actuated, Robotic End-Effector for Minimally Invasive Surgery,” In: 2014 IEEE Intemational Conference on Robotics and Automation, (2014) pp. 2844–2849.Google Scholar
Cao, Z., Li, J., Zhang, D., Zhou, M. and Abusorrah, A., “A multi-object tracking algorithm with center-based feature extraction and occlusion handling,” IEEE Trans Intell Transp 24(4), 4464–4473 (2023).Google Scholar
Mu, H., Zhang, G., Ma, Z., Zhou, M. and Cao, Z., “Dynamic obstacle avoidance system based on rapid instance segmentation network,” IEEE Trans Intell Transp 25(5), 4578–4592 (2023). doi: 10.1109/TITS.2023.3323210.Google Scholar