Robot Collision Detection Based on Deep Lagrangian Network Integrated Momentum Observer
Abstract
sensors or complex experiments. To address this, we propose a momentum observer-based collision detection method that identifies external
torques caused by collisions. It integrates a deep Lagrangian network (DeLaN) to model robot dynamics without needing parameter identification or prior knowledge of robot structure. The DeLaN model is trained on real robot data and performs well. Experiments confirm the method
effectively detects collisions.
Keywords
Full Text:
PDFReferences
[1] S. Lou, Z. Hu, Y. Zhang, and Y. Feng, "Human-cyber-physical system for industry 5.0: a review from a human-centric perspective, "
IEEE Trans. Autom. Sci. Eng., 2024, doi: 10.1109/TASE.2024.3360476.
[2] S. Proia, G. Cavone, S. Member, and P. Scarabaggio, "Safety compliant, ergonomic and time-optimal trajectory planning for collaborative robotics, " IEEE Trans. Autom. Sci. Eng., 2023, doi: 10.1109/TASE.2023.3331505.
[3] W. Li, Y. Hu, Y. Zhou, and D. Truong, "Safe human - robot collaboration for industrial settings: a survey, " J. Intell. Manuf., 2023, doi:
10.1007/s10845-023-02159-4.
[4] S. Proia, R. Carli, G. Cavone and M. Dotoli, "Control techniques for safe, ergonomic, and effi cient human-robot collaboration in the
digital industry: a survey, " IEEE Trans. Autom. Sci. Eng., vol. 19, no. 3, pp. 1798-1819, 2022, doi: 10.1109/TASE.2021.3131011.
[5] S. Huang, M. Gao, L. Liu, J. Chen, and J. Zhang, "Collision detection for cobots : A back-input compensation approach, " IEEE/ASME
Trans. Mechatronics, vol. 27, no. 1, pp. 4951-4962, 2022, doi: 10.1109/TMECH.2022.3169084.
[6] S. Haddadin, A. Albu-Schaffer, A. De Luca and G. Hirzinger, "Collision detection and reaction: A contribution to safe physical human-robot interaction, " in 2008 IEEE/RSJ Int. Conf. Intell. Robot. Syst., Nice, France, 2008, pp. 3356-3363, doi: 10.1109/
IROS.2008.4650764.
[7] S. Patil and V. V. K. V. S. Srinadh, "Advances and perspectives in collaborative robotics: a review of key technologies and emerging
trends, " Discov. Mech. Eng., 2023, doi: 10.1007/s44245-023-00021-8.
[8] G. Pang, G. Yang, and Z. Pang, "Review of robot skin: A potential enabler for safe collaboration, immersive teleoperation, and affective interaction of future collaborative robots, " IEEE Trans. Med. Robot. Bionics., vol. 3, no. 3, pp. 681-700, 2021, doi: 10.1109/
TMRB.2021.3097252.
[9] Z. Ye, G. Pang, G. S. Member, K. Xu, Z. Hou, and H. Lv, "Soft robot skin with conformal adaptability for on-body tactile perception of
collaborative robots, " IEEE Robot. Autom. Lett., vol. 7, no. 2, pp. 5127-5134, 2022, doi: 10.1109/LRA.2022.3155225.
[10] Y. J. Heo, D. Kim, W. Lee, H. Kim, J. Park, and W. K. Chung, "Collision detection for industrial collaborative robots: A deep learning
approach, " IEEE Robot. Autom. Lett., vol. 4, no. 2, pp. 740-746, 2019, doi: 10.1109/LRA.2019.2893400.
[11] T. Zhang, Y. Chen, P. Ge, and Y. Zou, "LSTM-based external torque prediction for 6-DOF robot collision detection, " J. Mech. Sci.
Technol., 37, 4847-4855 (2023). vol. 37, no. 9, pp. 4847-4855, 2023, doi: 10.1007/s12206-023-0837-3.
[12] A. N Sharkawy, P. N. Koustoumpardis, and N.Aspragathos, "Humanrobot collisions detection for safe human-robot interaction using
one multi-input-output neural network, " Soft Comput., vol. 24, pp. 66876719, 2020, doi: 10.1007/s00500-019-04306-7.
[13] S. Long, X. Dang, S. Sun, Y. Wang, and M. Gui, "A novel sliding mode momentum observer for collaborative robot collision detection,
" Machines, vol. 10, pp. 818, 2022, doi: 10.3390/ machines10090818
[14] D. Wu, Q. Liu, W. Xu, A. Liu, and Z. Zhou, "External force detection for physical human-robot interaction using dynamic model identification, " Intell. Robot. Appl., vol. 4, pp. 581-592, doi: 10.1007/978-3-319-65289-4.
[15] X. Xu, Y. Gan, C. Xu and X. Dai, "Robot collision detection based on dynamic model, " in 2017 Chinese Autom. Congr., Jinan, China,
2017, pp. 6578-6582, doi: 10.1109/CAC.2017.8243962.
[16] P. Cao, Y. Gan, and X. Dai, "Model-based sensorless robot collision detection under model uncertainties with a fast dynamics identification, " Int. J. Adv. Robot. Syst., vol. 16, no. 3, 2019, doi: 10.1177/1729881419853713.
[17] Z. Chen and L. Wang, "Research on dynamic parameter identification of large inertia industrial robot based on RBFNNs, " in 2022 4th
Int. Conf. Control Robot., 2022, pp. 204-210, doi: 10.1109/ICCR55715.2022.10053871.
[18] C. Zhuang, Y. Yao, Y. Shen, and Z. Xiong, "A convolution neural network based semi-parametric dynamic model for industrial robot, "
Proc. Inst. Mech. Eng. Part C J. Mech. Eng. Sci., vol. 236, no. 7, pp. 3683-3700, 2022, doi: 10.1177/09544062211039875.
[19] S. Haddadin, A. De Luca and A. Albu-Schffer, "Robot collisions: A survey on detection, isolation, and identification, " IEEE Trans. Robot., vol. 33, no. 6, pp. 1292-1312, 2017, doi: 10.1109/TRO.2017.2723903.
[20] L. Han, W. Xu, B. Li, and P. Kang, "Collision detection and coordinated compliance control for a dual-arm robot without force/
torque sensing based on momentum observer, " IEEE/ASME Trans. Mechatronics, vol. 24, no. 5, pp. 2261-2272, 2019, doi: 10.1109/
TMECH.2019.2934141.
[21] C. Zhang, C. Mu, and Y. Wang, "Collision detection for six-DOF serial robots force /position hybrid control based on continuous friction
model, " Meas. Contrl., vol. 56, pp. 571-582, 2023, doi: 10.1177/00202940221091575.
[22] D. Lim, D. Kim, and J. Park, "Momentum observer-based collision detection using LSTM for model uncertainty learning, " in 2021
IEEE Int. Conf. Robot. Autom., Xi'an, China, 2021, pp. 4516-4522, doi: 10.1109/ICRA48506.2021.9561667.
[23] M. Lutter, C. Ritter, and J. Peters, "Deep lagrangian networks: Using physics as model prior for deep learning, " arXiv preprint,
arXiv:1907.04490.
[24] K. M. Park, Y. Park, S. Yoon, and F. C. Park, "Collision detection for robot manipulators using unsupervised anomaly detection algorithms, " IEEE/ASME Trans. Mechatronics, vol. 27, no. 5, pp. 2841-2851, 2022, doi: 10.1109/TMECH.2021.3119057.
[25] C. Yu, Z. Li, W. Chou, and H. Liu, "Low-gain control strategy for robot manipulators based on sparse feature learning dynamics with
an application to collision detection, " in 2022 IEEE Int. Symp. Safety, Secur. Rescue Robot., Sevilla, Spain, 2022, pp. 314-321, doi:
10.1109/SSRR56537.2022.10018693.
[26] A. D. Libera, "A data-efficient geometrically inspired polynomial kernel for robot inverse dynamic, " IEEE Robot. Autom. Lett., vol. 5,
no. 1, pp. 24-31, 2020, doi: 10.1109/LRA.2019.2945240.
DOI: http://dx.doi.org/10.70711/aitr.v4i1.9649
Refbacks
- There are currently no refbacks.
