Abstract
Trajectory generation for biped robots is very complex due to the challenge posed by real-world uneven terrain. To address this complexity, this paper proposes a data-driven Gait model that can handle continuously changing conditions. Data-driven approaches are used to incorporate the joint relationships. Therefore, the deep learning methods are employed to develop seven different data-driven models, namely DNN, LSTM, GRU, BiLSTM, BiGRU, LSTM+GRU, and BiLSTM+BiGRU. The dataset used for training the Gait model consists of walking data from 10 able subjects on continuously changing inclines and speeds. The objective function incorporates the standard error from the inter-subject mean trajectory to guide the Gait model to not accurately follow the high variance points in the gait cycle, which helps in providing a smooth and continuous gait cycle. The results show that the proposed Gait models outperform the traditional finite state machine (FSM) and Basis models in terms of mean and maximum error summary statistics. In particular, the LSTM+GRU-based Gait model provides the best performance compared to other data-driven models.
Similar content being viewed by others
Code availability
Not applicable.
Abbreviations
- DNN:
-
Deep neural network
- LSTM:
-
Long short term memory
- GRU:
-
Gated recurrent units
- BiLSTM:
-
Bidirectional LSTM
- BiGRU:
-
Bidirectional GRU
- COMBO BI:
-
BiLSTM + BiGRU
- FSM:
-
Finite state machine
- MAE:
-
Mean absolute error
- MSE:
-
Mean squared error
- SE:
-
Standard error
References
Allen, D. M. (1971). Mean square error of prediction as a criterion for selecting variables. Technometrics, 13(3), 469–475. https://doi.org/10.1080/00401706.1971.10488811
Aoi, S., & Tsuchiya, K. (2011). Generation of bipedal walking through interactions among the robot dynamics, the oscillator dynamics, and the environment: Stability characteristics of a five-link planar biped robot. Autonomous Robots, 30(2), 123–141.
Burman, V., & Kumar, R. (2021). Wheel robot review. Innovations in cyber physical systems (pp. 781–791). Singapore: Springer.
Canziani, A., Paszke, A., & Culurciello, E., (2016). An analysis of deep neural network models for practical applications. arXiv preprint arXiv:1605.07678.
Castillo, G. A., Weng, B., Zhang, W., & Hereid, A. (2022). Reinforcement learning-based cascade motion policy design for robust 3D bipedal locomotion. IEEE Access, 10, 20135–20148.
Chai, T., & Draxler, R. R. (2014). Root mean square error (RMSE) or mean absolute error (MAE)?-Arguments against avoiding RMSE in the literature. Geoscientific Model Development, 7(3), 1247–1250. https://doi.org/10.5194/gmd-7-1247-2014
Chai, L., Du, J., Liu, Q. F., & Lee, C. H. (2019). Using generalized Gaussian distributions to improve regression error modeling for deep learning-based speech enhancement. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 27(12), 1919–1931. https://doi.org/10.1109/TASLP.2019.2935803
Coyle, E. J., & Lin, J. H. (1988). Stack filters and the mean absolute error criterion. IEEE Transactions on Acoustics, Speech, and Signal Processing, 36(8), 1244–1254. https://doi.org/10.1109/29.1653
Dey, R., & Salem, F.M., (2017). Gate-variants of gated recurrent unit (GRU) neural networks. In 2017 IEEE 60th international midwest symposium on circuits and systems (MWSCAS), IEEE (pp. 1597–1600).
Doerschuk, P. I., Nguyen, V., & Li, A. (2002). A scalable intelligent takeoff controller for a simulated running jointed leg. Applied Intelligence, 17(1), 75–87. https://doi.org/10.1023/A:1015731916039
Dong, Y., (2018). A survey on neural network-based summarization methods. arXiv:1804.04589.
Embry, K.R., Villarreal, D.J., Gregg, R.D., (2016). A unified parameterization of human gait across ambulation modes. In 38th annual international conference of the IEEE engineering in medicine and biology society, IEEE (pp. 2179–2183).
Embry, K., Villarreal, D., Macaluso, R., & Gregg, R. (2018). The effect of walking incline and speed on human leg kinematics, kinetics, and EMG. IEEE Dataport. https://doi.org/10.21227/gk32-e868
Embry, K. R., Villarreal, D. J., Macaluso, R. L., & Gregg, R. D. (2018). Modeling the kinematics of human locomotion over continuously varying speeds and inclines. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 26(12), 2342–2350. https://doi.org/10.1109/TNSRE.2018.2879570
Gao, Y., Wei, W., Wang, X., Li, Y., Wang, D., & Yu, Q. (2021). Feasibility, planning and control of ground-wall transition for a suctorial hexapod robot. Applied Intelligence, 51, 1–19. https://doi.org/10.1007/s10489-020-01955-2
Gouk, H., Frank, E., Pfahringer, B., & Cree, M. J. (2021). Regularisation of neural networks by enforcing lipschitz continuity. Machine Learning, 110(2), 393–416. https://doi.org/10.1007/s10994-020-05929-w
Greff, K., Srivastava, R. K., Koutník, J., Steunebrink, B. R., & Schmidhuber, J. (2016). LSTM: A search space odyssey. IEEE Transactions on Neural Networks and Learning Systems, 28(10), 2222–2232. https://doi.org/10.1109/TNNLS.2016.2582924
Hildebrandt, A. C., Schwerd, S., Wittmann, R., Wahrmann, D., Sygulla, F., Seiwald, P., & Buschmann, T. (2019). Kinematic optimization for bipedal robots: A framework for real-time collision avoidance. Autonomous Robots, 43(5), 1187–1205.
Holgate, M A., Sugar, T G., Bohler, A.W., (2009). A novel control algorithm for wearable robotics using phase plane invariants. In 2009 IEEE international conference on robotics and automation, IEEE, pp 3845-3850.
Hosseinmemar, A., Baltes, J., Anderson, J., Lau, M. C., Lun, C. F., & Wang, Z. (2019). Closed-loop push recovery for inexpensive humanoid robots. Applied Intelligence, 49(11), 3801–3814. https://doi.org/10.1007/s10489-019-01446-z
Huang, Z., Xu, W., & Yu, K., (2015). Bidirectional LSTM-CRF models for sequence tagging. arXiv:1508.01991.
Huang, C. F., & Yeh, T. J. (2019). Anti slip balancing control for wheeled inverted pendulum vehicles. IEEE Transactions on Control Systems Technology, 28(3), 1042–1049. https://doi.org/10.1109/TCST.2019.2891522
Huang, B., Xiong, C., Chen, W., Liang, J., Sun, B. Y., & Gong, X. (2021). Common kinematic synergies of various human locomotor behaviours. Royal Society open science, 8(4), 210161. https://doi.org/10.1098/rsos.210161
Juang, C. F., & Yeh, Y. T. (2017). Multiobjective evolution of biped robot gaits using advanced continuous ant-colony optimized recurrent neural networks. IEEE Transactions on Cybernetics, 48(6), 1910–1922. https://doi.org/10.1109/TCYB.2017.2718037
Kim, J. H., Lee, J., & Oh, Y. (2018). A theoretical framework for stability regions for standing balance of humanoids based on their LIPM treatment. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 50(11), 4569–4586. https://doi.org/10.1109/TSMC.2018.2855190
Kim, D., Jorgensen, S. J., Lee, J., Ahn, J., Luo, J., & Sentis, L. (2020). Dynamic locomotion for passive-ankle biped robots and humanoids using whole-body locomotion control. The International Journal of Robotics Research, 39(8), 936–956. https://doi.org/10.1177/0278364920918014
Kim, N., Jeong, B., & Park, K. (2021). A novel methodology to explore the periodic gait of a biped walker under uncertainty using a machine learning algorithm. Robotica. https://doi.org/10.1017/S0263574721000424
Kim, K., Spieler, P., Lupu, E. S., Ramezani, A., & Chung, S. J. (2021). A bipedal walking robot that can fly, slackline, and skateboard. Science Robotics., 6(59), eabf8136. https://doi.org/10.1126/scirobotics.abf8136
Kormushev, P., Ugurlu, B., Caldwell, D. G., & Tsagarakis, N. G. (2019). Learning to exploit passive compliance for energy-efficient gait generation on a compliant humanoid. Autonomous Robots, 43(1), 79–95.
Kuffner, J. J., Kagami, S., Nishiwaki, K., Inaba, M., & Inoue, H. (2002). Dynamically-stable motion planning for humanoid robots. Autonomous robots, 12(1), 105–118.
Kwon, O., & Park, J. H. (2009). Asymmetric trajectory generation and impedance control for running of biped robots. Autonomous Robots, 26(1), 47–78.
Lee, Y., Hwang, S., & Park, J. (2016). Balancing of humanoid robot using contact force/moment control by task-oriented whole body control framework. Autonomous Robots, 40(3), 457–472.
Li, T. H. S., Su, Y. T., Lai, S. W., & Hu, J. J. (2010). Walking motion generation, synthesis, and control for biped robot by using PGRL, LPI, and fuzzy logic. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 41(3), 736–748. https://doi.org/10.1109/TSMCB.2010.2089978
Li, Z., Tsagarakis, N. G., & Caldwell, D. G. (2013). Walking pattern generation for a humanoid robot with compliant joints. Autonomous Robots, 35(1), 1–14.
Li, T. H. S., Kuo, P. H., Cheng, C. H., Hung, C. C., Luan, P. C., & Chang, C. H. (2020). Sequential sensor fusion-based real-time LSTM gait pattern controller for biped robot. IEEE Sensors Journal, 21(2), 2241–2255. https://doi.org/10.1109/JSEN.2020.3016968
Liu, C., Zhang, T., Liu, M., & Chen, Q. (2020). Active balance control of humanoid locomotion based on foot position compensation. Journal of Bionic Engineering, 17(1), 134–147.
Liu, J., Chen, H., Wensing, P. M., & Zhang, W. (2021). Instantaneous capture input for balancing the variable height inverted pendulum. IEEE Robotics and Automation Letters, 6(4), 7421–7428. https://doi.org/10.1109/LRA.2021.3097074
Macaluso, R., Embry, K., Villarreal, D. J., & Gregg, R. D. (2021). Parameterizing human locomotion across quasi-random treadmill perturbations and inclines. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 29, 508–516. https://doi.org/10.1109/TNSRE.2021.3057877
Mangasarian, O. L., & Shiau, T. H. (1987). Lipschitz continuity of solutions of linear inequalities, programs and complementarity problems. SIAM Journal on Control and Optimization, 25(3), 583–595. https://doi.org/10.1137/0325033
Morris, K. J., Samonin, V., Baltes, J., Anderson, J., & Lau, M. C. (2019). A robust interactive entertainment robot for robot magic performances. Applied Intelligence, 49(11), 3834–3844. https://doi.org/10.1007/s10489-019-01565-7
Pon, MZ, KK, KP., (2021). Hyperparameter tuning of deep learning models in keras. Sparklinglight Transactions on Artificial Intelligence and Quantum Computing (STAIQC). 1(1):36-40. https://doi.org/10.55011/staiqc.2021.1104
Qi, J., Du, J., Siniscalchi, S. M., Ma, X., & Lee, C. H. (2020). On mean absolute error for deep neural network based vector-to-vector regression. IEEE Signal Processing Letters, 27, 1485–1489. https://doi.org/10.1109/LSP.2020.3016837
Quintero, D., Villarreal, D. J., Lambert, D. J., Kapp, S., & Gregg, R. D. (2018). Continuous-phase control of a powered knee-ankle prosthesis: Amputee experiments across speeds and inclines. IEEE Transactions on Robotics, 34(3), 686–701. https://doi.org/10.1109/TRO.2018.2794536
Razavi, H., Faraji, S., & Ijspeert, A. (2019). From standing balance to walking: A single control structure for a continuum of gaits. The International Journal of Robotics Research, 38(14), 1695–1716. https://doi.org/10.1177/0278364919875205
Shrestha, A., & Mahmood, A. (2019). Review of deep learning algorithms and architectures. IEEE Access, 7, 53040–53065. https://doi.org/10.1109/ACCESS.2019.2912200
Siekmann, J., Godse, Y., Fern, A., & Hurst, J., (2021). Sim-to-real learning of all common bipedal gaits via periodic reward composition. In 2021 IEEE international conference on robotics and automation (ICRA), pp. 7309-7315.
Simon, A. M., Ingraham, K. A., Fey, N. P., Finucane, S. B., Lipschutz, R. D., Young, A. J., & Hargrove, L. J. (2014). Configuring a powered knee and ankle prosthesis for transfemoral amputees within five specific ambulation modes. PloS One, 9(6), e99387. https://doi.org/10.1371/journal.pone.0099387
Singh, B., Gupta, V., & Kumar, R. (2021). Probabilistic modeling of human locomotion for biped robot trajectory generation. In 2021 IEEE 8th Uttar Pradesh section international conference on electrical electronics and computer engineering (UPCON) (pp. 1–6).
Singh, B., Kumar, R., Singh, V. P., et al. (2021). Reinforcement learning in robotic applications: A comprehensive survey. Artificial Intelligence Review. https://doi.org/10.1007/s10462-021-09997-9
Singh, B., Vijayvargiya, A., & Kumar, R. (2022). Kinematic modeling for biped robot gait trajectory using machine learning techniques. Journal of Bionic Engineering, 19, 355–369. https://doi.org/10.1007/s42235-021-00142-4
Sun, Y., Tang, H., Tang, Y., Zheng, J., Dong, D., Chen, X., & Luo, J. (2021). Review of recent progress in robotic knee prosthesis related techniques: Structure, actuation and control. Journal of Bionic Engineering, 18(4), 764–785.
Vicon Motion Systems Ltd. (2018) Vicon nexus reference guide. https://docs.vicon.com/display/Nexus26/Vicon+Nexus+Reference+Guide
Wang, L., Liu, Z., Chen, C. P., & Zhang, Y. (2014). Interval type-2 fuzzy weighted support vector machine learning for energy efficient biped walking. Applied Intelligence, 40(3), 453–463. https://doi.org/10.1007/s10489-013-0472-2
Wang, Z., He, B., Zhou, Y., Yuan, T., Xu, S., & Shao, M. (2018). An experimental analysis of stability in human walking. Journal of Bionic Engineering, 15(5), 827–838.
Wang, K., Ren, L., Qian, Z., Liu, J., Geng, T., & Ren, L. (2021). Development of a 3D printed bipedal robot: Towards humanoid research platform to study human musculoskeletal biomechanics. Journal of Bionic Engineering, 18(1), 150–170.
Yamaguchi, J. I., & Takanishi, A. (1997). Development of a leg part of a humanoid robot-development of a biped walking robot adapting to the humans’ normal living floor. Autonomous Robots, 4(4), 369–385.
Yang, W., Tan, R. T., Wang, S., Fang, Y., & Liu, J. (2021). Single image deraining: From model-based to data-driven and beyond. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(11), 4059–4077. https://doi.org/10.1109/TPAMI.2020.2995190
Zhou, C., Wang, X., Li, Z., & Tsagarakis, N. (2017). Overview of gait synthesis for the humanoid COMAN. Journal of Bionic Engineering, 14(1), 15–25.
Funding
The authors declare that no funds, grants, or other support were received during the preparation of this manuscript.
Author information
Authors and Affiliations
Contributions
Mr. Bharat Singh has contributed to develop the methodology, analysis, and drafting of this paper by carrying out a thorough study of the literature regarding the mentioned topics. He has also contributed in the sense of presenting a comparison between the various techniques of gait models. All authors read and approved the final manuscript. Mr. Suchit Patel has contributed on the development of gait model. Mr. Ankit Vijayvargiya has contributed in analyzing the results and provided the suggestion in developing the gait models. Prof. Rajesh Kumar has also contributed this work by supervising all aspects related to methodology, analysis and drafting.
Corresponding author
Ethics declarations
Conflicts of interest
All authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript.
Ethics approval
Not applicable.
Consent to participate
Not applicable.
Consent to publication
Not applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Singh, B., Patel, S., Vijayvargiya, A. et al. Data-driven gait model for bipedal locomotion over continuous changing speeds and inclines. Auton Robot 47, 753–769 (2023). https://doi.org/10.1007/s10514-023-10108-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10514-023-10108-6