Time Efficiency Improvement in Quadruped Walking with Supervised Training Joint Model
Source abstract
Abstract
To generate stable walking of a quadruped, the complexity of the configuration of the robot involves a significant amount of optimization that decreases to its time efficiency. To address this issue, a machine learning method was used to build a simplified control policy using joint models for the supervised training of quadruped robots. This study considered 12 joints for a four-legged robot, and each joint value was determined based on the conventional method of walking simulation and prepossessed, equaling 2508 sets of data. For data training, the multilayer perceptron model was used, and the optimized number of epochs used to train the model was 5000. The trained models were implemented in robot walking simulations, and they improved performance with an average distance error of 0.0719 m and a computational time as low as 91.98 s.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Robotic Locomotion and Control · Robot Manipulation and Learning · Viral Infectious Diseases and Gene Expression in Insects
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Mechanical Engineering, Graduate School, Kyungpook National University, Daegu 41566, Republic of Korea
Department of Mechanical and Aerospace Engineering, University of California, 420 Westwood Plaza, Rm 32-117E, Los Angeles, CA 90095, USA
Funding
BK21
References (30)
Show source-provided references
1. Patrick, W., and Michael, B. (1986). Legged Robots That Balance, MIT Press.
2. Liu, M.M., Qu, D.K., Xu, F., Zou, F.S., Di, P., and Tang, C. (2019). Quadrupedal robots whole-body motion control based on centroidal momentum dynamics. Appl. Sci., 9.10.3390/app9071335 ↗
3. Whole-Body Control and Angular Momentum Regulation using Torque Sensors for Quadrupedal Robots10.1007/s10846-021-01418-x ↗
4. Motion Planning for Quadrupedal Locomotion: Coupled Planning, Terrain Mapping, and Whole-Body Control10.1109/TRO.2020.3003464 ↗
5. Passive Whole-Body Control for Quadruped Robots: Experimental Validation Over Challenging Terrain10.1109/LRA.2019.2908502 ↗
6. Trajectory optimization for wheeled-legged quadrupedal robots using linearized ZMP constraints10.1109/LRA.2019.2896721 ↗
7. Jin, B., Zhou, Y., Zhao, Y., Liu, M., Song, C., and Luo, J. (2022). An Adaptive Control Algorithm for Quadruped Locomotion with Proprioceptive Linear Legs. arXiv.10.1109/TMECH.2022.3170548 ↗
8. Chen, H., Hong, Z., Yang, S., Patrick, M.W., and Zhang, W. (2022). Quadruped Capturability and Push Recovery via a Switched-Systems Characterization of Dynamic Balance. arXiv.
9. Alberto, D.P., Santanu, S.D., and Marco, M. (2014). Mixed-integer Quadratic Programming is in NP. arXiv.
10. Ahn, M.S., Chae, H., and Hong, D.W. (2018, January 1–5). Unknown Terrain Locomotion for Quadrupeds based on Visual Feedback and Mixed-Integer Convex Optimization. Proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain.10.1109/IROS.2018.8594015 ↗
11. Kohl, N., and Stone, P. (May, January 26). Policy gradient reinforcement learning for fast quadrupedal locomotion. Proceedings of the 2004 IEEE International Conferrence Robotic Automation (ICRA), New Orleans, LA, USA.10.1109/ROBOT.2004.1307456 ↗
12. Jain, D., Iscen, A., and Caluwaerts, K. (2019, January 3–8). Hierarchical reinforcement learning for quadruped locomotion. Proceedings of the 2019 IEEE International Confonference Intelligent Robots Systems (IROS), Macau, China.10.1109/IROS40897.2019.8967913 ↗
13. Generalization of movements in quadruped robot locomotion by learning specialized motion data10.1186/s40648-020-00174-1 ↗
14. Asoke, K.G. (2004). Fundamentals of Robotics: Analysis and Control, Prentice-Hall of India Private Limited.
15. Pereira, M.A., Fan, D.D., An, G.N., and Theodorou, E.A. (2018). Mpc-inspired neural network policies for sequential decision making. arXiv.
16. Predicting citation counts based on deep neural network learning techniques10.1016/j.joi.2019.02.011 ↗
17. Chattopadhyay, A., Manupriya, P., Sarkar, A., and Balasubramanian, V.N. (2019, January 10–15). Neural network attributions: A causal perspective, In Proceedings of the 36th International Conference Machine Learning (ICML). Long Beach, CA, USA.
18. Deep learning base modified MLP model for precise scattering parameter prediction of capacitive feed antenna10.1002/jnm.2682 ↗
19. Putra, M.A.P., Hermawan, A.P., Kim, D.S., and Lee, J.M. (2021, January 7–10). Energy Efficient-based Sensor Data Prediction using Deep Concatenate MLP. Proceedings of the 2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), Vasteras, Sweden.10.1109/ETFA45728.2021.9613213 ↗
20. Chen, S., Xie, E., Ge, C., Liang, D., Chen, R., and Luo, P. (2022). Cyclemlp: A mlp-like architecture for dense prediction. arXiv.
21. A comparison of deep networks with ReLU activation function and linear spline-type methods10.1016/j.neunet.2018.11.005 ↗
22. Hayou, S., Doucet, A., and Rousseau, J. (2019). On the impact of the activation function on deep neural networks training. arXiv.
23. Glorot, X., and Bengio, Y. (2010, January 13–15). Understanding the difficulty of training deep feedforward neural networks. Proceedings of the 13th International Conference Artificial Intelligent Statistics, PMLR 9, Sardinia, Italy.
24. Suriya, G., Lee, J., Soudry, D., and Srebro, N. (2019). Implicit bias of gradient descent on linear convolutional networks. arXiv.
25. Ultrametric fitting by gradient descent
26. Adaptive moment estimation for polynomial nonlinear equalizer in PAM8-based optical interconnects10.1364/OE.27.032210 ↗
27. Balakrishnan, N., Colton, T., Everitt, B., Piegorsch, W., Ruggeri, F., and Teugels, J. (2014). Wiley Statsref: Statistics Reference Online, John Wiley & Sons, Inc.10.1002/9781118445112 ↗
28. Reliable accuracy estimates from k-fold cross validation10.1109/TKDE.2019.2912815 ↗
29. Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., and Isard, M. (2016, January 2–4). Tensorflow: A system for large-scale machine learning. Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI’16), Savannah, GA, USA.
30. Gulli, A., and Pal, S. (2017). Deep Learning with Keras, Packt Publishing Ltd.