2000 character limit reached
Machine Learning-Driven Burrowing with a Snake-Like Robot
Published 19 Sep 2023 in cs.RO | (2309.10802v1)
Abstract: Subterranean burrowing is inherently difficult for robots because of the high forces experienced as well as the high amount of uncertainty in this domain. Because of the difficulty in modeling forces in granular media, we propose the use of a novel machine-learning control strategy to obtain optimal techniques for vertical self-burrowing. In this paper, we realize a snake-like bio-inspired robot that is equipped with an IMU and two triple-axis magnetometers. Utilizing magnetic field strength as an analog for depth, a novel deep learning architecture was proposed based on sinusoidal and random data in order to obtain a more efficient strategy for vertical self-burrowing. This strategy was able to outperform many other standard burrowing techniques and was able to automatically reach targeted burrowing depths. We hope these results will serve as a proof of concept for how optimization can be used to unlock the secrets of navigating in the subterranean world more efficiently.
- C. Li, T. Zhang, and D. I. Goldman, “A terradynamics of legged locomotion on granular media,” science, vol. 339, no. 6126, pp. 1408–1412, 2013.
- S. Pradhan and T. Siddique, “Mass wasting: an overview,” Landslides: Theory, Practice and Modelling, pp. 3–20, 2019.
- R. D. Maladen, Y. Ding, P. B. Umbanhowar, A. Kamor, and D. I. Goldman, “Mechanical models of sandfish locomotion reveal principles of high performance subsurface sand-swimming,” Journal of The Royal Society Interface, vol. 8, no. 62, pp. 1332–1345, 2011.
- A. Martinez, J. DeJong, I. Akin, A. Aleali, C. Arson, J. Atkinson, P. Bandini, T. Baser, R. Borela, R. Boulanger et al., “Bio-inspired geotechnical engineering: Principles, current work, opportunities and challenges,” Géotechnique, vol. 72, no. 8, pp. 687–705, 2022.
- I. Taylor, K. Lehner, E. McCaskey, N. Nirmal, Y. Ozkan-Aydin, M. Murray-Cooper, R. Jain, E. W. Hawkes, P. C. Ronald, D. I. Goldman, and P. N. Benfey, “Mechanism and function of root circumnutation,” Proceedings of the National Academy of Sciences, vol. 118, no. 8, p. e2018940118, 2021.
- N. D. Naclerio, A. Karsai, M. Murray-Cooper, Y. Ozkan-Aydin, E. Aydin, D. I. Goldman, and E. W. Hawkes, “Controlling subterranean forces enables a fast, steerable, burrowing soft robot,” Science Robotics, vol. 6, no. 55, p. eabe2922, 2021.
- H. Omori, T. Hayakawa, and T. Nakamura, “Locomotion and turning patterns of a peristaltic crawling earthworm robot composed of flexible units,” in 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE, 2008, pp. 1630–1635.
- J. J. Tao, “Burrowing soft robots break new ground,” Science Robotics, vol. 6, no. 55, 2021.
- B. Liu, Y. Ozkan-Aydin, D. I. Goldman, and F. L. Hammond, “Kirigami skin improves soft earthworm robot anchoring and locomotion under cohesive soil,” in 2019 2nd IEEE International Conference on Soft Robotics (RoboSoft), 2019, pp. 828–833.
- R. A. Russell, “Crabot: A biomimetic burrowing robot designed for underground chemical source location,” Advanced Robotics, vol. 25, no. 1-2, pp. 119–134, 2011. [Online]. Available: https://doi.org/10.1163/016918610X538516
- L. K. Treers, B. McInroe, R. J. Full, and H. S. Stuart, “Mole crab-inspired vertical self-burrowing,” Frontiers in Robotics and AI, vol. 9, 2022. [Online]. Available: https://www.frontiersin.org/articles/10.3389/frobt.2022.999392
- H. Bagheri, D. Stockwell, B. Bethke, N. K. Okwae, D. Aukes, J. Tao, and H. Marvi, “A bio-inspired helically driven self-burrowing robot,” Acta Geotechnica, Apr 2023. [Online]. Available: https://doi.org/10.1007/s11440-023-01882-9
- K. Lee and R. C. Hurley, “Force inference in granular materials: Uncertainty analysis and application to three-dimensional experiment design,” Phys. Rev. E, vol. 105, p. 064902, Jun 2022. [Online]. Available: https://link.aps.org/doi/10.1103/PhysRevE.105.064902
- J. Kober, J. A. Bagnell, and J. Peters, “Reinforcement learning in robotics: A survey,” The International Journal of Robotics Research, vol. 32, no. 11, pp. 1238–1274, 2013.
- J. Ibarz, J. Tan, C. Finn, M. Kalakrishnan, P. Pastor, and S. Levine, “How to train your robot with deep reinforcement learning: lessons we have learned,” The International Journal of Robotics Research, vol. 40, no. 4-5, pp. 698–721, 2021.
- A. Cura, H. Küçük, E. Ergen, and İ. B. Öksüzoğlu, “Driver profiling using long short term memory (lstm) and convolutional neural network (cnn) methods,” IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 10, pp. 6572–6582, 2020.
- B. C. Jayne, “Kinematics of terrestrial snake locomotion,” Copeia, pp. 915–927, 1986.
- N. J. Gidmark, J. A. Strother, J. M. Horton, A. P. Summers, and E. L. Brainerd, “Locomotory transition from water to sand and its effects on undulatory kinematics in sand lances (ammodytidae),” Journal of Experimental Biology, vol. 214, no. 4, pp. 657–664, 2011.
- M. Tokic, “Adaptive ε𝜀\varepsilonitalic_ε-greedy exploration in reinforcement learning based on value differences,” in Annual Conference on Artificial Intelligence. Springer, 2010, pp. 203–210.
- F. Liu, L. Viano, and V. Cevher, “Understanding deep neural function approximation in reinforcement learning via ϵitalic-ϵ\epsilonitalic_ϵ-greedy exploration,” Advances in Neural Information Processing Systems, vol. 35, pp. 5093–5108, 2022.
- A. dos Santos Mignon and R. L. d. A. da Rocha, “An adaptive implementation of ε𝜀\varepsilonitalic_ε-greedy in reinforcement learning,” Procedia Computer Science, vol. 109, pp. 1146–1151, 2017.
- B. Young, M. Morain, and R. Wood, “Vertical burrowing in the saharan sand vipers (cerastes),” Copeia, vol. 2003, pp. 131–137, 02 2003.
- G. Marketos and M. D. Bolton, “Flat boundaries and their effect on sand testing,” International Journal for Numerical and Analytical Methods in Geomechanics, vol. 34, no. 8, pp. 821–837, 2010. [Online]. Available: https://onlinelibrary.wiley.com/doi/abs/10.1002/nag.835
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.