Abstract
Tensegrity rovers incorporate design principles that give rise to many desirable properties, such as adaptability and robustness, while also creating challenges in terms of locomotion control. A recent milestone in this area combined reinforcement learning and optimal control to effect fixed-axis rolling of NASA’s 6-bar spherical tensegrity rover prototype, SUPERball, with use of 12 actuators. The new 24-actuator version of SUPERball presents the potential for greatly increased locomotive abilities, but at a drastic nominal increase in the size of the data-driven control problem. This paper is focused upon unlocking those abilities while crucially moderating data requirements by incorporating symmetry reduction into the controller design pipeline, along with other new considerations. Experiments in simulation and on the hardware prototype demonstrate the resulting capability for any-axis rolling on the 24-actuator version of SUPERball, such that it may utilize diverse ground-contact patterns to smoothly locomote in arbitrary directions.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
NASA Tensegrity Robotics Toolkit. https://ti.arc.nasa.gov/tech/asr/groups/intelligent-robotics/tensegrity/NTRT/
Bliss, T., Iwasaki, T., Bart-Smith, H.: Central pattern generator control of a tensegrity swimmer. Trans. Mech. 18(2), 586–597 (2013)
Iscen, A., Caluwaerts, K., Bruce, J., Agogino, A., SunSpiral, V., Tumer, K.: Learning tensegrity locomotion using open-loop control signals and coevolutionary algorithms. Artif. Life 21(2), 119–140 (2015)
Khazanov, M., Jocque, J., Rieffel, J.: Developing morphological computation in tensegrity robots for controllable actuation. In: 2014 Annual Conference on Genetic and Evolutionary Computation, pp. 1049–1052. ACM, New York (2014). https://doi.org/10.1145/2598394.2605680
Kim, K., Agogino, A.K., Toghyan, A., Moon, D., Taneja, L., Agogino, A.M.: Robust learning of tensegrity robot control for locomotion through form-finding. In: IROS (2015)
Koizumi, Y., Shibata, M., Hirai, S.: Rolling tensegrity driven by pneumatic soft actuators. In: ICRA, pp. 1988–1993 (2012). https://doi.org/10.1109/ICRA.2012.6224834
Levine, S., Finn, C., Darrell, T., Abbeel, P.: End-to-end training of deep visuomotor policies. J. Mach. Learn. Res. 17(1), 1334–1373 (2016)
Littlefield, Z., Surovik, D., Wang, W., Bekris, K.E.: From quasi-static to kinodynamic planning for spherical tensegrity locomotion. In: International Symposium on Robotics Research (ISRR), Puerto Varas, Chile (2017)
Mirletz, B., Bhandal, P., Adams, R.D., Agogino, A.K., Quinn, R.D., SunSpiral, V.: Goal directed CPG based control for high DOF tensegrity spines traversing irregular terrain. Soft Robot. 2, 165–176 (2015)
Mirletz, B.T., Park, I.W., Quinn, R.D., SunSpiral, V.: Towards bridging the reality gap between tensegrity simulation and robotic hardware. In: 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5357–5363. IEEE (2015)
Montgomery, W., Ajay, A., Finn, C., Abbeel, P., Levine, S.: Reset-free guided policy search: efficient deep reinforcement learning with stochastic initial states. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 3373–3380 (2017). https://doi.org/10.1109/ICRA.2017.7989383
Paul, C., Valero-Cuevas, F.J., Lipson, H.: Design and control of tensegrity robots for locomotion. TRO 22(5) (2006). https://doi.org/10.1109/TRO.2006.878980
Rovira, A.G., Mirats Tur, J.M.: Control and simulation of a tensegrity-based mobile robot. RAS 57(5), 526–535 (2009)
Sultan, C., Skelton, R.: Deployment of tensegrity structures. Int. J. Solids Struct. 40(18), 4637–4657 (2003). https://doi.org/10.1016/S0020-7683(03)00267-1
Surovik, D.A., Bekris, K.E.: Symmetric reduction of tensegrity rover dynamics for efficient data-driven control. In: ASCE International Conference on Engineering, Science, Construction and Operations in Challenging Environments (2018)
Vespignani, M., Ercolani, C., Friesen, J.M., Bruce, J.: Steerable locomotion controller for six-strut icosahedral tensegrity robots. In: IROS (2018)
Vespignani, M., Friesen, J.M., SunSpiral, V., Bruce, J.: Design of superball v2, a compliant tensegrity robot for absorbing large impacts. In: IROS (2018)
Zhang, M., Geng, X., Bruce, J., Caluwaerts, K., Vespignani, M., SunSpiral, V., Abbeel, P., Levine, S.: Deep reinforcement learning for tensegrity robot locomotion. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 634–641 (2017). https://doi.org/10.1109/ICRA.2017.7989079
Zhu, S., Kimmel, A., Bekris, K.E., Boularias, A.: Fast model identification via physics engines for data-efficient policy search. In: International Joint Conference on Artificial Intelligence (IJCAI), Stockholm, Sweden (2018)
Acknowledgment
Supported by NASA ECF grant NNX15AU47G.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Surovik, D., Bruce, J., Wang, K., Vespignani, M., Bekris, K. (2020). Any-Axis Tensegrity Rolling via Symmetry-Reduced Reinforcement Learning. In: Xiao, J., Kröger, T., Khatib, O. (eds) Proceedings of the 2018 International Symposium on Experimental Robotics. ISER 2018. Springer Proceedings in Advanced Robotics, vol 11. Springer, Cham. https://doi.org/10.1007/978-3-030-33950-0_36
Download citation
DOI: https://doi.org/10.1007/978-3-030-33950-0_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-33949-4
Online ISBN: 978-3-030-33950-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)