Rostok Framework: Automating Underactuated Robot Gripper Design

Table of Links

Abstract and I. Introduction

II. Methods

III. Generation of Tendon Driven Grippers

IV. Results and Discussion

V. Conclusion and References

V. CONCLUSION

This paper explores the intricate process of designing robots, emphasizing the convergence of hardware and software in complex, conflicting criteria. We introduced a novel approach combining morphological computation, according to which the major portion of robots’ desired behavior can be achieved with the “body” instead of the “brain”, and generative design, highlighting the potential of automatic design for underactuated tendon-driven grippers, with opensource framework details and comprehensive testing results. The result of the “rostok”[2] pipeline for the task of generating tendon driven grippers is the set of designs with top rewards. The designs were thoroughly tested in a physical setup to ensure their ability to accurately reproduce the simulated kinematics and securely hold the object in place.

REFERENCES

[1] Y. Sun, J. Falco, M. A. Roa, and B. Calli, “Research challenges and progress in robotic grasping and manipulation competitions,” IEEE robotics and automation letters, vol. 7, no. 2, pp. 874–881, 2021.

[2] I. I. Borisov, E. E. Khomutov, S. A. Kolyubin, and S. Stramigioli, “Computational design of reconfigurable underactuated linkages for adaptive grippers,” in 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2021, pp. 6117–6123.

[3] I. I. Borisov, E. E. Khornutov, D. V. Ivolga, N. A. Molchanov, I. A. Maksimov, and S. A. Kolyubin, “Reconfigurable underactuated adaptive gripper designed by morphological computation,” in 2022 International Conference on Robotics and Automation (ICRA). IEEE, 2022, pp. 1130–1136.

[4] K. V. Nasonov, D. V. Ivolga, I. I. Borisov, and S. A. Kolyubin, “Computational design of closed-chain linkages: Hopping robot driven by morphological computation,” in 2023 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2023, pp. 7419–7425.

[5] B. Thomaszewski, S. Coros, D. Gauge, V. Megaro, E. Grinspun, and M. Gross, “Computational design of linkage-based characters,” ACM Transactions on Graphics (TOG), vol. 33, no. 4, pp. 1–9, 2014.

[6] F. De Vincenti, D. Kang, and S. Coros, “Control-aware design optimization for bio-inspired quadruped robots,” in 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2021, pp. 1354–1361.

[7] T. Chen, L. Wang, M. Haas-Heger, and M. Ciocarlie, “Underactuation design for tendon-driven hands via optimization of mechanically realizable manifolds in posture and torque spaces,” IEEE Transactions on Robotics, vol. 36, no. 3, pp. 708–723, 2020.

[8] J. Bhatia, H. Jackson, Y. Tian, J. Xu, and W. Matusik, “Evolution gym: A large-scale benchmark for evolving soft robots,” Advances in Neural Information Processing Systems, vol. 34, 2021.

[9] N. Cheney, J. Bongard, V. SunSpiral, and H. Lipson, “Scalable cooptimization of morphology and control in embodied machines,” Journal of The Royal Society Interface, vol. 15, no. 143, p. 20170937, 2018.

[10] H. Ha, S. Agrawal, and S. Song, “Fit2form: 3d generative model for robot gripper form design,” in Conference on Robot Learning. PMLR, 2021, pp. 176–187.

[11] J. Hu, J. Whitman, M. Travers, and H. Choset, “Modular robot design optimization with generative adversarial networks,” in 2022 International Conference on Robotics and Automation (ICRA). IEEE, 2022, pp. 4282–4288.

[12] A. Zhao, J. Xu, M. Konakovic-Lukovi ´ c, J. Hughes, A. Spielberg, ´ D. Rus, and W. Matusik, “Robogrammar: graph grammar for terrainoptimized robot design,” ACM Transactions on Graphics (TOG), vol. 39, no. 6, pp. 1–16, 2020.

[13] T. Wang, Y. Zhou, S. Fidler, and J. Ba, “Neural graph evolution: Towards efficient automatic robot design,” arXiv preprint arXiv:1906.05370, 2019.

[14] A. Gupta, L. Fan, S. Ganguli, and L. Fei-Fei, “Metamorph: Learning universal controllers with transformers,” arXiv preprint arXiv:2203.11931, 2022.

[15] D. Pathak, C. Lu, T. Darrell, P. Isola, and A. A. Efros, “Learning to control self- assembling morphologies: A study of generalization via modularity,” in NeurIPS, 2019.

[16] L. Zlokapa, Y. Luo, J. Xu, M. Foshey, K. Wu, P. Agrawal, and W. Matusik, “An integrated design pipeline for tactile sensing robotic manipulators,” in 2022 International Conference on Robotics and Automation (ICRA). IEEE, 2022, pp. 3136–3142.

[17] A. Rocchi and K. Hauser, “A generic simulator for underactuated compliant hands,” in 2016 IEEE International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR). IEEE, 2016, pp. 37–42.

[18] T. Wang, Y. Zhou, S. Fidler, and J. Ba, “Neural graph evolution: Automatic robot design,” in International Conference on Learning Representations, 2019. [Online]. Available: https://openreview.net/for um?id=BkgWHnR5tm

[19] K. Sims, “Evolving virtual creatures,” Proceedings of the 21st annual conference on Computer graphics and interactive techniques nbsp; - SIGGRAPH ’94, 1994.

[20] A. Tasora, R. Serban, H. Mazhar, A. Pazouki, D. Melanz, J. Fleischmann, M. Taylor, H. Sugiyama, and D. Negrut, “Chrono: An open source multi-physics dynamics engine,” in High Performance Computing in Science and Engineering: Second International Conference, HPCSE 2015, Sola´n, Czech Republic, May 25-28, 2015, Revised ˇ Selected Papers 2. Springer, 2016, pp. 19–49.

[21] L. Kocsis and C. Szepesvari, “Bandit based monte-carlo planning,” in ´ Machine Learning: ECML 2006: 17th European Conference on Machine Learning Berlin, Germany, September 18-22, 2006 Proceedings 17. Springer, 2006, pp. 282–293.

[2] All methods and algorithms described in the paper are available as a part of the open-source framework rostok (https://github.com/aim club/rostok)