Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
175 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Design and Control Co-Optimization for Automated Design Iteration of Dexterous Anthropomorphic Soft Robotic Hands (2403.09933v2)

Published 15 Mar 2024 in cs.RO

Abstract: We automate soft robotic hand design iteration by co-optimizing design and control policy for dexterous manipulation skills in simulation. Our design iteration pipeline combines genetic algorithms and policy transfer to learn control policies for nearly 400 hand designs, testing grasp quality under external force disturbances. We validate the optimized designs in the real world through teleoperation of pickup and reorient manipulation tasks. Our real world evaluation, from over 900 teleoperated tasks, shows that the trend in design performance in simulation resembles that of the real world. Furthermore, we show that optimized hand designs from our approach outperform existing soft robot hands from prior work in the real world. The results highlight the usefulness of simulation in guiding parameter choices for anthropomorphic soft robotic hand systems, and the effectiveness of our automated design iteration approach, despite the sim-to-real gap.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (35)
  1. C. Piazza, G. Grioli, M. Catalano, and A. Bicchi, “A century of robotic hands,” Annual Review of Control, Robotics, and Autonomous Systems, vol. 2, 2019.
  2. T. Feix, J. Romero, H.-B. Schmiedmayer, A. M. Dollar, and D. Kragic, “The grasp taxonomy of human grasp types,” IEEE Transactions on human-machine systems, 2015.
  3. B. Calli, A. Singh, J. Bruce, A. Walsman, K. Konolige, S. S. Srinivasa, P. Abeel, and A. M. Dollar, “Ycb benchmarking project: Object set, data set and their applications,” Journal of The Society of Instrument and Control Engineers, vol. 56, no. 10, pp. 792–797, 2017.
  4. S. Cruciani, B. Sundaralingam, K. Hang, V. Kumar, T. Hermans, and D. Kragic, “Benchmarking in-hand manipulation,” IEEE RA-L, 2020.
  5. B. Yang, P. E. Lancaster, S. S. Srinivasa, and J. R. Smith, “Benchmarking robot manipulation with the rubik’s cube,” IEEE RA-L, 2020.
  6. A. Rajeswaran, V. Kumar, A. Gupta, G. Vezzani, J. Schulman, E. Todorov, and S. Levine, “Learning complex dexterous manipulation with deep reinforcement learning and demonstrations,” RSS 2018, 2018.
  7. A. S. Morgan, W. G. Bircher, B. Calli, and A. M. Dollar, “Learning from transferable mechanics models: Generalizable online mode detection in underactuated dexterous manipulation,” in ICRA 2019, 2019.
  8. S. Cruciani, C. Smith, D. Kragic, and K. Hang, “Dexterous manipulation graphs,” in IROS, 2018.
  9. X. Liu, D. Pathak, and K. M. Kitani, “Revolver: Continuous evolutionary models for robot-to-robot policy transfer,” arXiv preprint arXiv:2202.05244, 2022.
  10. Xingyu Liu and Deepak Pathak and Kris M. Kitani, “HERD: Continuous human-to-robot evolution for learning from human demonstration,” in CoRL, 2022.
  11. T. W. Manikas, K. Ashenayi, and R. L. Wainwright, “Genetic algorithms for autonomous robot navigation,” IEEE Instrumentation & Measurement Magazine, 2007.
  12. S. Števo, I. Sekaj, and M. Dekan, “Optimization of robotic arm trajectory using genetic algorithm,” IFAC Proceedings Volumes, pp. 1748–1753, 2014.
  13. X. Liu, D. Pathak, and D. Zhao, “Meta-evolve: Continuous robot evolution for one-to-many policy transfer,” in ICLR, 2024.
  14. P. Mannam, K. Shaw, D. Bauer, J. Oh, D. Pathak, and N. Pollard, “Designing anthropomorphic soft hands through interaction,” in Humanoids 2023, 2023.
  15. J. Whitman, M. Travers, and H. Choset, “Modular mobile robot design selection with deep reinforcement learning,” in NeurIPS Workshop on ML for engineering modeling, simulation and design, 2020.
  16. T. Chen, Z. He, and M. Ciocarlie, “Co-designing hardware and control for robot hands,” Science Robotics, 2021.
  17. C. Chen, P. Xiang, H. Lu, Y. Wang, and R. Xiong, “𝙲2superscript𝙲2\texttt{C}^{2}C start_POSTSUPERSCRIPT 2 end_POSTSUPERSCRIPT:co-design of robots via concurrent networks coupling online and offline reinforcement learning,” 2022.
  18. S. Ha, S. Coros, A. Alspach, J. Kim, and K. Yamane, “Joint optimization of robot design and motion parameters using the implicit function theorem.” in RSS 2017.
  19. C. Schaff, D. Yunis, A. Chakrabarti, and M. R. Walter, “Jointly learning to construct and control agents using deep reinforcement learning,” in ICRA 2019, 2019.
  20. J. Whitman, M. Travers, and H. Choset, “Learning modular robot control policies,” IEEE T-RO, 2023.
  21. J. Xu, T. Chen, L. Zlokapa, M. Foshey, W. Matusik, S. Sueda, and P. Agrawal, “An end-to-end differentiable framework for contact-aware robot design,” in Robotics: Science and Systems XVII, 2021.
  22. T. Salimans, J. Ho, X. Chen, S. Sidor, and I. Sutskever, “Evolution strategies as a scalable alternative to reinforcement learning,” arXiv:1703.03864, 2017.
  23. A. Meixner, C. Hazard, and N. Pollard, “Automated design of simple and robust manipulators for dexterous in-hand manipulation tasks using evolutionary strategies,” in Humanoids 2019.   IEEE, 2019, pp. 281–288.
  24. R. Deimel, P. Irmisch, V. Wall, and O. Brock, “Automated co-design of soft hand morphology and control strategy for grasping,” in IROS 2017, 2017.
  25. S. P. Arunachalam, S. Silwal, B. Evans, and L. Pinto, “Dexterous imitation made easy: A learning-based framework for efficient dexterous manipulation,” 2022.
  26. K. Shaw, S. Bahl, and D. Pathak, “Videodex: Learning dexterity from internet videos,” in CoRL 2022, 2022.
  27. Y. Chen, C. Wang, L. Fei-Fei, and C. K. Liu, “Sequential dexterity: Chaining dexterous policies for long-horizon manipulation,” 2023.
  28. J. Kim, K. Iwamoto, J. J. Kuffner, Y. Ota, and N. S. Pollard, “Physically based grasp quality evaluation under pose uncertainty,” IEEE T-RO, 2013.
  29. M. Bonilla, E. Farnioli, C. Piazza, M. Catalano, G. Grioli, M. Garabini, M. Gabiccini, and A. Bicchi, “Grasping with soft hands,” in Humanoids 2014, 2014.
  30. D. Bauer, C. Bauer, A. Lakshmipathy, R. Shu, and N. S. Pollard, “Towards very low-cost iterative prototyping for fully printable dexterous soft robotic hands,” in RoboSoft 2022, 2022, pp. 490–497.
  31. “Ninjaflex edge,” https://ninjatek.com/shop/edge/, accessed on 2023-10-08.
  32. “Robotis:dynamixel-x,” https://www.robotis.us/dynamixel-xc330-m288-t/, accessed on 2023-10-08.
  33. “Ufactory xarm7,” https://www.ufactory.cc/product-page/ufactory-xarm-7, accessed on 2023-10-08.
  34. V. Makoviychuk, L. Wawrzyniak, Y. Guo, M. Lu, K. Storey, M. Macklin, D. Hoeller, N. Rudin, A. Allshire, A. Handa, and G. State, “Isaac gym: High performance gpu-based physics simulation for robot learning,” 2021.
  35. “Manus,” https://www.manus-meta.com, accessed on 2022-11-28.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now