Abstract
For decades, robots have been able to reliably follow precise trajectories making them ideal tools for assembly lines and other structured environments. However, pre-programmed motions fail under uncertainty and are unsafe around humans, making them inadequate for unstructured environments. This paper presents a framework to generate safe, robust, and generalizable robot behaviors for contact tasks where compliance plays a key role. First, we collect task data from haptic demonstrations. Then, we segment the data into a sequence of compliant primitives. Finally, we extract the key parameters required for a robot to perform each of the primitive actions using interpretable, model-based controllers.
This method was experimentally validated on a steel bolting task using a 7-DOF Franka Panda robot. By recombining the primitives, we were also able to screw a cap onto containers of different sizes, placed in arbitrary configurations, using two different 7-DOF manipulators. The results show that our method generates position and orientation invariant, robot-agnostic controllers.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Brosque, C., Galbally, E., Khatib, O., Fischer, M.: Human-robot collaboration in construction: opportunities and challenges. In: Proceedings of the 2nd International Congress on Human-Computer Interaction, Optimization and Robotic Applications, HORA 2020 (2020). https://doi.org/10.1109/HORA49412.2020.9152888
Choi, T., Do, H., Park, D., Park, C., Kyung, J.: Bolting with the industrial dual-arm robot. In: 2014 11th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2014, pp. 484–485 (2014). https://doi.org/10.1109/URAI.2014.7057464
Edmonds, M., et al.: A tale of two explanations: enhancing human trust by explaining robot behavior. Technical report (2019). http://robotics.sciencemag.org/
Galbally, E., Jorda, M.: Real time collision detection and identification for robotic manipulators (2018). https://arxiv.org/abs/1802.00546v1
Herrero, E.G., Ho, J., Khatib, O.: Understanding and segmenting human demonstrations into reusable compliant primitives. In: 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 9437–9444 (2021). https://doi.org/10.1109/IROS51168.2021.9636523. https://ieeexplore.ieee.org/document/9636523/
Hogan, N.: Impedance control: an approach to manipulation. In: Proceedings of the American Control Conference, vol. 1, pp. 304–313 (1984). https://doi.org/10.23919/ACC.1984.4788393
Hoque, R., et al.: LazyDAgger: reducing context switching in interactive imitation learning (2021)
Jang, E., Vijayanarasimhan, S., Pastor, P., Ibarz, J., Levine, S.: End-to-end learning of semantic grasping (2017). https://arxiv.org/abs/1707.01932v3
Jorda, M.: Robust robotic manipulation for effective multi-contact and safe physical interactions. Ph.D. thesis, Stanford University (2020)
Khansari, M., Klingbeil, E., Khatib, O.: Adaptive human-inspired compliant contact primitives to perform surface–surface contact under uncertainty. Int. J. Robot. Res. 3513, 1651–1675 (2016). https://doi.org/10.1177/0278364916648389. https://doi-org.stanford.idm.oclc.org/10.1177/0278364916648389
Khatib, O.: A unified approach for motion and force control of robot manipulators: the operational space formulation. IEEE J. Robot. Autom. 3(1), 43–53 (1987). https://doi.org/10.1109/JRA.1987.1087068
Kim, H., Kwon, J., Oh, Y., You, B.J., Yang, W.: Weighted hybrid admittance-impedance control with human intention based stiffness estimation for human-robot interaction. In: IEEE International Conference on Intelligent Robots and Systems, pp. 6926–6931 (2018). https://doi.org/10.1109/IROS.2018.8594435
Kordia, A.H., Melo, F.S.: An end-to-end approach for learning and generating complex robot motions from demonstration. In: 16th IEEE International Conference on Control, Automation, Robotics and Vision, ICARCV 2020, pp. 1008–1014 (2020). https://doi.org/10.1109/ICARCV50220.2020.9305399
Lopes, M., Melo, F., Montesano, L., Santos-Victor, J.: Abstraction levels for robotic imitation: overview and computational approaches. Stud. Comput. Intell. 264, 313–355 (2010). https://doi.org/10.1007/978-3-642-05181-4_14. https://link.springer.com/chapter/10.1007/978-3-642-05181-4_14
Maples, J.A., Becker, J.J.: Experiments in force control of robotic manipulators, pp. 695–702 (1986). https://doi.org/10.1109/ROBOT.1986.1087590
Nam, H., Choi, W., Ryu, D., Lee, Y., Lee, S.H., Ryu, B.: Design of a bolting robot for constructing steel structure. In: International Conference on Control, Automation and Systems, ICCAS 2007, pp. 1946–1949 (2007). https://doi.org/10.1109/ICCAS.2007.4406667
Ott, C., Mukherjee, R., Nakamura, Y., Mukherjee, R., Nakamura, Y.: A hybrid system framework for unified impedance and admittance control. J. Intell. Robot. Syst. 78, 359–375 (2015). https://doi.org/10.1007/s10846-014-0082-1. www.sarcos.com
Park, J., Khatib, O.: A haptic teleoperation approach based on contact force control. Int. J. Robot. Res. 25(5-6), 575–591 (2016). https://doi.org/10.1177/0278364906065385. https://journals.sagepub.com/doi/abs/10.1177/0278364906065385
Rahmatizadeh, R., Abolghasemi, P., Boloni, L., Levine, S.: Vision-based multi-task manipulation for inexpensive robots using end-to-end learning from demonstration. In: Proceedings of the IEEE International Conference on Robotics and Automation, pp. 3758–3765 (2018). https://doi.org/10.1109/ICRA.2018.8461076
Shahdi, A., Sirouspour, S.: Adaptive/robust control for time-delay teleoperation. IEEE Trans. Rob. 25(1), 196–205 (2009). https://doi.org/10.1109/TRO.2008.2010963
Sharma, M., Kroemer, O.: Generalizing object-centric task-axes controllers using keypoints. Technical report (2013). https://deepai.org/publication/generalizing-object-centric-task-axes-controllers-using-keypoints
Acknowledgements
Thank you to everyone at the Stanford Robotics Lab! Special thanks as well to Toki Migimatsu for his invaluable help with the initial exploration of this work. Thank you also to Mikael for his guidance and to Marco Speziali for his help with rendering and grasping advice.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Herrero, E.G., Piedra, A., Brosque, C., Khatib, O. (2022). Parametrization of Compliant, Object-Level Controllers from Human Demonstrations. In: Altuzarra, O., Kecskeméthy, A. (eds) Advances in Robot Kinematics 2022. ARK 2022. Springer Proceedings in Advanced Robotics, vol 24. Springer, Cham. https://doi.org/10.1007/978-3-031-08140-8_42
Download citation
DOI: https://doi.org/10.1007/978-3-031-08140-8_42
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08139-2
Online ISBN: 978-3-031-08140-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)