Abstract
In learning robotics, techniques such as Learning from Demonstrations (LfD) and Reinforcement Learning (RL) have become widely popular among developers. However, this approximations can result in inefficient strategies when it comes to train more than one agent interacting in the same space with several objects and unknown obstacles. To solve this problematic, Reinforcement Learning from Demonstration (RLfD) allows the agent to learn and evaluate its performance from a set of demonstrations provided by a human expert while generalising from them using RL training. In dual-robot applications this approach is suitable for training agents that perform collaborative tasks. For this reason, a dual-robot haptic interface has been designed in order to produce dual manipulation trajectories to feed a RLfD agent. Haptics allows to perform high quality demonstrations following an impedance control approach. Trajectories obtained will be used as positive demonstrations so the training environment can generate automatic ones. As a result, this dual-robot haptic interface will provide a few trajectory demonstrations on dual manipulation in order to train agents using RL strategies. The aim of this research is to generate trajectories with this dual-robot haptic interface to train one or more agents following RLfD paradigms. Results show that trajectories performed with this interface present less error and deviation than others performed with a non-haptic interface, increasing the quality of the training data.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Argall, B. D., Chernova, S., Veloso, M., Browning, B.: A survey of robot learning from demonstration. In: Robotics and Autonomous Systems, vol. 57, pp. 469-483. Elsevier (2009). https://doi.org/10.1016/j.robot.2008.10.024
Calli, B., et al.: Yale-CMU-Berkeley dataset for robotic manipulation research. Int. J. Robot. Res. 36, 261–268. SAGE Publications Sage UK (2017). https://doi.org/10.1177/0278364917700714
Chen, Q., Dallas, E., Shahverdi, P., Korneder, J., Rawashdeh, O. A., Geoffrey Louie, W. -Y.: A sample efficiency improved method via hierarchical reinforcement learning networks. In: 2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), pp. 1498-1505. IEEE (2022). https://doi.org/10.1109/RO-MAN53752.2022.9900738
Clark, J. P., Lentini, G., Barontini, F., Catalano, M. G., Bianchi, M., O’Malley, M. K.: On the role of wearable haptics for force feedback in teleimpedance control for dual-arm robotic teleoperation. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 5187-5193. IEEE (2019). https://doi.org/10.1109/ICRA.2019.8793652
Corke, P. I.: A simple and systematic approach to assigning Denavit–Hartenberg parameters. IEEE Trans. Robot. 23, 590–594. IEEE (2007). https://doi.org/10.1109/TRO.2007.896765
De Coninck, E., Verbelen, T., Van Molle, P., Simoens, P., Dhoedt, B.: Learning robots to grasp by demonstration. Robot. Auton. Syst. 127, 103474. Elsevier (2020). https://doi.org/10.1016/j.robot.2020.103474
Gao, Q., Ju, Z., Chen, Y., Wang, Q., Zhao, Y., Lai, S.: Parallel dual-hand detection by using hand and body features for robot teleoperation. IEEE Trans. Hum.-Mach. Syst. 53(2), 417-426. IEEE (2023). https://doi.org/10.1109/THMS.2023.3243774
Girbés-Juan, V., Schettino, V., Demiris, Y., Tornero, J.: Haptic and visual feedback assistance for dual-arm robot teleoperation in surface conditioning tasks. IEEE Trans. Haptics 14(1), 44–56. IEEE (2021). https://doi.org/10.1109/TOH.2020.3004388
Girbés-Juan, V., Schettino, V., Gracia, L., Solanes, J.E., Demiris, Y., Tornero, J.: Combining haptics and inertial motion capture to enhance remote control of a dual-arm robot. J. Multimodal User Interfaces 16, 219–238 (2022). https://doi.org/10.1007/s12193-021-00386-8
Hu, H., Zhao, Z., Yang, X., Lou, Y.: A Learning from Demonstration Method for Robotic Assembly with a Dual-Sub-6-DoF Parallel Robot. In: 2021 WRC Symposium on Advanced Robotics and Automation (WRC SARA), pp. 73-78. IEEE (2021). https://doi.org/10.1109/WRCSARA53879.2021.9612676
Arulkumaran, K., Deisenroth, M.P., Brundage, M., Bharath, A.A.: Deep reinforcement learning: a brief survey. IEEE Signal Process. Mag. 34(6), 26–38. IEEE (2017). https://doi.org/10.1109/MSP.2017.2743240
Kyrarini, M., Zheng, Q., Haseeb, M. A., Gräser, A.: Robot learning of assistive manipulation tasks by demonstration via head gesture-based interface. In: 2019 IEEE 16th International Conference on Rehabilitation Robotics (ICORR), pp. 1139–1146. IEEE (2019). https://doi.org/10.1109/ICORR.2019.8779379
Laghi, M., et al.: Shared-autonomy control for intuitive bimanual tele-manipulation. In: 2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids), pp. 1-9. IEEE (2019). https://doi.org/10.1109/HUMANOIDS.2018.8625047
Li, Y.: Deep reinforcement learning: an overview. In: arXiv preprint arXiv:1701.07274 (2017)
Lindner, T., Milecki, A.: Reinforcement learning-based algorithm to avoid obstacles by the anthropomorphic robotic arm. Appl. Sci. (2022). https://doi.org/10.3390/app12136629
Love, L.J., Book, W.J.: Force reflecting teleoperation with adaptive impedance control. In: IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 34, pp. 159–165. IEEE (2004). https://doi.org/10.1109/TSMCB.2003.811756
Nair, A., McGrew, B., Andrychowicz, M., Zaremba, W., Abbeel P.: Overcoming exploration in reinforcement learning with demonstrations. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 6292–6299. Arxiv arXiv:1709.10089 (2018)
Ramírez, J., Yu, W., Perrusquía, A.: Model-free reinforcement learning from expert demonstrations: a survey. Artif. Intell. Rev. 55, 3213–3241. Springer (2022). https://doi.org/10.1007/s10462-021-10085-1
Ravichandar, H., Polydoros, A. S., Chernova, S., Billard, A.: Recent advances in robot learning from demonstration. In: Annual Review of Control, Robotics, and Autonomous Systems, pp. 297–330. Annual Reviews (2020). https://doi.org/10.1146/annurev-control-100819-063206
Sasaki, M., Muguro, J., Kitano, F., Njeri, W., Matsushita, K.: Sim-real mapping of an image-based robot arm controller using deep reinforcement learning. Appl. Sci. (2022). https://doi.org/10.3390/app122010277
Selvaggio, M., Abi-Farraj, F., Pacchierotti, C., Giordano, P. R., Siciliano, B.: Haptic-based shared-control methods for a dual-arm system. IEEE Robot. Autom. Lett. 3(4), 4249–4256. IEEE (2018). https://doi.org/10.1109/LRA.2018.2864353
Si, W., Wang, N., Yang, C.: A review on manipulation skill acquisition through teleoperation-based learning from demonstration. Cogn. Comput. Syst. 3, 1–16. Wiley Online Library (2021). https://doi.org/10.1049/ccs2.12005
Sun, X., Li, J., Kovalenko, A. V., Feng, W., Ou, Y.: Integrating reinforcement learning and learning from demonstrations to learn nonprehensile manipulation. IEEE Trans. Autom. Sci. Eng. 20(3), 1735–1744. IEEE (2023). https://doi.org/10.1109/TASE.2022.3185071
Turlapati, S. H., Campolo, D.: Towards haptic-based dual-arm manipulation. Sensors 23, 376. MDPI (2022). https://doi.org/10.3390/s23010376
Wu, R., Zhang, H., Peng, T., Fu, L., Zhao, J.: Variable impedance interaction and demonstration interface design based on measurement of arm muscle co-activation for demonstration learning. In: Biomedical Signal Processing and Control, pp. 8–18. Elsevier (2019). https://doi.org/10.1016/j.bspc.2019.02.008
Xie, Z.W., Zhang, Q., Jiang, Z.N., Liu, H.: Robot learning from demonstration for path planning: a review. Sci. China Technol. Sci. 63(8), 1325–1334 (2020). https://doi.org/10.1007/s11431-020-1648-4
Zhang, Y., Zhao, X., Tao, B., Ding, H.: Multi-objective synchronization control for dual-robot interactive cooperation using nonlinear model predictive policy. IEEE Trans. Ind. Electron. 70, 582–593. IEEE (2022). https://doi.org/10.1109/TIE.2022.3150090
Zhang, S., Xia, Q., Chen, M., Cheng, S.: Multi-objective optimal trajectory planning for robotic arms using deep reinforcement learning. Sensors (2023). https://doi.org/10.3390/s23135974
Zhao, W., Queralta, J. P., Westerlund, T.: Sim-to-real transfer in deep reinforcement learning for robotics: a survey. In: 2020 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 737–744, IEEE (2020). https://doi.org/10.1109/SSCI47803.2020.9308468
Acknowledgement
Research work was funded by the Spanish Government through the project PID2021-122685OB-I00.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Frau-Alfaro, D., Puente, S.T., Páez-Ubieta, I.d.L. (2024). Trajectory Generation Using Dual-Robot Haptic Interface for Reinforcement Learning from Demonstration. In: Marques, L., Santos, C., Lima, J.L., Tardioli, D., Ferre, M. (eds) Robot 2023: Sixth Iberian Robotics Conference. ROBOT 2023. Lecture Notes in Networks and Systems, vol 976. Springer, Cham. https://doi.org/10.1007/978-3-031-58676-7_36
Download citation
DOI: https://doi.org/10.1007/978-3-031-58676-7_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-58675-0
Online ISBN: 978-3-031-58676-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)