Abstract
This work addresses the problem of retrieving a target object from cluttered environment using a robot manipulator. In the details, the proposed solution relies on a Task and Motion Planning approach based on a two-level architecture: the high-level is a Task Planner aimed at finding the optimal objects sequence to relocate, according to a metric based on the objects weight; the low-level is a Motion Planner in charge of planning the end-effector path for reaching the specific objects taking into account the robot physical constraints. The high-level task planner is a Reinforcement Learning agent, trained using the information coming from the low-level Motion Planner. In this work we consider the Q-Tree algorithm, which is based on a dynamic tree structure inspired by the Q-learning technique. Three different RL-policies with two kinds of tree exploration techniques (Breadth and Depth) are compared in simulation scenarios with different complexity. Moreover, the proposed learning methods are experimentally validated in a real scenario by adopting a KINOVA Jaco\(^{2}\) 7-DoFs robot manipulator.
Similar content being viewed by others
References
Correll, N., Bekris, K.E., Berenson, D., Brock, O., Causo, A., Hauser, K., Okada, K., Rodriguez, A., Romano, J.M., Wurman, P.R.: Analysis and observations from the first amazon picking challenge. IEEE Trans. Autom. Sci. Eng. 15(1), 172 (2016)
Ceola, F., Tosello, E., Tagliapietra, L., Nicola, G., Ghidoni S.: Robot task planning via deep reinforcement learning: a tabletop object sorting application. In: 2019 IEEE Int. Conf. on Systems, Man and Cybernetics (SMC), pp. 486–492. IEEE (2019)
Nam, C., Lee, J., Cheong, S.H., Cho, B.Y., Kim C.: Fast and resilient manipulation planning for target retrieval in clutter. In: 2020 IEEE Int. Conf. on Robotics and Automation (ICRA), pp. 3777–3783. IEEE (2020)
Lee, J., Cho, Y., Nam, C., Park, J., Kim, C.: Efficient obstacle rearrangement for object manipulation tasks in cluttered environments. In: 2019 Int. Conf. on Robotics and Automation (ICRA), pp. 183–189. IEEE (2019)
Stilman, M., Kuffner, J.: Planning among movable obstacles with artificial constraints. Int. Journ. Robot. Res. 27(11–12), 1295 (2008)
Hang, K., Stork, J.A., Pokorny, F.T., Kragic, D.: Combinatorial optimization for hierarchical contact-level grasping. In: 2014 IEEE Int. Conf. on Robotics and Automation (ICRA), pp. 381–388. IEEE (2014)
Stilman, M., Schamburek, J.U., Kuffner, J., Asfour, T.: Manipulation planning among movable obstacles. In Proceedings 2007 IEEE Int. Conf. on Robotics and Automation, pp. 3327–3332. IEEE (2007)
Yuan, W., Hang, K. Kragic, D., Wang, M.Y., Stork, J.A.: End-to-end nonprehensile rearrangement with deep reinforcement learning and simulation-to-reality transfer. Robotics and Autonomous Systems 119 (2019)
Haustein, J.A., King, J., Srinivasa, S.S., Asfour, T.: Kinodynamic randomized rearrangement planning via dynamic transitions between statically stable states. In: 2015 IEEE Int. Conf. on Robotics and Automation (ICRA), pp. 3075–3082. IEEE (2015)
Dantam, N.T., Kingston, Z.K., Chaudhuri, S., Kavraki, L.E.: Incremental task and motion planning: A constraint-based approach. In Robotics: Science and systems, vol. 12, p. 00052. Ann Arbor, MI, USA (2016)
Havur, G., Ozbilgin, G., Erdem, E., Patoglu, V.: Geometric rearrangement of multiple movable objects on cluttered surfaces: A hybrid reasoning approach. In: 2014 IEEE Int. Conf. on Robotics and Automation (ICRA), pp. 445–452. IEEE (2014)
Karami, H., Thomas, A., Mastrogiovanni, F.: A task-motion planning framework using iteratively deepened and/or graph networks. arXiv:2104.01549 (2021)
Eppe, M., Nguyen, P.D., Wermter, S.: From semantics to execution: Integrating action planning with reinforcement learning for robotic causal problemsolving. Front. Robot. AI 6, 123 (2019)
Bonet, B., Geffner, H.: Planning as heuristic search. Artif. Intell. 129(1–2), 5 (2001)
Qureshi, A.H., Mousavian, A., Paxton, C., Yip, M.C., Fox, D.: Nerp: Neural rearrangement planning for unknown objects. arXiv:2106.01352 (2021)
Mohammed, M.Q., Chung, K.L., Chyi, C.S.: Review of deep reinforcement learning-based object grasping: Techniques, open challenges and recommendations. IEEE Access (2020)
Kormushev, P., Calinon, S., Caldwell, D.G.: Reinforcement learning in robotics: Applications and real-world challenges. Robotics 2(3), 122 (2013)
Bejjani, W., Agboh, W.C., Dogar, M.R., Leonetti, M.: Occlusion-aware search for object retrieval in clutter. In: 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4678–4685. IEEE (2021)
Deng, Y., Guo, X., Wei, Y., Lu, K., Fang, B., Guo, D., Liu, H., Sun, F.: Deep reinforcement learning for robotic pushing and picking in cluttered environment. In 2019 IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), pp. 619–626. IEEE (2019)
Wu, B., Akinola, I., Allen, P.K.: Pixel-attentive policy gradient for multi-fingered grasping in cluttered scenes. In: 2019 IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), pp. 1789–1796. IEEE (2019)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436 (2015)
Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.: Playing atari with deep reinforcement learning. arXiv:1312.5602 (2013)
Mnih, V., Badia, A.P., Mirza, M., Graves, A., Lillicrap, T., Harley, T., Silver, D., Kavukcuoglu, K.: Asynchronous methods for deep reinforcement learning. In: Int. Conf. on Machine Learning, pp. 1928–1937. PMLR (2016)
Golluccio, G., Di Vito, D., Marino, A., Bria, A., Antonelli, G.: Task-motion planning via tree-based q-learning approach for robotic object displacement in cluttered spaces. In: Proceedings of the 18th Int. Conf. on Informatics in Control, Automation and Robotics - ICINCO. INSTICC, pp. 130–137. SciTePress (2021) https://doi.org/10.5220/0010542601300137
Golluccio, G., Di Vito, D., Marino, A., Antonelli, G.: Robotic weight-based object relocation in clutter via tree-based q-learning approach using breadth and depth search techniques. In 2021 20th Int. Conf. on Advanced Robotics (ICAR), pp. 676–681. IEEE (2021)
Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3–4), 279 (1992)
Di Vito, D., Bergeron, M., Meger, D., Dudek, G., Antonelli, G.: Dynamic planning of redundant robots within a set-based task-priority inverse kinematics framework. In 2020 IEEE Conf. on Control Technology and Applications (CCTA), pp. 549–554. IEEE (2020)
Kuffner, J.J., LaValle, S.M.: Rrt-connect: An efficient approach to singlequery path planning. In: Proceedings 2000 ICRA. Millennium Conference. IEEE Int. Conf. on Robotics and Automation. Symposia Proceedings (Cat. No. 00CH37065), vol. 2, pp. 995–1001. IEEE (2000),
Chiaverini, S.: Singularity-robust task-priority redundancy resolution for real-time kinematic control of robot manipulators. IEEE Trans. Robot. Autom. 13(3), 398 (1997)
Siciliano, B., Slotine, J.J.E.: A general framework for managing multiple tasks in highly redundant robotic systems. In: Proc. Fifth Int. Conf. on Advanced Robotics (ICAR), pp. 1211–1216. IEEE, Pisa (1991) https://doi.org/10.1109/ICAR.1991.240390
Di Lillo, P., Arrichiello, F., Di Vito, D., Antonelli, G.: BCIcontrolled assistive manipulator: developed architecture and experimental results. IEEE Trans. Cognitive Development. Syst. pp. 1–1 (2020). https://doi.org/10.1109/TCDS.2020.2979375
Di Lillo, P., Simetti, E., Wanderlingh, F., Casalino, G., Antonelli, G.: Underwater intervention with remote supervision via satellite communication: Developed control architecture and experimental results within the dexrov project. IEEE Trans. Control Syst. Technol. 29(1), 108 (2021). https://doi.org/10.1109/TCST.2020.2971440
Garrido-Jurado, S., Muñoz-Salinas, R., Madrid-Cuevas, F.J., Marín-Jiménez, M.J.: Automatic generation and detection of highly reliable fiducial markers under occlusion. Patt. Recognit. 47(6), 2280 (2014)
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: Proceedings of the IEEE Conf. on Computer Vision and Pattern Recognition, pp. 779–788 (2016)
Funding
The Authors declare that this work was supported by Dipartimento di Eccellenza granted to DIEI Department, University of Cassino and Southern Lazio, by H2020-ICT project CANOPIES (Grant Agreement N. 101016906) and by POR FSE LAZIO 2014-2020, Project DE G06374/2021.
Author information
Authors and Affiliations
Contributions
All Authors have contributed equally to the ideas, theories and analysis of results. The first draft of the manuscript was written by Giacomo Golluccio. Paolo Di Lillo, Daniele Di Vito, Alessandro Marino and Gianluca Antonelli commented and revised this first version. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflicts of interest
The Authors declare that they have no conflict of interest.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Golluccio, G., Di Lillo, P., Di Vito, D. et al. Objects Relocation in Clutter with Robot Manipulators via Tree-based Q-Learning Algorithm: Analysis and Experiments. J Intell Robot Syst 106, 44 (2022). https://doi.org/10.1007/s10846-022-01719-9
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10846-022-01719-9