Abstract
Finding objects in dense clutter and placing them in specific poses play an important role in robot manipulation in fields like warehousing and logistics, and have a significant influence on the automation of these fields. However, most methods that perform well in simple clutter do not hold up well in dense clutter because of severe stacking and occlusion between objects, which prevents the target objects from grasping successfully. In this paper, we propose an interactive exploration framework called AE-Reorient based on reinforcement learning to let robots learn the interactive exploration autonomously. AE-Reorient enables robots to actively find the target objects and accomplish the pick-and-place task. Our AE-Reorient generates iterative and interactive actions to improve the visibility of the target objects which is an important factor affecting the success of grasping. Specifically, we first collect the scene information through an RGB-D camera. Then, using the point cloud reconstruction and pose estimation methods to obtain the height map of the clutter, through which we generate the grasp pose or predict the position. We apply interaction to change the state of the scene by pushing if the grasp is unsuccessful. The generated push action is applied to disrupt and recreate a new state of the clutter with the target objects more exposed, which greatly improves the probability of grasp success. Robots can successfully perform pick-and-place tasks in dense clutter by applying our proposed framework. We test our AE-Reorient in 130 dense clutters and it enhances the success rate and the visibility of the target object by 7.60% and 4.10% compared with the baseline method.
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
References
Calli, B., Walsman, A., Singh, A., Srinivasa, S., Abbeel, P., Dollar, A.M.: Benchmarking in manipulation research: the ycb object and model set and benchmarking protocols. arXiv preprint arXiv:1502.03143 (2015)
Cheng, S., Mo, K., Shao, L.: Learning to regrasp by learning to place. arXiv preprint arXiv:2109.08817 (2021)
Coumans, E., Bai, Y.: Pybullet, a python module for physics simulation for games, robotics and machine learning (2016)
Huang, S., Wang, Z., Zhou, J., Jiwen, L.: Planning irregular object packing via hierarchical reinforcement learning. RAL 8(1), 81–88 (2022)
Liu, Z., Wang, Z., Huang, S., Zhou, J., Lu, J.: Ge-grasp: efficient target-oriented grasping in dense clutter. In: IROS, pp. 1388–1395 (2022)
Novkovic, T., Pautrat, R., Furrer, F., Breyer, M., Siegwart, R., Nieto, J.: Object finding in cluttered scenes using interactive perception. In: ICRA, pp. 8338–8344 (2020)
Raessa, M., Wan, W., Harada, K.: Planning to repose long and heavy objects considering a combination of regrasp and constrained drooping. Assem. Autom. 41(3), 324–332 (2021)
Tang, B., Sukhatme, G.S.: Selective object rearrangement in clutter. In: Conference on Robot Learning (2022)
Wada, K., James, S., Davison, A.J.: Reorientbot: learning object reorientation for specific-posed placement. In: ICRA, pp. 8252–8258 (2022)
Wang, Z., Jiwen, L., Ziyi, W., Zhou, J.: Learning efficient binarized object detectors with information compression. PAMI 44(6), 3082–3095 (2021)
Wang, Z., Jiwen, L., Zhou, J.: Learning channel-wise interactions for binary convolutional neural networks. PAMI 43(10), 3432–3445 (2020)
Wang, Z., Xiao, H., Duan, Y., Zhou, J., Lu, J.: Learning deep binary descriptors via bitwise interaction mining. PAMI 45, 1919–1933 (2022)
Wermelinger, M., Johns, R., Gramazio, F., Kohler, M., Hutter, M.: Grasping and object reorientation for autonomous construction of stone structures. RAL 6(3), 5105–5112 (2021)
Wu, Z., Wang, Z., Lu, J., Yan, H.: Category-level shape estimation for densely cluttered objects. arXiv preprint arXiv:2302.11983 (2023)
Wu, Z., Wang, Z., Wei, Z., Wei, Y., Yan, H.: Smart explorer: recognizing objects in dense clutter via interactive exploration. In: IROS, pp. 6600–6607 (2022)
Xu, P., Chen, Z., Wang, J., Meng, M.Q.H.: Planar manipulation via learning regrasping. arXiv preprint arXiv:2210.05349 (2022)
Xu, X., Wang, Z., Zhou, J., Lu, J.: Binarizing sparse convolutional networks for efficient point cloud analysis. arXiv preprint arXiv:2303.15493 (2023)
Ye, X., Yang, Y.: Efficient robotic object search via hiem: Hierarchical policy learning with intrinsic-extrinsic modeling. RAL 6(3), 4425–4432 (2021)
Yuan, S., Shao, L., Yako, C.L., Gruebele, A., Salisbury, J.K.: Design and control of roller grasper v2 for in-hand manipulation. In: IROS, pp. 9151–9158 (2020)
Zeng, A., Song, S., Welker, S., Lee, J., Rodriguez, A., Funkhouser, T.: Learning synergies between pushing and grasping with self-supervised deep reinforcement learning. In: IROS, pp. 4238–4245 (2018)
Acknowledgements
This work was supported in part by the National Natural Science Foundation of China under Grant 61976023 and Grant U22B2050.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Luo, H., Wu, Z., Yan, H. (2023). AE-Reorient: Active Exploration Based Reorientation for Robotic Pick-and-Place. In: Lu, H., et al. Image and Graphics . ICIG 2023. Lecture Notes in Computer Science, vol 14358. Springer, Cham. https://doi.org/10.1007/978-3-031-46314-3_22
Download citation
DOI: https://doi.org/10.1007/978-3-031-46314-3_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-46313-6
Online ISBN: 978-3-031-46314-3
eBook Packages: Computer ScienceComputer Science (R0)