Weitere Artikel dieser Ausgabe durch Wischen aufrufen
The online version of this article (https://doi.org/10.1007/s10514-018-9799-1) contains supplementary material, which is available to authorized users.
This work was supported by: the Innovate UK KTP partnership 9573 between KUKA UK and University of Birmingham; EU H2020 RoMaNS, 645582; EPSRC Grant EP/M026477/1. We also acknowledge MoD/Dstl and EPSRC for supporting Aleš Leonardis’ involvement in this work, via an ONR MURI project.
Marturi and Kopicki are identified as joint lead authors of this work.
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This paper shows how a robot arm can follow and grasp moving objects tracked by a vision system, as is needed when a human hands over an object to the robot during collaborative working. While the object is being arbitrarily moved by the human co-worker, a set of likely grasps, generated by a learned grasp planner, are evaluated online to generate a feasible grasp with respect to both: the current configuration of the robot respecting the target grasp; and the constraints of finding a collision-free trajectory to reach that configuration. A task-based cost function enables relaxation of motion-planning constraints, enabling the robot to continue following the object by maintaining its end-effector near to a likely pre-grasp position throughout the object’s motion. We propose a method of dynamic switching between: a local planner, where the hand smoothly tracks the object, maintaining a steady relative pre-grasp pose; and a global planner, which rapidly moves the hand to a new grasp on a completely different part of the object, if the previous graspable part becomes unreachable. Various experiments are conducted using a real collaborative robot and the obtained results are discussed.
Supplementary material 1 (mp4 21761 KB)
Aldoma, A., Marton, Z. C., Tombari, F., Wohlkinger, W., Potthast, C., Zeisl, B., et al. (2012). Point cloud library. IEEE Robotics & Automation Magazine, 19(3), 80–91. CrossRef
Bekiroglu, Y., Damianou, A., Detry, R., Stork, J. A., Kragic, D., & Ek, C. H. (2016). Probabilistic consolidation of grasp experience. In Proceedings of the IEEE International Conference on Robotics and Automation, pp. 193–200. https://doi.org/10.1109/ICRA.2016.7487133.
Choi, C., & Christensen, H. I. (2013). Rgb-d object tracking: A particle filter approach on gpu. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 1084–1091.
Fontanals, J., Dang-Vu, B. A., Porges, O., Rosell, J., & Roa, M. A. (2014a). Integrated grasp and motion planning using independent contact regions. In Proceedings of the International Conference on Humanoid Robots, pp. 887–893. https://doi.org/10.1109/HUMANOIDS.2014.7041469.
Fontanals, J., Dang-Vu, B. A., Porges, O., Rosell, J., & Roa, M. A. (2014b). Integrated grasp and motion planning using independent contact regions. In Proceedings of the IEEE-RAS International Conference on Humanoid Robots, pp. 887–893. https://doi.org/10.1109/HUMANOIDS.2014.7041469.
Fukui, S., Hayakawa, S., Iwahori, Y., Nakamura, T., & Bhuyan, M. (2016). Particle filter based tracking with image-based localization. Procedia Computer Science, 96, 977–986. CrossRef
Horowitz, M. B., & Burdick, J. W. (2012). Combined grasp and manipulation planning as a trajectory optimization problem. In Proceedings of the IEEE IEEE International Conference on Robotics and Automation, pp. 584–591. https://doi.org/10.1109/ICRA.2012.6225104.
Houshangi, N. (1990). Control of a robotic manipulator to grasp a moving target using vision. In Proceedings of the IEEE International Conference on Robotics and Automation, pp. 604–609 vol. 1. https://doi.org/10.1109/ROBOT.1990.126048.
Hsiao, K., Chitta, S., Ciocarlie, M., & Jones. E. G. (2010). Contact-reactive grasping of objects with partial shape information. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 1228–1235. https://doi.org/10.1109/IROS.2010.5649494.
Kitaev, N., Mordatch, I., Patil, S., & Abbeel, P. (2015). Physics-based trajectory optimization for grasping in cluttered environments. In Proceedings of the IEEE International Conference on Robotics and Automation, pp. 3102–3109. https://doi.org/10.1109/ICRA.2015.7139625.
Kopicki, M. (2010). Prediction learning in robotic manipulation. Ph.D. thesis, University of Birmingham.
Kopicki, M., Detry, R., Schmidt, F., Borst, C., Stolkin, R., & Wyatt, J. L. (2014). Learning dextrous grasps that generalise to novelobjects by combining hand and contact models. In Proceedings of the IEEE International Conference on Robotics and Automation, IEEE, pp. 5358–5365.
Kopicki, M., Detry, R., Adjigble, M., Stolkin, R., Leonardis, A., & Wyatt, J. L. (2016). One-shot learning and generation of dexterous grasps for novel objects. International Journal of Robotics Research, 35(8), 959–976. CrossRef
Lenz, I., Lee, H., & Saxena, A. (2015). Deep learning for detecting robotic grasps. International Journal of Robotics Research, 34(4–5), 705–724. CrossRef
Levine, S., Pastor, P., Krizhevsky, A., & Quillen, D. (2016). Learning hand-eye coordination for robotic grasping with large-scale data collection. In International Symposium on Experimental Robotics, Springer, pp. 173–184.
Li, M., Bekiroglu, Y., Kragic, D., & Billard, A. (2014). Learning of grasp adaptation through experience and tactile sensing. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 3339–3346.
Ma, M., Marturi, N., Li, Y., Stolkin, R., & Leonardis, A. (2016). A local-global coupled-layer puppet model for robust online human pose tracking. Computer Vision and Image Understanding, 153, 163–178. CrossRef
Magnusson, M. (2009). The three-dimensional normal-distributions transform: An efficient representation for registration, surface analysis, and loop detection. Ph.D. thesis, Örebro universitet.
Marturi, N., Ortenzi, V., Xiao, J., Adjigble, M., Stolkin, R., & Leonardis, A. (2015). A real-time tracking and optimised gaze control for a redundant humanoid robot head. In Proceedings of the IEEE-RAS International Conference on Humanoid Robots, pp. 467–474.
Menon, A., Cohen, B., & Likhachev, M. (2014). Motion planning for smooth pickup of moving objects. In Proceedings of the IEEE International Conference on Robotics and Automation, pp. 453–460. https://doi.org/10.1109/ICRA.2014.6906895.
Ortenzi, V., Marturi, N., Stolkin, R., Kuo, J. A., & Mistry, M. (2016). A vision-guided approach to estimate the configuration of an under-sensored manipulator. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 3567–3574. https://doi.org/10.1109/IROS.2016.7759525.
Roa, M. A., & Suárez, R. (2015). Grasp quality measures: Review and performance. Autonomous Robots, 38(1), 65–88. CrossRef
Rusinkiewicz, S., & Levoy, M. (2001). Efficient variants of the icp algorithm. In International Conference on 3-D Digital Imaging and Modeling, IEEE, pp. 145–152.
Sauser, E. L., Argall, B., Metta, G., & Billard, A. (2012). Iterative learning of grasp adaptation through human corrections. Robotics and Autonomous Systems, 60(1), 55–71. CrossRef
Smith, C. E., & Papanikolopoulos, N. P. (1995). Grasping of static and moving objects using a vision-based control approach. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, vol 1, pp. 329–334 vol. 1. https://doi.org/10.1109/IROS.1995.525816.
Soto, A. (2005). Self adaptive particle filter. In Proceedings of the 19th International Joint Conference on Artificial Intelligence, Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, IJCAI’05. pp. 1398–1403. http://dl.acm.org/citation.cfm?id=1642293.1642515.
Vogel, J., Hertkorn, K., Menon, R. U., & Roa, M. A. (2016). Flexible,semi-autonomous grasping for assistive robotics. In Proceedings of the IEEE International Conference on Robotics and Automation, IEEE, pp. 4872–4879.
Wu, Y., Lim, J., & Yang, M. H. (2013). Online object tracking: A benchmark. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2411–2418.
Zhang, M., & Buehler, M. (1994). Sensor-based online trajectory generation for smoothly grasping moving objects. In IEEE International Symposium on Intelligent Control, pp. 141–146. https://doi.org/10.1109/ISIC.1994.367827.
- Dynamic grasp and trajectory planning for moving objects
- Springer US
Print ISSN: 0929-5593
Elektronische ISSN: 1573-7527
Neuer Inhalt/© Filograph | Getty Images | iStock