Consumption and Realization of Conditional Convolutional Variational Autoencoder for Robot Trajectory Learning
Keywords:
Variational Autoencoder, Robotics, Deep Learning, Machine Learning, Trajectory Continuous TaskAbstract
Learning‐based motion planning methods have recently shown notable advantages in solving multiple planning challenges in high‐dimensional spaces and challenging situations. The complex higher‐dimensional trajectory with many constraints makes the robot task generation complicated. Furthermore, the availability of a sizeable robot open dataset for path learning is a significant challenge. In this work, a variant of Conditional Variational Autoencoder with Convolutional Neural network is utilised to capture each task’s hidden probability distribution and generated back from the latent representation. The proposed approaches focuses on a generative model for offline generation of trajectory continuous task under static structured environment. The implemented model interfaced with the Robot Operating System (ROS) layer, which can directly feed into any ROS enabled robots. Reconstructed error, precision and accuracy were evaluated by the experiment of robot trajectory with reconstructed trajectory and yielded encouraging results.
Downloads
References
H. Ravichandar, A. S. Polydoros, S. Chernova, and A. Billard, “Recent Advances in Robot Learning from Demonstration,” Annu. Rev. Control Robot. Auton. Syst., vol. 3, no. 1, pp. 297–330, May 2020, doi: 10.1146/annurev-control-100819-063206.
S. Cebollada, L. Payá, M. Flores, A. Peidró, and O. Reinoso, “A state-of-the-art review on mobile robotics tasks using artificial intelligence and visual data,” Expert Syst. Appl., vol. 167, p. 114195, Apr. 2021, doi: 10.1016/j.eswa.2020.114195.
F. Zacharias, C. Borst, M. Beetz, and G. Hirzinger, “Positioning mobile manipulators to perform constrained linear trajectories,” in 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, Sep. 2008, pp. 2578–2584. doi: 10.1109/IROS.2008.4650617.
G. B. Avanzini, A. M. Zanchettin, and P. Rocco, “Constraint-based Model Predictive Control for holonomic mobile manipulators,” in 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Sep. 2015, pp. 1473–1479. doi: 10.1109/IROS.2015.7353562.
Q.-N. Nguyen and Q.-C. Pham, “Planning Optimal Trajectories for Mobile Manipulators under End-effector Trajectory Continuity Constraint,” 2023, doi: 10.48550/ARXIV.2309.12251.
R. Li, M. Liu, J. Teutsch, and D. Wollherr, “Constraint trajectory planning for redundant space robot,” Neural Comput. Appl., vol. 35, no. 34, pp. 24243–24258, Dec. 2023, doi: 10.1007/s00521-023-08972-5.
Q.-N. Nguyen, N. Adrian, and Q.-C. Pham, “Task-Space Clustering for Mobile Manipulator Task Sequencing,” 2023, doi: 10.48550/ARXIV.2305.17345.
J. Xu, Y. Domae, T. Ueshiba, W. Wan, and K. Harada, “Planning a Minimum Sequence of Positions for Picking Parts From Multiple Trays Using a Mobile Manipulator,” IEEE Access, vol. 9, pp. 165526–165541, 2021, doi: 10.1109/ACCESS.2021.3135374.
R. Malhan and S. K. Gupta, “Finding Optimal Sequence of Mobile Manipulator Placements for Automated Coverage Planning of Large Complex Parts,” in Volume 2: 42nd Computers and Information in Engineering Conference (CIE), St. Louis, Missouri, USA: American Society of Mechanical Engineers, Aug. 2022, p. V002T02A006. doi: 10.1115/DETC2022-90105.
L. Velazquez, G. Palardy, and C. Barbalata, “A robotic 3D printer for UV-curable thermosets: dimensionality prediction using a data-driven approach,” Int. J. Comput. Integr. Manuf., pp. 1–18, Sep. 2023, doi: 10.1080/0951192X.2023.2257652.
J. Sustarevas, D. Kanoulas, and S. Julier, “Task-Consistent Path Planning for Mobile 3D Printing,” in 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Sep. 2021, pp. 2143–2150. doi: 10.1109/IROS51168.2021.9635916.
K. Nagatani, T. Hirayama, A. Gofuku, and Y. Tanaka, “Motion planning for mobile manipulator with keeping manipulability,” in IEEE/RSJ International Conference on Intelligent Robots and Systems, Sep. 2002, pp. 1663–1668 vol.2. doi: 10.1109/IRDS.2002.1043994.
H. Ha, S. Agrawal, and S. Song, “Fit2Form: 3D Generative Model for Robot Gripper Form Design,” 2020, doi: 10.48550/ARXIV.2011.06498.
S. Kumra, S. Joshi, and F. Sahin, “Antipodal Robotic Grasping using Generative Residual Convolutional Neural Network,” 2019, doi: 10.48550/ARXIV.1909.04810.
J. J. Bird, A. Naser, and A. Lotfi, “Writer-independent signature verification; Evaluation of robotic and generative adversarial attacks,” Inf. Sci. Int. J., vol. 633, no. C, pp. 170–181, Jul. 2023, doi: 10.1016/j.ins.2023.03.029.
D. Ha and D. Eck, “A Neural Representation of Sketch Drawings,” 2017, doi: 10.48550/ARXIV.1704.03477.
F. Chao et al., “An LSTM Based Generative Adversarial Architecture for Robotic Calligraphy Learning System,” Sustainability, vol. 12, no. 21, p. 9092, Oct. 2020, doi: 10.3390/su12219092.
Y. Shao and C.-L. Liu, “Teaching machines to write like humans using L-attributed grammar,” Eng. Appl. Artif. Intell., vol. 90, p. 103489, Apr. 2020, doi: 10.1016/j.engappai.2020.103489.
G. E. Hinton and R. R. Salakhutdinov, “Reducing the Dimensionality of Data with Neural Networks,” Science, vol. 313, no. 5786, pp. 504–507, Jul. 2006, doi: 10.1126/science.1127647.
D. P. Kingma and M. Welling, “Auto-Encoding Variational Bayes,” 2013, doi: 10.48550/ARXIV.1312.6114.
K. O’Shea and R. Nash, “An Introduction to Convolutional Neural Networks,” 2015, doi: 10.48550/ARXIV.1511.08458.
B. Zhang and P. Liu, “Control and benchmarking of a 7-DOF robotic arm using Gazebo and ROS,” PeerJ Comput. Sci., vol. 7, p. e383, Mar. 2021, doi: 10.7717/peerj-cs.383.
J. Denavit and R. S. Hartenberg, “A Kinematic Notation for Lower-Pair Mechanisms Based on Matrices,” J. Appl. Mech., vol. 22, no. 2, pp. 215–221, Jun. 1955, doi: 10.1115/1.4011045.
I. A. Sucan, M. Moll, and L. E. Kavraki, “The Open Motion Planning Library,” IEEE Robot. Autom. Mag., vol. 19, no. 4, pp. 72–82, Dec. 2012, doi: 10.1109/MRA.2012.2205651.
S. Chitta, I. Sucan, and S. Cousins, “MoveIt! [ROS Topics],” IEEE Robot. Autom. Mag., vol. 19, no. 1, pp. 18–19, Mar. 2012, doi: 10.1109/MRA.2011.2181749.
M. Quigley et al., “ROS: an open-source Robot Operating System,” in ICRA workshop on open source software, Kobe, Japan, 2009, p. 5.
M. Cashmore et al., “ROSPlan: Planning in the Robot Operating System,” Proc. Int. Conf. Autom. Plan. Sched., vol. 25, pp. 333–341, Apr. 2015, doi: 10.1609/icaps.v25i1.13699.
A. Koubaa, Ed., Robot Operating System (ROS): The Complete Reference (Volume 6), vol. 962. in Studies in Computational Intelligence, vol. 962. Cham: Springer International Publishing, 2021. doi: 10.1007/978-3-030-75472-3.
A. Collette, Python and HDF5, First edition. Beijiing: O’Reilly, 2014.
D. Bank, N. Koenigstein, and R. Giryes, “Autoencoders,” 2020, doi: 10.48550/ARXIV.2003.05991.
D. E. Rumelhart and J. L. McClelland, “Learning Internal Representations by Error Propagation,” in Parallel Distributed Processing: Explorations in the Microstructure of Cognition: Foundations, MIT Press, 1987, pp. 318–362. Accessed: Feb. 19, 2024. [Online]. Available: https://ieeexplore.ieee.org/document/6302929
P. Baldi, “Autoencoders, unsupervised learning and deep architectures,” in Proceedings of the 2011 International Conference on Unsupervised and Transfer Learning workshop - Volume 27, in UTLW’11. Washington, USA: JMLR.org, Jul. 2011, pp. 37–50.
A. Radford, L. Metz, and S. Chintala, “Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks,” 2015, doi: 10.48550/ARXIV.1511.06434.
J. M. Joyce, “Kullback-Leibler Divergence,” in International Encyclopedia of Statistical Science, M. Lovric, Ed., Berlin, Heidelberg: Springer Berlin Heidelberg, 2011, pp. 720–722. doi: 10.1007/978-3-642-04898-2_327.
ISO, “Manipulating industrial robots Performance criteria and related test methods.” International Organization for Standardization, Geneva, CH, Apr. 1998. Accessed: Feb. 19, 2024. [Online]. Available: https://www.iso.org/standard/22244.html
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
