OBJECT IDENTIFICATION METHOD FOR INTEGRATION WITH ROBOTIC SYSTEMS
Keywords:
Selective laser sintering, object detection, neural network, data generation, object change modelingAbstract
The aim of the research is to develop a methodology for identifying and determining the location of objects
under conditions of low visibility and potential changes in their shape, with a focus on extracting parts
created using selective laser sintering (SLS) from a powder medium. The study examines two fundamentally
different approaches to forming control algorithms for a robotic manipulator. The first approach, trust-based, is
based on the assumption of minimal displacement of the object during manipulation. The manipulator moves
along a trajectory calculated from a preliminary three-dimensional model without correction until the moment
of capture. This method is characterized by high operational speed and minimal computational costs. However,
it carries risks such as object deformation due to environmental resistance, displacement of the part upon contact
with the tool, and the inability to capture the object if it deviates significantly from its nominal position.
The second approach, cautious, involves the gradual removal of powder layers to visualize the object and adjust
the trajectory before capture. This method includes several stages: removing the top layer of the medium to
partially expose the part, analyzing data to refine the object's position, and constructing an adaptive trajectory
considering possible displacement. Special attention in the article is given to data generation for training neural
networks, which are used for object identification under noisy conditions. Two methods of artificial modeling of
powder coatings are considered. The primitive method involves expanding the vertices of a three-dimensional
model along their normals with the addition of random noise. The improved method proposes differentiated
powder distribution considering local surface curvature. Subsequent experimental results showed that training a
neural network using real data has low efficiency. Recognition accuracy ranged from 60% to 75%, which is
attributed to the small sample size and the influence of external factors such as lighting and interference. At the
same time, the use of synthetic data, prepared according to the methodology presented in the study, increased
recognition accuracy to 92%. The practical significance of the work lies in the development of a methodology
for searching, detecting, and identifying a part immersed in powder, which can be used to automate postprocessing
processes in industries utilizing selective laser sintering. The developed solutions are adapted for
integration into robotic systems operating under conditions of limited visibility. The proposed methods can be
scaled to a wide range of tasks in additive manufacturing and robotics, making them promising for implementation
in industrial processes.
References
1. Waltermann R.D. Method and system for locating objects, US7049960B2, 23 май 2006 г.
2. Janabi-Sharifi F. Collision: Modeling, simulation and identification of robotic manipulators interacting
with environments, J. Intell. Robot. Syst., May 1995, Vol. 13, Issue 1, pp. 1-44. DOI:
10.1007/BF01664754.
3. Wojcienchowski C.R., Steele D.S., and Scudder H.J. III. Device for method for manipulating a part,
4802195, 31 January 1989.
4. Abbe E. and Sandon C. On the universality of deep learning, Advances in Neural Information Processing
Systems. Curran Associates, Inc., 2020, pp. 20061-20072.
5. Comprehensive system based on a DNN and LSTM for predicting sinter composition, Appl. Soft
Comput., October 2020, Vol. 95, pp. 106574. DOI: 10.1016/J.ASOC.2020.106574.
6. Ahmd W.A. Data preprocessing for neural networks, в IEEE Students Conference, ISCON ’02. Proceedings,
August 2002, 6-6. DOI: 10.1109/ISCON.2002.1214589.
7. Lopez E. et al. Evaluation of 3D-printed parts by means of high-performance computer tomography,
J. Laser Appl., June 2018, Vol. 30, Issue 3, pp. 032307. DOI: 10.2351/1.5040644.
8. Usher J.S. and Srinivasan M.K. Quality Improvement of a Selective Laser Sintering Process, Qual.
Eng., December 2000, Vol. 13, Issue 2, pp. 161-168. DOI: 10.1080/08982110108918638.
9. He K., Gkioxari G., Dollár P., и Girshick R. Mask R-CNN», 24 January 2018, arXiv:
arXiv:1703.06870. DOI: 10.48550/arXiv.1703.06870.
10. Stomakhin A., Schroeder C., Chai L., Teran J., and Selle A. A material point method for snow simulation,
ACM Trans Graph, July 201, Vol. 32, Issue 4, pp. 102:1-102:10, 3. DOI:
10.1145/2461912.2461948.
11.Moeslund T.B., Madsen C.B., Aagaard M., и Lerche D. Modeling Falling and Accumulating Snow.
The Eurographics Association, 2005. DOI: 10.2312/vvg.20051008.
12. Buls E., Kadikis R., Cacurs R., и Ārents J. Generation of synthetic training data for object detection in
piles, In: Eleventh International Conference on Machine Vision (ICMV 2018), March 2019,
Vol. 11041, pp. 110411Z. DOI: 10.1117/12.2523203.
13. Dwibedi D., Misra I., and Hebert M. Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance
Detection, 4 August 2017, arXiv: arXiv:1708.01642. DOI: 10.48550/arXiv.1708.01642.
14. Tobin J., Fong R., Ray A., Schneider J., Zaremba W., and Abbeel P. Domain randomization for transferring
deep neural networks from simulation to the real world, 2017 IEEE/RSJ International Conference
on Intelligent Robots and Systems (IROS), September 2017, pp. 23-30. DOI:
10.1109/IROS.2017.8202133.
15. Rajpura P.S., Bojinov H., and Hegde R.S. Object Detection Using Deep CNNs Trained on Synthetic
Images, 18 September 2017, arXiv: arXiv:1706.06782. DOI: 10.48550/arXiv.1706.06782.
16. Danielczuk M. at al. Segmenting Unknown 3D Objects from Real Depth Images using Mask R-CNN
Trained on Synthetic Data, 2019 International Conference on Robotics and Automation (ICRA), May
2019, pp. 7283-7290. DOI: 10.1109/ICRA.2019.8793744.
17. Dehban A., Borrego J., Figueiredo R., Moreno P., Bernardino A., и Santos-Victor J. The Impact of
Domain Randomization on Object Detection: A Case Study on Parametric Shapes and Synthetic Textures,
2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), November
2019, pp. 2593-2600. DOI: 10.1109/IROS40897.2019.8968139.
18. Lim J.X.-Y.и Pham Q.-C. Automated post-processing of 3D-printed parts: artificial powdering for deep
classification and localisation, Virtual Phys. Prototyp., May 2021, Vol. 16, Issue 3, pp. 333-346. DOI:
10.1080/17452759.2021.1927762.
19. Jia Y. at al. Caffe: Convolutional Architecture for Fast Feature Embedding, 20 June 2014, arXiv:
arXiv:1408.5093. DOI: 10.48550/arXiv.1408.5093.
20. Taniguchi Y., Morimoto T., Nakada A., and Ohmi T. Data generating method, data generating device,
and program, WO2006109709A1, 19 October 2006.
