Advertisement

Planar Pose Estimation Using Object Detection and Reinforcement Learning

  • Frederik Nørby Rasmussen
  • Sebastian Terp Andersen
  • Bjarne Grossmann
  • Evangelos Boukas
  • Lazaros NalpantidisEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11754)

Abstract

Pose estimation concerns systems or models dealing with the determination of a static object’s pose using, in this case, vision. This paper approaching the problem with an active vision-based solution, that integrates both perception and action in the same model. The problem is solved using a combination of neural networks for object detection and a reinforcement learning architecture for moving a camera and estimating the pose. A robotic implementation of the proposed active vision system is used for testing with promising results. Experiments show that our approach does not only solve the simple task of planar visual pose estimation, but also exhibits robustness to changes in the environment.

Keywords

Pose estimation Object detection Reinforcement learning 

References

  1. 1.
    Boukas, E., Gasteratos, A.: Modeling regions of interest on orbital and rover imagery for planetary exploration missions. Cybern. Syst. 47(3), 180–205 (2016).  https://doi.org/10.1080/01969722.2016.1154771CrossRefGoogle Scholar
  2. 2.
    Brockman, G., et al.: OpenAI Gym (2016)Google Scholar
  3. 3.
    Brooks, R.A.: Intelligence without representation. Artif. Intell. 47, 139–159 (1991)CrossRefGoogle Scholar
  4. 4.
    Huang, J., et al.: Speed/accuracy trade-offs for modern convolutional object detectors. In: Computer Vision and Pattern Recognition (2017)Google Scholar
  5. 5.
    Jia, Z., Chang, Y.J., Chen, T.: Active view selection for object and pose recognition. In: 2009 IEEE 12th International Conference on Computer Vision Workshops, September 2009, pp. 641–648 (2009)Google Scholar
  6. 6.
    Kostavelis, I., Nalpantidis, L., Gasteratos, A.: Object recognition using saliency maps and HTM learning. In: IEEE International Conference on Imaging Systems and Techniques, pp. 528–532. IEEE, Manchester (2012)Google Scholar
  7. 7.
    Krull, A., Brachmann, E., Michel, F., Yang, M.Y., Gumhold, S.: Learning analysis-by-synthesis for 6D pose estimation in RGB-D images. In: 2015 IEEE International Conference on Computer Vision, December 2015, pp. 954–962 (2015)Google Scholar
  8. 8.
    Krull, A., Brachmann, E., Nowozin, S., Michel, F., Shotton, J., Rother, C.: PoseAgent: budget-constrained 6D object pose estimation via reinforcement learning. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, July 2017, pp. 2566–2574 (2017)Google Scholar
  9. 9.
    Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015).  https://doi.org/10.1038/nature14236CrossRefGoogle Scholar
  10. 10.
    Piater, J., Jodogne, S., Detry, R., Kraft, D., Krueger, N., Kroemer, O.: Learning visual representations for perception-action systems. Int. J. Robot. Res. 30, 294–307 (2015)CrossRefGoogle Scholar
  11. 11.
    Plappert, M.: Keras-RL (2016). https://github.com/keras-rl/keras-rl
  12. 12.
    Polydoros, A.S., Boukas, E., Nalpantidis, L.: Online multi-target learning of inverse dynamics models for computed-torque control of compliant manipulators. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Vancouver (2017)Google Scholar
  13. 13.
    Toshev, A., Szegedy, C.: DeepPose: human pose estimation via deep neural networks. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, June 2014, pp. 1653–1660 (2014)Google Scholar
  14. 14.
    Tremblay, J., To, T., Sundaralingam, B., Xiang, Y., Fox, D., Birchfield, S.: Deep object pose estimation for semantic robotic grasping of household objects. Cornell University Library (2018)Google Scholar
  15. 15.
    Wooldridge, M., Jennings, N.R.: Agent theories, architectures, and languages: a survey. In: Wooldridge, M.J., Jennings, N.R. (eds.) ATAL 1994. LNCS, vol. 890, pp. 1–39. Springer, Heidelberg (1995).  https://doi.org/10.1007/3-540-58855-8_1CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Frederik Nørby Rasmussen
    • 1
  • Sebastian Terp Andersen
    • 1
  • Bjarne Grossmann
    • 1
  • Evangelos Boukas
    • 2
  • Lazaros Nalpantidis
    • 2
    Email author
  1. 1.Department of Materials and ProductionAalborg UniversityCopenhagenDenmark
  2. 2.Department of Electrical EngineeringTechnical University of DenmarkKongens LyngbyDenmark

Personalised recommendations