A Data-Driven Method for Real-Time Character Animation in Human-Agent Interaction

  • David Vogt
  • Steve Grehl
  • Erik Berger
  • Heni Ben Amor
  • Bernhard Jung
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8637)


We address the problem of creating believable animations for virtual humans that need to react to the body movements of a human interaction partner in real-time. Our data-driven approach uses prerecorded motion capture data of two interacting persons and performs motion adaptation during the live human-agent interaction. Extending the interaction mesh approach, our main contribution is a new scheme for efficient identification of motions in the prerecorded animation data that are similar to the live interaction. A global low-dimensional posture space serves to select the most similar interaction example, while local, more detail-rich posture spaces are used to identify poses closely matching the human motion. Using the interaction mesh of the selected motion example, an animation can then be synthesized that takes into account both spatial and temporal similarities between the prerecorded and live interactions.


character animation interaction mesh virtual agent interactive characters 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Deng, L., Leung, H., Gu, N., Yang, Y.: Real-time mocap dance recognition for an interactive dancing game. Computer Animation and Virtual Worlds 22(2-3), 229–237 (2011)CrossRefGoogle Scholar
  2. 2.
    Kim, J., Seol, Y., Lee, J.: Human motion reconstruction from sparse 3d motion sensors using kernel cca-based regression. Computer Animation and Virtual Worlds 24(6), 565–576 (2013)CrossRefGoogle Scholar
  3. 3.
    Weimin, X., Wenhong, X.: E-learning assistant system based on virtual human interaction technology. In: Shi, Y., van Albada, G.D., Dongarra, J., Sloot, P.M.A. (eds.) ICCS 2007, Part III. LNCS, vol. 4489, pp. 551–554. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  4. 4.
    Osterlund, J., Lawrence, B.: Virtual reality: Avatars in human spaceflight training. Acta Astronautica 71(0), 139–150 (2012)CrossRefGoogle Scholar
  5. 5.
    Chattaraman, V., Kwon, W.-S., Gilbert, J.E.: Virtual agents in retail web sites: Benefits of simulated social interaction for older users. Computers in Human Behavior 28(6), 2055–2066 (2012)CrossRefGoogle Scholar
  6. 6.
    Jung, B., Amor, H.B., Heumer, G., Vitzthum, A.: Action capture: A vr-based method for character animation. In: Coquillart, S., Brunnett, G., Welch, G. (eds.) Virtual Realities, pp. 97–122. Springer, Heidelberg (2008)Google Scholar
  7. 7.
    Bouchard, D., Badler, N.I.: Semantic segmentation of motion capture using laban movement analysis. In: Pelachaud, C., Martin, J.-C., André, E., Chollet, G., Karpouzis, K., Pelé, D. (eds.) IVA 2007. LNCS (LNAI), vol. 4722, pp. 37–44. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  8. 8.
    Ho, E.S.L., Chan, J.C.P., Komura, T., Leung, H.: Interactive partner control in close interactions for real-time applications. ACM Trans. Multimedia Comput. Commun. Appl. 9, 21:1–21:19 (2013)Google Scholar
  9. 9.
    Barnachon, M., Bouakaz, S., Boufama, B., Guillou, E.: Ongoing human action recognition with motion capture. Pattern Recognition 47(1), 238–247 (2014)CrossRefGoogle Scholar
  10. 10.
    Camporesi, C., Huang, Y., Kallmann, M.: Interactive motion modeling and parameterization by direct demonstration. In: Allbeck, J., Badler, N., Bickmore, T., Pelachaud, C., Safonova, A. (eds.) IVA 2010. LNCS, vol. 6356, pp. 77–90. Springer, Heidelberg (2010)Google Scholar
  11. 11.
    Le Naour, T., Courty, N., Gibet, S.: Spatiotemporal coupling with the 3d+t motion laplacian. Computer Animation and Virtual Worlds 24(3-4), 419–428 (2013)CrossRefGoogle Scholar
  12. 12.
    Sorkine, O., Cohen-Or, D., Lipman, Y., Alexa, M., Rössl, C., Seidel, H.-P.: Laplacian surface editing. In: Proceedings of the 2004 Eurographics/ACM SIGGRAPH Symposium on Geometry Processing, SGP 2004, pp. 175–184. ACM, New York (2004)CrossRefGoogle Scholar
  13. 13.
    Ho, E.S.L., Komura, T., Tai, C.-L.: Spatial relationship preserving character motion adaptation. ACM Trans. Graph. 29 (July 2010)Google Scholar
  14. 14.
    Taubert, N., Löffler, M., Ludolph, N., Christensen, A., Endres, D., Giese, M.A.: A virtual reality setup for controllable, stylized real-time interactions between humans and avatars with sparse gaussian process dynamical models. In: Proceedings of the ACM Symposium on Applied Perception, SAP 2013, pp. 41–44. ACM, New York (2013)Google Scholar
  15. 15.
    Ben Amor, H.: Imitation Learning of Motor Skills for Synthetic Humanoids. PhD thesis, Technische Universität Bergakademie Freiberg (2010)Google Scholar
  16. 16.
    Bankó, Z., Abonyi, J.: Correlation based dynamic time warping of multivariate time series. Expert Systems with Applications 39(17), 12814–12823 (2012)CrossRefGoogle Scholar
  17. 17.
    Krzanowski, W.J.: Between-groups comparison of principal components  74, 703–707 (September 1979)Google Scholar
  18. 18.
    Vlachos, M., Hadjieleftheriou, M., Keogh, E.J., Gunopulos, D.: Indexing multi-dimensional trajectories for similarity queries. In: Spatial Databases, pp. 107–128 (2005)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • David Vogt
    • 1
  • Steve Grehl
    • 1
  • Erik Berger
    • 1
  • Heni Ben Amor
    • 2
  • Bernhard Jung
    • 1
  1. 1.Institut für InformatikTechnische Universität Bergakademie FreibergFreibergGermany
  2. 2.Institute for Robotics and Intelligent MachinesGeorgia Institute of TechnologyAtlantaUSA

Personalised recommendations