“Continuous character control with low-dimensional embeddings” by Levine, Wang, Haraux, Popovic and Koltun

  • ©Sergey Levine, Jack M. Wang, Alexis Haraux, Zoran Popovic, and Vladlen Koltun




    Continuous character control with low-dimensional embeddings



    Interactive, task-guided character controllers must be agile and responsive to user input, while retaining the flexibility to be readily authored and modified by the designer. Central to a method’s ease of use is its capacity to synthesize character motion for novel situations without requiring excessive data or programming effort. In this work, we present a technique that animates characters performing user-specified tasks by using a probabilistic motion model, which is trained on a small number of artist-provided animation clips. The method uses a low-dimensional space learned from the example motions to continuously control the character’s pose to accomplish the desired task. By controlling the character through a reduced space, our method can discover new transitions, tractably precompute a control policy, and avoid low quality poses.


    1. Arikan, O., and Forsyth, D. A. 2002. Interactive motion generation from examples. ACM Transactions on Graphics 21, 3, 483–490. Google ScholarDigital Library
    2. Bertsekas, D. P. 2001. Dynamic Programming and Optimal Control. Athena Scientific, Belmont, MA. Google ScholarDigital Library
    3. Chai, J., and Hodgins, J. K. 2007. Constraint-based motion optimization using a statistical dynamic model. ACM Transactions on Graphics 26, 3, 8:1–8:9. Google ScholarDigital Library
    4. Geiger, A., Urtasun, R., and Darrell, T. 2009. Rank priors for continuous non-linear dimensionality reduction. In Proc. CVPR, IEEE, 880–887.Google Scholar
    5. Grochow, K., Martin, S. L., Hertzmann, A., and Popović, Z. 2004. Style-based inverse kinematics. ACM Transactions on Graphics 23, 3, 522–531. Google ScholarDigital Library
    6. Hsu, E., Pulli, K., and Popovic, J. 2005. Style translation for human motion. ACM Transactions on Graphics 24, 3, 1082–1089. Google ScholarDigital Library
    7. Ikemoto, L., Arikan, O., and Forsyth, D. 2009. Generalizing motion edits with gaussian processes. ACM Transactions on Graphics 28, 1, 1:1–1:12. Google ScholarDigital Library
    8. Johansen, R. S. 2009. Automated Semi-Procedural Animation for Character Locomotion. Master’s thesis, Aarhus University.Google Scholar
    9. Kalbfleisch, J. D., and Lawless, J. F. 1985. The analysis of panel markov data under a assumption. Journal of the American Statistical Association 80, 392, 863–871.Google ScholarCross Ref
    10. Kondor, R. I., and Vert, J.-P. 2004. Diffusion kernels. In Kernel Methods in Computational Biology. The MIT Press, 171–192.Google Scholar
    11. Kovar, L., Gleicher, M., and Pighin, F. H. 2002. Motion graphs. ACM Transactions on Graphics 21, 3, 473–482. Google ScholarDigital Library
    12. Lau, M., Bar-Joseph, Z., and Kuffner, J. 2009. Modeling spatial and temporal variation in motion data. ACM Transactions on Graphics 28, 5, 171:1–171:10. Google ScholarDigital Library
    13. Lawrence, N. D., and Quiñonero Candela, J. 2006. Local distance preservation in the GP-LVM through back constraints. In Proc. ICML, ACM, 513–520. Google ScholarDigital Library
    14. Lawrence, N. D. 2005. Probabilistic non-linear principal component analysis with Gaussian process latent variable models. Journal of Machine Learning Research 6, 1783–1816. Google ScholarDigital Library
    15. Lawrence, N. D. 2006. The Gaussian process latent variable model. Tech. rep., University of Sheffield.Google Scholar
    16. Lawrence, N. D. 2007. Learning for larger datasets with the gaussian process latent variable model. Journal of Machine Learning Research 2, 243–250.Google Scholar
    17. Lee, J., and Lee, K. H. 2006. Precomputing avatar behavior from human motion data. Graphical Models 68, 2, 158–174. Google ScholarDigital Library
    18. Lee, J., Chai, J., Reitsma, P. S. A., Hodgins, J. K., and Pollard, N. S. 2002. Interactive control of avatars animated with human motion data. ACM Transactions on Graphics 21, 3, 491–500. Google ScholarDigital Library
    19. Lee, Y., Lee, S. J., and Popović, Z. 2009. Compact character controllers. ACM Transactions on Graphics 28, 5, 169:1–169:8. Google ScholarDigital Library
    20. Lee, Y., Wampler, K., Bernstein, G., Popović, J., and Popović, Z. 2010. Motion fields for interactive character locomotion. ACM Transactions on Graphics 29, 6, 138:1–138:8. Google ScholarDigital Library
    21. Lo, W.-Y., and Zwicker, M. 2008. Real-time planning for parameterized human motion. In Symposium on Computer Animation, ACM/Eurographics, 29–38. Google ScholarDigital Library
    22. McCann, J., and Pollard, N. 2007. Responsive characters from motion fragments. ACM Transactions on Graphics 26, 3, 6:1–6:8. Google ScholarDigital Library
    23. Min, J., Chen, Y.-L., and Chai, J. 2009. Interactive generation of human animation with deformable motion models. ACM Transactions on Graphics 29, 1. Google ScholarDigital Library
    24. Mukai, T., and Kuriyama, S. 2005. Geostatistical motion interpolation. ACM Transactions on Graphics 24, 3, 1062–1070. Google ScholarDigital Library
    25. Ormoneit, D., and Sen, S. 2002. Kernel-based reinforcement learning. Machine Learning 49, 2-3, 161–178. Google ScholarDigital Library
    26. Quiñonero Candela, J., and Rasmussen, C. E. 2005. A unifying view of sparse approximate Gaussian process regression. Journal of Machine Learning Research 6, 1939–1959. Google ScholarDigital Library
    27. Ren, C., Zhao, L., and Safonova, A. 2010. Human motion synthesis with optimization-based graphs. Computer Graphics Forum 29, 2, 545–554.Google ScholarCross Ref
    28. Rose, C., Cohen, M. F., and Bodenheimer, B. 1998. Verbs and adverbs: Multidimensional motion interpolation. IEEE Computer Graphics and Applications 18, 5, 32–40. Google ScholarDigital Library
    29. Shin, H. J., and Lee, J. 2006. Motion synthesis and editing in low-dimensional spaces. Journal of Visualization and Computer Animation 17, 3-4, 219–227. Google ScholarDigital Library
    30. Shin, H. J., and Oh, H. S. 2006. Fat Graphs: Constructing an interactive character with continuous controls. In Symposium on Computer Animation, ACM/Eurographics, 291–298. Google ScholarDigital Library
    31. Titsias, M. K., and Lawrence, N. D. 2010. Bayesian gaussian process latent variable model. Journal of Machine Learning Research 9, 844–851.Google Scholar
    32. Treuille, A., Lee, Y., and Popović, Z. 2007. Near-optimal character animation with continuous control. ACM Transactions on Graphics 26, 3, 7:1–7:8. Google ScholarDigital Library
    33. Urtasun, R., Fleet, D. J., Hertzmann, A., and Fua, P. 2005. Priors for people tracking from small training sets. In Proc. ICCV, IEEE, 403–410. Google ScholarDigital Library
    34. Urtasun, R., Fleet, D. J., Geiger, A., Popović, J., Darrell, T. J., and Lawrence, N. D. 2008. Topologically-constrained latent variable models. In Proc. ICML, ACM, 1080–1087. Google ScholarDigital Library
    35. Walder, C., Kim, K. I., and Schölkopf, B. 2008. Sparse multiscale Gaussian process regression. In Proc. ICML, ACM, 1112–1119. Google ScholarDigital Library
    36. Wang, J. M., Fleet, D. J., and Hertzmann, A. 2007. Multi-factor Gaussian process models for style-content separation. In Proc. ICML, ACM, 975–982. Google ScholarDigital Library
    37. Wang, J. M., Fleet, D. J., and Hertzmann, A. 2008. Gaussian process dynamical models for human motion. IEEE Transactions on Pattern Analysis and Machine Intelligence 30, 2, 283–298. Google ScholarDigital Library
    38. Wei, X. K., Min, J., and Chai, J. 2011. Physically valid statistical models for human motion generation. ACM Transactions on Graphics 30, 3, 19. Google ScholarDigital Library
    39. Ye, Y., and Liu, C. K. 2010. Synthesis of responsive motion using a dynamic model. Computer Graphics Forum 29, 2, 555–562.Google ScholarCross Ref
    40. Zhao, L., and Safonova, A. 2009. Achieving good connectivity in motion graphs. Graphical Models 71, 4, 139–152. Google ScholarDigital Library

ACM Digital Library Publication:

Overview Page: