Abstract
The motor synthesis of humanoid characters is one of the main problems in data-driven animations, with applications in robotics, entertainment and game development. Both in the commercial and academic fields there is a strong interest in developing new synthesis techniques. The attention of researchers in this field has recently turned to artificial intelligence techniques with the use of neural networks, in particular recurrent neural networks (RNN) that are well suited to predict data sequences, such as animations. The use of RNNs for the generation of animations despite the high success in the scientific field and the excellent results in real development, still has limitations that prevent its use on a larger scale. In this work, therefore, the need to overcome these limits has required to focus on the phase following the generation of interactions by the network. In particular, starting from a work present in the literature, the limitations were analyzed and solutions were proposed that made it possible to improve the visual rendering of the Carry and Sit operations. The results obtained are positive and did not require any intervention on the neural network. New items and characters have been successfully introduced. Both pre-existing characters and imported characters are able to interact with all objects with greater effectiveness, responsiveness and visual fidelity.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bollo, D.: High performance animation in gears of war 4. In: ACM SIGGRAPH 2017 Talks. SIGGRAPH ’17, Association for Computing Machinery, New York, NY, USA (2017). https://doi.org/10.1145/3084363.3085069
Burelli, P., Yannakakis, G.: Combining local and global optimisation for virtual camera control, pp. 403–410 (2010). https://doi.org/10.1109/ITW.2010.5593328
Buro, M.: Real-time strategy games: a new AI research challenge. IJCAI 2003, 1534–1535 (2003)
Clavet, S.: Motion matching and the road to next-gen animation. GDC Vault, New York, NY, USA (2016). https://www.gdcvault.com/play/1023280/Motion-Matching-and-The-Road
Fragkiadaki, K., Levine, S., Felsen, P., Malik, J.: Recurrent network models for human dynamics. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 4346–4354 (2015)
Frontoni, E., Loncarski, J., Pierdicca, R., Bernardini, M., Sasso, M.: Cyber physical systems for industry 4.0: towards real time virtual reality in smart manufacturing. In: De Paolis, L.T., Bourdot, P. (eds.) AVR 2018. LNCS, vol. 10851, pp. 422–434. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-95282-6_31
Hazim, N., Al-Dabbagh, S.S.M., Naser, M.A.S.: Pathfinding in strategy games and maze solving using a* search algorithm. J. Comput. Commun. 04, 15–25 (2016). https://doi.org/10.4236/jcc.2016.411002
Herzog, I.: Teaching a character how to walk with procedural assisted animations. CitizenCon (2017). http://youtube.com/watch?v=ZMgHhu7XT78
Lee, J., Chai, J., Reitsma, P.S.A., Hodgins, J.K., Pollard, N.S.: Interactive control of avatars animated with human motion data. ACM Trans. Graph. 21(3), 491–500 (2002)
Li, Z., Zhou, Y., Xiao, S., He, C., Huang, Z., Li, H.: Auto-conditioned recurrent networks for extended complex human motion synthesis (2017)
Liciotti, D., Paolanti, M., Frontoni, E., Zingaretti, P.: People detection and tracking from an RGB-D camera in top-view configuration: review of challenges and applications. In: Battiato, S., Farinella, G.M., Leo, M., Gallo, G. (eds.) ICIAP 2017. LNCS, vol. 10590, pp. 207–218. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-70742-6_20
Lo, W.Y., Knaus, C., Zwicker, M.: Learning motion controllers with adaptive depth perception. In: Proceedings of the ACM SIGGRAPH/Eurographics Symposium on Computer Animation, SCA ’12, Eurographics Association, Goslar, DEU, pp. 145–154 (2012)
Loyall, A.B.: Believable agents: Building interactive personalities. CARNEGIE-MELLON UNIV PITTSBURGH PA DEPT OF COMPUTER SCIENCE, Technical report (1997)
Lucas, S.M., Kendall, G.: Evolutionary computation and games. Comp. Intell. Mag. 1(1), 10–18 (2006)
Paolanti, M., Frontoni, E.: Multidisciplinary pattern recognition applications: a review. Comput. Sci. Rev. 37, 100276 (2020)
Park, S., Ryu, H., Lee, S., Lee, S., Lee, J.: Learning predict-and-simulate policies from unorganized human motion data. ACM Trans. Graph. 38(6) (2019). https://doi.org/10.1145/3355089.3356501
Safonova, A., Hodgins, J.K.: Construction and optimal search of interpolated motion graphs. ACM Trans. Graph. 26(3), 106-es (2007). https://doi.org/10.1145/1276377.1276510
Shaker, N., Togelius, J., Nelson, M.J.: Procedural Content Generation in Games. Springer, Heidelberg (2016). https://doi.org/10.1007/978-3-319-42716-4
Starke, S., Zhang, H., Komura, T., Saito, J.: Neural state machine for character-scene interactions. ACM Trans. Graph. 38(6) (2019). https://doi.org/10.1145/3355089.3356505
Xia, B., Ye, X., Abuassba, A.O.: Recent research on ai in games. In: 2020 International Wireless Communications and Mobile Computing (IWCMC), pp. 505–510. IEEE (2020)
Yannakakis, G.N., Togelius, J.: A panorama of artificial and computational intelligence in games. IEEE Trans. Comput. Intell. AI Games 7(4), 317–335 (2015)
Yannakakis, G.N., Spronck, P., Loiacono, D., André, E.: Player modeling (2013)
Zhang, H., Starke, S., Komura, T., Saito, J.: Mode-adaptive neural networks for quadruped motion control. ACM Trans. Graph. 37(4) (2018). https://doi.org/10.1145/3197517.3201366
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Mameli, M., De Carolis, D., Frontoni, E., Zingaretti, P. (2021). Overcoming the Limits of a Neural Network for Character-Scene Interactions. In: De Paolis, L.T., Arpaia, P., Bourdot, P. (eds) Augmented Reality, Virtual Reality, and Computer Graphics. AVR 2021. Lecture Notes in Computer Science(), vol 12980. Springer, Cham. https://doi.org/10.1007/978-3-030-87595-4_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-87595-4_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87594-7
Online ISBN: 978-3-030-87595-4
eBook Packages: Computer ScienceComputer Science (R0)