# Real-Time Character Control With Phase-Functioned Neural Networks | Two Minute Papers #154 ## Метаданные - **Канал:** Two Minute Papers - **YouTube:** https://www.youtube.com/watch?v=wlndIQHtiFw - **Дата:** 17.05.2017 - **Длительность:** 2:50 - **Просмотры:** 25,885 - **Источник:** https://ekstraktznaniy.ru/video/14659 ## Описание The paper "Phase-Functioned Neural Networks for Character Control" is available here: http://theorangeduck.com/page/phase-functioned-neural-networks-character-control Two Minute Papers Merch: US: http://twominutepapers.com/ EU/Worldwide: https://shop.spreadshirt.net/TwoMinutePapers/ WE WOULD LIKE TO THANK OUR GENEROUS PATREON SUPPORTERS WHO MAKE TWO MINUTE PAPERS POSSIBLE: Andrew Melnychuk, Christian Lawson, Dave Rushton-Smith, Dennis Abts, e, Esa Turkulainen, Michael Albrecht, Sunil Kim, VR Wizard. https://www.patreon.com/TwoMinutePapers Music: Antarctica by Audionautix is licensed under a Creative Commons Attribution license (https://creativecommons.org/licenses/by/4.0/) Artist: http://audionautix.com/ Thumbnail background image credit: https://pixabay.com/photo-1835354/ Splash screen/thumbnail design: Felícia Fehér - http://felicia.hu Károly Zsolnai-Fehér's links: Facebook → https://www.facebook.com/TwoMinutePapers/ Twitter → https://twitter.com/karoly_zsolnai Web → https://cg ## Транскрипт ### [] Dear Fellow Scholars, this is Two Minute Papers with Károly Zsolnai-Fehér. In this piece of work, we seek to control digital characters in real-time. It happens the following way: we specify a target trajectory, and the algorithm has to synthesize a series of motions that follows that path. To make these motions as realistic as possible, this is typically accomplished by unleashing a learning algorithm on a large database that contains a ton of motion information. Previous techniques did not have a good understanding of these databases and they often synthesized ### Standard Neural Network [0:30] motions from pieces that corresponded to different kinds of movements. ### Recurrent LSTM (ERD) Network [0:36] This lack of understanding results in stiff, unnatural output motion. ### Autoregressive Gaussian Process [0:42] Intuitively, it is a bit like putting together a sentence from a set of letters that were cut out one by one from different newspaper articles. It is a fully formed sentence, but it lacks the smoothness and the flow of a properly aligned piece of text. This is a neural network based technique that introduces a phase function to the learning process. This phase function augments the learning with the timing information of a given motion. With this phase function, the neural network recognizes that we are not only learning periodic motions, but it knows when these motions start and when they end. The final technique takes very little memory, runs in real time, and it accomplishes smooth walking, running, jumping and climbing motions and so much more over a variety of terrains with flying colors. In a previous episode, we have discussed a different technique that accomplished something similar with a low and high level controller. One of the major selling points of this technique is that this one offers a unified solution for terrain traversal with using only one neural network. This has the potential to make it really big on computer games and real-time animation. It is absolutely amazing to witness this and be a part of the future. Make sure to have a look at the paper, which also contains the details of a terrain fitting step to make this learning algorithm capable of taking into consideration a variety of obstacles. I would also like to thank Claudio Pannacci for his amazing work in translating so many of these episodes to Italian. This makes Two Minute Papers accessible for more people around the globe, and the more people we can reach, the happier I am. Thanks for watching and for your generous support, and I'll see you next time!