GAMES Webinar 2018-59期（Siggraph 2018论文）| 张贺（爱丁堡大学），高明（威斯康星大学麦迪逊分校）
【GAMES Webinar 2018-59期（Siggraph 2018论文）】
报告时间：2018年8月9日（星期四）晚8:00 – 8:45（北京时间）
报告题目：Mode-Adaptive Neural Networks for Quadruped Motion Control
Quadruped motion includes a wide variation of gaits such as walk, pace, trot and canter, and actions such as jumping, sitting, turning and idling. Applying existing data-driven character control frameworks to such data requires a significant amount of data preprocessing such as motion labeling and alignment. In this paper, we propose a novel neural network architecture called Mode-Adaptive Neural Networks for controlling quadruped characters. The system is composed of the motion prediction network and the gating network. At each frame, the motion prediction network computes the character state in the current frame given the state in the previous frame and the user-provided control signals. The gating network dynamically updates the weights of the motion prediction network by selecting and blending what we call the expert weights, each of which specializes in a particular movement. Due to the increased flexibility, the system can learn consistent expert weights across a wide range of non-periodic/periodic actions, from unstructured motion capture data, in an end-to-end fashion. In addition, the users are released from performing complex labeling of phases in different gaits. We show that this architecture is suitable for encoding the multimodality of quadruped locomotion and synthesizing responsive motion in real-time.
He Zhang is a first year PhD student under supervision of Prof. Taku Komura in Computer Graphics and Visualization Group at the University of Edinburgh. Before that, he received Master degree in Data Science from the University of Edinburgh and Bachelor degree in Computer Science from Shandong University. His research interests include computer graphics and character animation.
报告时间：2018年8月9日（星期四）晚8:45 – 9:30（北京时间）
报告题目：Animating Fluid Sediment Mixture in Particle-Laden Flows
In this paper, we present a mixed explicit and semi-implicit Material Point Method for simulating particle-laden flows. We develop a Multigrid Preconditioned fluid solver for the Locally Averaged Navier Stokes equation. This is discretized purely on a semi-staggered standard MPM grid. Sedimentation is modeled with the Drucker-Prager elastoplasticity flow rule, enhanced by a novel particle density estimation method for converting particles between representations of either continuum or discrete points. Fluid and sediment are two-way coupled through a momentum exchange force that can be easily resolved with two MPM background grids. We present various results to demonstrate the efficacy of our method.
Ming Gao is a fifth year Ph.D. student under the supervision of Eftychios Sifakis in the UW Graphics Group. His interests are focused on physics-based simulation, scientific computing, and high performance and parallel computing. He got his master degree (Computer Science, 2013) in UCLA under Demetri Terzopoulos and obtained bachelor degree (Modern Physics, 2011) in University of Science and Technology of China (USTC).
GAMES主页的“使用教程”中有 “如何观看GAMES Webinar直播？”及“如何加入GAMES微信群？”的信息；