Learning Body Shape Variation in Physics-based Characters

作     者：Won, Jungdam Lee, Jehee 

作者机构：Seoul Natl Univ Dept Comp Sci & Engn Seoul South Korea 

出 版 物：《ACM TRANSACTIONS ON GRAPHICS》 (美国计算机学会图形学汇刊)

年 卷 期：2019年第38卷第6期

页      面：207-207页

核心收录：

学科分类：08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：MSIT (Ministry of Science and ICT)  Korea  under the SW Starlab support program [IITP-2017-0-00878] 

主　　题：Character Animation Physics-based Simulation and Control Reinforcement Learning Deep Learning Neural Network Locomotion Control 

摘      要：Recently, deep reinforcement learning (DRL) has attracted great attention in designing controllers for physics-based characters. Despite the recent success of DRL, the learned controller is viable for a single character. Changes in body size and proportions require learning controllers from scratch. In this paper, we present a new method of learning parametric controllers for body shape variation. A single parametric controller enables us to simulate and control various characters having different heights, weights, and body proportions. The users are allowed to create new characters through body shape parameters, and they can control the characters immediately. Our characters can also change their body shapes on the fly during simulation. The key to the success of our approach includes the adaptive sampling of body shapes that tackles the challenges in learning parametric controllers, which relies on the marginal value function that measures control capabilities of body shapes. We demonstrate parametric controllers for various physically simulated characters such as bipeds, quadrupeds, and underwater animals.