Paper Info
Title
How to train your dragon: example-guided control of flapping flight.
Abstract
Imaginary winged creatures in computer animation applications are expected to perform a variety of motor skills in a physically realistic and controllable manner. Designing physics-based controllers for a flying creature is still very challenging particularly when the dynamic model of the creatures is high-dimensional, having many degrees of freedom. In this paper, we present a control method for flying creatures, which are aerodynamically simulated, interactively controllable, and equipped with a variety of motor skills such as soaring, gliding, hovering, and diving. Each motor skill is represented as Deep Neural Networks (DNN) and learned using Deep Q-Learning (DQL). Our control method is example-guided in the sense that it provides the user with direct control over the learning process by allowing the user to specify keyframes of motor skills. Our novel learning algorithm was inspired by evolutionary strategies of Covariance Matrix Adaptation Evolution Strategy (CMA-ES) to improve the convergence rate and the final quality of the control policy. The effectiveness of our Evolutionary DQL method is demonstrated with imaginary winged creatures flying in a physically simulated environment and their motor skills learned automatically from user-provided keyframes.
Year
DOI
Venue
2017
10.1145/3130800.3130833
ACM Trans. Graph.
Keywords
Field
DocType
character animation, deep learning, flapping flight, neural network, physics simulation, physics-based control, reinforcement learning
Computer vision,Dynamical simulation,Motor skill,Character animation,Evolution strategy,Artificial intelligence,CMA-ES,Deep learning,Computer animation,Mathematics,Reinforcement learning
Journal
Volume
Issue
ISSN
36
6
0730-0301
Citations 
PageRank 
References 
10
0.55
26
Authors
4
Name
Order
Citations
PageRank
Jungdam Won1293.71
Jongho Park2110.90
Kwanyu Kim3100.55
Jehee Lee41912118.33