MAAIP: Multi-Agent Adversarial Interaction Priors for imitation from fighting demonstrations for physics-based characters
No Thumbnail Available
Date
2023
Journal Title
Journal ISSN
Volume Title
Publisher
ACM Association for Computing Machinery
Abstract
Simulating realistic interaction and motions for physics-based characters is of great interest for interactive applications, and automatic secondary character animation in the movie and video game industries. Recent works in reinforcement learning have proposed impressive results for single character simulation, especially the ones that use imitation learning based techniques. However, imitating multiple characters interactions and motions requires to also model their interactions. In this paper, we propose a novel Multi-Agent Generative Adversarial Imitation Learning based approach that generalizes the idea of motion imitation for one character to deal with both the interaction and the motions of the multiple physics-based characters. Two unstructured datasets are given as inputs: 1) a single-actor dataset containing motions of a single actor performing a set of motions linked to a specific application, and 2) an interaction dataset containing a few examples of interactions between multiple actors. Based on these datasets, our system trains control policies allowing each character to imitate the interactive skills associated with each actor, while preserving the intrinsic style. This approach has been tested on two different fighting styles, boxing and full-body martial art, to demonstrate the ability of the method to imitate different styles.
Description
CCS Concepts: Computing methodologies -> Procedural animation; Adversarial learning; Multiagent reinforcement learning Character Animation, Multi-Agent Reinforcement Learning, Adversarial Imitation learning, Physics-based Simulation, Motion Capture"
@inproceedings{10.1145:3606926,
booktitle = {Proceedings of the ACM on Computer Graphics and Interactive Techniques},
editor = {Wang, Huamin and Ye, Yuting and Victor Zordan},
title = {{MAAIP: Multi-Agent Adversarial Interaction Priors for imitation from fighting demonstrations for physics-based characters}},
author = {Younes, Mohamed and Kijak, Ewa and Kulpa, Richard and Malinowski, Simon and Multon, Franck},
year = {2023},
publisher = {ACM Association for Computing Machinery},
ISSN = {2577-6193},
ISBN = {},
DOI = {10.1145/3606926}
}