This repository contains the source code and supplemental video of our research project.
Real-time character animation for gaming and film industries is challenging and achieving production-ready quality requires a huge amount of time and resources. Animation through marker-based motion capture is quite a tiresome process that requires costly motion-capture suits, multiple cameras, and a large database. In this paper, we propose a model that aims to generate real-time character animation for biped locomotion in Unity ML agents using Reinforcement learning and Imitation learning algorithms. We first evaluate the training with solely the state-of-the-art RL algorithm, PPO(Proximal Policy Optimization). Then we analyze the combination of IL algorithms BC(Behavioral Cloning) and GAIL(Generative Adversarial Imitation Learning) in conjunction with PPO. We further discuss the comparison between the two training results and show that our model is able to generate animations in real-time avoiding all the tedious work and large databases. We demonstrate that our approach is effortlessly easy to implement while maintaining the quality.
In the following video, the final training results for both character models(WalkerRagdoll and Ybot) are shown.