Agent-based cooperative animation for box-manipulation using reinforcement learning
Hsiang-Yu Yang, Sai‐Keung Wong · Proceedings of the ACM on Computer Graphics and Interactive Techniques · 2019
This paper presents an approach to assist the generation of agent-based cooperative animation using reinforcement learning. We focus on manipulation skills for box-shaped objects, including pushing, pulling, and moving objects in a relay way. There are a learning process and an animation process. In the learning process, different kinds of agents are trained using reinforcement learning. Policies are learned to control the agents to perform specific tasks. A physics simulator is adopted to simulate the interaction among objects. In the animation process, users animate agents with the learned policies. We propose several tools to intuitively create cooperative animations. We applied our method to generate several animations in which agents work together to finish tasks. A user study indicates that by using our tools, diverse cooperative animations can be easily created.