RACon: Retrieval-Augmented Simulated Character Locomotion Control

TL;DR

RACon is a hierarchical reinforcement learning framework that enhances simulated character locomotion by integrating a retrieval system for motion experts, improving responsiveness, quality, and adaptability in animation control.

Contribution

Introduces RACon, a novel retrieval-augmented reinforcement learning approach that improves responsiveness and adaptability in simulated character locomotion control.

Findings

Outperforms existing methods in quality and quantity of locomotion control

Enables real-time adaptation to different motion types by switching databases

Stabilizes training with a retrieval-augmented discriminator

Abstract

In computer animation, driving a simulated character with lifelike motion is challenging. Current generative models, though able to generalize to diverse motions, often pose challenges to the responsiveness of end-user control. To address these issues, we introduce RACon: Retrieval-Augmented Simulated Character Locomotion Control. Our end-to-end hierarchical reinforcement learning method utilizes a retriever and a motion controller. The retriever searches motion experts from a user-specified database in a task-oriented fashion, which boosts the responsiveness to the user's control. The selected motion experts and the manipulation signal are then transferred to the controller to drive the simulated character. In addition, a retrieval-augmented discriminator is designed to stabilize the training process. Our method surpasses existing techniques in both quality and quantity in locomotion control, as demonstrated in our empirical study. Moreover, by switching extensive databases for retrieval, it can adapt to distinctive motion types at run time.