A GAN-Like Approach for Physics-Based Imitation Learning and Interactive Control

by   Pei Xu, et al.

We present a simple and intuitive approach for interactive control of physically simulated characters. Our work builds upon generative adversarial networks (GAN) and reinforcement learning, and introduces an imitation learning framework where an ensemble of classifiers and an imitation policy are trained in tandem given pre-processed reference clips. The classifiers are trained to discriminate the reference motion from the motion generated by the imitation policy, while the policy is rewarded for fooling the discriminators. Using our GAN-based approach, multiple motor control policies can be trained separately to imitate different behaviors. In runtime, our system can respond to external control signal provided by the user and interactively switch between different policies. Compared to existing methods, our proposed approach has the following attractive properties: 1) achieves state-of-the-art imitation performance without manually designing and fine tuning a reward function; 2) directly controls the character without having to track any target reference pose explicitly or implicitly through a phase state; and 3) supports interactive policy switching without requiring any motion generation or motion matching mechanism. We highlight the applicability of our approach in a range of imitation and interactive control tasks, while also demonstrating its ability to withstand external perturbations as well as to recover balance. Overall, our approach generates high-fidelity motion, has low runtime cost, and can be easily integrated into interactive applications and games.


page 1

page 8

page 10


CALM: Conditional Adversarial Latent Models for Directable Virtual Characters

In this work, we present Conditional Adversarial Latent Models (CALM), a...

Perpetual Humanoid Control for Real-time Simulated Avatars

We present a physics-based humanoid controller that achieves high-fideli...

3D Ego-Pose Estimation via Imitation Learning

Ego-pose estimation, i.e., estimating a person's 3D pose with a single w...

AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control

Synthesizing graceful and life-like behaviors for physically simulated c...

HandMime: Sign Language Fingerspelling Acquisition via Imitation Learning

Learning fine-grained movements is among the most challenging topics in ...

Composite Motion Learning with Task Control

We present a deep learning method for composite and task-driven motion c...

Visual Imitation Learning with Recurrent Siamese Networks

People solve the difficult problem of understanding the salient features...

Please sign up or login with your details

Forgot password? Click here to reset