Composite Motion Learning with Task Control

Abstract

We present a deep learning method for composite and task-driven motion control for physically simulated characters. In contrast to existing data-driven approaches using reinforcement learning that imitate full-body motions, we learn decoupled motions for specific body parts from multiple reference motions simultaneously and directly by leveraging the use of multiple discriminators in a GAN-like setup. In this process, there is no need of any manual work to produce composite reference motions for learning. Instead, the control policy explores by itself how the composite motions can be combined automatically. We further account for multiple task-specific rewards and train a single, multi-objective control policy. To this end, we propose a novel framework for multi-objective learning that adaptively balances the learning of disparate motions from multiple sources and multiple goal-directed control objectives. In addition, as composite motions are typically augmentations of simpler behaviors, we introduce a sample-efficient method for training composite control policies in an incremental manner, where we reuse a pre-trained policy as the meta policy and train a cooperative policy that adapts the meta one for new composite tasks. We show the applicability of our approach on a variety of challenging multi-objective tasks involving both composite motion imitation and multiple goal-directed control.

arXiv commentSIGGRAPH 2023. Code: https://github.com/xupei0610/CompositeMotion. Video: https://youtu.be/mcRAxwoTh3E

References in corpus (15)

• Adam: A Method for Stochastic Optimization
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games
• AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control
• Character Controllers Using Motion VAEs
• Robust Motion In-betweening
• ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters
• Learning human behaviors from motion capture by adversarial imitation
• Neural probabilistic motor primitives for humanoid control
• Motion Puzzle: Arbitrary Motion Style Transfer by Body Part
• Geometric GAN
• MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies
• A GAN-Like Approach for Physics-Based Imitation Learning and Interactive Character Control
• UniCon: Universal Neural Controller For Physics-based Character Motion
• Generating Upper-Body Motion for Real-Time Characters Making their Way through Dynamic Environments

Cited by in corpus (5)

• AdaptNet: Policy Adaptation for Physics-Based Character Control
• Synchronize Dual Hands for Physics-Based Dexterous Guitar Playing
• PhysicsFC: Learning User-Controlled Skills for a Physics-Based Football Player Controller
• AMOR: Adaptive Character Control through Multi-Objective Reinforcement Learning
• CBIL: Collective Behavior Imitation Learning for Fish from Real Videos