FreeMusco: Motion-Free Learning of Latent Control for Morphology-Adaptive Locomotion in Musculoskeletal Characters

TL;DR

FreeMusco is a novel motion-free framework that learns energy-efficient, morphology-adaptive locomotion control policies for musculoskeletal characters using model-based reinforcement learning, without requiring motion data or demonstrations.

Contribution

It introduces a motion-free method that jointly learns latent representations and control policies for diverse musculoskeletal characters, enabling adaptive locomotion and downstream tasks.

Findings

Generalizes across multiple morphologies including human and non-human characters

Learns diverse, physically plausible locomotion behaviors without motion data

Enables downstream tasks like goal navigation and path following

Abstract

We propose FreeMusco, a motion-free framework that jointly learns latent representations and control policies for musculoskeletal characters. By leveraging the musculoskeletal model as a strong prior, our method enables energy-aware and morphology-adaptive locomotion to emerge without motion data. The framework generalizes across human, non-human, and synthetic morphologies, where distinct energy-efficient strategies naturally appear--for example, quadrupedal gaits in Chimanoid versus bipedal gaits in Humanoid. The latent space and corresponding control policy are constructed from scratch, without demonstration, and enable downstream tasks such as goal navigation and path following--representing, to our knowledge, the first motion-free method to provide such capabilities. FreeMusco learns diverse and physically plausible locomotion behaviors through model-based reinforcement learning, guided by the locomotion objective that combines control, balancing, and biomechanical terms. To better capture the periodic structure of natural gait, we introduce the temporally averaged loss formulation, which compares simulated and target states over a time window rather than on a per-frame basis. We further encourage behavioral diversity by randomizing target poses and energy levels during training, enabling locomotion to be flexibly modulated in both form and intensity at runtime. Together, these results demonstrate that versatile and adaptive locomotion control can emerge without motion capture, offering a new direction for simulating movement in characters where data collection is impractical or impossible.