Burden, Bounty, or Bliss? Muscle-Aware Retargeting and Null-Space Exploration for Whole-Body Musculoskeletal Control

Ruiyang Kong, Takeshi OishiarXiv 2026 · arXiv

TL;DR

This paper introduces the first end-to-end pipeline capable of transforming monocular video into a trained whole-body imitation policy for a complex 700-muscle musculoskeletal model. By leveraging muscle redundancy through "muscle-aware" motion retargeting and "null-space" exploration, the authors achieve a 44% reduction in tracking error and double the learning speed compared to standard reinforcement learning baselines.

What Problem Does This Paper Address?

Controlling a musculoskeletal model is significantly more difficult than controlling a standard torque-actuated humanoid. While a typical robot might have 30 degrees of freedom (DoF) controlled by motors, the MS-Human-700 model used here features 700 muscle-tendon units. These muscles can only pull (not push), and their activation dynamics act as a low-pass filter, making high-frequency movements extremely difficult to execute.

The authors identify two primary "gaps" in current research:

  1. The Retargeting Gap: Human motion data (from video or MoCap) often contains artifacts like "foot skating" or jitter. While a torque-driven robot can brute-force its way through these errors, a muscle-driven model finds them physically impossible or prohibitively "expensive" to track, leading to training failure.
  2. The Exploration Gap: In a 700-dimensional action space, standard random exploration is disastrous. Most random muscle activations simply cause the character to collapse before it can learn anything useful.

Methods

The core philosophy of this work is that muscle redundancy—having many more muscles than joints—is not just a burden (high dimensionality) but also a bounty (flexibility).

The proposed motion-to-policy pipeline, showing how raw input is refined through MAR and explored via NSE to produce a stable 700-muscle policy.

1. Muscle-Aware Retargeting (MAR)

Instead of forcing the model to follow a "dirty" kinematic reference, MAR performs bounded, smooth edits to the trajectory. It uses a B-spline basis to ensure edits are low-frequency and "muscle-friendly." Crucially, it enforces hard anatomical and contact constraints (e.g., feet cannot go through the floor) while prioritizing "root feasibility"—ensuring the center of mass movement is actually achievable by the model's physics.

2. Null-Space Exploration (NSE)

NSE addresses the exploration problem by identifying the null space of muscle excitations. Because the system is highly redundant, many different combinations of muscle activations result in the same net force on the joints. NSE calculates this local mapping and injects exploration noise specifically into these "task-neutral" directions. This allows the agent to try out diverse muscle coordination strategies without disrupting its balance or the overall motion.

Visualization of null directions within the muscle excitation space. NSE projects exploration noise into the subspace that minimizes mechanical disturbance.

Datasets

  • HUMAPS-4D Benchmark: A quality-gated subset of 24 motion-capture clips covering three subjects and eight actions (walking, jogging, jumping, squats, etc.).
  • In-the-Wild Video: The authors demonstrate the pipeline's robustness using monocular videos of tennis and dancing, processed through the GVHMR world-grounded motion estimator.

Key Insights and Ideas

  • Artifact Amplification: The authors mathematically demonstrate that tracking high-frequency noise is roughly 23x more costly for a muscle-driven system than a torque-driven one. This explains why standard retargeting fails for musculoskeletal models.
  • Redundancy as a Safety Valve: By exploring in the null space, the agent can "practice" muscle recruitment patterns that don't affect the immediate task, effectively decoupling the learning of muscle coordination from the learning of balance and task completion.
  • Two-Rate Gating: NSE uses a "fast" state to track policy uncertainty and a "slow" state to track overall competence. This creates a high-low-high exploration schedule that keeps the policy robust even in late-stage training.

Key Results

The combination of MAR and NSE outperformed the baseline (BA + Pure QFlex) across all metrics:

  • Success Rate: Solved 100% of the benchmark references, whereas the baseline failed on several.
  • Sample Efficiency: Reached full-horizon completion in 8.1 million samples, nearly twice as fast as the baseline's 16.1 million.
  • Fidelity: Reduced the Mean Per-Joint Position Error (MPJPE) by 44% (from 95.4mm to 53.7mm).
  • Stability: Eliminated "late collapse," a common issue where a policy suddenly fails after millions of steps of successful training.
Learning curves showing that MAR+NSE (solid orange) reaches higher returns faster and more reliably than baselines.

The end-to-end video-to-policy results are particularly striking, showing a 700-muscle model successfully imitating a tennis swing from a single camera view.

Qualitative results of the full pipeline transforming a monocular tennis video into a stable musculoskeletal control policy.

Limitations and Future Work

  • Short-Horizon Mapping: NSE currently uses a "one-control-frame" mapping for the null space. The authors suggest that a longer-horizon mapping could unlock even more effective exploration.
  • Task-Specific Null Spaces: Currently, the null space is defined by what doesn't move the joints. Future work could define it by what doesn't affect a specific task (e.g., "don't fall"), which would provide an even larger "blissful" subspace for exploration.
  • Hardware Transfer: While this work is simulation-based, the principles of muscle-aware control are directly applicable to emerging tendon-driven musculoskeletal robot hardware.

Summary updated

Abstract

Learning whole-body musculoskeletal control from human motion is important for developing human-like robots, assistive devices, and rehabilitation systems. This task presents two main challenges, namely reference trajectories that are kinematically plausible but difficult to reproduce through muscle-driven dynamics, and a highly redundant 700-dimensional action space in which unstructured exploration can easily disrupt the target motion. In this paper, we propose a motion-to-policy pipeline that exploits muscle redundancy in two complementary stages. First, muscle-aware retargeting (MAR) performs bounded adaptation of kinematic trajectories subject to hard semantic, anatomical, and contact constraints. We motivate the constraint bounds by analyzing how reference-trajectory artifacts affect muscle-driven tracking. Second, null-space exploration (NSE) estimates a one-control-frame mapping from muscle excitations to generalized forces and injects bounded, anatomically structured perturbations along its null space into the actions of a value-guided flow policy. On a 24-clip motion-capture benchmark, MAR and NSE together solve every reference, reach the full horizon with half the samples of the baseline pipeline, and lower joint-center error by 44% without late collapse. To the best of our knowledge, this is the first end-to-end pipeline that transforms monocular video into a trained whole-body imitation policy controlling 700 muscles.
BibTeX
@misc{kong2026burden,
  author = {Ruiyang Kong and Takeshi Oishi},
  title = {{Burden, Bounty, or Bliss? Muscle-Aware Retargeting and Null-Space Exploration for Whole-Body Musculoskeletal Control}},
  year = {2026},
  eprint = {2611.10682},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.10682},
}

Loading related content...

Figure