Skip to content

Learning Options for Compositional Motor Control with Adapter Banks

Sep 2026 · 0 citations · 32 references
Computer Science Biology

TL;DR

The ability to generalize to novel motor sequences within the closed-loop control setting is demonstrated, improving on the generalization error of a task-input-conditioned multitask baseline by upto order of magnitude.

Abstract

Learning flexible motor primitives is a hallmark of skilled motor control. Recent neuroscience theory proposes that motor primitives may be implemented as low-rank perturbations of a shared recurrent network, but leaves open how such a system is learned. We translate this principle into a novel architecture for learning motor skills end-to-end: a shared recurrent core modulated by a bank of residual adapters, each selected by a discrete latent code. Trained on closed-loop biomechanical control, the adapters develop emergent low-rank perturbations of the recurrent dynamics despite no architectural rank constraint, placing task representations in disparate subspaces of the shared core network. A simple high-level policy over the learned options, optimized while the whole network is frozen, sequences the low-rank adapters to produce novel out-of-distribution movements. We demonstrate the ability to generalize to novel motor sequences within the closed-loop control setting, improving on the generalization error of a task-input-conditioned multitask baseline by upto order of magnitude.

View source

Similar papers

Preprint Aug 2026

PredVLA: Predictive Sensorimotor Modeling for Sub-Million-Parameter Robot Manipulation

A mechanism-by-mechanism transition to the recurrent behavior-cloning baseline shows that replacing the predictive pathway with direct observation input produces the largest single performance drop, accounting for approximately $70\% of the endpoint gap.

Hiroki Sawada, Shunichi Kasahara · 1 citation
Review Open access Aug 2026

De novo motor learning as controller synthesis: a conceptual framework

This framework interprets slow or variable acquisition, structured generalization, context dependence, and learning-rate/outcome dissociations as possible consequences of controller-memory formation, stabilization, retrieval, and expression, rather than of slow parameter convergence within an established controller.

Ian S. Howard · 0 citations
Preprint Oct 2026

Continual Humanoid Motion Learning

Humanoid whole-body controllers can now track a diverse set of dynamic motions, but they are typically trained offline and then frozen, so teaching such a controller a new skill tends to erode the skills it already mastered. We study continual learning for humanoid whole-body motion, where a single controller must acqu...

Zhe-Wen He, Hao Huang, Geeta Chandra Raju Bethala et al. · 0 citations
Preprint Oct 2026

Imitation Learning via Discrete and Rhythmic Primitive Composition

This work proposes Neural Dynamic Composition (NDC), a supervised framework to compose Dynamic Movement Primitives (DMPs) using only raw trajectories for supervision, given a single example of each primitive.

Rafid Saif, A. Ijspeert, Hsiu-Chin Lin · 0 citations

Learning Expressive and Compositional Motion Representation via Spectral Skills

Robotic foundation models offer a promising path toward general-purpose humanoid robot control, often through hierarchical architectures. However, their effectiveness depends on the command interface between the planner and the controller, which must support accurate execution while remaining easy to predict, and ideal...

Fei-Yang Wu, Chen-Xiao Gao, Chen Yang et al. · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.