Reinforcement learning in linear embedding space unlocks generalizable control across soft robot configurations

• URL: http://arxiv.org/abs/2606.08104v1
• Date: Sat, 06 Jun 2026 11:09:46 GMT
• Title: Reinforcement learning in linear embedding space unlocks generalizable control across soft robot configurations
• Abstract summary: Soft-bodied organisms such as octopuses and elephant trunks exhibit remarkable morphological adaptability.<n>Various soft robots have emerged in recent decades, featuring diverse materials, stiffnesses, and morphologies tailored to specific tasks.<n>Here, we introduce a generalizable control system that enables rapid adaptation across diverse soft robot configurations.
• Score: 60.42735420750131
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Soft-bodied organisms such as octopuses and elephant trunks exhibit remarkable morphological adaptability, dynamically reconfiguring body shape and stiffness, and flexibly adjusting their control strategies to enable versatile behaviors. Inspired by these biological systems, various soft robots have emerged in recent decades, featuring diverse materials, stiffnesses, and morphologies tailored to specific tasks. Despite substantial advances in the materials and structural designs of soft robots, developing a generalizable control framework capable of rapid adaptation across diverse configurations remains a long-standing challenge. Existing controllers are limited to fixed configurations, demanding laborious configuration-specific remodelling and policy redesign for new configurations. Here, we introduce a generalizable control system that enables rapid adaptation across diverse soft robot configurations via reinforcement learning in a shared linear Koopman embedding space. By encoding robot dynamics into this embedding space, our method decouples control policies from specific morphologies, allowing real-time, model-free policy adaptation across diverse configurations without retraining from scratch. We validate our system across 33 distinct robot configurations. Our system achieves a 75 times reduction in transfer samples across configurations, while sustaining robust performance under high-speed motion, heavy payloads, and multiactuator faults, and achieving real-world skills previously unattainable in soft robotics. This work establishes a unified and adaptable control paradigm for diverse soft robot configurations, bridging mechanical reconfigurability with control flexibility, and may offer broader insights for generalizable control in complex physical systems.

Related papers

• Tensegrity Continuum Robots Enable Task-Adaptive Morphologies for Cooperative Behaviors [3.443736248915025]
  We introduce an MRR that unifies the advantages of both architectures by combining a tensegrity-based compliant body with claw-based connection mechanisms.<n>We demonstrate the robots' capability across diverse tasks and environments, including coordinated object manipulation and transport, multimodal locomotion, and loco-manipulation.<n>These results lay a foundation for adaptable and multifunctional robotic collectives, with broad potential applications in manufacturing, space exploration, and search-and-rescue operations.
  arXiv  Detail & Related papers  (2026-08-27T15:05:30Z)
• Morphing MILR: Design and control of a cable-driven limbless robot with rolling joints for maneuvering in complex environments [5.94633614993598]
  Limbless robots offer exceptional mobility in confined and cluttered environments.<n>Recent designs incorporating compliance demonstrate robust locomotion without complex sensing or control.<n>We present a cable-driven limbless robot that robustnesss body morphology and compliance to enable diverse locomotion modes.
  arXiv  Detail & Related papers  (2026-07-22T03:29:39Z)
• A Continual Learning Framework for Adaptive Control of Modular Soft Robots [4.374184567811783]
  Soft robots have attracted significant attention in applications such as medical intervention, rehabilitation, and robotic manipulation.<n>MSRs represent an emerging class of robotic systems with highly deformable and reconfigurable structures capable of performing complex tasks.<n>Existing approaches typically require controllers to be retrained from scratch whenever the robot morphology changes.<n>We propose a continual learning inspired control framework capable of incrementally adapting to changes in robot morphology.
  arXiv  Detail & Related papers  (2026-07-07T19:11:07Z)
• Learning Context-Aware Neural ODE Dynamics for Adaptive Robotic Control [55.01272784312405]
  We propose a context-aware dynamics model based on neural ordinary differential equations.<n>We validate the approach across diverse robotic platforms, including a quadrotor in simulation, as well as a Sphero BOLT robot and a Fanuc manipulator in real-world experiments.
  arXiv  Detail & Related papers  (2026-06-13T20:55:46Z)
• COSMIC: Concurrent Optimization of Structure, Material, and Integrated Control for robotic systems [9.321828591115567]
  Most robotic systems have their structure, materials, and locomotion designed separately.<n>This separation often leads to suboptimal designs, and we still have individual and collective contributions of these entities.<n>We propose a limited landscape-based co-design framework that simultaneously optimize material design, locomotion, and other complex autonomous behaviors.
  arXiv  Detail & Related papers  (2026-05-12T19:00:01Z)
• Learning Reactive Dexterous Grasping via Hierarchical Task-Space RL Planning and Joint-Space QP Control [50.28263951510334]
  We propose a hybrid hierarchical control framework for reactive dexterous grasping.<n>The proposed framework explicitly decouples high-level spatial intent from low-level joint execution.<n>We extensively validate the proposed framework through a rigorous simulation-to-reality pipeline.
  arXiv  Detail & Related papers  (2026-05-05T04:49:38Z)
• Simulation-Driven Evolutionary Motion Parameterization for Contact-Rich Granular Scooping with a Soft Conical Robotic Hand [14.911239660367926]
  Tool-based scooping is vital in robot-assisted tasks, enabling interaction with objects of varying sizes, shapes, and material states.<n>Recent studies have shown that flexible, reconfigurable soft robotic end-effectors can adapt their shape to maintain consistent contact during scooping.<n>These soft tools can adjust to varying container sizes and materials without requiring complex sensing or control.<n>This paper presents the development of a physics-based simulation model of a deformable soft conical robotic hand.
  arXiv  Detail & Related papers  (2026-04-07T07:30:21Z)
• ZipFold: Modular Actuators for Scaleable Adaptive Robots [52.52738470247707]
  This paper introduces a compact, easy-to-fabricate deployable actuator that achieves reversible scale and stiffness transformations.<n>The simple actuation method allows for smooth, continuous transitions between compact (flexible) and expanded (quasi-rigid) states.
  arXiv  Detail & Related papers  (2026-04-06T23:50:03Z)
• A General Lie-Group Framework for Continuum Soft Robot Modeling [3.0588867238694157]
  This paper introduces a general Lie group framework for modeling continuum soft robots.<n>The framework is extended to handle complex robotic structures, including segmented, branched, nested, and rigid-soft composite configurations.
  arXiv  Detail & Related papers  (2026-03-09T11:03:21Z)
• Surrogate compliance modeling enables reinforcement learned locomotion gaits for soft robots [5.193389420813379]
  Adaptive morphogenetic robots adapt their morphology and control policies to meet changing tasks and environmental conditions.<n>Many such systems leverage soft components, which enable shape morphing but also introduce simulation and control challenges.<n>Here, we present a surrogate compliance modeling approach: rather than explicitly modeling soft-body physics, we introduce indirect variables representing soft-material deformation within a rigid-body simulator.
  arXiv  Detail & Related papers  (2025-12-08T02:52:42Z)
• Universal Morphology Control via Contextual Modulation [52.742056836818136]
  Learning a universal policy across different robot morphologies can significantly improve learning efficiency and generalization in continuous control. Existing methods utilize graph neural networks or transformers to handle heterogeneous state and action spaces across different morphologies. We propose a hierarchical architecture to better model this dependency via contextual modulation.
  arXiv  Detail & Related papers  (2023-02-22T00:04:12Z)
• Differentiable Simulation of Soft Multi-body Systems [99.4302215142673]
  We develop a top-down matrix assembly algorithm within Projective Dynamics. We derive a differentiable control framework for soft articulated bodies driven by muscles, joint torques, or pneumatic tubes.
  arXiv  Detail & Related papers  (2022-05-03T20:03:22Z)
• An End-to-End Differentiable Framework for Contact-Aware Robot Design [37.715596272425316]
  We build an end-to-end differentiable framework for contact-aware robot design. A novel deformation-based parameterization allows for the design of articulated rigid robots with arbitrary, complex geometry. A differentiable rigid body simulator can handle contact-rich scenarios and computes analytical gradients for a full spectrum of kinematic and dynamic parameters.
  arXiv  Detail & Related papers  (2021-07-15T17:53:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.