Variable Stiffness for Robust Locomotion through Reinforcement Learning

• URL: http://arxiv.org/abs/2502.09436v2
• Date: Tue, 22 Apr 2025 06:55:59 GMT
• Title: Variable Stiffness for Robust Locomotion through Reinforcement Learning
• Abstract summary: This paper introduces a novel control paradigm that integrates variable stiffness into the action space alongside joint positions.<n>We show that variable stiffness policies, with grouping in per-leg stiffness (PLS), outperform position-based control in velocity tracking and push recovery.
• Score: 8.577291729956137
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement-learned locomotion enables legged robots to perform highly dynamic motions but often accompanies time-consuming manual tuning of joint stiffness. This paper introduces a novel control paradigm that integrates variable stiffness into the action space alongside joint positions, enabling grouped stiffness control such as per-joint stiffness (PJS), per-leg stiffness (PLS) and hybrid joint-leg stiffness (HJLS). We show that variable stiffness policies, with grouping in per-leg stiffness (PLS), outperform position-based control in velocity tracking and push recovery. In contrast, HJLS excels in energy efficiency. Despite the fact that our policy is trained on flat floor only, our method showcases robust walking behaviour on diverse outdoor terrains, indicating robust sim-to-real transfer. Our approach simplifies design by eliminating per-joint stiffness tuning while keeping competitive results with various metrics.

Related papers

• VIDP: Variable Impedance Diffusion Policy for Compliant Robot Manipulation from Diverse Demonstrations [8.606058461805732]
  This letter introduces Variable Impedance Diffusion Policy (PVID), an imitation learning-based variable impedance control framework.<n>By mapping to stiffness profiles, VIDP jointly predicts pose actions and task compliance without force sensors.<n>Real-world experiments show that VIDP significantly outperforms fixed-impedance baselines in task success rate.
  arXiv  Detail & Related papers  (2026-08-06T16:03:00Z)
• Active Stiffness Control of a Supportive Continuum Robot [0.764671395172401]
  Supportive continuum robots (SCRs) enhance the load-bearing capability of an operative continuum robot by mechanically coupling it with a supportive arm.<n>Active stiffness control is needed to regulate the load response and maintain positioning accuracy.<n>This paper presents an active task-space stiffness control framework for a tendon-driven SCR.
  arXiv  Detail & Related papers  (2026-08-04T13:51:05Z)
• Adaptive Control of Motor-Position-Controlled Flexible Joint Robots with Uncertain Joint Stiffness [12.14646384398074]
  We propose an adaptive control approach to improve model-based control of flexible joint robots.<n>As opposed to classical adaptive control approaches for non-elastic robots, we rely on an implicit control law and a control-input-dependent regressor matrix.<n> Experimental results on a flexible joint with nonlinear stiffness characteristics demonstrate the effectiveness of the proposed approach.
  arXiv  Detail & Related papers  (2026-07-15T12:53:04Z)
• 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)
• Learn Weightlessness: Imitate Non-Self-Stabilizing Motions on Humanoid Robot [56.377161933570335]
  Humans naturally exploit a "weightless" state during non-self-stabilizing (NSS) motions.<n>Inspired by this biological mechanism, we propose a weightlessness-state auto-labeling strategy for dataset annotation.<n>Our work bridges the gap between precise trajectory tracking and adaptive environmental interaction, offering a biologically-inspired solution for contact-rich humanoid control.
  arXiv  Detail & Related papers  (2026-04-23T07:10:05Z)
• Probe-to-Grasp Manipulation Using Self-Sensing Pneumatic Variable-Stiffness Joints [9.920023397258435]
  This paper presents a probe-to-grasp manipulation framework for estimating the relative stiffness of objects.<n>We use a passive soft-rigid two-finger hybrid gripper equipped with self-sensing pneumatic variable-stiffness joints.<n>We validate the self-sensing model through stiffness characterization experiments and demonstrate stiffness-aware probing-and-grasping in real-life applications.
  arXiv  Detail & Related papers  (2026-03-29T18:43:19Z)
• Weight Updates as Activation Shifts: A Principled Framework for Steering [54.70188910511715]
  Activation steering promises to be an extremely parameter-efficient form of adaptation, but its effectiveness depends on critical design choices.<n>We establish a first-order equivalence between activation-space interventions and weight-space updates, deriving the conditions under which activation steering can replicate fine-tuning behavior.<n>This equivalence yields a principled framework for steering design and identifies the post-block output as a theoretically-backed and highly expressive intervention site.
  arXiv  Detail & Related papers  (2026-02-28T02:50:04Z)
• Grasp to Act: Dexterous Grasping for Tool Use in Dynamic Settings [5.05447792208957]
  We present Grasp-to-Act, a hybrid system that combines physics-based grasp optimization with reinforcement-learning-based grasp adaptation to maintain stable grasps.<n>Our method synthesizes robust grasp configurations informed by human demonstrations and employs an adaptive controller that residually issues joint corrections to prevent in-hand slip.<n>Across simulation and real-world hardware trials with a 16-DoF dexterous hand, our method reduces translational and rotational in-hand slip and achieves the highest task completion rates.
  arXiv  Detail & Related papers  (2026-02-24T01:53:39Z)
• HUSKY: Humanoid Skateboarding System via Physics-Aware Whole-Body Control [67.58927286226925]
  We propose a learning-based framework that integrates humanoid-skateboard system modeling and physics-aware whole-body control.<n>Experiments on the Unitree G1 humanoid platform demonstrate that our framework enables stable and agile maneuvering on skateboards in real-world scenarios.
  arXiv  Detail & Related papers  (2026-02-03T07:18:01Z)
• CHIP: Adaptive Compliance for Humanoid Control through Hindsight Perturbation [70.5382178207975]
  hIsight Perturbation (CHIP) is a plug-and-play module that enables controllable end-effector stiffness.<n>CHIP is easy to implement and requires neither data augmentation nor additional reward tuning.<n>We show that a generalist motion-tracking controller trained with CHIP can perform a diverse set of forceful manipulation tasks.
  arXiv  Detail & Related papers  (2025-12-16T18:56:04Z)
• RobotDancing: Residual-Action Reinforcement Learning Enables Robust Long-Horizon Humanoid Motion Tracking [50.200035833530876]
  RobotDancing is a simple, scalable framework that predicts residual joint targets to explicitly correct dynamics discrepancies.<n>It can track multi-minute, high-energy behaviors (jumps, spins, cartwheels) and deploys zero-shot to hardware with high motion tracking quality.
  arXiv  Detail & Related papers  (2025-09-25T03:30:34Z)
• Improving Human Motion Plausibility with Body Momentum [49.636235399261494]
  Many studies decompose human motion into local motion in a frame attached to the root joint and global motion of the root joint in the world frame.<n>We propose using whole-body linear and angular momentum as a constraint to link local motion with global movement.<n>We introduce a new loss term that enforces consistency between the generated momentum profiles and those observed in ground-truth data.
  arXiv  Detail & Related papers  (2025-09-11T14:34:32Z)
• MULE: Multi-terrain and Unknown Load Adaptation for Effective Quadrupedal Locomotion [1.479858319622657]
  Quadrupedal robots are increasingly deployed for load-carrying tasks across diverse terrains. We propose an Adaptive Reinforcement Learning framework that enables quadrupedal robots to adapt to both varying payloads and diverse terrains. We validate the proposed approach through large-scale simulation experiments in Isaac Gym and real-world hardware deployment on a Unitree Go1 quadruped.
  arXiv  Detail & Related papers  (2025-05-01T12:41:35Z)
• Coordinating Spinal and Limb Dynamics for Enhanced Sprawling Robot Mobility [0.047116288835793156]
  A flexible spine enables undulation of the body through a wavelike motion along the spine, aiding navigation over uneven terrains and obstacles. Environmental uncertainties, such as surface irregularities and variations in friction, can significantly disrupt body-limb coordination. Deep reinforcement learning offers a promising framework for handling non-deterministic environments. We comparatively examine learning-based control strategies and biologically inspired gait design methods on a salamander-like robot.
  arXiv  Detail & Related papers  (2025-04-18T23:08:48Z)
• Spatial-Temporal Graph Diffusion Policy with Kinematic Modeling for Bimanual Robotic Manipulation [88.83749146867665]
  Existing approaches learn a policy to predict a distant next-best end-effector pose. They then compute the corresponding joint rotation angles for motion using inverse kinematics. We propose Kinematics enhanced Spatial-TemporAl gRaph diffuser.
  arXiv  Detail & Related papers  (2025-03-13T17:48:35Z)
• GainAdaptor: Learning Quadrupedal Locomotion with Dual Actors for Adaptable and Energy-Efficient Walking on Various Terrains [0.8739101659113157]
  Deep reinforcement learning (DRL) has emerged as an innovative solution for controlling legged robots in challenging environments.<n>We propose GainAdaptor, an adaptive gain control framework that autonomously tunes joint PD gains to enhance terrain adaptability and energy efficiency.<n>We validate the effectiveness of the proposed method through experiments conducted on a Unitree Go1 robot, demonstrating improved locomotion performance across diverse terrains.
  arXiv  Detail & Related papers  (2024-12-12T18:06:22Z)
• Deep-Learning Control of Lower-Limb Exoskeletons via simplified Therapist Input [0.0]
  Partial-assistance exoskeletons hold significant potential for gait rehabilitation.<n>The control of interaction torques in exoskeletons relies on a hierarchical control structure.<n>This work proposes a three-step, data-driven approach to address the limitations of hierarchical control in exoskeletons.
  arXiv  Detail & Related papers  (2024-12-10T22:52:44Z)
• 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)
• VAE-Loco: Versatile Quadruped Locomotion by Learning a Disentangled Gait Representation [78.92147339883137]
  We show that it is pivotal in increasing controller robustness by learning a latent space capturing the key stance phases constituting a particular gait. We demonstrate that specific properties of the drive signal map directly to gait parameters such as cadence, footstep height and full stance duration. The use of a generative model facilitates the detection and mitigation of disturbances to provide a versatile and robust planning framework.
  arXiv  Detail & Related papers  (2022-05-02T19:49:53Z)
• Next Steps: Learning a Disentangled Gait Representation for Versatile Quadruped Locomotion [69.87112582900363]
  Current planners are unable to vary key gait parameters continuously while the robot is in motion. In this work we address this limitation by learning a latent space capturing the key stance phases constituting a particular gait. We demonstrate that specific properties of the drive signal map directly to gait parameters such as cadence, foot step height and full stance duration.
  arXiv  Detail & Related papers  (2021-12-09T10:02:02Z)
• Learning to Jump from Pixels [23.17535989519855]
  We present Depth-based Impulse Control (DIC), a method for synthesizing highly agile visually-guided behaviors. DIC affords the flexibility of model-free learning but regularizes behavior through explicit model-based optimization of ground reaction forces. We evaluate the proposed method both in simulation and in the real world.
  arXiv  Detail & Related papers  (2021-10-28T17:53:06Z)
• Consolidating Kinematic Models to Promote Coordinated Mobile Manipulations [96.03270112422514]
  We construct a Virtual Kinematic Chain (VKC) that consolidates the kinematics of the mobile base, the arm, and the object to be manipulated in mobile manipulations. A mobile manipulation task is represented by altering the state of the constructed VKC, which can be converted to a motion planning problem.
  arXiv  Detail & Related papers  (2021-08-03T02:59:41Z)
• Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots [121.42930679076574]
  We present a model-free reinforcement learning framework for training robust locomotion policies in simulation. domain randomization is used to encourage the policies to learn behaviors that are robust across variations in system dynamics. We demonstrate this on versatile walking behaviors such as tracking a target walking velocity, walking height, and turning yaw.
  arXiv  Detail & Related papers  (2021-03-26T07:14:01Z)
• ADD: Analytically Differentiable Dynamics for Multi-Body Systems with Frictional Contact [26.408218913234872]
  We present a differentiable dynamics solver that is able to handle frictional contact for rigid and deformable objects. Through a principled mollification of normal and tangential contact forces, our method circumvents the main difficulties inherent to the non-smooth nature of frictional contact.
  arXiv  Detail & Related papers  (2020-07-02T09:51:36Z)
• Learning Compliance Adaptation in Contact-Rich Manipulation [81.40695846555955]
  We propose a novel approach for learning predictive models of force profiles required for contact-rich tasks. The approach combines an anomaly detection based on Bidirectional Gated Recurrent Units (Bi-GRU) and an adaptive force/impedance controller.
  arXiv  Detail & Related papers  (2020-05-01T05:23:34Z)

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.