Diffusion-Based Impedance Learning for Contact-Rich Manipulation Tasks

• URL: http://arxiv.org/abs/2509.19696v2
• Date: Mon, 29 Sep 2025 11:22:15 GMT
• Title: Diffusion-Based Impedance Learning for Contact-Rich Manipulation Tasks
• Abstract summary: Impedance Control shapes physical interaction but requires task-aware tuning by selecting feasible impedance parameters.<n>We present Diffusion-Based Impedance Learning, a framework that combines both domains.
• Score: 13.17252299377244
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning methods excel at motion generation in the information domain but are not primarily designed for physical interaction in the energy domain. Impedance Control shapes physical interaction but requires task-aware tuning by selecting feasible impedance parameters. We present Diffusion-Based Impedance Learning, a framework that combines both domains. A Transformer-based Diffusion Model with cross-attention to external wrenches reconstructs a simulated Zero-Force Trajectory (sZFT). This captures both translational and rotational task-space behavior. For rotations, we introduce a novel SLERP-based quaternion noise scheduler that ensures geometric consistency. The reconstructed sZFT is then passed to an energy-based estimator that updates stiffness and damping parameters. A directional rule is applied that reduces impedance along non task axes while preserving rigidity along task directions. Training data were collected for a parkour scenario and robotic-assisted therapy tasks using teleoperation with Apple Vision Pro. With only tens of thousands of samples, the model achieved sub-millimeter positional accuracy and sub-degree rotational accuracy. Its compact model size enabled real-time torque control and autonomous stiffness adaptation on a KUKA LBR iiwa robot. The controller achieved smooth parkour traversal within force and velocity limits and 30/30 success rates for cylindrical, square, and star peg insertions without any peg-specific demonstrations in the training data set. All code for the Transformer-based Diffusion Model, the robot controller, and the Apple Vision Pro telemanipulation framework is publicly available. These results mark an important step towards Physical AI, fusing model-based control for physical interaction with learning-based methods for trajectory generation.

Related papers

• Actuator Reality Shaping for Zero-Shot Sim-to-Real Robot Learning [0.5277024349608834]
  Sim-to-real transfer in robot learning is often limited by discrepancies between the ideal actuator dynamics assumed during policy training and the nonlinear, hardware-dependent behavior of physical motors.<n>We introduce an alternative paradigm: actuator reality shaping.<n>We validate the approach on a single-joint high-gear-ratio servo under external loads and a 7-DOF robotic arm reaching task.
  arXiv  Detail & Related papers  (2026-07-02T14:12:41Z)
• 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)
• Physics-Informed Reinforcement Learning of Spatial Density Velocity Potentials for Map-Free Racing [73.88859384645264]
  Out-Of-Distribution (OOD) generalization to various racetracks utilizes Machine Learning (ML) to encode the mathematical relation between sensor data and vehicle actuation for end-to-end control.<n>This paper presents a DRL method that parameterizes nonlinear vehicle dynamics from the spectral distribution of depth measurements with a non-geometric, physics-informed reward, to infer vehicle time-optimal and overtaking racing controls with an Artificial Neural Network (ANN)<n>The policy outperforms human demonstrations by 12% in OOD tracks on proportionally scaled hardware, by maximizing the friction circle with tire dynamics that resemble an empirical Pacejka tire model.
  arXiv  Detail & Related papers  (2026-04-10T17:12:07Z)
• Dual-Agent Multiple-Model Reinforcement Learning for Event-Triggered Human-Robot Co-Adaptation in Decoupled Task Spaces [3.349003999623489]
  This paper presents a shared-control rehabilitation policy for a custom 6-degree-of-freedom upper-limb robot.<n>The patient governs the primary reaching direction using binary commands, while the robot autonomously manages corrective motions.
  arXiv  Detail & Related papers  (2026-03-06T11:15:10Z)
• Robot-DIFT: Distilling Diffusion Features for Geometrically Consistent Visuomotor Control [31.523644271297616]
  A key bottleneck in generalizable robot manipulation is a structural mismatch between current visual backbones and the physical requirements of closed-loop control.<n>We propose Robot-DIFT, a framework that decouples the source of geometric information from the process of inference via Manifold Distillation.<n>By distilling a frozen diffusion teacher into a deterministic Spatial-Semantic Feature Pyramid Network (S2-FPN), we retain the rich geometric priors of the generative model while ensuring temporal stability, real-time execution, and robustness against drift.
  arXiv  Detail & Related papers  (2026-02-12T13:30:24Z)
• Obstacle Avoidance using Dynamic Movement Primitives and Reinforcement Learning [36.09105994195904]
  This work proposes an alternative approach that quickly generates smooth, near-optimal collision-free 3D Cartesian trajectories from a single artificial demonstration.<n>The demonstration is encoded as a Dynamic Movement Primitive (DMP) and iteratively reshaped using policy-based reinforcement learning.<n>The approach is validated in simulation and real-robot experiments, outperforming a RRT-Connect baseline in terms of computation and execution time.
  arXiv  Detail & Related papers  (2025-10-10T10:51:42Z)
• 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)
• Physical Autoregressive Model for Robotic Manipulation without Action Pretraining [65.8971623698511]
  We build upon autoregressive video generation models to propose a Physical Autoregressive Model (PAR)<n>PAR leverages the world knowledge embedded in video pretraining to understand physical dynamics without requiring action pretraining.<n>Experiments on the ManiSkill benchmark show that PAR achieves a 100% success rate on the PushCube task.
  arXiv  Detail & Related papers  (2025-08-13T13:54:51Z)
• Embodied Neuromorphic Control Applied on a 7-DOF Robotic Manipulator [10.642836177302533]
  Inverse dynamics is a fundamental robotics problem, which maps from joint space to torque space of robotic systems.<n>We use Spiking Neural Network to leverage continuity of the motion data to improve control accuracy and eliminate tuning parameters.<n>This work advances embodied neuromorphic control by one step forward from proof of concept to applications in complex real-world tasks.
  arXiv  Detail & Related papers  (2025-04-17T07:13:37Z)
• FAST: Efficient Action Tokenization for Vision-Language-Action Models [98.15494168962563]
  We propose a new compression-based tokenization scheme for robot actions, based on the discrete cosine transform.<n>Based on FAST, we release FAST+, a universal robot action tokenizer, trained on 1M real robot action trajectories.
  arXiv  Detail & Related papers  (2025-01-16T18:57:04Z)
• RobotDiffuse: Motion Planning for Redundant Manipulator based on Diffusion Model [13.110235244912474]
  Redundant manipulators offer enhanced kinematic performance and versatility.<n>Motion planning for these manipulators is challenging due to increased DOFs and complex, dynamic environments.<n>This paper introduces RobotDiffuse, a diffusion model-based approach for motion planning in redundant manipulators.
  arXiv  Detail & Related papers  (2024-12-27T07:34:54Z)
• End-to-End Reinforcement Learning for Torque Based Variable Height Hopping [5.34772724436823]
  Legged locomotion is arguably the most suited and versatile mode to deal with natural or unstructured terrains. In this paper, we present a end-to-end RL based torque controller that learns to implicitly detect the relevant jump phases. We also extend a method for simulation to reality transfer of the learned controller to contact rich dynamic tasks, resulting in successful deployment on the robot.
  arXiv  Detail & Related papers  (2023-07-31T13:51:29Z)
• Value function estimation using conditional diffusion models for control [62.27184818047923]
  We propose a simple algorithm called Diffused Value Function (DVF) It learns a joint multi-step model of the environment-robot interaction dynamics using a diffusion model. We show how DVF can be used to efficiently capture the state visitation measure for multiple controllers.
  arXiv  Detail & Related papers  (2023-06-09T18:40:55Z)
• OSCAR: Data-Driven Operational Space Control for Adaptive and Robust Robot Manipulation [50.59541802645156]
  Operational Space Control (OSC) has been used as an effective task-space controller for manipulation. We propose OSC for Adaptation and Robustness (OSCAR), a data-driven variant of OSC that compensates for modeling errors. We evaluate our method on a variety of simulated manipulation problems, and find substantial improvements over an array of controller baselines.
  arXiv  Detail & Related papers  (2021-10-02T01:21:38Z)
• Online Body Schema Adaptation through Cost-Sensitive Active Learning [63.84207660737483]
  The work was implemented in a simulation environment, using the 7DoF arm of the iCub robot simulator. A cost-sensitive active learning approach is used to select optimal joint configurations. The results show cost-sensitive active learning has similar accuracy to the standard active learning approach, while reducing in about half the executed movement.
  arXiv  Detail & Related papers  (2021-01-26T16:01:02Z)

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.