Robotics Research Hub
VIDP: Variable Impedance Diffusion Policy for Compliant Robot Manipulation from Diverse Demonstrations

VIDP: Variable Impedance Diffusion Policy for Compliant Robot Manipulation from Diverse Demonstrations

Hisham Khalil, Neil Fernandes, Thomas M. Kwok, Hsiu-Chin Lin, Yue Hu · N/A · 2026

manipulation reinforcement-learning control learning-from-demonstration
PDF arXiv

Framework

N/A

License

N/A

Stars

N/A

Summary

Contact-rich manipulation requires precise tracking and mechanical compliance, where variable impedance control can improve robustness in task success, whereas static compliance cannot adapt to varying contact constraints.

Abstract Summary

Contact-rich manipulation requires precise tracking and mechanical compliance, where variable impedance control can improve robustness in task success, whereas static compliance cannot adapt to varying contact constraints. Variable impedance skills can be learned from demonstrations, avoiding complex modeling, but compliance is a hidden variable in force-agnostic kinematic data. While existing methods infer compliance from trajectory variations, these variations may reflect geometric adaptation and not intentional compliance when subject to changing spatial layouts. Therefore, this letter introduces Variable Impedance Diffusion Policy (VIDP), an imitation learning-based variable impedance control framework leveraging a Task-Parameterized Directionality-Aware Mixture Model (TP-DAMM) to extract physically consistent trajectory distributions from diverse demonstrations. By mapping distributions to stiffness profiles, VIDP jointly predicts pose actions and task compliance without force sensors. Real-world experiments show that VIDP significantly outperforms fixed-impedance baselines in task success rate while reducing interaction forces with respect to high stiffness controllers and tracking errors with respect to low stiffness baselines.

Key Points

  • Contact-rich manipulation requires precise tracking and mechanical compliance, where variable impedance control can improve robustness in task success, whereas static compliance cannot adapt to varying contact constraints.
  • Variable impedance skills can be learned from demonstrations, avoiding complex modeling, but compliance is a hidden variable in force-agnostic kinematic data.
  • While existing methods infer compliance from trajectory variations, these variations may reflect geometric adaptation and not intentional compliance when subject to changing spatial layouts.
  • Therefore, this letter introduces Variable Impedance Diffusion Policy (VIDP), an imitation learning-based variable impedance control framework leveraging a Task-Parameterized Directionality-Aware Mixture Model (TP-DAMM) to extract physically consistent trajectory distributions from diverse demonstrations.
  • By mapping distributions to stiffness profiles, VIDP jointly predicts pose actions and task compliance without force sensors.

Methodology

VIDP bridges kinematic demonstrations and compliant policy execution through three stages, as shown in Fig. 1 . First, TP-DAMM extracts spatially and directionally consistent trajectory distributions from diverse demonstrations. Their variance is then mapped to target Cartesian stiffness profiles, which supervise a Diffusion Policy to jointly predict pose actions and compliance from visual and state observations.

Methodology — VIDP: Variable Impedance Diffusion Policy for Compliant Robot Manipulation from Diverse Demonstrations
Fig. 3: Phase-wise analysis of one representative successful and failed trial per task. (Top) Snapshots of execution phases completed by VIDP and corresponding failed task phases by Stiff-DP for (a) and (b) and Compliant-DP for (c). (Middle) Cartesian stiffness profiles inferred by VIDP, dynamically modulated to accommodate task constraints. (Bottom) Interaction forces and tracking errors over time. Fixed-impedance baselines experience severe force spikes, causing jamming in (a) Peg-in-Hole Insertion and slipping in (b) Pulley Assembly , or large tracking errors causing workspace collisions in Cable Routing . In contrast, VIDP adapts its compliance to safely and precisely complete all task phases. Experiment trials can be found in the attached video.

Experimental Evaluation

Does TP-DAMM extract more directionally consistent and representative task trajectory distributions from spatially diverse demonstrations compared to standard clustering methods? RQ2: Does VIDP outperform fixed-impedance baselines in success rate across tasks characterized by varying contact constraints and diverse spatial layouts?

RQ3: How does the inferred variable impedance profile optimize the physical interaction metrics, specifically interaction forces, tracking errors, and energy efficiency, during critical execution phases? We collect d...

Sources and Demonstrations

Figures are reproduced from Khalil et al. See the full paper for experimental details and the project page, when the paper links one, for demonstrations and videos.

Share

Related Papers

A Sim-to-Real Integration Pipeline for Training and Deployment of Chunk-Based VLA Manipulation Policies
arXiv preprint

A Sim-to-Real Integration Pipeline for Training and Deployment of Chunk-Based VLA Manipulation Policies

Mathilde Kappel, Clémence Grislain, Mohamed Chetouani et al.

Vision-Language-Action (VLA) models have become a prominent paradigm for mapping multimodal inputs, including semantic instructions, visual observations of the scene, and proprioceptive observations, to robot actions.

manipulation vision vla reinforcement-learning sim-to-real control learning-from-demonstration benchmark
PDF Advanced
AHEAD: Anticipatory Hand-Driven Teleoperation via Human Intent Prediction
arXiv preprint

AHEAD: Anticipatory Hand-Driven Teleoperation via Human Intent Prediction

Seok Joon Kim, Junho Lee, Federica Spinola et al.

Direct hand-driven teleoperation maps an operator's hand motion to robot end-effector commands at every frame, enabling precise control, but it requires constant monitoring and correction during approach, grasp, and placement, which can be slow and fatiguing.

manipulation reinforcement-learning planning control learning-from-demonstration
PDF Intermediate
Behavioral Cloning Mystery
arXiv preprint

Behavioral Cloning Mystery

Seohong Park, Sergey Levine

Behavioral cloning (BC), despite its simplicity, exhibits many counterintuitive phenomena in the real world. For example, the performance of BC often keeps increasing as the model overfits more to the dataset, and fully closed-loop policies often completely fail without action chunking.

manipulation reinforcement-learning control learning-from-demonstration benchmark
Code PDF Intermediate
GitHub ★ —