Continuous Manifold-Decomposed Impedance Retargeting for Contact-Rich Imitation Learning

• URL: http://arxiv.org/abs/2609.15716v1
• Date: Mon, 14 Sep 2026 15:16:34 GMT
• Title: Continuous Manifold-Decomposed Impedance Retargeting for Contact-Rich Imitation Learning
• Abstract summary: CMDIR transforms fixed-impedance demonstrations into continuous variable-impedance controllers.<n>TMIR pairs an evolving task frame with controller instructions.<n>FastMPO achieves a $5.8$--$9.4times$ speedup over C-MPO with comparable closed-loop outcomes.
• Score: 33.980402689056895
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: CMDIR extends Manifold-Decomposed Impedance Retargeting (MDIR) to transform fixed-impedance demonstrations into continuous variable-impedance controllers, which can also serve as structured supervision for imitation learning. Continuous Task-Manifold Impedance Representation (TMIR) pairs an evolving task frame with controller instructions. Demo-relative Compromise dynamics retain moving-basis transport and control/physical metric mismatch, yielding displacement, reaction-impulse, and perturbation-sensitivity criteria. Quality-to-Fast automatically compiles a solver structure from development paths within a predefined finite space, re-instantiates that structure for each demonstration, and certifies the resulting candidate by multi-resolution evaluation. Across 225 retargeted-controller trials in three real contact tasks, full CMDIR improves mean task-proxy retention and reduces mean pose deviation, force fluctuation, and peak force relative to discrete MDIR. FastMPO achieves a $5.8$--$9.4\times$ speedup over C-MPO with comparable closed-loop outcomes. Downstream experiments demonstrate learnability of the complete TMIR supervision interface; lower force fluctuation and peak force are observed among successful executions, while completion reliability remains uneven across tasks and environments.

Related papers

• TTSD-FAR: Test-Time Self-Distillation with Fisher-Anchored Restoration for Missing-Modality Emotion Recognition in LVLMs [83.78708832901194]
  Large video-language models (LVLMs) have shown remarkable performance on multimodal tasks like multimodal emotion recognition (ER) in the wild.<n>However, real-world deployment remains challenging: modalities may be missing or noisy at test time.<n>We propose a solution in which a frozen teacher guides an adaptive low-rank student via self-distillation.<n>Experiments on MELD, DFEW, and BAH under 0%-50% missing modalities show that this unified adaptation-restoration design consistently outperforms entropy-based adaptation, RAG, and perplexity-based generation.
  arXiv  Detail & Related papers  (2026-08-18T23:40:28Z)
• 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)
• MDIR: A Task-Manifold Impedance Retargeting Method for Contact-Rich Teleoperation [15.013711120696854]
  Single-demonstration controller-to-controller determines impact and force variability.<n>Manifold-De Impedance Retargeting (MDIR) deterministically recomposed the recorded controller into an executable task-channel variable-impedance command.
  arXiv  Detail & Related papers  (2026-07-31T10:41:45Z)
• SegDiff: Segmented Trajectory Diffusion for Consistent and Adaptive Robot Manipulation [65.81476183180527]
  We introduce SegDiff, a closed-loop visuomotor policy that integrates the strengths of both paradigms.<n>SegDiff decomposes demonstrations into motion segments between keyposes and learns to predict the continuous trajectory from the current state to the next keypose.<n>SegDiff demonstrates significant performance gains over existing approaches across various simulated and real-world scenarios.
  arXiv  Detail & Related papers  (2026-07-13T02:48:03Z)
• Repurposing Adversarial Perturbations for Continual Learning: From Defense to Active Alignment [20.37950128370149]
  AdvCL combines three plug-in modules: Intra-Smooth promotes local smoothness via small adversarial perturbations; Proto-Clip uses similarity clipping to prevent excessive alignment to current task prototype; and Inter-Align applies directional alignment toward previous task prototype to reduce representational gaps.<n>Experiments show consistent gains in both standard performance and robustness, with lower forgetting and stronger transfer.
  arXiv  Detail & Related papers  (2026-06-01T14:35:59Z)
• Metropolis-Scale Resilient and Trustworthy Traffic Flow Inference Using Multi-Source Data [20.65202203037699]
  Task-Aware Attentive Neural Process (TA-ANP) is a unified framework for trustworthy global traffic state inference (GTSI)<n>For uncertainty quantification, we combine neural processes with Monte Carlo Dropout to capture both aleatoric and uncertainty.<n>Experiments show TA-ANP achieves state-of-the-art performance across all sub-tasks under deterministic and probabilistic metrics.
  arXiv  Detail & Related papers  (2026-05-24T11:12:02Z)
• Multi-scale Coarse-to-fine Modeling for Test-time Human Motion Control [51.92884966472683]
  MSCoT is a multi-scale, coarse-to-fine model for test-time human motion synthesis and control.<n> MSCoT discretizes motion into a multi-scale hierarchical representation and predicts the entire token sequence at each temporal scale.
  arXiv  Detail & Related papers  (2026-05-14T15:09:49Z)
• Master Micro Residual Correction with Adaptive Tactile Fusion and Force-Mixed Control for Contact-Rich Manipulation [11.467329921917546]
  M2-ResiPolicy is a novel Master-Micro residual control architecture that synergizes high-level action guidance with low-level correction.<n>M2-ResiPolicy significantly outperforms standard Diffusion Policy and state-of-the-art Reactive Diffusion Policy.
  arXiv  Detail & Related papers  (2026-03-16T11:47:52Z)
• When Sensors Fail: Temporal Sequence Models for Robust PPO under Sensor Drift [64.37959940809633]
  We study robustness of Proximal Policy Optimization (PPO) under temporally persistent sensor failures.<n>We show Transformer-based sequence policies substantially outperform, RNN, and SSMs in robustness, maintaining high returns even when large fractions of sensors are unavailable.
  arXiv  Detail & Related papers  (2026-03-04T22:21:54Z)
• Error-Propagation-Free Learned Video Compression With Dual-Domain Progressive Temporal Alignment [92.57576987521107]
  We propose a novel unifiedtransform framework with dual-domain progressive temporal alignment and quality-conditioned mixture-of-expert (QCMoE)<n>QCMoE allows continuous and consistent rate control with appealing R-D performance.<n> Experimental results show that the proposed method achieves competitive R-D performance compared with the state-of-the-arts.
  arXiv  Detail & Related papers  (2025-12-11T09:14:51Z)
• Drift No More? Context Equilibria in Multi-Turn LLM Interactions [58.69551510148673]
  contexts drift is the gradual divergence of a model's outputs from goal-consistent behavior across turns.<n>Unlike single-turn errors, drift unfolds temporally and is poorly captured by static evaluation metrics.<n>We show that multi-turn drift can be understood as a controllable equilibrium phenomenon rather than as inevitable decay.
  arXiv  Detail & Related papers  (2025-10-09T04:48:49Z)

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.