A Hierarchical Approach to Imitation Learning for Manipulation Tasks Requiring Time Varying Forces

• URL: http://arxiv.org/abs/2608.03103v1
• Date: Tue, 04 Aug 2026 04:21:00 GMT
• Title: A Hierarchical Approach to Imitation Learning for Manipulation Tasks Requiring Time Varying Forces
• Abstract summary: We introduce the Diffusion Policy Augmented by Fast Trajectory Generation (DPA-FTG)<n>Compared to recent visual-tactile approaches that focus on positional correction, DPA-FTG decouples low-frequency planning from high-frequency force regulation.<n>We validate our approach on a bimanual battery disassembly task involving the separation of a compliant sheet.
• Score: 14.372073538832803
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion policies have shown strong performance in learning complex, multi-modal behaviors for robotic manipulation. However, their application to contact-rich disassembly tasks remains limited by a key trade-off: the iterative denoising process introduces inference latencies that makes high frequency control difficult, which is essential for realizing dynamic interactions such as chiseling and prying. Recent action-chunking techniques mitigate latency but use an open-loop execution window, rendering the system blind to rapid force transients caused by fracture events. To bridge this gap, we introduce the Diffusion Policy Augmented by Fast Trajectory Generation (DPA-FTG). Compared to recent visual-tactile approaches that focus on positional correction, DPA-FTG decouples low-frequency planning from high-frequency force regulation. At the high level ($5$ Hz), a conditional diffusion model predicts a sequence of latent parameters for selecting a strategy from a learned vocabulary of task primitives. At the low level ($60$ Hz), a lightweight, force-conditioned policy acts as a neural impedance controller, modulating execution in real-time to maintain contact stability. We validate our approach on a bimanual battery disassembly task involving the separation of a compliant sheet. Experimental evaluation demonstrates that DPA-FTG outperforms state-of-the-art baselines, including Reactive Diffusion Policy (RDP).

Related papers

• FA-RDP: A Frequency-Adaptive Reactive Diffusion Policy for Contact-Rich Manipulation [46.70731586911338]
  Action multimodality and reactivity dominate different stages of a single episode.<n>Standard diffusion policies use a fixed inference frequency and sampling steps throughout the episode.<n>We present FA-RDP, a frequency-adaptive reactive diffusion policy.
  arXiv  Detail & Related papers  (2026-07-30T17:47:49Z)
• Asynchronous Multimodal Diffusion Policy Composition via Latency-Aware Guidance Fusion [52.50952605013304]
  We propose LAG-Fusion, a latency-aware guidance fusion framework for asynchronous multimodal diffusion policy composition.<n>We instantiate LAG-Fusion in contact-rich manipulation by composing a low-frequency vision policy with a high-frequency force policy.
  arXiv  Detail & Related papers  (2026-07-19T13:48:52Z)
• VADF: Vision-Adaptive Diffusion Policy Framework for Efficient Robotic Manipulation [26.316939305877145]
  Diffusion policies are becoming mainstream in robotic manipulation but suffer from hard negative class imbalance due to uniform sampling and lack of sample difficulty awareness.<n>We propose VADF (Vision-Adaptive Diffusion Policy Framework), a vision-driven dual-adaptive framework that significantly achieves early success in inference.
  arXiv  Detail & Related papers  (2026-04-17T10:56:59Z)
• From Flow to One Step: Real-Time Multi-Modal Trajectory Policies via Implicit Maximum Likelihood Estimation-based Distribution Distillation [18.70033095161235]
  We propose a framework that distills a Conditional Flow Matching expert into a fast single-step student via Implicit Likelihood Estimation (IMLE)<n>A bi-directional Chamfer distance provides a set-level objective that promotes both mode coverage and fidelity.<n>A unified perception encoder further integrates multi-view RGB, depth, point clouds, and proprioception into a geometry-aware representation.
  arXiv  Detail & Related papers  (2026-03-10T09:30:05Z)
• FAVLA: A Force-Adaptive Fast-Slow VLA model for Contact-Rich Robotic Manipulation [20.067295745725257]
  Force/torque feedback can substantially improve Vision-Language-Action (VLA) models on contact-rich manipulation.<n>Most existing approaches fuse all modalities at a single operating frequency.<n>We propose FAVLA, a force-adaptive fast-slow VLA that decouples slow perception planning from fast contact-aware control.
  arXiv  Detail & Related papers  (2026-02-27T03:33:10Z)
• TS-DP: Reinforcement Speculative Decoding For Temporal Adaptive Diffusion Policy Acceleration [64.32072516882947]
  Diffusion Policy excels in embodied control but suffers from high inference latency and computational cost.<n>We propose Temporal-aware Reinforcement-based Speculative Diffusion Policy (TS-DP)<n>TS-DP achieves up to 4.17 times faster inference with over 94% accepted drafts, reaching an inference frequency of 25 Hz.
  arXiv  Detail & Related papers  (2025-12-13T07:53:14Z)
• ImplicitRDP: An End-to-End Visual-Force Diffusion Policy with Structural Slow-Fast Learning [52.86018040861575]
  We propose a unified end-to-end visual-force diffusion policy that integrates visual planning and reactive force control within a single network.<n>We introduce Structural Slow-Fast Learning, a mechanism utilizing causal attention to simultaneously process asynchronous visual and force tokens.<n>Experiments on contact-rich tasks demonstrate that ImplicitRDP significantly outperforms both vision-only and hierarchical baselines.
  arXiv  Detail & Related papers  (2025-12-11T18:59:46Z)
• Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach [78.4812458793128]
  We propose textbfTACO, a test-time-scaling framework that applies a lightweight pseudo-count estimator as a high-fidelity verifier of action chunks.<n>Our method resembles the classical anti-exploration principle in offline reinforcement learning (RL), and being gradient-free, it incurs significant computational benefits.
  arXiv  Detail & Related papers  (2025-12-02T14:42:54Z)
• Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation [58.95799126311524]
  Humans can accomplish contact-rich tasks using vision and touch, with highly reactive capabilities such as fast response to external changes and adaptive control of contact forces.<n>Existing visual imitation learning approaches rely on action chunking to model complex behaviors.<n>We introduce TactAR, a low-cost teleoperation system that provides real-time tactile feedback through Augmented Reality.
  arXiv  Detail & Related papers  (2025-03-04T18:58:21Z)

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.