AI 中文总结
该研究针对接触密集拆卸任务中扩散策略的延迟问题，提出DPA-FTG分层方法，解耦高低频控制，在双手电池拆卸任务上性能优于RDP等基线。
AI 中文摘要
扩散策略在学习机器人操作的复杂多模态行为方面已表现出强大性能，但将其应用于接触密集的拆卸任务仍受限于一个关键权衡：迭代去噪过程会引入推理延迟，导致难以实现高频控制，而这对于实现凿削、撬动等动态交互至关重要。近期的动作分块技术可缓解延迟，但采用开环执行窗口，使系统无法感知断裂事件引发的快速力瞬变。为填补这一空白，我们提出了快速轨迹生成增强的扩散策略（DPA-FTG）。与专注于位置校正的近期视觉-触觉方法不同，DPA-FTG将低频规划与高频力调节解耦：在高频（5 Hz）层级，条件扩散模型预测潜在参数序列，用于从学习到的原语任务词汇中选择策略；在低频（60 Hz）层级，轻量级的力条件策略作为神经阻抗控制器，实时调节执行以维持接触稳定性。我们在涉及柔性薄片分离的双手电池拆卸任务上验证了该方法，实验评估表明，DPA-FTG的性能优于包括反应式扩散策略（RDP）在内的当前最优基线。
英文摘要
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).
DOI：10.1016/j.rcim.2026.103309
