ForceDelta-VLA：面向接触丰富操作的力条件动作校正蒸馏

中文摘要 AI 辅助

力感知视觉-语言-动作（VLA）策略可改善接触丰富的操作，但通常将任务级运动与接触相关调整合并为单一动作预测。演示数据未提供显式标签，用于将该预测分解为可复用的参考动作与校正项。我们提出ForceDelta-VLA，一种校正蒸馏框架，利用冻结教师模型的力条件模式与学习得到的力无关模式的配对预测，构建显式的力校正目标。单独的延迟校正目标用于处理参考动作不匹配及参考状态变化。训练采用异步调度回放，并在执行期间使用缓存的任务上下文。所得轻量级策略利用近期力历史与机器人状态调整参考动作，在参考动作更新之间响应接触变化，而无需重新生成完整动作块。在九个单臂及双臂接触丰富任务中，ForceDelta-VLA实现了82.2%的平均成功率，而原始ForceVLA基线为54.4%。直接执行我们的第一阶段时间教师模型达到70.6%。与ForceVLA相比，完整系统在两个平台上将成功试验的平均峰值接触力降低了约26%。

英文摘要

Force-aware Vision-Language-Action (VLA) policies improve contact-rich manipulation, but typically combine task-level motion and contact-dependent adjustment in a single action prediction. Demonstrations provide no explicit labels for decomposing that prediction into a reusable reference action and a correction. We present ForceDelta-VLA, a correction-distillation framework that constructs an explicit force-correction target using paired predictions from a frozen teacher's force-conditioned and learned force-agnostic modes. A separate delay-correction target accounts for reference-action mismatch and the change in reference state. Training uses asynchronous schedule replay with the cached task context available during execution. The resulting lightweight policy adjusts the reference actions using recent force history and robot state, responding to contact changes between reference-action updates without regenerating complete action chunks. Across nine single-arm and bimanual contact-rich tasks, ForceDelta-VLA achieves an 82.2% mean success rate, compared with 54.4% for the original ForceVLA baseline. Direct execution of our Stage-1 Temporal Teacher achieves 70.6%. Relative to ForceVLA, the complete system reduces mean peak contact force over successful trials by approximately 26% on both platforms.

发表机构

• University of Hamburg（汉堡大学）
• University of Science and Technology of China（中国科学技术大学）
• Technical University of Munich（慕尼黑工业大学）

机构由 AI 辅助整理，请以论文原文为准。

补充信息

备注

8 pages, 8 figures