发表机构
Zhejiang University（浙江大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出PathTime-VLA，通过路径-时间解耦优化VLA策略，经分阶段后训练后，在三项任务中成功率优于基线，且成功试验平均完成时间缩短39%-52%。
AI 中文摘要
视觉-语言-动作（VLA）策略通常以固定时间间隔预测动作，将机器人的运动路径与其执行节奏耦合在一起。这种耦合给遥操作的适配带来了困难：有用的几何指导会附带由界面延迟和操作者行为决定的时间特性。我们的核心见解是将经典运动规划的路径-时间参数化引入VLA的学习动作表示中。我们提出PathTime-VLA，它将运动表示为进度索引的交互路径$X(s)$和正区间时间轮廓。后者定义了一个单调时间律$t(s)$，生成控制器命令$X(s(t))$。对于给定路径，可通过时间轮廓表达替代执行方式，从而在不改变几何预测目标的情况下实现分块速度选择。该表示支持分阶段后训练流程：演示和DAgger干预建立目标领域先验，Speed-DQN从机器人交互中学习执行乘数，Path-AWR使用回滚结果优化扩散路径生成器。路径条件动作专家实现生成的运动，同时保持路径生成与执行计时的不同学习接口。在三项任务中，完整方法的成功率为58/60，而PathTime-VLA在固定1×下采用BC+DAgger的成功率为57/60，成功试验的平均完成时间缩短了约39%-52%。
英文摘要
Vision-Language-Action (VLA) policies typically predict actions at fixed time intervals, coupling the route a robot follows with its execution pace. This coupling complicates adaptation from teleoperation: useful geometric guidance comes with timing shaped by interface delays and operator behavior. Our key insight is to bring the path-time parameterization of classical motion planning into the learned action representation of a VLA. We introduce PathTime-VLA, which represents motion as a progress-indexed interaction path $X(s)$ and a positive interval-time profile. The latter defines a monotone time law $t(s)$, yielding controller commands $X(s(t))$. For a given path, alternative executions are expressed through the time profile, allowing chunk-wise speed choices without changing the geometric prediction target. This representation supports a staged post-training procedure: demonstrations and DAgger interventions establish a target-domain prior, Speed-DQN learns execution multipliers from robot interaction, and Path-AWR uses rollout outcomes to refine the diffusion path generator. A path-conditioned action expert realizes the resulting motions while maintaining distinct learning interfaces for path generation and execution timing. Across three tasks, the complete method achieves $58/60$ successes versus $57/60$ for PathTime-VLA under BC + DAgger at fixed $1\times$, with approximately $39$-$52\%$ shorter mean completion times over successful trials.
Comments8 pages, 7 figures
