外观
论文arXiv 2610.1177120 天前
PathTime-VLA解耦路径与时间，VLA策略执行效率提升39%-52%
本文由 AI 根据公开内容整理，可能有误，请以原文为准：PathTime-VLA: Path-Time Decoupling for Factorized Post-Training of Vision-Language-Action Policies（arXiv 2610.11771）
核心内容
针对视觉-语言-动作（VLA）模型因固定时间步预测导致路径与执行节奏强耦合、难以适配含延迟遥操作数据的痛点，研究提出PathTime-VLA框架。该方法引入经典运动规划中的路径-时间参数化思想，将机器人运动表征为进度索引的交互路径$X(s)$与单调时间律$t(s)$。实验显示，在三项基准任务中，完整方法取得58/60的成功率，且成功试验的平均完成时间相比BC+DAgger固定1倍速基线缩短约39%-52%，验证了解耦表征对提升VLA执行效率的有效性。
技术架构上，PathTime-VLA采用分阶段后训练流程：首先通过演示数据与DAgger干预建立目标域先验；其次利用Speed-DQN从机器人交互中学习执行倍率，实现不改变几何预测目标下的分块速度调节；最后通过Path-AWR基于Rollout结果优化扩散路径生成器。系统通过路径条件动作专家生成最终指令，保持了路径生成与执行时序的独立学习接口，使模型能在复用几何引导的同时，自主适应不同任务的动态执行节奏。
关键看点
- 时空解耦表征：将运动分解为进度索引路径$X(s)$与正区间时间轮廓，通过单调时间律$t(s)$生成控制指令，支持几何不变下的速度调节
- 三阶段后训练：依次采用演示+DAgger建立先验、Speed-DQN学习执行倍率、Path-AWR优化扩散路径生成器，实现路径与时序的独立优化
- 执行效率提升：在三项任务中成功率达58/60，成功样本平均完成时间较固定速率BC+DAgger基线缩短39%-52%，显著优于传统定频预测
工程与产业观察
该工作证明了将经典运动规划的路径-时间解耦思想引入VLA后训练的有效性。对于具身智能算法工程师而言，这种分离几何与动力学的表征方式，不仅解决了遥操作数据中人为时序噪声的干扰问题，还为VLA模型提供了类似传统规划器的速度自适应能力，是提升端到端策略在真实物理环境中执行效率与鲁棒性的重要技术路径。
英文摘要 (Abstract)
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.
作者：Qing Huang, Yifei Yang, Ziqing Zou, Anzhe Chen, Zhenjie Zhu, Yufei Wei, Rong Xiong, Yue Wang
来源
本页事实对应的公开页面，以原文为准。