共享执行时钟漂移策略用于动态精度操作
Shared Execution-Clock Drifting Policy for Dynamic Precision Manipulation
浏览论文内容
中文总结 AI 辅助
提出共享执行时钟漂移策略，将执行节奏显式纳入单步动作生成，在真实机器人任务中优于基线，实现高成功率。
中文摘要 AI 辅助
在时间约束下的操作既需要精确的动作，也需要与动态场景相匹配的执行节奏。当机器人必须拦截移动物体或在截止时间前完成一系列调整时，这一点变得至关重要。尽管单步策略降低了生成成本，但其直接预测的动作序列隐含了时间分配。我们提出了共享执行时钟漂移（SECD），使执行节奏成为单步动作生成中显式的一部分。基于观测和潜在样本，该策略联合预测一个进度索引的动作曲线和一个共享的单调时钟，该时钟将固定的控制时间映射到曲线上的位置。演示派生的对齐锚定了这种分解，并通过在解码动作上的漂移进行联合训练。所得策略保持固定速率的控制接口，且仅需一次网络评估。我们在NVIDIA Thor上对四个真实机器人任务进行了SECD评估。在300次试验中，它实现了77.00%的任务平均成功率，并在每个任务上优于所评估的单步基线，包括在16米/分钟的传送带上取杯任务中达到91%的成功率，以及在90秒内恢复并折叠皱衬衫的任务中达到54%的成功率。固定时钟变体在同一传送带协议上达到79%的成功率。补充的基于状态的RoboMimic实验，包括在Transport和Square上的跨种子消融，进一步支持了时间表示和演示对齐的联合设计。项目页面：此https URL
英文摘要
Manipulation under time constraints requires both accurate actions and an execution rhythm that matches the evolving scene. This becomes critical when a robot must intercept moving objects or complete a sequence of adjustments before a deadline. Although one-step policies reduce generation cost, their directly predicted action sequences leave temporal allocation implicit. We propose Shared Execution-Clock Drifting (SECD), which makes execution rhythm an explicit part of one-step action generation. Conditioned on an observation and a latent sample, the policy jointly predicts a progress-indexed action curve and a shared monotone clock that maps fixed control times to locations on the curve. Demonstration-derived alignment anchors this decomposition, which is trained jointly through drifting on the decoded actions. The resulting policy retains a fixed-rate control interface and requires one network evaluation. We evaluate SECD across four real-robot tasks with inference on NVIDIA Thor. Across 300 trials, it achieves 77.00% task-averaged success and outperforms the evaluated one-step baselines on every task, including 91% success in cup retrieval from a 16 m/min conveyor and 54% in restoring and folding a crumpled shirt within 90 s. A fixed-clock variant reaches 79% on the same conveyor protocol. Complementary state-based RoboMimic experiments, including cross-seed ablations on Transport and Square, further support the joint design of the temporal representation and demonstration alignment. Project page: https://secd-anonymous-ewn.pages.dev/
发表机构
- The Hong Kong Polytechnic University（香港理工大学）
- University of California San Diego（加利福尼亚大学圣迭戈分校）
- Zhejiang University（浙江大学）
- Université Paris-Saclay（巴黎萨克雷大学）
- Shanghai University of Engineering Science（上海工程技术大学）
机构由 AI 辅助整理，请以论文原文为准。
