发表机构
Sun Yat-sen University; Stanford University; Southeast University（中山大学; 斯坦福大学; 东南大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出DynamicManip，通过静态转动态数据增强流水线、动态感知自适应策略及动态操作基准，解决机器人动态操作的数据效率与实时性问题，实验显示其性能显著优于现有方法。
AI 中文摘要
动态操作是机器人在复杂动态环境中作业的关键能力，机器人需与运动物体交互或进行快速调整。然而，学习动态操作任务模型面临两大挑战：（1）动态场景的组合复杂性导致数据需求巨大；（2）动力学的快速变化要求策略执行实时且准确。本文提出DynamicManip以应对这些挑战，通过高效的数据增强流水线和低延迟模仿策略实现。首先，提出静态到动态的增强流水线，从单个静态演示合成多样化的动态操作演示；其次，引入动态感知自适应策略，根据任务动力学调整推理频率，实现响应迅速且有效的动态操作；第三，构建动态操作基准，包含多样化动态任务及自动评估系统，用于可扩展且一致的评估。仿真和真实世界中的大量实验表明，DynamicManip不仅显著提升数据效率，还在动态操作任务中取得更优性能，平均成功率提高18.4个百分点，策略查询延迟降低32.9%。
英文摘要
Dynamic manipulation is a critical capability for robots operating in complex and dynamic environments, where robots must interact with objects that are moving or require rapid adjustments. However, learning models for dynamic manipulation tasks face two major challenges: (1) the combinatorial complexity of dynamic scenarios leads to substantial data requirements, and (2) rapid variations in dynamics require real-time and accurate policy execution. In this paper, we propose DynamicManip to address these challenges through an efficient data augmentation pipeline and a low-latency imitation policy. We first propose a static-to-dynamic augmentation pipeline that synthesizes diverse dynamic manipulation demonstrations from a single static demonstration. Second, we introduce a dynamic-aware adaptive policy that adjusts its inference frequency according to task dynamics, enabling responsive and effective dynamic manipulation. Third, we build a dynamic manipulation benchmark, which includes diverse dynamic tasks with an automatic evaluation system for scalable and consistent assessment. Extensive experiments in both simulation and the real world demonstrate that DynamicManip not only provides significant improvements in data efficiency but also achieves better performance in dynamic manipulation tasks, with a mean success rate 18.4 percentage points higher and policy-query latency 32.9% lower.
CommentsProject page: https://liaohr9.github.io/DynamicManip/ Code: https://github.com/liaohr9/DynamicManip
