用可稳定追踪的动态系统，让机器人少练几遍就能完成长序列操作。
Single-Shot Learning of Stable Dynamical Systems for Long-Horizon Manipulation Tasks
- 将长任务拆成带目标点的短步骤，用稳定动力学模型逐段控制
- 在仿真和真实机器人上均实现高成功率，且对干扰有强鲁棒性
- 适合需要少样本、高可靠性的工业级机器人任务部署
掌握复杂序列任务仍是机器人领域的重大挑战。尽管已有方法在学习长时序操作任务方面取得进展，但多数方法缺乏严格的数学保证，难以确保执行的可靠性。本文拓展了先前关于长时序任务与稳定策略的学习工作，旨在提升任务成功率的同时减少训练数据需求。提出一种新方法：（1）将长时序示范数据按路径关键点（即航点与子目标）分割为离散步骤；（2）学习全局稳定的动力学系统策略，引导机器人在存在感知噪声和随机扰动的情况下仍能准确抵达每个子目标。通过仿真与真实世界实验验证，该方法在从仿真到物理平台的迁移中表现优异。代码已公开于 https://github.com/Alestaubin/stable-imitation-policy-with-waypoints。
原文摘要 · Abstract (English)
Mastering complex sequential tasks continues to pose a significant challenge in robotics. While there has been progress in learning long-horizon manipulation tasks, most existing approaches lack rigorous mathematical guarantees for ensuring reliable and successful execution. In this paper, we extend previous work on learning long-horizon tasks and stable policies, focusing on improving task success rates while reducing the amount of training data needed. Our approach introduces a novel method that (1) segments long-horizon demonstrations into discrete steps defined by waypoints and subgoals, and (2) learns globally stable dynamical system policies to guide the robot to each subgoal, even in the face of sensory noise and random disturbances. We validate our approach through both simulation and real-world experiments, demonstrating effective transfer from simulation to physical robotic platforms. Code is available at https://github.com/Alestaubin/stable-imitation-policy-with-waypoints
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。