TWISTED-RL：无人类示范的分层技能代理用于打结
TWISTED-RL: Hierarchical Skilled Agents for Knot-Tying without Human Demonstrations
AI总结：
TWISTED-RL通过强化学习和拓扑动作实现无示范的复杂打结任务，提升泛化能力和效率。
摘要：
机器人打结代表了机器人学中的基本挑战，由于变形物体与严格拓扑约束之间的复杂相互作用。我们提出了TWISTED-RL框架，该框架在无示范打结方面超越了之前的最先进方法（TWISTED），该方法巧妙地将单个打结问题分解为可管理的子问题，每个子问题由专门的代理解决。我们的方法用多步强化学习策略取代了TWISTED中通过监督学习学习的单步逆模型，该策略基于抽象拓扑动作而非目标状态。这种改变允许更精细的拓扑状态转换，同时避免了昂贵且无效的数据收集协议，从而在多样化的打结配置中实现更好的泛化。实验结果表明，TWISTED-RL能够解决之前无法达到的更高复杂度的打结，包括常用的Figure-8和Overhand打结。此外，成功率的增加和规划时间的下降使TWISTED-RL成为无人类示范的机器人打结的新最先进方法。
英文摘要：
Robotic knot-tying represents a fundamental challenge in robotics due to the complex interactions between deformable objects and strict topological constraints. We present TWISTED-RL, a framework that improves upon the previous state-of-the-art in demonstration-free knot-tying (TWISTED), which smartly decomposed a single knot-tying problem into manageable subproblems, each addressed by a specialized agent. Our approach replaces TWISTED's single-step inverse model that was learned via supervised learning with a multi-step Reinforcement Learning policy conditioned on abstract topological actions rather than goal states. This change allows more delicate topological state transitions while avoiding costly and ineffective data collection protocols, thus enabling better generalization across diverse knot configurations. Experimental results demonstrate that TWISTED-RL manages to solve previously unattainable knots of higher complexity, including commonly used knots such as the Figure-8 and the Overhand. Furthermore, the increase in success rates and drop in planning time establishes TWISTED-RL as the new state-of-the-art in robotic knot-tying without human demonstrations.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
