CHEQ-ing the Box：用于机器人打磨的安全变阻抗学习
CHEQ-ing the Box: Safe Variable Impedance Learning for Robotic Polishing
AI总结：
本工作展示了混合强化学习算法CHEQ在变阻抗机器人打磨任务中的实验应用，证明其在仿真与物理硬件上均能实现安全高效的学习和有效的打磨行为。
摘要：
机器人系统日益广泛地应用于工业自动化，其中打磨等接触丰富的任务需要灵巧性和柔顺行为。这些任务难以建模，使得经典控制具有挑战性。深度强化学习（RL）通过直接从数据中学习模型和控制策略，提供了一种有前景的解决方案。然而，其在现实问题中的应用受到数据低效和不安全探索的限制。自适应混合RL方法将经典控制与RL自适应地融合，结合了两者的优势：来自控制的结构和来自RL的学习。这带来了数据效率和探索安全性的提升。然而，它们在硬件应用中的潜力仍然未被充分探索，迄今为止尚未在物理系统上进行评估。此类评估对于充分评估这些方法在现实环境中的实用性和有效性至关重要。本工作展示了混合RL算法CHEQ在变阻抗机器人打磨中的实验演示，该任务需要精确的力和速度跟踪。在仿真中，我们表明变阻抗提升了打磨性能。我们将独立RL与自适应混合RL进行比较，证明CHEQ在遵守安全约束的同时实现了有效学习。在硬件上，CHEQ实现了有效的打磨行为，仅需8小时训练且仅发生5次失败。这些结果突显了自适应混合RL在直接于硬件上训练的现实接触丰富任务中的潜力。
英文摘要：
Robotic systems are increasingly employed for industrial automation, with contact-rich tasks like polishing requiring dexterity and compliant behaviour. These tasks are difficult to model, making classical control challenging. Deep reinforcement learning (RL) offers a promising solution by enabling the learning of models and control policies directly from data. However, its application to real-world problems is limited by data inefficiency and unsafe exploration. Adaptive hybrid RL methods blend classical control and RL adaptively, combining the strengths of both: structure from control and learning from RL. This has led to improvements in data efficiency and exploration safety. However, their potential for hardware applications remains underexplored, with no evaluations on physical systems to date. Such evaluations are critical to fully assess the practicality and effectiveness of these methods in real-world settings. This work presents an experimental demonstration of the hybrid RL algorithm CHEQ for robotic polishing with variable impedance, a task requiring precise force and velocity tracking. In simulation, we show that variable impedance enhances polishing performance. We compare standalone RL with adaptive hybrid RL, demonstrating that CHEQ achieves effective learning while adhering to safety constraints. On hardware, CHEQ achieves effective polishing behaviour, requiring only eight hours of training and incurring just five failures. These results highlight the potential of adaptive hybrid RL for real-world, contact-rich tasks trained directly on hardware.
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。
