School of Computer Science, University of St Andrews, Jack Cole Building, North Haugh, St Andrews KY16 9SX, UK.
Sensors (Basel). 2023 Feb 21;23(5):2389. doi: 10.3390/s23052389.
Manipulating cloth-like deformable objects (CDOs) is a long-standing problem in the robotics community. CDOs are flexible (non-rigid) objects that do not show a detectable level of compression strength while two points on the article are pushed towards each other and include objects such as ropes (1D), fabrics (2D) and bags (3D). In general, CDOs' many degrees of freedom (DoF) introduce severe self-occlusion and complex state-action dynamics as significant obstacles to perception and manipulation systems. These challenges exacerbate existing issues of modern robotic control methods such as imitation learning (IL) and reinforcement learning (RL). This review focuses on the application details of data-driven control methods on four major task families in this domain: cloth shaping, knot tying/untying, dressing and bag manipulation. Furthermore, we identify specific inductive biases in these four domains that present challenges for more general IL and RL algorithms.
操纵类布状可变形物体（CDO）是机器人领域长期存在的问题。CDO 是指柔性（非刚性）物体，当物体上的两点相互靠近时，不会显示出可检测到的压缩强度，包括绳索（1D）、织物（2D）和袋子（3D）等物体。通常，CDO 的自由度（DoF）众多，会引入严重的自遮挡和复杂的状态-动作动态，成为感知和操纵系统的重大障碍。这些挑战加剧了现代机器人控制方法（如模仿学习（IL）和强化学习（RL））中的现有问题。本综述重点介绍了数据驱动控制方法在该领域四个主要任务领域的应用细节：布料成型、系结/解结、穿衣和袋子操作。此外，我们还确定了这四个领域中存在的特定归纳偏差，这些偏差给更通用的 IL 和 RL 算法带来了挑战。
