从不可握姿势学习物体的预握操作
Learning Pregrasp Manipulation of Objects from Ungraspable Poses
摘要：
在机器人抓取中，物体通常被遮挡在不可抓取的配置中，使得无法找到预抓取姿势，例如只能从侧面抓取的桌子上的大扁平盒子。受人类双手操作的启发，例如一只手举起东西，另一只手抓住，我们通过引入预抓取操作-推和举动作来解决这类问题。我们提出了一个无模型的深度强化学习框架，训练控制策略，利用机器人的视觉信息和本体感受状态，自主发现强大的预抓取操作。机器人手臂学习首先将物体推向支撑表面，并建立枢轴以抬起物体的一侧，从而在物体和工作台之间产生间隙，用于可能的抓取解决方案。此外，我们证明了我们提出的学习框架的有效性，在训练强大的预抓取政策，可以直接从模拟到真正的硬件，通过适当的设计训练程序，状态和动作空间。最后，我们评估的有效性和泛化能力的学习政策在现实世界的实验，并展示pregrasp操纵的对象具有不同的大小，形状，重量和表面摩擦。
英文摘要：
In robotic grasping, objects are often occluded in ungraspable configurations such that no pregrasp pose can be found, eg large flat boxes on the table that can only be grasped from the side. Inspired by humans' bimanual manipulation, eg one hand to lift up things and the other to grasp, we address this type of problems by introducing pregrasp manipulation - push and lift actions. We propose a model-free Deep Reinforcement Learning framework to train control policies that utilize visual information and proprioceptive states of the robot to autonomously discover robust pregrasp manipulation. The robot arm learns to first push the object towards a support surface and establishes a pivot to lift up one side of the object, thus creating a clearance between the object and the table for possible grasping solutions. Furthermore, we show the effectiveness of our proposed learning framework in training robust pregrasp policies that can directly transfer from simulation to real hardware through suitable design of training procedures, state, and action space. Lastly, we evaluate the effectiveness and the generalisation ability of the learned policies in real-world experiments, and demonstrate pregrasp manipulation of objects with various size, shape, weight, and surface friction.
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。
