Most research on robot manipulation focuses on objects that are light enough for the robot to pick them up. However, in our daily life, some objects are too big or too heavy to be picked up or carried, so that dragging them is necessary. Although bipedal humanoid robots have nowadays good mobility on level ground, dragging unfamiliar objects including large and heavy objects on various surfaces is an interesting research area with many applications, which will provide insights into human manipulation and will encourage the development of novel algorithms for robot motion planning and control. This is a challenging problem, not only because of the unknown and potentially variable friction of the foot, but also because the feet of the robot may slip during unbalanced poses. In this paper, we propose a novel hierarchical deep learning algorithm that learns how to drag heavy objects with an adult-sized humanoid robot for the first time. First, we present a Three-layered Convolution Volumetric Network (TCVN) for 3D object classification with point clouds volumetric occupancy grid integration. Second, we propose a lightweight real-time instance segmentation method named Tiny-YOLACT for the detection and classification of the floor surface. Third, we propose a deep Q-learning algorithm to learn the policy control of the Center of Mass of the robot (DQL-COM). The DQL-COM algorithm learning is bootstrapped using the ROS Gazebo simulator. After initial training, we complete training on the THORMANG-Wolf, a 1.4 m tall adult-sized humanoid robot with 27 degrees of freedom and weighing 48 kg, on three distinct types of surfaces. We evaluate the performance of our approach by dragging eight different types of objects (e.g., a small suitcase, a large suitcase, a chair). The extensive experiments (480 times on the real robot) included dragging a heavy object with a mass of 84.6 kg (two times greater than the robot’s weight) and showed remarkable success rates of 92.92% when combined with the force–torque sensors, and 83.75% without force–torque sensors.

大多数关于机器人操纵的研究都集中在足够轻的物体上，机器人可以捡起它们。但是，在我们的日常生活中，有些物体太大或太重，拿不起来或搬不动，拖着就成了必需品。尽管双足人形机器人现在在水平地面上具有良好的移动性，但在各种表面上拖动不熟悉的物体，包括大而重的物体是一个有趣的研究领域，具有许多应用，这将为人类操纵提供见解，并将鼓励开发新的机器人运动算法计划和控制。这是一个具有挑战性的问题，不仅因为脚的未知和潜在的可变摩擦，而且因为机器人的脚在不平衡的姿势中可能会滑动。在本文中，我们提出了一种新颖的分层深度学习算法，该算法首次学习如何使用成人大小的人形机器人拖动重物。首先，我们提出了一个三层卷积体积网络（TCVN），用于具有点云体积占用网格集成的 3D 对象分类。其次，我们提出了一种名为 Tiny-YOLACT 的轻量级实时实例分割方法，用于地板表面的检测和分类。第三，我们提出了一种深度 Q 学习算法来学习机器人质量中心的策略控制（DQL-COM）。DQL-COM 算法学习使用 ROS Gazebo 模拟器进行引导。初始训练后，我们完成了 THORMANG-Wolf 的训练，这是一个 1.4 m 高的成人大小的人形机器人，具有 27 个自由度，重 48 kg，在三种不同类型的表面上。我们通过拖动八种不同类型的对象（例如，小手提箱、大手提箱、椅子）来评估我们方法的性能。广泛的实验（在真实机器人上进行了 480 次）包括拖动质量为 84.6 kg（比机器人的重量大两倍）的重物，当与力-扭矩传感器结合使用时，成功率高达 92.92%，成功率为 83.75 % 不带力-扭矩传感器。