Anthropomorphic Grasping of Complex-Shaped Objects Using Imitation Learning

Abstract

This paper presents an autonomous grasping approach for complex-shaped objects using an anthropomorphic robotic hand. Although human-like robotic hands have a number of distinctive advantages, most of the current autonomous robotic pickup systems still use relatively simple gripper setups such as a two-finger gripper or even a suction gripper. The main difficulty of utilizing human-like robotic hands lies in the sheer complexity of the system; it is inherently tough to plan and control the motions of the high degree of freedom (DOF) system. Although data-driven approaches have been successfully used for motion planning of various robotic systems recently, it is hard to directly apply them to high-DOF systems due to the difficulty of acquiring training data. In this paper, we propose a novel approach for grasping complex-shaped objects using a high-DOF robotic manipulation system consisting of a seven-DOF manipulator and a four-fingered robotic hand with 16 DOFs. Human demonstration data are first acquired using a virtual reality controller with 6D pose tracking and individual capacitive finger sensors. Then, the 3D shape of the manipulation target object is reconstructed from multiple depth images recorded using the wrist-mounted RGBD camera. The grasping pose for the object is estimated using a residual neural network (ResNet), K-means clustering (KNN), and a point-set registration algorithm. Then, the manipulator moves to the grasping pose following the trajectory created by dynamic movement primitives (DMPs). Finally, the robot performs one of the object-specific grasping motions learned from human demonstration. The suggested system is evaluated by an official tester using five objects with promising results.

Anthropomorphic motion planning for multi-degree-of-freedom arms

“… Mülling et al (2013) and Calinon et al (2010) developed table tennis robotic systems for anthropomorphic motion using mixture of motor primitives (MoMP), HMM and Gaussian mixture regression (GMR), respectively. Yi et al (2022) developed an autonomous robotic grasping system using an imitation learning algorithm consisting of K-means clustering and DMP, which could be finely manipulated using a variety of machine learning methods, and proved its reliability through evaluation. There are also studies on improving individual algorithms or combining multiple algorithms to improve iterative efficiency and reproduction accuracy, such as task-parameterized GMM is used to learn the demonstration trajectory to obtain motion characteristics, which enables the robot to perform the dual-arm sweeping task smoothly ( Silvério et al, 2015 ).…”

A Survey on Deep Reinforcement Learning Algorithms for Robotic Manipulation

“…Yi et al [ 105 ] describe an autonomous grasping strategy for complex-shaped items utilizing a high-DoF robotic manipulation system made up of a four-fingered robotic hand with 16 DoFs and a 7 DoF manipulator. The system gathers data on human demonstrations using a virtual reality controller equipped with 6D position tracking and individual capacitive finger sensors.…”

Remote Control Device to Drive the Arm Gestures of an Assistant Humanoid Robot

“…Future work will cover the application of the remote control device to optimize the control and torque demands of each joint and the addition of end-effectors in the hands [78,79]. Additional future works will focus on improving the spatial awareness of the teleoperator [80] by using a virtual reality headset and a stereoscopic camera in the mobile robot [81] and the implementation of direct 5G device-to-device communication [70,71].…”