A Learning Framework of Adaptive Manipulative Skills From Human to Robot

Simultaneously Encoding Movement and sEMG-Based Stiffness for Robotic Skill Learning

“…One solution to this issue is to equally treat movement trajectories and stiffness profiles by simultaneously encoding them in a systematic manner [26]. In [27,28], a framework was proposed to achieve this goal by encoding movement and stiffness in parallel using dynamic movement primitives (DMP). DMP encodes each dimension of movement and stiffness separately, allowing the learning of the control policies in each dimension without changes to the basic approach [29].…”

Obstacle Avoidance and Tracking Control of Redundant Robotic Manipulator: An RNN-Based Metaheuristic Approach

“…For a redundant robotic manipulator, the problem of tracking control and obstacle avoidance aims at computing an optimal control action to steer the end-effector along a required reference trajectory, while avoiding obstacles present in the environment. With the advances in robotics, the robotic manipulators have found increased research attention from academia as well as from industry [1]- [4]. Industries are interested in using the manipulators to automate the common tasks, e.g., moving, assembling, packing, and transporting the products.…”

Single Master Bimanual Teleoperation System With Efficient Regulation

“…Unlike purely autonomous robotic systems that are limited in their performance for jobs requiring complex movements and high-level dexterity, teleoperation involving human intelligence can effectively and safely realize greater robustness and reliability [5]. In certain cases, human factors (e.g., muscle activation) are also involved in teleoperation research to ease potential burdens and to improve operation [6]- [8]. A particular subset of teleoperation research considers bimanual teleoperation, which allows the operator to remotely drive a dual-arm robot, which can improve efficacy, precision, dexterity, loading capacity and handling capability [9], [10].…”