GlobDesOpt: A Global Optimization Framework for Optimal Robot Manipulator Design

Cursi, Francesco; Bai, Weibang; Yeatman, Eric M.; Kormushev, Petar

doi:10.1109/access.2022.3141660

Cited by 5 publications

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each link of the robot can be characterized by four kinematic parameters, with two describing the link itself and the other two representing the connection relationship between the links. The method in which these kinematic parameters express the kinematic relationship of the robot mechanism is commonly referred to as the Denavit-Hartenberg (DH) method [20], and the Denavit-Hartenberg parameters [21] are shown in Figure 1. For a six-degree-of-freedom manipulator, the transformation formula for the connecting rod, represented from the base to the end effector, can be obtained by articulating the parameter configuration in the form of a homogeneous transformation matrix, q = [q 1 , q 2 , .…”

Section: Kinematics and Dynamics Of Manipulatormentioning

confidence: 99%

Multi-Objective Optimal Trajectory Planning for Robotic Arms Using Deep Reinforcement Learning

Zhang

Xia

Chen³

et al. 2023

Sensors

View full text Add to dashboard Cite

This study investigated the trajectory-planning problem of a six-axis robotic arm based on deep reinforcement learning. Taking into account several characteristics of robot motion, a multi-objective optimization approach is proposed, which was based on the motivations of deep reinforcement learning and optimal planning. The optimal trajectory was considered with respect to multiple objectives, aiming to minimize factors such as accuracy, energy consumption, and smoothness. The multiple objectives were integrated into the reinforcement learning environment to achieve the desired trajectory. Based on forward and inverse kinematics, the joint angles and Cartesian coordinates were used as the input parameters, while the joint angle estimation served as the output. To enable the environment to rapidly find more-efficient solutions, the decaying episode mechanism was employed throughout the training process. The distribution of the trajectory points was improved in terms of uniformity and smoothness, which greatly contributed to the optimization of the robotic arm’s trajectory. The proposed method demonstrated its effectiveness in comparison with the RRT algorithm, as evidenced by the simulations and physical experiments.

show abstract

Section: Kinematics and Dynamics Of Manipulatormentioning

confidence: 99%