The Robotic Arm Velocity Planning Based on Reinforcement Learning

Huang, Hao-Hsuan; Cheng, Chih-Kai; Chen, Yi-Hung; Tsai, Hung-Yin

doi:10.1007/s12541-023-00880-x

Cited by 4 publications

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another significant issue is the motion planning challenge, which has been the focus of numerous academics aiming to develop motion planners that minimize planning time, enhance motion performance, and generate seamless and improved motion profiles. in [12] the performance of the ABB IRB140 industrial robot has improved by using a velocity planning model developed by artificial intelligence in the simulation system. Using a novel methodology [13] provides optimal measurement configurations adapted to the experimental setup for the KUKA KR500 MT robot mounted on a rail.…”

Section: Related Workmentioning

confidence: 99%

Kinematic Analysis and Simulation of an Industrial Rail-Mounted Robot Manipulator Using Ruckig for Enhanced Path Planning

mahrous,

Ali,

Mohamed

et al. 2024

JES. Journal of Engineering Sciences

View full text Add to dashboard Cite

Robotic manipulators are being widely used in industrial operations and healthcare due to their versatile functionalities. However, the confined workspace of fixed robotic arms limits their applicability in scenarios requiring a broader range of configurations. To overcome this limitation, this research provides a case study on a robotic system composed of two primary subsystems an articulated robotic arm and a linear rail. A simple path planning task was carried out using CoppeliaSim simulation software to study the effect of Ruckig, an advanced online trajectory generation algorithm, alongside the RRT-Connect path planning algorithm. This study demonstrates the capacity of Ruckig to improve the efficiency of path planning regarding the process time and path length. The results showed that Ruckig helped reducing the process time by 90% with an exceptional improvement to the motion profiles of the system. Regarding the path length, it seems that it was able to decrease the length in certain cases, but not all. The reduction reached a maximum of 50% compared to the original length.

show abstract

Section: Related Workmentioning

confidence: 99%