Enhancing Robotic Autonomy: A Review and Case Study of Traditional and Deep Learning Approaches to Inverse Kinematics | ||||
| International Journal of Engineering and Applied Sciences-October 6 University | ||||
| Article 15, Volume 1, Issue 1, July 2024 PDF (477.54 K) | ||||
| Document Type: Research Article | ||||
| DOI: 10.21608/ijeasou.2024.374260 | ||||
 View on SCiNiTO | ||||
| Abstract | ||||
| Inverse kinematics (IK) is a fundamental concept in robotics, essential for calculating the necessary joint angles to achieve a desired position and orientation of an end-effector in robotic arms and other articulated systems. Traditional methods of solving IK, such as analytical and numerical approaches, face significant challenges when addressing modern robotic applications' complexities and computational demands. This paper explores the integration of deep neural networks (DNNs) as a transformative approach to these IK challenges. DNNs offer a significant advantage in handling the nonlinearities inherent in robotic systems and provide a flexible framework for optimizing joint configurations with energy efficiency and obstacle avoidance considerations. The study presents a detailed comparison of traditional and neural network-based methods, highlighting the enhanced adaptability, efficiency, and robustness of neural networks. The paper discusses neural network architectures and their implementation for a 2D robotic arm. This advancement represents a pivotal shift from rigidity to flexibility in robotic motion planning and control, promising substantial improvements in robotic autonomy and functionality. | ||||
| Keywords | ||||
| : Inverse Kinematics; Neural Networks; Robotics; Deep Learning; Articulated Robots | ||||
|
Statistics Article View: 124 PDF Download: 215 |
||||
