Abstract
In the era of Industry 4.0, optimizing the trajectory of intelligent textile robotic arms within cluttered configuration spaces for enhanced operational safety and efficiency has emerged as a pivotal area of research. Traditional path-planning methodologies predominantly employ inverse kinematics. However, the inherent non-uniqueness of these solutions often leads to varied motion patterns in identical settings, potentially leading to convergence issues and hazardous collisions. A further complication arises from an overemphasis on the tool center point, which can cause algorithms to settle into suboptimal solutions. To address these intricacies, our study introduces an innovative path-planning optimization strategy utilizing a model-free, deep reinforcement learning framework guided by inverse kinematics experience. We developed a deep reinforcement learning algorithm for path planning, amalgamating environmental enhancement strategies with multi-information entropy-based geometric optimization. This approach specifically targets the challenges outlined. Extensive experimental analyses affirm the enhanced optimality and robustness of our method in robotic arm path planning, especially when integrated with inverse kinematics, outperforming existing algorithms in terms of safety. This advancement notably elevates the operational efficiency and safety of intelligent textile robotic arms, offering a groundbreaking and pragmatic solution for path planning in real-world intelligent knitting applications.