Andreas Schwung
Papers
12
Total Citations
108
H-Index
7
About
Andreas Schwung is a leading researcher at the intersection of artificial intelligence, operations research, and industrial robotics. His work focuses on developing intelligent, data-driven solutions for complex manufacturing challenges, particularly through reinforcement learning and neural network architectures. Schwung’s major contributions include pioneering the use of graph neural networks for job shop scheduling (18 citations) and state-space decomposition for dynamic routing optimization (19 citations), enabling real-time decision-making in industrial environments. He has also advanced cooperative robot control, comparing centralized and distributed approaches for flexible manufacturing cells (11 citations), and developed novel neural network architectures like the Homogeneous Transformation Matrix-based network (7 citations) and the Kinematic Neural Network (KineNN) for model-based robot control (9 citations). His work on integrating ABB robot manipulators with the Robot Operating System (12 citations) has practical significance for industrial automation. More recently, Schwung has explored multimodal data fusion and synthetic dataset generation to improve the robustness of deep learning models in manufacturing. With over 100 citations across his most-cited papers, his research is shaping the future of intelligent, adaptive, and cooperative industrial automation.
Research Focus
Key Achievements
Top Papers
- 1
- 2Reinforcement Learning on Job Shop Scheduling Problems Using Graph Networks.18 citations · 2020
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10