Mochammad Rizky Diprasetya
Papers
5
Total Citations
48
H-Index
4
About
Mochammad Rizky Diprasetya is a rising researcher at the intersection of robotics, artificial intelligence, and operations research, whose work is shaping the future of intelligent industrial automation. His core research focuses on developing novel, data-driven control and optimization frameworks for robot manipulators, with a particular emphasis on bridging the gap between simulation and real-world deployment. Diprasetya’s major contributions include the introduction of the Kinematic Neural Network (KineNN), an invertible neural architecture that leverages homogeneous transformation matrices and dual quaternions for precise inverse model policies. He has also pioneered the use of Homogeneous Transformation Matrix (HTM) neural networks for model-based reinforcement learning, demonstrating their superiority over standard feed-forward networks in robotic control tasks. His work on dynamic robot routing optimization, which integrates state–space decomposition with reinforcement learning, addresses the critical challenge of real-time decision-making in industrial environments. With a growing citation record—including 19 citations for his 2024 routing paper and 12 for his work on integrating ABB manipulators with ROS—Diprasetya is establishing himself as a key innovator in making advanced robotics more adaptive, efficient, and practically deployable.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5