Papers
7
Total Citations
206
H-Index
6
About
Yudha Pane is a robotics researcher whose work bridges reinforcement learning and industrial automation, with a focus on making robots more adaptive and user-friendly. His most impactful contribution is a reinforcement learning-based compensation method for robot manipulators (2018, 122 citations), which uses an actor-critic scheme to improve tracking control by adding correction signals to nominal feedback controllers—a significant advance for precision robotics. Pane’s research spans two key areas: learning-based control for manipulators and skill-based programming for assembly tasks. In the latter, he has developed system architectures that translate CAD models into sensor-based robot skills, enabling intuitive programming for collaborative robots. His work on constraint-based skill frameworks (2021, 8 citations) addresses the challenge of composing reactive behaviors in real-time, allowing robots to dynamically reconfigure tasks in response to disturbances. Notable achievements include a three-layered architecture for CAD-based robotic assembly (2020, 19 citations) and a user-friendly programming framework for human-robot collaboration in industrial case studies (2019, 10 citations). With over 200 total citations, Pane’s contributions are shaping the future of flexible, autonomous manufacturing systems.
Research Focus
Key Achievements
Top Papers
- 1Reinforcement learning based compensation methods for robot manipulators122 citations · 2018
- 2Actor-critic reinforcement learning for tracking control in robotics30 citations · 2016
- 3
- 4
- 5
- 6
- 7