Viktor Johansson
Papers
3
Total Citations
8
H-Index
2
About
Viktor Johansson’s research focuses on advancing robotic control systems through machine learning and model-based compensation. His primary contributions lie in feed-forward friction compensation and multi-axis robot control, where he bridges classical friction modeling with modern learning approaches. In his most cited work, "A Learning Approach for Feed-Forward Friction Compensation" (2018, 4 citations), Johansson experimentally compares the LuGre friction model against a B-spline network that learns compensation from data, demonstrating how adaptive methods can outperform traditional parameter identification. This work has implications for improving precision in industrial robotics and automation. His other studies, including "Virtual Commissioning: Emulation of a production cell" (2016, 2 citations) and "Learning local models of multi-axis robot for improved feed-forward control" (2017, 2 citations), explore how emulation and local learning models can reduce commissioning time and enhance control accuracy in manufacturing settings. Though his citation counts are modest, Johansson’s work is notable for its practical focus on real-world industrial challenges, particularly at Volvo, where his research directly addresses the need for faster, more reliable automation upgrades. His approach—combining physical modeling with data-driven learning—offers a promising pathway for next-generation robot control.
Research Focus
Key Achievements
Top Papers
- 1A Learning Approach for Feed-Forward Friction Compensation4 citations · 2018
- 2Virtual Commissioning : Emulation of a production cell2 citations · 2016
- 3