Manuel Scharffenberg

Papers

1

Total Citations

24

H-Index

1

About

Manuel Scharffenberg is a robotics researcher whose work centers on computer vision, deep learning, and autonomous perception for humanoid robots, particularly in the competitive context of the RoboCup Soccer AdultSize League. His most cited contribution, “Detection and Localization of Features on a Soccer Field with Feedforward Fully Convolutional Neural Networks (FCNN) for the Adult-Size Humanoid Robot Sweaty” (2017, 24 citations), demonstrates a breakthrough in real-time visual perception. Scharffenberg developed a single fully convolutional neural network capable of simultaneously detecting and localizing the ball, opponents, and other field features, enabling the humanoid robot Sweaty to perceive its environment efficiently. Remarkably, this network can be trained from scratch in just a few hours and operates in real time—a critical requirement for dynamic robotic soccer. This work highlights his expertise in bridging deep learning with resource-constrained robotic systems, advancing the state of the art in autonomous robot vision. Scharffenberg’s research has practical implications for real-world robotics, where fast, accurate, and trainable perception systems are essential. His contributions underscore the potential of compact neural architectures in enabling humanoid robots to perform complex tasks under time-sensitive conditions.

Research Focus

Key Achievements

1
H-Index
1
Papers
24
Total Citations
24
Avg Citations/Paper
🏆 Most Cited Paper
Detection and Localization of Features on a Soccer Field with Feedforward Fully Convolutional Neural Networks (FCNN) for the Adult-Size Humanoid Robot Sweaty
24 citations · 2017
📈 Most Prolific Year: 2017 (1 Papers)
🤝 Key Collaborators: 4

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 11 days ago