Tobias Scherer
Papers
1
Total Citations
36
H-Index
1
About
Tobias Scherer is a researcher at the intersection of robotics, machine learning, and sensor-based perception, with a primary focus on enabling mobile robots to understand and adapt to their physical environment through vibration analysis. His most cited work, "Recurrent Neural Networks for fast and robust vibration-based ground classification on mobile robots" (2016, 36 citations), introduces a novel application of Recurrent Neural Networks—specifically Dynamic Cortex Memories (DCMs), an extension of Long Short-Term Memory (LSTMs)—to classify 14 distinct ground types from vibration data. This contribution is significant for improving robot locomotion and safety in unstructured terrains. Scherer also developed Sequence Boundary Dropout, a regularization technique that enhances model robustness during sequential data processing. His work bridges deep learning and real-world robotic systems, offering practical solutions for terrain-adaptive control. With impact reflected in citations from robotics and AI communities, Scherer’s research continues to influence autonomous navigation and sensor fusion, making him a notable figure in applied machine learning for robotics.
Research Focus
Key Achievements
Top Papers
- 1