Thomas Gossard

TH Bingen University of Applied Sciences

Papers

Total Citations

H-Index

About

Thomas Gossard is a rising researcher at the intersection of neuromorphic computing, robotics, and high-speed vision. His work focuses on enabling machines to perceive and react to fast-moving objects, with a particular emphasis on dynamic environments like table tennis. Gossard’s most cited paper, “SpinDOE: A Ball Spin Estimation Method for Table Tennis Robot” (2023, 14 citations), tackles the notoriously difficult problem of measuring ball spin in real-time—a key challenge for robotic sports. He also explores the practical limitations of event cameras, proposing a simulation framework in “Real-time event simulation with frame-based cameras” (2023, 8 citations) to democratize access to this emerging sensor technology. More recently, his 2025 work on “Detection of Fast-Moving Objects with Neuromorphic Hardware” (2 citations) advances the use of Spiking Neural Networks (SNNs) for energy-efficient, spike-based perception. By combining theoretical contributions with real-world robotic applications, Gossard is helping to bridge the gap between neuromorphic hardware and practical, high-speed vision systems—work that holds promise for autonomous drones, industrial automation, and interactive robotics.