Jonas Schwinn

Papers

Total Citations

H-Index

About

Jonas Schwinn is a researcher at the forefront of integrating machine learning with robotics and motion planning. His primary research areas include neural implicit representations, collision detection, and sampling-based motion planning. Schwinn’s most notable contribution is the development of Neural Implicit Swept Volume Models, a novel approach that leverages neural signed distance functions to dramatically accelerate collision detection—a traditionally time-intensive bottleneck in motion planning. By replacing conventional geometric computations with learned models, his work enables faster and more efficient robot navigation in complex environments. His 2024 paper on this topic has already garnered 7 citations, signaling growing recognition in the field. Schwinn’s research bridges the gap between deep learning and practical robotics, offering scalable solutions for real-time motion planning. His work is particularly impactful for autonomous systems, where rapid collision checking is critical. As a rising voice in the intersection of computer graphics and robotics, Schwinn continues to push the boundaries of how neural implicit models can streamline core robotic operations.