Lars Hinneburg

Papers

Total Citations

H-Index

About

Lars Hinneburg is a robotics researcher whose work focuses on advancing autonomous systems through deep learning, with key contributions in robotic manipulation and visual perception. His research addresses two critical challenges in modern robotics: enabling reliable object grasping and improving self-localization without pre-existing maps. In his highly cited 2022 paper, Hinneburg tackled the problem of robotic grasp detection by demonstrating how proper label encoding and uncertainty estimation significantly improve a model's ability to grasp arbitrary objects—a fundamental skill for smart manufacturing and human-robot interaction. This work has garnered 4 citations, establishing a foundation for more robust manipulation systems. More recently, his 2024 paper on weakly supervised end-to-end deep visual odometry pushes the boundaries of mapless navigation for automated driving. By reducing the need for extensive labeled training data, this approach mitigates catastrophic failures common in traditional systems while achieving superior localization accuracy. With 2 citations already, this work represents an important step toward practical, scalable visual odometry. Hinneburg's research sits at the intersection of perception and control, offering elegant deep learning solutions to long-standing robotics challenges.