Stefan Harrer
Papers
2
Total Citations
212
H-Index
2
About
Stefan Harrer is a leading researcher at the intersection of artificial intelligence and robotics, with a primary focus on robotic manipulation and grasp detection. His major contributions lie in developing efficient, deep-learning-based systems that enable robots to perceive and grasp objects in real time, even on low-powered devices. His seminal work, "GraspNet: An Efficient Convolutional Neural Network for Real-time Grasp Detection for Low-powered Devices" (2018, 167 citations), introduced a compact CNN architecture that achieved high grasp detection accuracy while minimizing memory and computational demands—a critical advancement for deploying AI on edge devices. Building on this, Harrer proposed the "Densely Supervised Grasp Detector (DSGD)" (2019, 45 citations), a framework that fuses multi-level features to produce grasp confidence scores across global, region, and pixel hierarchies, significantly improving detection robustness. His research has been instrumental in bridging the gap between theoretical deep learning and practical, real-world robotics applications. Harrer’s work is widely cited in both academic and industrial contexts, underscoring its impact on autonomous systems and human-robot interaction.
Research Focus
Key Achievements
Top Papers
- 1
- 2Densely Supervised Grasp Detector (DSGD)45 citations · 2019