David Peer

Papers

Total Citations

H-Index

About

David Peer is a researcher at the forefront of robotic perception and manipulation, with a focus on affordance detection—the ability of machines to understand how objects can be used or interacted with from visual data. His key contributions lie in advancing deep learning architectures for this task, notably through his work on "Affordance detection with Dynamic-Tree Capsule Networks" (2022), which addresses a critical limitation of convolutional neural networks: their inability to capture spatial hierarchies and part-to-whole relationships in visual input. By introducing capsule networks that dynamically model these structures, Peer’s approach enhances the precision and robustness of affordance detection, a fundamental step for autonomous robotic manipulation. Though his most-cited paper currently has 2 citations, its innovative framework signals growing recognition in the field. Peer’s research bridges computer vision and robotics, aiming to equip machines with a more human-like understanding of object functionality. His work is particularly notable for challenging conventional CNN-based methods, offering a path toward more interpretable and geometrically aware AI systems. For students and researchers, Peer’s contributions represent a promising direction in embodied AI and autonomous systems.