Marion Neumann
Papers
3
Total Citations
70
H-Index
3
About
Marion Neumann’s research lies at the intersection of robotics, machine learning, and reasoning, with a particular focus on enabling robots to grasp objects intelligently. Her major contribution is the development of a probabilistic logic framework that seamlessly integrates high-level semantic reasoning with low-level geometric and perceptual learning. This approach allows robots to move beyond simple stable grasps to task-aware grasping—considering object properties, functionalities, and task constraints. Her most cited work, “Semantic and geometric reasoning for robotic grasping: a probabilistic logic approach” (2018, 45 citations), exemplifies this synthesis, while her earlier paper on graph kernels for object category prediction in task-dependent grasping (2013, 19 citations) laid foundational groundwork. Neumann’s work is notable for bridging symbolic reasoning and data-driven learning, a challenging and impactful direction in robotics. Her 2014 paper on a probabilistic logic pipeline further refined this integration, demonstrating how manifolds can support reasoning under uncertainty. With a focused but growing citation impact, Neumann is recognized for advancing robot grasping from a purely geometric problem to one that incorporates semantic understanding, making her contributions valuable for researchers aiming to build more capable, context-aware robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3