Sabrina Hoppe

Robert Bosch (Germany), University of Stuttgart

Papers

Total Citations

H-Index

About

Sabrina Hoppe is a leading researcher in robotic manipulation, specializing in reinforcement learning for contact-rich tasks and flexible manufacturing. Her work bridges the gap between simulated learning and real-world industrial applications, with a focus on sample-efficient, model-free approaches. Her most cited paper, "Planning Approximate Exploration Trajectories for Model-Free Reinforcement Learning in Contact-Rich Manipulation" (2019, 26 citations), demonstrates how to reduce data complexity in deep RL by integrating expert demonstrations, enabling robots to learn complex assembly behaviors from scratch. She further advanced this field with "Sample-Efficient Learning for Industrial Assembly using Qgraph-bounded DDPG" (2020, 12 citations), introducing a novel algorithm that improves learning efficiency for intricate manipulation tasks. Her recent work, "The e-Bike motor assembly: Towards advanced robotic manipulation for flexible manufacturing" (2023, 9 citations), showcases her commitment to translating research into practical, scalable automation solutions. Hoppe’s contributions are pivotal for making robotic assembly more adaptive and cost-effective, with potential to revolutionize industries from automotive to electronics. Her research is essential reading for anyone interested in the future of autonomous manufacturing and real-world reinforcement learning.