Marek Daniv

Technische Universität Darmstadt

Papers

1

Total Citations

5

H-Index

1

About

Marek Daniv is a robotics researcher advancing the frontier of adaptive robot learning, with a focus on skill acquisition and generalization in dynamic environments. His work centers on integrating probabilistic modeling with reinforcement learning to enable robots to learn tasks efficiently and adapt to real-world changes. His most-cited paper, "Adapting Object-Centric Probabilistic Movement Primitives with Residual Reinforcement Learning" (2022, 5 citations), introduces a novel framework that combines Probabilistic Movement Primitives (ProMPs) with residual reinforcement learning. This approach allows robots to generate generalizable trajectory distributions from demonstrations while fine-tuning behaviors through trial-and-error, addressing the critical challenge of adapting learned skills to novel or shifting conditions. Daniv’s contributions are particularly impactful for applications requiring rapid task learning and robust adaptation, such as manufacturing and service robotics. Though early in his career, his work has already garnered attention for bridging model-based and model-free learning paradigms, offering a path toward more versatile and autonomous robotic systems.

Research Focus

Key Achievements

1
H-Index
1
Papers
5
Total Citations
5
Avg Citations/Paper
🏆 Most Cited Paper
Adapting Object-Centric Probabilistic Movement Primitives with Residual Reinforcement Learning
5 citations · 2022
📈 Most Prolific Year: 2022 (1 Papers)
🤝 Key Collaborators: 3
🏛 Institutions: Technische Universität Darmstadt

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 11 days ago