Papers
6
Total Citations
146
H-Index
5
About
Julian Viereck is a robotics researcher whose work sits at the intersection of whole-body motion planning, dexterous manipulation, and model-based learning for legged systems. His most influential contribution is the BiConMP framework, a nonlinear model predictive control (MPC) approach that enables online generation of whole-body trajectories for legged robots—a notoriously difficult problem due to the nonlinear dynamics involved. This work, which has accumulated over 90 citations across its versions, demonstrates how to exploit robot structure for real-time control. Viereck is also a key contributor to the TriFinger platform, an open-source robotic system designed to lower the barrier for dexterous manipulation research. With over 40 citations, TriFinger provides an affordable, reproducible testbed that has accelerated progress in learning-based manipulation. Additionally, his work on real-robot datasets for dynamics model transferability (10 citations) addresses the critical challenge of sim-to-real transfer in model-based reinforcement learning. Through these contributions, Viereck has advanced both the theoretical foundations and practical tools for agile, autonomous robots.
Research Focus
Key Achievements
Top Papers
- 1
- 2TriFinger: An Open-Source Robot for Learning Dexterity24 citations · 2020
- 3TriFinger: An Open-Source Robot for Learning Dexterity16 citations · 2020
- 4
- 5
- 6Learning a Centroidal Motion Planner for Legged Locomotion3 citations · 2021