Christian Daniel

About

Christian Daniel is a leading researcher in robot learning, with his work centered on probabilistic movement primitives, hierarchical skill acquisition, and active reward learning. His most influential contribution is the development of **Probabilistic Movement Primitives (ProMPs)**, introduced in his 2013 paper (413 citations), which provides a modular, data-driven framework for generating and reusing complex movements—enabling simultaneous activation of multiple primitives and robust generalization under stochastic conditions. This foundational work has been extended in subsequent studies (e.g., 196 citations for its 2017 robotics application) and has become a cornerstone for modern motor skill learning. Daniel also pioneered methods for **hierarchical skill learning** in multi-phase manipulation tasks (109 citations), allowing robots to decompose complex behaviors into sequential phases, and advanced **active reward learning** (88 citations) to address the challenge of defining reward functions in practical robotics, such as grasping. His research on learning concurrent motor skills in versatile solution spaces (36 citations) further highlights his focus on scalable, adaptive robot learning. With over 900 total citations, Daniel’s work bridges theory and application, as demonstrated in his comparative study of reinforcement learning versus human programming in tetherball games (14 citations), showcasing his commitment to advancing autonomous robotic systems.

Research Focus

Key Achievements

Top Papers

1. 1
   Probabilistic Movement Primitives

   413 citations · 2013
2. 2
   Using probabilistic movement primitives in robotics

   196 citations · 2017
3. 3
   Towards learning hierarchical skills for multi-phase manipulation tasks

   109 citations · 2015
4. 4
   Active Reward Learning

   88 citations · 2014
5. 5
   Active reward learning with a novel acquisition function

   50 citations · 2015
6. 6
   Learning sequential motor tasks

   41 citations · 2013
7. 7
   Learning concurrent motor skills in versatile solution spaces

   36 citations · 2012
8. 8
   Learning modular policies for robotics

   20 citations · 2014
9. 9
   Reinforcement learning vs human programming in tetherball robot games

   14 citations · 2015
10. 10
    Bayesian Optimization for Policy Search in High-Dimensional Systems via Automatic Domain Selection

    13 citations · 2019

Key Collaborators

Contact & Links