Simon Hangl
Papers
7
Total Citations
59
H-Index
5
About
Simon Hangl’s research lies at the intersection of autonomous robotics, skill acquisition, and human-robot interaction, with a focus on enabling robots to learn manipulation skills through self-directed exploration. His major contribution is the development of a paradigm where robots autonomously “play” with objects to extend their problem-solving capabilities beyond narrow, pre-programmed scenarios. This approach, detailed in his most-cited work (21 citations), combines active learning and exploratory behavior composition to allow robots to acquire new skills without explicit human instruction. Hangl also pioneered a novel skill-based programming framework that integrates autonomous skill acquisition with visual programming, making robot programming more accessible to non-experts. His work on metric reinforcement learning for reactive, task-specific manipulation (7 citations) addresses the challenge of controlling dynamic systems, such as pouring liquids into moving targets. With over 50 total citations across his publications, Hangl’s research has been recognized for its potential to democratize robotics and reduce the need for extensive supervised training data. His contributions are particularly notable for advancing the field toward more adaptable, self-improving robotic systems that can operate in unstructured environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5Autonomous robots: potential, advances and future direction5 citations · 2017
- 6Hierarchical Haptic Manipulation for Complex Skill Learning3 citations · 2016
- 7Autonomous skill-centric testing using deep learning2 citations · 2017