Brendan Hertel
Papers
6
Total Citations
33
H-Index
4
About
Brendan Hertel is a robotics researcher whose work focuses on making robots more capable learners and more intuitive to control. His primary research areas include Learning from Demonstration (LfD), human-in-the-loop teleoperation, and adaptive robot manipulation in dynamic environments. Hertel’s major contribution is a novel optimization-based LfD method that encodes human demonstrations as elastic maps—a graph of connected nodes that allows robots to generalize skills from both successful and failed attempts. This approach, detailed in his most-cited papers (each garnering 8 citations), transforms skill reproduction into a convex optimization problem, enabling robots to reproduce motions with confidence even when faced with perturbations. Beyond learning, Hertel has explored practical human-robot interaction, comparing 2D keyboard-and-mouse interfaces to virtual reality for mobile manipulation planning (6 citations). He has also developed frameworks for combining autonomy metrics for unmanned aerial systems and for proactive adaptation in dynamic environments. By bridging theoretical optimization with real-world usability, Hertel’s work advances the frontier of accessible, robust robot teaching and control.
Research Focus
Key Achievements
Top Papers
- 1Robot Learning from Demonstration Using Elastic Maps8 citations · 2022
- 2Learning from Successful and Failed Demonstrations via Optimization8 citations · 2021
- 3
- 4
- 5
- 6Confidence-Based Skill Reproduction Through Perturbation Analysis3 citations · 2023