Jonas Herzog
Papers
1
Total Citations
2
H-Index
1
About
Jonas Herzog is a rising researcher at the intersection of robotics and machine learning, with a primary focus on developing scalable, data-efficient methods for robotic manipulation. His most notable contribution is the "Human2Bot" framework, which introduces a novel approach to learning zero-shot reward functions directly from human demonstrations. This work, published in 2025, addresses a critical bottleneck in robot learning: the need for manually engineered reward functions. By enabling robots to infer task objectives from natural human behavior, Herzog’s method paves the way for more intuitive and adaptable human-robot collaboration. Though early in his career, his work has already garnered attention, with his flagship paper accumulating 2 citations. Herzog’s research promises to democratize robotic skill acquisition, reducing the expertise required to program complex manipulation tasks. His achievements signal a promising trajectory in advancing autonomous systems that learn seamlessly from human interaction.
Research Focus
Key Achievements
Top Papers
- 1