Jeppe Langaa
Papers
2
Total Citations
12
H-Index
2
About
Jeppe Langaa is a researcher at the intersection of control theory, reinforcement learning, and robotics, with a focus on developing safe and practical algorithms for real-world systems. His most influential work, "Safe robust adaptive control under both parametric and nonparametric uncertainty" (2024, 7 citations), introduces a novel method that combines robust adaptive control barrier functions (RaCBF) with Gaussian processes. This approach guarantees safety for systems facing both structured and unstructured uncertainties while significantly reducing conservatism compared to traditional methods—a critical step toward deploying autonomous systems in unpredictable environments. In his earlier work, "Expert Initialized Reinforcement Learning with Application to Robotic Assembly" (2022, 5 citations), Langaa bridges the gap between simulation and industrial practice. He systematically compares actor-critic algorithms—Cycle of Learning, DDPG, and TD3—demonstrating how expert demonstrations can accelerate learning for complex assembly tasks. By addressing both theoretical safety guarantees and practical deployment challenges, Langaa’s research offers a compelling blueprint for next-generation autonomous systems, making him a rising voice in safe learning-based control.
Research Focus
Key Achievements
Top Papers
- 1
- 2