Jelle Luijkx
Papers
2
Total Citations
9
H-Index
2
About
Jelle Luijkx is a robotics researcher whose work sits at the intersection of reinforcement learning, tactile sensing, and foundation models. His research addresses two fundamental challenges in robotic manipulation: sample efficiency and safe physical interaction. In his widely-cited work "ExploRLLM: Guiding Exploration in Reinforcement Learning with Large Language Models" (2025, 5 citations), Luijkx pioneers a novel approach that leverages large language models to direct exploration in complex robot manipulation tasks, dramatically improving sample efficiency and convergence in high-dimensional action spaces. This work bridges the gap between the semantic reasoning of foundation models and the structured decision-making of reinforcement learning. Equally impactful is his paper "Learning to estimate incipient slip with tactile sensing to gently grasp objects" (2024, 4 citations), where Luijkx develops a learning-based method for detecting early-stage slip using tactile sensors, enabling robots to apply precisely the minimum force needed for secure grasping without damaging objects. This contribution is critical for handling delicate or variable-friction objects. Luijkx’s work is notable for its practical focus on real-world robotic systems, combining theoretical advances with deployable solutions that push toward more capable, safer, and more intelligent robot manipulation.
Research Focus
Key Achievements
Top Papers
- 1
- 2