Erik Leitch
Papers
1
Total Citations
2
H-Index
1
About
Erik Leitch is a robotics researcher whose work lies at the intersection of deep reinforcement learning and robotic manipulation, with a particular focus on semantic grasping. His most notable contribution, "Toward Sim-to-Real Directional Semantic Grasping," addresses the challenging problem of enabling robots to grasp a specific object from a specific direction—a critical capability for real-world applications. Leitch approaches this problem using a double deep Q-network (DDQN) that learns to map downsampled RGB images from a wrist-mounted camera directly to Q-values, effectively bridging the sim-to-real gap. While his most-cited paper currently holds 2 citations, the work represents an important step toward more intelligent and context-aware robotic grasping systems. Leitch's research is particularly relevant for students and researchers interested in combining computer vision with reinforcement learning to create robots that can interact with their environments in a semantically meaningful way. His work contributes to the broader goal of making robotic manipulation more adaptive and capable of handling the nuanced demands of real-world tasks.
Research Focus
Key Achievements
Top Papers
- 1Toward Sim-to-Real Directional Semantic Grasping2 citations · 2020