Eunji Im
Papers
1
Total Citations
4
H-Index
1
About
Eunji Im is a rising researcher at the intersection of robotics, artificial intelligence, and formal methods. Her work centers on mission-conditioned path planning, where she develops deep learning frameworks that enable robots to autonomously navigate complex environments while adhering to high-level task specifications. In her most cited work, "Mission-Conditioned Path Planning with Transformer Variational Autoencoder" (2024, 4 citations), Im introduces a novel architecture that integrates Linear Temporal Logic (LTL) mission constraints with cost-aware trajectory generation in configuration space. This approach addresses two critical challenges in modern robotics: ensuring that autonomous systems follow formal, verifiable mission rules while optimizing path quality. By combining transformer-based variational autoencoders with LTL conditioning, Im’s framework represents a significant step toward more reliable and adaptable robotic systems. Though early in her career, her work has already garnered attention for bridging the gap between symbolic reasoning and data-driven planning. For students and researchers, Im’s research offers a compelling glimpse into how deep learning can be harnessed to create robots that are not only intelligent but also formally verifiable—a key requirement for real-world deployment in safety-critical domains.
Research Focus
Key Achievements
Top Papers
- 1