Shadi Endrawis
Papers
1
Total Citations
5
H-Index
1
About
Shadi Endrawis is a robotics researcher whose work centers on bridging the critical gap between simulation and real-world deployment—a challenge known as sim2real. Her most notable contribution, "Validate on Sim, Detect on Real – Model Selection for Domain Randomization" (2022), introduces a practical framework for training robot control policies in simulation using domain randomization (DR), then effectively selecting and transferring the best-performing models to physical robots. This approach addresses a core bottleneck in robotics: ensuring that policies trained on diverse, randomized simulated environments can generalize reliably to unpredictable real-world conditions. While her work has garnered early citations (5 for this key paper), its impact lies in its methodological clarity and direct applicability to real robotic systems. Endrawis’s research is particularly valuable for students and engineers working in robot learning, reinforcement learning, and autonomous systems, offering a principled way to validate simulation-based policies before costly real-world testing. Her focus on practical, deployable solutions positions her as an emerging voice in the sim2real community, where her work helps democratize access to robust robot control.
Research Focus
Key Achievements
Top Papers
- 1