Erica Salvato
Papers
7
Total Citations
199
H-Index
4
About
Erica Salvato is a robotics researcher whose work sits at the intersection of reinforcement learning, control theory, and real-world deployment. Her most influential contribution, the 2021 survey *Crossing the Reality Gap* (174 citations), systematically analyzed sim-to-real transfer for robot controllers—a critical challenge for autonomous systems. This work established her as a leading voice on how RL agents trained in simulation can successfully operate on physical hardware despite modeling inaccuracies. She has since advanced this theme through research on modeling errors in deep RL controllers and neuroevolution for continuous control policies. Salvato has also made significant contributions to practical robot control, including singularity avoidance for hand-guided collaborative robots, model-free kinematic control, and position-based visual servoing without hand-eye calibration. Her work spans both theoretical foundations and applied solutions, addressing challenges in cable robot control and collaborative robotics. By tackling the fundamental gap between simulation and reality, Salvato’s research directly enables more robust, adaptable robots capable of operating in complex, unstructured environments—a key step toward truly autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Model-free kinematic control for robotic systems6 citations · 2024
- 4Position-based visual servo control without hand-eye calibration4 citations · 2025
- 5
- 6
- 7Model-free cable robot control2 citations · 2023