Alan Sullivan

About

Alan Sullivan is a leading researcher in robotics and reinforcement learning, with a primary focus on bridging the gap between simulated and real-world environments. His most influential work, "Sim-to-Real Transfer Learning using Robustified Controllers in Robotic Tasks involving Complex Dynamics" (2019, 15 citations), tackles a critical challenge in robotics: enabling policies trained in simulation to perform reliably in the physical world. Sullivan’s key contribution lies in developing robustified controllers that account for complex, unpredictable dynamics—such as friction, actuator delays, and sensor noise—that simulations often fail to capture. This work has been foundational for researchers seeking to deploy deep reinforcement learning in real robotic systems without extensive retraining. By demonstrating that simulated training can be made practical for tasks with high-dimensional state spaces, Sullivan has advanced the field’s understanding of domain randomization and policy robustness. His research continues to influence autonomous systems, from industrial manipulators to legged robots, and his citation record reflects the growing importance of sim-to-real methodologies in modern robotics.

Research Focus

Key Achievements

Top Papers

1. 1
   Sim-to-Real Transfer Learning using Robustified Controllers in Robotic Tasks involving Complex Dynamics

   15 citations · 2019

Key Collaborators

Contact & Links