Dionis Totsila
Papers
2
Total Citations
7
H-Index
2
About
Dionis Totsila is a researcher at the forefront of robotics and machine learning, with a focus on developing safe, stable, and interpretable sensorimotor learning algorithms. His work addresses a critical challenge in modern robotics: ensuring that learned policies—whether derived from reinforcement or imitation learning—do not produce unstable behaviors that could damage robots or their environments. In his highly cited 2025 paper, "Sensorimotor Learning With Stability Guarantees via Autonomous Neural Dynamic Policies," Totsila introduces a novel framework that provides formal stability guarantees while maintaining the flexibility of neural network-based control. This work has quickly garnered 3 citations, signaling its importance to the field. Additionally, Totsila is a key contributor to RobotDART (2024), an open-source robot simulator designed specifically for robotics and machine learning researchers, which has already received 4 citations. By bridging the gap between theoretical guarantees and practical deployment, Totsila’s research is paving the way for safer, more reliable autonomous systems—a vital step toward real-world robotic applications.
Research Focus
Key Achievements
Top Papers
- 1
- 2