Alexandre Capone
Papers
2
Total Citations
18
H-Index
2
About
Alexandre Capone is a researcher at the forefront of safe and learning-based control for autonomous systems. His work masterfully bridges the gap between machine learning and control theory, focusing on how systems with unknown or uncertain dynamics can operate safely and reliably. Capone’s key contributions lie in developing algorithms that integrate Gaussian processes with control barrier functions, enabling real-time learning while guaranteeing safety. His 2020 paper, “Smart Forgetting for Safe Online Learning with Gaussian Processes” (11 citations), pioneered a method to manage data in online learning, ensuring that a model-based controller can adapt without catastrophic forgetting. Building on this, his 2024 work, “Learning-Based Prescribed-Time Safety for Control of Unknown Systems with Control Barrier Functions” (7 citations), tackles the critical challenge of guaranteeing safety within a strict time limit—even when the system’s dynamics are completely unknown. This is a significant step toward deploying learning controllers in time-critical applications like autonomous driving and robotics. By addressing the fundamental tension between exploration and safety, Capone’s research is shaping the next generation of intelligent, certifiably safe autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1Smart Forgetting for Safe Online Learning with Gaussian Processes11 citations · 2020
- 2