Anthony Corso

Papers

Total Citations

H-Index

About

Anthony Corso is a leading researcher in the safe validation and planning of autonomous systems, with a focus on robotics and safety-critical decision-making under uncertainty. His work bridges the gap between theoretical guarantees and practical deployment, particularly in high-dimensional domains where traditional methods falter. Corso's major contributions include pioneering diffusion-based failure sampling techniques for evaluating safety-critical autonomous systems, offering a more efficient alternative to black-box Markov chain Monte Carlo approaches that require prohibitive sample sizes. He has also advanced constrained planning under partial observability, developing hierarchical Monte Carlo methods for Constrained Partially Observable Markov Decision Processes (CPOMDPs) that enable optimal reward maximization while satisfying hard cost constraints—a critical capability for safe real-world operation. His recent papers have already garnered attention, with citations accumulating rapidly as the community recognizes the practical significance of his work. Corso's research is notable for its direct applicability to autonomous driving, robotics, and other domains where safety is paramount, positioning him as a rising authority in the field of safe AI and autonomy validation.