Jesse Jiang

Papers

Total Citations

H-Index

About

Jesse Jiang is a rising leader in the intersection of robotics, control theory, and formal methods, with a primary focus on enabling safe and uncertainty-aware planning for legged locomotion. His research uniquely bridges abstraction-based verification and bipedal robotics, developing rigorous frameworks to guarantee performance even under environmental and dynamic uncertainties. His most influential work, "Safe Learning for Uncertainty-Aware Planning via Interval MDP Abstraction" (2022, 16 citations), introduces a novel method to iteratively refine satisfiability bounds for partially-known stochastic systems against temporal logic specifications, establishing a foundational approach for safe autonomy. Building on this, his 2023 paper on "Abstraction-Based Planning for Uncertainty-Aware Legged Navigation" (6 citations) pioneers the use of Interval Markov Decision Processes to model bipedal locomotion, incorporating motion perturbations from terrain and dynamics. Most recently, his 2024 work on "Bipedal Safe Navigation over Uncertain Rough Terrain" (3 citations) unifies terrain mapping with locomotion stability, addressing the critical challenge of navigating over uncertain elevation. Together, Jiang’s contributions are shaping a new paradigm for certifiably safe robot navigation in the real world.